Digital Circuit Correlation Optimization of Neural Networks for Apnea Detection During Transplantation

Xu Lin1,*, Heng Li1,*, Yukun Qian1, Yun Lu2 and Mingjiang Wang1, 1College of Electronic and Information Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China, *These authors contributed to the work equally and should be regarded as co-first authors and 2School of Computer Science and Engineering, Huizhou University, Huizhou, China

ABSTRACT

Sleep apnea syndrome (SAS) is a dangerous and high incidence sleep disorder. As more and more people are affected by SAS, monitoring SAS in family life becomes increasingly important. It is very meaningful to design an automatic SAS monitoring device. We designed a SAS detection model based on neural network, and transplanted the model to an application specific integrated circuit (ASIC). There are many problems in the process of transplanting neural network to ASIC. One of the most serious problems is the transplantation of nonlinear activation functions. We proposed a software-hardware joint optimization method to solve the problem of activation function in the SAS model transplantation. In the process of building the neural network model, our research modified the activation function in the traditional LSTM model and the attention mechanism, and adopted hard-sigmoid and Leaky-ReLU activation function for digital circuits. In the hardware transplantation, the activation function was constructed using the binary shift-based division, three-segment and two-segment function. A digital circuit without migration errors can be obtained with a small area and time consumption. We jointly optimized the structure of the model design and the digital circuit implementation. The model was more suitable for the digital circuit structure, so that the neural network can be transplanted more smoothly.

KEYWORDS

Sleep apnea detection, Neural network, Hardware transplantation, Activation function.

From 3D Point Cloud Towards Hbim. The Role of Artificial Intelligence in Cultural Heritage: a Literature Review

Victoria Andrea Cotella, Department of Architecture, University of Naples Federico II, Naples, Italy

ABSTRACT

In recent years, interest in the automatic semantic segmentation of 3D point clouds using machine and deep learning (ML/DL) has grown due to its fundamental role in scene understanding in various computer vision, robotics and remote sensing applications. In the architecture, engineering and construction (AECO) sector, Building Information Modelling (BIM) has become a standard approach to design and the use of 3D point clouds is currently the basis for the creation of as-built BIM models. Today, there is a research gap concerning the interface between point cloud segmentation and the Historical BIM process: there are no consistent studies demonstrating the possibility of automating the modelling of BIM families from the result obtained in the segmentation process in terms of geometry and semantic labels. Based on these assumptions, the present research aims to conduct a systematic review of the state of the art, including both empirical and conceptual studies, with the goal of offering a constructive synthesis that will provide a starting point for the development of innovative approaches in the field of BIM and AI.

KEYWORDS

Artificial Intelligence, 3D Point cloud, HBIM, Cultural Heritage, Digitalisation.

Review of Class Imbalance Dataset Handling Techniques for Depression Prediction and Detection

Simisani Ndaba, Department of Computer Science, Faculty of Science, University of Botswana

ABSTRACT

Depression is a prevailing mental disturbance affecting an individual’s thinking and mental development. There have been many researches demonstrating effective automated prediction and detection of Depression. The majority of datasets used suffer from class imbalance where samples of a dominant class outnumber the minority class that is to be detected. This review paper uses the PRISMA review methodology to enlist different class imbalance handling techniques used in Depression prediction and detection research. The articles were taken from information technology databases. The results revealed that the common data level technique is SMOTE as a single method and the common ensemble method is SMOTE, oversampling and under sampling techniques. The model level consists of various algorithms that can be used to tackle the class imbalance problem. The research gap was found that under sampling methods were few for predicting and detecting Depression and regression modelling could be considered for future research.

KEYWORDS

Depression prediction, Depression detection, Class Imbalance, Sampling, Data Level and Model Level.

A Mobile Platform for Teachers and Parents to Track Children’s Behavior During Online Classes Using Artificial Intelligence

Ziqi Liu1, Yujia Zhang2, 1The Governor’s Academy, 1 Elm St, Byfield, MA 01922, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768

ABSTRACT

Online schooling has become more and more popular during recent years due to COVID-19 [1][15]. It allowsteaching to continue without in-person contacts. A prominent issue with online schooling is teachers are unabletooversee students’ behavior during class as they would in-person. It has been known that many students tend toloseattention. This can make online schooling less ef ective, causing itci to yield worse results than in-person schooling[2]. In order to tackle this issue, this paper outlines a tool that has been developed to monitor children’s mouse andkeyboard movements during online classes and analyze the data with artificial intelligence to ensure students arefocused in class [3]. For example, if the students are typing and clicking their mouse frequently, then there is ahigher possibility the student is not focused because frequent keyboard and mouse movements might indicate theyare chatting with friends or playing games; on the other hand, if they are attentive in class, there would be lesskeyboard and mouse movements, as they should be taking notes.

KEYWORDS

Depression prediction, Depression detection, Class Imbalance, Sampling, Data Level and Model Level.

A Exploring the Role of Extracted Features in Deep Learning-based 3D Face Reconstruction From Single 2D Images

Mahfoudh Batarfi and Manohar Mareboyana, Department Of Computer Science, Bowie State University, Bowie, MD, USA

ABSTRACT

Features that can be extracted from a single image are very important in 3D face reconstruction neural networks because they provide additional information beyond the image’s size and quality. These features can be used to compensate for the lack of prior knowledge provided by a single 2D image and to overcome the dimensional differences between 2D and 3D. This paper collects features that can be extracted from a single image include facial landmarks, which provide information about the geometric structure of a face, and texture maps, which provide information about the surface properties of a face. Additionally, depth maps, shading information, and albedo maps can be used to understand the 3D structure of the face and how light interacts with it. By using these features, 3D face reconstruction neural networks can create more detailed and accurate 3D models of faces, even when the input image is of low quality or has extreme poses or occlusions.

KEYWORDS

Landmarks, Depth, Texture, UV, Shading, Albedo,Face Parsing.

Max-policy Sharing for Multi-agent Reinforcement Learning in Autonomous Mobility on Demand

Ebtehal T. Alotaibi1 and Michael Herrmann2, 1, 2Institute of Perception, Action and Behaviour, Edinburgh, UK, 1Computer Science Department, Imam Mohammad Ibn Saud University, Riyadh, Saudi Arabia

ABSTRACT

Autonomous Mobility on Demand (AMoD) systems have the potential to revolutionize urban transportation by offering customers mobility as a service without the need for car ownership. However, optimizing the performance of AMoD systems presents a challenge due to competing objectives of reducing customer wait times and increasing system utilization while minimizing empty miles. To address this challenge, this study compares the performance of max-policy sharing agents and independent learners in an AMoD system using reinforcement learning. The results demonstrate the advantages of the max-policy sharing approach in improving Quality of Service (QoS) indicators such as completed orders, empty miles, lost customers due to competition, and out-of-charge events. The study identifies the importance of striking a balance between competition and cooperation among individual autonomous vehicles (AVs) and tuning the frequency of policy sharing to avoid suboptimal policies. The findings suggest that the max-policy sharing approach has the potential to accelerate learning in multi-agent reinforcement learning systems, particularly under conditions of low exploration.

KEYWORDS

reinforcement learning, multi-agent, consensus learner, max-policy sharing, autonomous mobility on demand.

Improved Speech Enhancement by Using Both Clean Speech and ‘clean’ Noise

Jianqiao Cui and Stefan Bleeck, Institute of Sound and Vibration Research, University of Southampton, Southampton, UK

ABSTRACT

Generally, speech enhancement (SE) models based on supervised deep learning technology use input features from both noisy and clean speech, but not from the noise itself. In this paper, we propose that the clean background noise, before mixing with speech, can also be utilized to improve SE, which has not been described in previous literature to our knowledge. Our proposed model initially enhances not only the speech but also the noise, which is later combined for improved intelligibility and quality. We also present a second innovation to capture better contextual information that traditional networks often struggle with. To leverage speech and background noise information, as well as long-term context information, we describe a sequence-to-sequence (S2S) mapping structure using a novel two-path speech enhancement system consisting of two parallel paths: a Noise Enhancement Path (NEP) and a Speech Enhancement Path (SEP). In the NEP, the encoder-decoder structure is used to enhance only the clean noise, while the SEP is used to suppress the background noise in the clean speech. In the SEP, we adopt a Hierarchical Attention (HA) mechanism to capture long-range sequences more effectively. In the NEP, we utilize a traditional gated controlled mechanism from ConvTasnet but improve it by adding dilated convolution to increase receptive fields. We conducted experiments on the Librispeech dataset, and the results show that our proposed model outperforms recent models in various measures, including ESTOI and PESQ scores. We conclude that the simple speech plus noise paradigm often adopted for training such models is not optimal.

KEYWORDS

Supervised speech enhancement, separate paths, hierarchical attention mechanism, gated control, magnitude.

Can Complexity Measures and Instance Hardness Measuresreflect the Actualcomplexity of Microarray Data?

Omaimah Al Hosni, Andrew Starkey, School of Engineering, University of Aberdeen, Scotland/UK

ABSTRACT

This study aims to examine the performance of Complexity Measures andInstance Hardness Measures in Microarray dataset properties. The study assumes that since these measures are data dependent, they might also be negatively affected by complex datacharacteristics in not reflecting the actual data complexity.In addition, the study argues that the experiment strategy adopted mainly by others in examining only the correlation between the classification algorithm and measures performance is not a good independent indicator to validate the measures performance in estimating the actual data difficulty nor for showing the causes of the poor prediction of the learning algorithms performance as both are data dependant. Therefore, the study adopted a different experiment strategy than other works undertaken in this context. The outcomes indicated thatAmong 35 measures covered in this study, the measures had responded differently against each data challenge due to the different assumptions they adopted and their sensitivity to the different data challenges.

KEYWORDS

Complexity Measures, Instance Hardness Measures, Small Sample size, High Dimensionality, Imbalanced Classes, Microarray dataset.

A Pose-estimate Smart Home Heating Control System Based on Body Cover Detection Using Artificial Intelligence and Computer Vision

Tingyu Zhang1, Jonathan Sahagun2, 1Materdei High School, 1202 W Edinger Ave, Santa Ana, CA 92707, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

The background to the problem we are trying to solve is the need for a reliable and affordable baby monitor that provides parents with real-time information on their babys condition and wellbeing [1]. While there are various baby monitors on the market, many of them have limitations such as limited range, poor connectivity, and lack of features [2]. Our proposal is to develop a smart baby monitor that incorporates a range of technologies such as Wi-Fi connectivity, temperature and humidity sensors, audio and video monitoring, and a smartphone app for remote monitoring and control [3]. Our device also includes features such as a nightlight, lullabies, and two-way communication, making it a comprehensive solution for parents. One of the main challenges we faced was ensuring that the devices connectivity was reliable and stable, particularly when transmitting data wirelessly over Wi-Fi. We addressed this challenge by using high-quality components and optimizing the devices firmware to ensure optimal performance [4]. During experimentation, we tested the device in various scenarios such as different room sizes, WiFi network setups, and environmental conditions. The results showed that the device performed reliably and accurately in all scenarios, providing parents with real-time updates on their babys condition and wellbeing. The most important results we found were that our device provided parents with a comprehensive and reliable solution for monitoring their babys condition and wellbeing. Our devices features, such as video monitoring and smartphone control, made it easier for parents to stay connected with their baby, even when they were not in the same room [5]. Our idea is ultimately something that people should use because it provides parents with peace of mind, knowing that they can monitor their babys condition and wellbeing in real-time, even when they are not in the same room. Additionally, our devices comprehensive features, such as video monitoring and two-way communication, make it a valuable tool for parents to use as their baby grows and develops [6].

KEYWORDS

Monitor, AI, Senser, baby.

Automated Models for the Classification of Magnetic Resonance Brain Tumour Images

Divya S1, Dr Athar Ali2 , Dr Nasir Ibrahim3 and Dr L Padma Suresh4, 1Department of Computing, University of Buckingham, UK, 2Department of Computing University of Buckingham, UK, 3Department of Computing University of Buckingham, UK, 4Department of CSE, Baselios Mathew II College of Engineering, India

ABSTRACT

Brain tumours are the second largest cause of cancer death in children under the age of 15 and young adults until age 34. Also, among people over 65, these tumours are the second-fastest-growing cause of cancer death. Computer-assisted tumour diagnosis is challenging, and efforts to increase the accuracy of tumour classification and generalisation are continually being made despite the plethora of studies conducted. This study of automated multi-class brain tumour classification utilising Magnetic Resonance Images aims to design and develop three automatic brain tumour classification approaches to categorise the brain tumours as glioma, meningioma, and pituitary tumours, which assist clinicians in making brain tumour diagnoses and developing further treatment plans to save patient’s life. This research proposes methodologies such as a transfer learning approach using ResNet 50, hand-crafted features with machine learning classifiers, and hybrid firefly optimised multi-class classifier for tumour classification.The hybrid methodology yields the highest classification accuracy of 99% using the Figshare dataset. Furthermore, using the Figshare dataset, the hybrid technique yields the highest sensitivity (recall) of 99% for meningioma and pituitary tumours, the highest precision of 100% for pituitary tumours, and the highest F1-measure of 99% for pituitary tumours.

KEYWORDS

Brain Tumour Classification, Meningioma, Glioma, Pituitary, Deep Learning, Machine Learning, Resnet 50, MRI.

An Empirical Study on the Impact of Augmented Reality Technology on Improving Learning Motivation in E-learning Platform

Thayalini Majureshan, Department of Computer Engineering, AIMS Campus, Colombo, Sri Lanka

ABSTRACT

AR has the advantage of being able to reflect on real-life situations, allowing it to go beyond any potential limitations. To obtain a better knowledge of each subject, students can begin exploring them in the actual world using a simple AR simulation. However, research on the effects and outcomes of augmented reality in education is still in its early stages. The impact of augmented reality on learning motivation is the topic of this study. An AR-based eBook based on both the local and international school curriculum for grade 1 social science subjects has been produced to test the impact on learning motivation. 96 first-graders from six different schools were chosen for this study and evenly divided into two groups. The experimental students used AR-based learning materials, while the control students used 2D image-based learning resources. A variety of statistical analyses were performed, and the results revealed a statistically significant difference in ARCS aspects of learning motivation between the control and treatment groups, implying that using AR technology boosts learning motivation by 34.54 percent more than the traditional method. This discovery could aid researchers, educators, and industrialists in developing models, techniques, and materials to raise the primary educational standard as a revolution.

KEYWORDS

Immersive Technology, Augmented Reality, AR, 2D, 3D, Learning Motivation, Attention, Relevance, Confidence, Satisfaction, Primary School.

Exploring the Synergistic Integration of Artificial Intelligence and Dropshipping: A Comprehensive Investigation Into Optimizing Supply Chain Management, Enhancing Customer Experience, and Maximizing E-commerce Profitability Through Aidriven Solutions

Rundong Wang1, Lin Yang2, Patrick Le3, 1The Webb School of California, 1175 W Baseline Rd, Claremont, CA 91711, 2C13711 Somerset Ln SE, Bellevue, WA 98006, 3Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

The dropshipping industry presents significant challenges for entrepreneurs, particularly in product selection, website creation, and overall management of their online stores [1]. The sheer volume of products available, fierce competition, and the complexities of inventory management and customer service can be overwhelming for newcomers [2][3]. To address these issues, we propose a unique, AI-powered dropshipping platform that not only automates and optimizes essential aspects of running a dropshipping business but also offers a feature that distinguishes it from others: personalized website generation [4]. Our platform uses cutting-edge technologies such as artificial intelligence, machine learning, and data analytics to streamline operations and increase efficiency. It comprises essential components, including data acquisition via sophisticated web scraping techniques, AI analytics that use machine learning algorithms and mathematical formulas for data analysis and product performance prediction, and user interface generation, focusing on creating a user-friendly interface for straightforward navigation and informed decision-making [6]. What sets our platform apart is its ability to generate personalized websites based on the users chosen items to dropship. This unique feature enhances advertising capabilities by offering a tailored online presence that displays selected products in an engaging and persuasive way. These generated websites are visually appealing, user-friendly, and SEO-optimized for maximum exposure, enabling better engagement with the target audience, increasing conversions, and driving sales [5]. Our AI-powered dropshipping platform is more than a tool; its a comprehensive solution that allows dropshippers to efficiently manage their business, from product selection to website creation and advertising [7]. By enabling entrepreneurs to focus more on marketing and customer relationships, it contributes to increased efficiency and higher success rates. It satisfies the growing demand for personalized online experiences, empowering dropshippers to tailor their online stores to their specific niche or target market, thereby enhancing their branding in a highly competitive e-commerce landscape. In conclusion, our platform provides an effective solution to the challenges faced by dropshipping entrepreneurs. Its unique website generation feature, along with accurate product selection, scalability, and user-friendly interface, contribute to improved profitability, customer satisfaction, and long-term growth in the competitive drop shipping industry. The integrated approach of our solution eliminates the need for dropshippers to rely on multiple tools, thereby simplifying operations and reducing complexity, ultimately enhancing their success.

KEYWORDS

Automation, Artificial intelligence, Web scraping, User interface design/generation.

Study of a Genetic Algorithm for the Analysis of Data From the Abs Polymer Creep Test

Thiago Moreira da Silva1, Manoela Rabello Kohler1 and Marco Aurelio Cavalcanti Pacheco2, 1Department of Eletrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil, 2Rua Marquês de São Vicente, 225, Gávea, RJ-Brasil

ABSTRACT

In this paper, a genetic algorithm was proposed in order to compare it with experimental data and non-linear regression analysis for the creep test of ABS polymer and Br-ABS. The results of the correction coefficients were very close showing that genetic algorithms are a good tool for regression analysis. For the analysis, an attempt was made to model the data based on Burgers four-parameter model.

KEYWORDS

ABS, flame retardant, creep, viscoelasticity, Genetic algorithms.

The Introduction of Seasonal-trend Decomposition Technique Integrated With Tvf-emd and Longshort Term Memory Network in Monthly Rainfall Forecasting

Zixuan Jin1 and Bei Wang2, 1sucsoft, Hangzhou, Zhejiang, China, 2College of Computer Science, Zhejiang University, Zhejiang, China

ABSTRACT

Many efforts are carried out to acquire accurate rainfall forecasting to alleviate the damaging effects of extreme weather conditions. We introduced a new multi-decomposition-based technique to forecast monthly rainfall in Hangzhou, China. Firstly, the original rainfall signals were decomposed into trend, seasonal, and remainder components via seasonal-trend decomposition using LOESS (STL). In addition, the residual part was decomposed into intrinsic mode decomposition functions (IMFs) by the time-varying filter-based empirical mode decomposition (TVF-EMD). Then, we used the Principal Components Analysis (PCA) to decompose the IMFs signals. Multiple machine learning (ML) models, i.e. long-short term memory (LSTM), were developed to predict these three components. We added the predicted value of each component as the predicted monthly rainfall. Lastly, several statistical metrics, i.e. the root mean squared error (RMSE), were used to evaluate the performance of the ML models. The results show that the STLTVF-EMD-PCALSTM outperformed the benchmark models in predicting monthly rainfall.

KEYWORDS

Rainfall time series prediction; Seasonal-trend decomposition; Empirical mode decomposition; Deep learning.

On the Robustness of Federated Learning Towards Various Attacks

Mayank Kumar1, Shrey Yagnik2 and Priyanka Singh2, 1Indian Institute of Technology Jammu, Jammu, India, 2Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India

ABSTRACT

Federated Learning (FL) allows for training machine learning models on decentralized data. However, FL has been prone to adversarial attacks. This paper examines the vulnerability of FL towards white-box attacks using the CIFAR10 dataset. In the study, we have used ResNet20 and DenseNet. In the study, the required perturbation is added to find the adversarial samples to fool the model. This decentralized approach to training can make it more dif icult for attackers to access the training data, but it can also introduce new vulnerabilities that attackers can exploit. We conducted three types of white box attacks, i.e., Fast Gradient Sign Method (FGSM), Carlini-Wagner (CW), and DeepFool, and studied the models behavior. We have presented the results of the model behavior considering the dif erent scenarios.

KEYWORDS

Federated Learning, Machine Learning, White-Box Attacks.

License Plate Recognition for Smart Parking

Djalal Merad Boudia, Kheira Ziadi and Assia Touati, Department of Computer Science, Ain-Témouchent University, Algeria

ABSTRACT

Nowadays, in addition to the flexibility, efficiency, speed and comfort of the private car, the spatial dispersion of the habitat and their activities contribute to a considerable growth in traffic and the use of cars. This means of transport becomes the most popular and most preferred by users. For this, the automation of parking management is necessary because the human being is unable to identify, in real time and without mistakes, the cars that enter a safe place. Today, there are many systems of recognition of license plates, these systems have two major axes, which are the detection of the license plate and the recognition of its characters. Our system makes it possible to identify cars in a car park by reading the license plates. It relies on a camera associated with a plate recognition software and a database that contains the list of incoming and outgoing cars. First, pretreatments are applied to facilitate subsequent image analysis. We start with the detection of all areas that could be plates and then a procedure of recognition is applied in order to obtain the registration of the car.

KEYWORDS

Smart Parking, wireless sensor network, character recognition, image processing, license plate.

Semantic Framework for Query Synthesised 3D Scene Rendering

Sri Gayathri Devi I, Sowmiya Sree S, Jerrick Gerald, Geetha Palanisamy, College of Engineering, Anna University, Chennai, India

ABSTRACT

View synthesis allows the generation of new views of a scene given one or more images. Current methods rely on multiple input images which are practically not feasible for such applications. Whereas utilizing a single image to generate the 3D scene is challenging as it requires comprehensive understanding of 3D scenes. To facilitate this, a complete scene understanding of a single-view image is performed using spatial feature extraction and depth map prediction. This work proposes a novel end-to end model, trained on real images without any ground-truth 3D information. The learned 3D features are exploited to render the 3D view. Further, on querying, the target view is generated using the Query network. The refinement network decodes the projected features to in-paint missing regions and generates a realistic output image. The model was trained on two datasets namely RealEstate10K and KITTI containing an indoor and outdoor scene.

KEYWORDS

3D Scene Rendering, Dif erentiable Renderer, Scene Understanding, Quantized Variational Auto Encoder.

Strategies for Addressing Prosopagnosia as a Potential Solution to Facial Deepfake Detectiont

Fatimah Alanazi, Richard Davison, Gary Ushaw, and Graham Morgan, School of Computing, Newcastle University, Newcastle upon Tyne, UK

ABSTRACT

The detection of deep fakes simulating human faces for potentially nefarious purposes is an ongoing and evolving topic of interest. Research in prosopagnosia, or face-blindness, has indicated that specific parts of the face, and their movement, provide clues for identification to subjects with the condition. This paper outlines studies in the area of detecting and addressing the effects of prosopagnosia. For the first time, we suggest that the findings of these studies could be applied to the detection of deep fake faces, drawing a link between the facial features and movements most useful in combating the effects of prosopagnosia, with the features most productive for analysis in deep fake facial detection.

KEYWORDS

Deep fake detection, Facial recognition, Prosopagnosia, Deep learning & Biometric.

Systems Engineering Based Augmented Reality Ultra-high-definition Holographic Head-up Display Layout

Jana Skirnewskaja and Timothy D. Wilkinson, Electrical Engineering Division, Department of Engineering, University of Cambridge, 9 JJ Thomson Avenue, Cambridge, CB3 0FA, UK

ABSTRACT

Systems engineering based real-time head-up displays can increase safety and promote inclusivity in transportation. This works utilizes accelerated algorithms, a 4k spatial light modulator, virtual Fresnel lenses, a He-Ne laser resulting in the augmented reality floating holographic projections to appear within 0.9 seconds. Additionally, the personalised layout of the 3D head-up display is a paramount to this work. A robustness analysis based on Failure Mode and Effects Analysis (FMEA) was carried out. The study consisted of optical system architecture design and a failure-cause correlation. In addition, in-depth analyses of each system component were created within the optical setup boundary. The 3D floating holographic projections were assessed based on consumer demand, safety and comfort, and a cost/benefit analysis.

KEYWORDS

Augmented Reality, Systems Engineering, FMEA, 3D Computer-Generated Holography, Head-Up Displays, Automotive Applications.

Learning Weight of Loss on Multi-scale in Crowd Counting

Derya UYSAL and Ulug Bayazit, Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey

ABSTRACT

In this work, we improve the state-of-the-art in crowd counting by further developing a recently proposed multi-scale, and multi-task crowd counting approach. While most of the studies treat density-based architectures, this study proposed a point-based method for crowd analysis. We propose automatic, and optimal weight assignment to constituents of the loss function. This approach, which is applied to each patch, ensures that the weight parameters are updated in each epoch, and added to the optimizer with model parameters rather than remaining constant. For validation of our proposed approach, we use three popular crowd counting datasets, ShanghaiTech A, ShanghaiTech B, and UCF_CC_50. The performance of our approach exceeds the performances of the other studies on the ShanghaiTech dataset, and is highly competitive with the performances of the other studies on the UCF CC 50 dataset.

KEYWORDS

Crowd Counting, Multi Scale, Automatic Weighted Loss, Point Supervision.

Optimizing Heat Generation and Battery Efficiency for Portable Heaters: A Comparative Study of Copper Wire Gauges and Battery Capacities

Matthew King1, Jonathan Sahagun2, 1University high school, 4771 Campus Drive, Irvine 92612, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Heated jackets are a popular clothing item among outdoor enthusiasts, athletes, and workers who need to work outside in cold weather [1]. They offer a convenient and effective way to stay warm in cold temperatures, while also providing therapeutic benefits for those who suffer from certain medical conditions [2]. However, existing methods and tools can be expensive and bulky, and some may not provide even heat distribution. A new approach to creating a heater that can be added to any existing jacket and powered by plugging into a wall socket or connecting to a battery source offers a practical, flexible, and cost-effective solution to the need for warmth in cold weather [3]. This approach allows users to easily add heating elements to their existing clothing, without the need to purchase a new jacket or invest in expensive heated clothing. The option to power the heater through a wall socket or battery source offers flexibility and convenience for users who may not have access to a power source when they need it [4]. Overall, the innovative approach to adding heating elements to existing jackets offers a practical, flexible, and cost- effective solution to the need for warmth in cold weather.

KEYWORDS

Heat generation, Battery efficiency, Customization, Optimization.

Underwater Object Detection

Akshata Kumble, Sriveda Medatati, Dr. Shruthi M L J, Department of Electronics and Communication, PES University, Bangalore, India

ABSTRACT

Underwater object detection is a challenging task in computer vision, as traditional methods may struggle to detect objects reliably due to the high levels of background noise and clutter present in underwater environments. To address this problem, we propose an underwater object detection method based on the "You Only Look Once" (YOLO) v5 algorithm. Our approach aims to balance accuracy and speediness for target detection in marine environments, specifically targeting fishes, pipelines, rocks, and other obstacles that could impede the functioning of submarines. We trained and evaluated the YOLOv5 model on a dataset of underwater images, achieving a mean average precision (mAP) of 0.84 on a separate test set. The results show that our proposed approach is effective for underwater object detection and could have applications in marine biology, oceanography, and underwater exploration.

KEYWORDS

YOLO v5, object detection, deep learning, convolutional neural networks, IOU, object classification.

A Befitting Single-player Squash Program to Educate and Assist Disabled/autistic People Using Pose Estimation and Unity

Lung Ngok Fung1, Moddwyn Andaya2, 1Independent Schools Foundation, 1 Kong Sin Wan Road, Pokfulam, Hong Kong, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

The COVID pandemic has had a notable impact on sports education and exercise over the past few years [7]. Many students have lost access to physical education classes due to school closures or virtual instruction. This paper develops an application using pose estimation that allows users to experience a digital squash game that involves body movements on their phones or computers. Using post estimation, this application can track and identify player movements that let players control game avatars with their movements [8]. A crucial factor that deserves consideration is the degree of difficulty a game offers. The game has a bot as an opponent that can score points precisely. The game may make it easier for the player to move in the direction of the squash ball in order to lessen the challenge that the bot presents. In the experiment, the efficacy of post estimation was tested. In twenty-five swings, all swings were successfully accomplished. With the pandemic restricting access to public sports facilities and other fitness facilities, the application provides a convenient way to exercise from home and the opportunity to learn more about squash.

KEYWORDS

Pose Estimation, Unity, Single-player, Squash.

A Pose-based Walking/running Coach System for Cerebral Palsy Patients Using Artificial Intelligence and Computer Vision

Edward Zhu1, Yu Sun2, 1Chinese International School, 1 Hau Yuen Path, Braemar Hill, Hong Kong SAR, China, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Cerebral palsy, the most common motor disability in childhood, causes mobility issues, leading to gait abnormalities. The spectrum of these abnormalities includes having stiff or flaccid muscles, uncontrollable movements, or poor coordination. Around 1 in 3 children with cerebral palsy cannot walk. Current physical therapy solutions, including processes such as clinical gait analysis, are inaccessible and costly. We investigated the research question: how can we create an affordable and effective method using AI to provide gait analysis data to cerebral palsy patients? Machine learning and computer vision were used to develop a mobile application which provides gait analysis data for cerebral palsy patients. The MediaPipe computer vision library was applied to find pose vectors from the patient’s walking / jogging / running video, and from an expert’s video demonstrating proper form. Using this vector data, matching frames from the two videos were identified with numerous applications of the K-Means algorithm. Joint angle differences were calculated in order to identify gait abnormalities. A complete mobile application was developed to enable patients to monitor, track and get feedback live. The AI model was deployed in the cloud. The frontend was developed using Flutter, and it was designed to accommodate patients’ physical/mental limitations. This research demonstrates an application of machine learning and computer vision in an accessible mobile solution. The K-means algorithm showed high accuracy with an average silhouette score 0.514 when used on expert videos. MediaPipe output had 29.2FPS on average, higher than that of competing libraries which was 8.1FPS.

KEYWORDS

Cerebral palsy, Gait abnormalities, Artificial intelligence, Machine learning.

Depth Based Region Proposal: Multi-stage Real-time Object Detection

Shehab Eldeen Ayman1, Walid Hussein2, Omar H. Karam3, 1Department of Software Engineering, The British University in Egypt, Cairo, Egypt, 2, 3Department of Computer Science, The British University in Egypt, Cairo, Egypt

ABSTRACT

Many real-time object recognition systems operate on two-dimensional images, degrading the influence of the involved objects third-dimensional (i.e., depth) information. The depth information of a captured scene provides a thorough understanding of an object in full-dimensional space. During the last decade, several region proposal techniques have been integrated into object detection. scenes’objects are then localized and classified but only in a two-dimensional space.Such techniques exist under the umbrella of two-dimensional object detection models such as YOLO and SSD. However, these techniques have the issue of being uncertain that an objects boundaries are properly specified intothescene. This paper proposes a unique region proposal and object detection strategy based on retrieving depth information forlocalization and segmentation of the scenes’ objects in real-time manner. The obtained results on different datasets show superior accuracy in comparison to the commonly implemented techniques with regards to not only detection but also apixel-by-pixel accurate localization of objects.

KEYWORDS

Real time object detection,region proposal,computer vision, RGBD object detection, two stage object detection.

An Interactive Location Extraction System for Video Analysis Using Opencv and Google Apis

Cheng Zhou1, Yujia Zhang2, 1Arcadia High School, 180 Campus Dr, Arcadia, CA 91006, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Video Location Finder is an innovative project developed during the Covid-19 pandemic, inspired by the need to connect with travel destinations while being confined to our homes [4][5]. The project consists of three major components: frame extraction using OpenCV, an artificial intelligence program leveraging the Google Geocoding API to identify locations, and an interactive map display using the Google Maps JavaScript API [6][7]. The system allows users to extract geographic locations from videos, providing latitude and longitude coordinates. These coordinates are then visualized on an interactive map, enhancing the user experience. With its user-friendly website, Video Location Finder revolutionizes the process of exploring and planning future travel adventures by bridging the gap between captivating videos and real-world locations.

KEYWORDS

Artificial intelligence, Web development, Machine learning, Video Analysis.

Review: Evolution of Fractional Hot Deck Imputation for Curing Incomplete Data From Small to Ultra Large

In Cho Cho1, Jae-Kwang Kim2, Yicheng Yang3, Yonghyun Kwon4, and Ashish Chapagain5, 1Department of Civil, Construction, and Environmental Engineering (CCEE), Iowa State University (ISU), Ames, USA, 2Department of Statistics (STAT), ISU, Ames, USA, 3CCEE, ISU, Ames, USA, 4STAT, ISU, Ames, USA, 5CCEE, ISU, Ames, USA

ABSTRACT

Advancements in machine learning (ML) hinges upon data - the vital ingredient for training. Statistically curing the missing data is called imputation, and there are many imputation theories and tools.Butthey often require difficult statistical and/or discipline-specific assumptions, lacking general toolscapable ofcuring large data. Fractional hot deck imputation (FHDI) can cure data by filling nonresponses with observed values (thus, “hot-deck”) without resorting to assumptions. The review paper summarizes how FHDI evolves to ultra data-oriented parallel version (UP-FHDI).Here, “ultra” data have concurrentlylarge instances (big-n) and high dimensionality (big-p). The evolution is made possible with specialized parallelism and fast variance estimation technique. Validations with scientific and engineering data confirm thatUP-FHDI can cure ultra data(p >10,000& n > 1M) andthe cured data sets can improve the prediction accuracy of subsequent ML. The evolved FHDIwill help promote reliable ML with “cured” big data.

KEYWORDS

Big Incomplete Data, Fractional Hot-Deck Imputation,Machine Learning, High-Dimensional Missing Data.

A Content-based Intelligent Chrome Extensiontoassist Reading Time Management Using Artificialintelligence and Machine Learning

Richard Zhang1 and Ang Li2, 1Oakton High School, 2900 Sutton Rd, Vienna, VA 22181 and 2Computer Science Department, California State Polytechnic University, Pomona, CA91768

ABSTRACT

Oftentimes we lose track of the time we take to skim over a website or article online or we are simply curious about the time it might take for us to read over some text. We might also be curious about our attention span based onthelength or dif iculty of an article. This paper details the development process of an intelligent google chromeextension capable of gathering data from specific articles and processing the data to estimate the amount of timeneeded to read over an article based on the time it took to read similar or dissimilar articles [10]. This applicationtakes into account the length, readability, average word size, and comparisons to other reading times in order toreturn the most accurate time predictions. The benefit of this application is improved time management as anaccurate prediction of time will be provided.

KEYWORDS

Chrome-extension, Time management, Machine learning, Web scraping.

Trainees Perceptions About Distance Education During the Pandemic of Corona Virus (Covid19) in the Regional Center for Education and Training Careers Daraatafilalet

Abdelghani ZOUADI, Laboratory of Studies and Research in the Sciences of Education, Didactics and Management, Regional Center for Education and Training Careers Daraa-Tafilalet, Errachidia, Morocco

ABSTRACT

The issue of distance education is of great importance due to the development of mass media and information communication technologies. This importance has grown greater and greater, especially in the period of the coronavirus pandemic (Covid19) which obliged people to stay at home and continue studying online and via different tools. This study aimsis to investigate the trainees perceptions related to distance education at the Regional Center for Education and Training Careers – Daraa Tafilalet (RCETC-DT) during the period of coronavirus (Covid19). The research method included the quantitative approach. The data was collected through a questionnaire from a sample of 41 participants at the department of educational administration and preservice teachers in the RCETC-DT in Errachidia and Ouarzazate, Morocco. The findings indicated that distance education has strengths and weaknesses. They confirmed also that distance education can be more successful if more attention is given to from the official educational authorities.

KEYWORDS

Distance Education, E-Learning, Information Communication Technology, Education &Training, Educational Administration.

Empowering IoT Privacy: Exploring Self-Sovereign Identity Solutions

Maruf Farhan, Dr. Abdul Salih, Northumbria University, United Kingdom

ABSTRACT

Internet of Things (IoT) devices play bigger roles in providing smart, intelligent, and efficient industry solutions. IoT devices typically communicate over the network to perform a variety of activities, for example sharing collected information from the sensors and receiving instructions to perform a specific task. These activities require IoT devices to identify over the network. Verifying identity of IoT devices using traditional methods expose too much information. In case of security breach, malicious actors can use this information to perform impersonation attacks. A better approach to identify IoT devices over the network is required such as Self-sovereign identity (SSI). SSI is typically a decentralized digital identity framework which uses digital identity and verifiable credentials. This paper will explore the use of SSI solution with IoT devices to empower privacy of IoT devices.

KEYWORDS

IoT, Internet of Things, Self-Sovereign identity, SSI, Decentralized Identifiers, Privacy, Security

Design and operation of low energy consumption passive human comfort solutions

Abdeen Mustafa Omer, Energy Research Institute (ERI), Nottingham, United Kingdom

ABSTRACT

The rapid growth during the last decade has been accompanied by active construction, which in some instances neglected the impact on the environment and human activities. Policies to promote the rational use of electric energy and to preserve natural non-renewable resources are of paramount importance. Low energy design of urban environment and buildings in densely populated areas requires consideration of wide range of factors, including urban setting, transport planning, energy system design and architectural and engineering details. The focus of the world’s attention on environmental issues in recent years has stimulated response in many countries, which have led to a closer examination of energy conservation strategies for conventional fossil fuels. One way of reducing building energy consumption is to design buildings, which are more economical in their use of energy for heating, lighting, cooling, ventilation and hot water supply. However, exploitation of renewable energy in buildings and agricultural greenhouses can, also, significantly contribute towards reducing dependency on fossil fuels. This will also contribute to the amelioration of environmental conditions by replacing conventional fuels with renewable energies that produce no air pollution or greenhouse gases. This study describes various designs of low energy buildings. It also, outlines the effect of dense urban building nature on energy consumption, and its contribution to climate change. Measures, which would help to save energy in buildings, are also presented.

KEYWORDS

Renewable technologies, Built environment, Sustainable development, Mitigation measures.

Soft Labels for Rapid Satellite Object Detection

Matthew Ciolino and Grant Rosario and David Noever, PeopleTec, Inc, USA

ABSTRACT

Soft labels in image classification are vector representations of an images true classification. In this paper, we investigate soft labels in the context of satellite object detection. We propose using detections as the basis for a new dataset of soft labels. Much of the effort in creating a high-quality model is gathering and annotating the training data. If we could use a model to generate a dataset for us, we could not only rapidly create datasets, but also supplement existing open-source datasets. Using a subset of the xView dataset, we train a YOLOv5 model to detect cars, planes, and ships. We then use that model to generate soft labels for the second training set which we then train and compare to the original model. We show that soft labels can be used to train a model that is almost as accurate as a model trained on the original data.

KEYWORDS

Soft Labels, Object Detection, Datasets

Classifying Galaxy Images using Improved Residual Networks

Jaykumar Patel, Dan Wu, School of Computer Science, University of Windsor, Ontario, Canada

ABSTRACT

The field of astronomy has made tremendous progress in recent years thanks to advancements in technology and the development of sophisticated algorithms. One area of interest for astronomers is the classification of galaxy morphology, which involves categorizing galaxies based on their visual appearance. However, with the sheer number of galaxy images available, it would be a daunting task to manually classify them all. To address this challenge, a novel Residual Neural Network (ResNet) model, called ResNet_Var, that can classify galaxy images is proposed in this study. Subsets of the Galaxy Zoo 2 dataset are used in this research, one contains over 28,000 images for the five-class classification task, and the other contains over 25,000 images for the seven-class classification task. The overall classification accuracy of the ResNet_Var model was 95.35% for the five-class classification task and 93.54% for the seven-class classification task.

KEYWORDS

Galaxy Zoo, Deep Learning, Residual Networks, Galaxy Morphology

Enhancing Rocket Travel and Landing Efficiency through AI-Guided Control: A Three-Dimensional Simulation Approach

Zhenrui Guo1, Andrew Park2, 1Santa Margarita Catholic High School, 22062 Antonio Pkwy, Rancho Santa Margarita, CA 92688, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Launching rockets is a costly and complex task that is prone to a high rate of failure. To help address these challenges, the need for simulations to help emulate reality when developing rockets is crucial to making sure the cost overhead stays as low as possible. Our rocket AI seeks to tackle this challenge through the use of machine learning and a series of emulated phases to demonstrate an AI’s ability to properly operate a rocket. The primary challenge throughout the development of the rocket’s AI is the need to introduce and train for unexpected situations, which is done by training for a generalized variant of the situations in question.

KEYWORDS

Unity, Machine Learning, Rockets, Simulation

Improving Mass Shooting Survivability: a Systematic Machine Learning Approach Using Audio Classification and Source Localization

Jevon Mao1, Marisabel Chang2, 1Santa Margarita Catholic High School 22062 Antonio Pkwy, Rancho Santa Margarita, CA 92688, 2,Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Mass shootings have emerged as a significant threat to public safety, with devastating consequences for communities and individuals affected by such events [7]. However, a lack of widespread use of new technological infrastructure poses significant risk to victims [8]. This paper proposes a system to classify and localize gunshots in reverberant indoor urban conditions, using MFCC features and a Convolutional Neural Network binary classifier [9]. The location information is further relayed to users through a mobile client in real time. We installed a prototype of the system in a high school in Orange County, California and conducted a qualitative evaluation of the approach. Preliminary results show that such a mass shooting response system can effectively improve survivability.

KEYWORDS

Machine Learning, Public Safety, Acoustics, Directioning.

Top 10 Internet of Things Security Probing Areas

Puthiyavan Udayakumar, United Arab Emirates

ABSTRACT

Several domains of our daily lives are rapidly experiencing the Internet of Things, including home appliances, vehicles, industry, education, agriculture, hospitals, environmental monitoring, etc. These domains have reached new peaks and are rapidly growing in popularity. Each aspect of the Internet of things (IoT) has its own marks and milestones, gradually increasing as the technology becomes more advanced and convenient. The Internet of things (IoT) combines various technologies and techniques to create an organized and interconnected world so communication between entities can be done in a better, more efficient, and usable manner. The main characteristics of any technology are its security, privacy, authentication, and trustworthiness for the end users. Security, trust, and confidentiality are crucial in ensuring users satisfaction, and IoT security is chiefly concerned with authentication, confidentiality, and access control. There are several ways to manage IoT security, privacy, and trust, including NFC, RFID, and WSN. However, IoT systems are hampered by a lack of comprehensive security solutions across various vertical application domains due to a lack of comprehensive security solutions. This research paper will focus on the top ten areas that must be secured from a security and privacy standard point for IOT devices to fill this gap.

KEYWORDS

Sensors/Devices, Data Processing, Network connectivity, Network Protocols, Wireless Networks, Mobile Networks, Viruses, Worms, Trojan, Hardware-based Root of Trust, Small Trusted Computing Base, Defense in Depth, Compartmentalization, Certificate-based Authentication, Renewable Security, Failure Reporting.

Amadeus Migration Process: a Simulationdriven Process to Enhance the Migration to a Multi-cloud Environment

Bilel Ben Romdhanne, Mourad Boudia and Nicolas Bondoux, Artificial Intelligence Research, Amadeus SAS, Sophia Antipolis, France

ABSTRACT

With the development of the cloud offers, we observe a prominent trend of applications being migrated from private infrastructure to the cloud. Depending on the application’s complexity, the migration can be complex and needs to consider several dimensions, such as dependency issues, service continuity, and the service level agreement (SLA). Amadeus, the travel industry leader, had partnered with Microsoft to migrate its IT ecosystem to the Azure cloud. This work addresses the specificity of cloud-to-cloud migration and the multi-cloud constraints. In this paper, we summarise the Amadeus Migration process. The process aims to drive the migration from an initial private cloud environment to a target environment that can be a public or hybrid cloud. Further, the process focuses on a prediction phase that guides the migration process. This paper expects to provide an efficient decision-making process that guides managers and architects to optimise and secure their migration process while considering micro-services-oriented applications targeting an efficient deployment over multi-cloud or hybrid cloud. The prediction relies on the network simulation to predict applications’ behaviour in the cloud and evaluate different scenarios and deployment topologies beforehand. The objective is to predict migrated applications’ behaviour and identify any issue related to the performance, the application’s dependency on other components, or the deployment in the cloud. The migration process proposed in this paper relies on SimGrid, a toolkit developed by INRIA[52] for distributed application modelling. This framework offers a generic process to model IT infrastructure and can assist cloud-to-cloud migration. Specific attention is given to predictive and reactive optimisations. The first results show predictive optimisations impact on securing KPI and reactive optimisation to optimise the solution cost.

KEYWORDS

Cloud migration, SimGrid, system simulation, app modelling, decision support, cloud deployment strategy.

An Energy-efficient Tunable-precision Floating-point Fused Multiply-add Unit Based on Neural Networks

Xiyang Sun, Yue Zhao and Sheng Zhang, Key Laboratory of Advanced Sensor and Integrated System, Tsinghua Shenzhen, International Graduate School, Tsinghua University, Shenzhen, 518055, China

ABSTRACT

Convolutional neural networks have been continuously updated in the last decade, requiring more diverse floating-point formats for the supported domain specific architectures. We have presented VARFMA, a tunable-precision fused multiply-add architecture based on the Least Bit Reuse structure. VARFMA optimizes the core operation of convolutional neural networks and supports a range of precision that includes the common floating-point formats used widely in enterprises and research communities today. Compared to the latest standard baseline fused multiply-add unit, VARFMA is generally more energy-efficient in supporting multiple formats, achieving up to 28.93% improvement for LeNet with only an 8.04% increase in area. Our design meets the needs of the IoT for high energy efficiency, acceptable area, and data privacy protection for distributed networks.

KEYWORDS

Fused Multiply-add, Tunable-precision, Distributed Network, Energy Efficiency, IoT.

Green Computing in Cloud

Madhusudhan Rao Mulagala1 and Saketha Kusuru2, 1Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India, 2Department of Electrical and Electronics Engineering, Pondicherry Engineering College, Pillaichavady, India

ABSTRACT

Green computing is illustrated because of the examination and sees of arranging, creating, utilizing, and getting rid of PCs, servers, and related frameworks, for example, screens, printers, stock-piling gadgets, and systems administration and correspondences frameworks in a very efficient and able manner and in such a manner on accomplishing the ideal outcome with least or no effect on the climate. The objective of green distributed computing is to hack back the utilization of risky assets, augment vitality intensity all through the item’s time frame and advance the recyclability and reuse of out-of-date stock items and mechanical plant squander. Green distributed computing is regularly accomplished by utilizing the product long life Resource portion strategies or more virtualization systems or Power the board methods. Force is the bottleneck of rising the framework execution. Force utilization is delivering a major issue because of extreme warmth. As circuit speed expands, power utilization develops. The information focuses on working with computing models that have a few applications that require on-request asset provisioning and designation considering time-changing remaining burdens that square measure statically dispensed bolstered top burden qualities, to continue separation and give execution ensures while not giving much consideration to vitality utilization.

KEYWORDS

Cloud computing, Performance, Utilization, Green computing.

Verifiable Data Sharing Scheme for Dynamic Multi-owner Setting

Jing Zhao and Qianqian Su, Department of Computer Science and Technology, Qingdao University, Qingdao, China

ABSTRACT

One of scenarios in data-sharing applications is that files are managed by multiple owners, and the list of file owners may change dynamically. However, most existing solutions to this problem rely on trusted third parties and have complicated signature permission processes, resulting in additional overhead. Therefore, we propose a verifiable data-sharing scheme (VDS-DM) that can support dynamic multi-owner scenarios. We introduce a management entity that combines linear secret-sharing technology, multi-owner signature generation, and an aggregation technique to allow multi-owner file sharing. Without the help of trusted third parties, VDS-DM can update file signatures for dynamically changing file owners, which helps save communication overhead. Moreover, users independently verify the integrity of files without resorting to a third party. We analyse the security of VDS-DM through a security game. Finally, we conduct enough simulation experiments and the outcomes of experimental demonstrate the feasibility of VDS-DM.

KEYWORDS

Security, Data Sharing, Dynamic Multi-Owner, Verification

Iot in Practice: Investigating the Benefits and Challenges of Iot Adoption for the Sustainability of the Hospitality Sector

Nick Kalsi, Fiona Carroll, Kasha Minor, Jon Platts, Cardiff School of Technologies, Cardiff Metropolitan University, Llandaff Campus,Western Avenue, Cardiff, CF52YB

ABSTRACT

Enhancing the sustainability of the hospitality sector with technology is essential to achieving growth whilst also reducingthe hotel’s impact on the environment. Indeed, the concept of Internet of Things (IoT) has recently gained popularity as a new research topic in a wide variety of industrial disciplines, including the hospitality industry. IoT is being seen and used to transform the hospitality industry for the newly desired sustainable growth. However, it is not all ‘smooth sailing’ as multiple challenges must be addressed by organisations in the hospitality industry when installing IoT. These challenges include cost, security, infrastructure and IoT protocols. Taking into consideration the diversity of IoT applications, the paper will examine IoT’s use in hotels whilst also highlighting the challenges that hotels face when using IoT. In particular, it will cover the effect of cyber security including IoT’s protocol layers, potential monitoring and sensor technologies.

KEYWORDS

Hotel, Internet of Things (IoT), Sensors, IoT Security, Cloud, compliance, privacy, safety, standard, communication, information.

A Framework for SLA Violation Prevention in a Cloud of Things Environment

Falak Nawaz1 and Naeem Khalid Janjua2, 1National Computational Infrastructure (NCI), Australian National University, Canberra, ACT, Australia, 2Edith Cowan University, Perth, WA, Australia

ABSTRACT

In the literature, existing approaches use runtime monitoring to detect SLA violation and prediction techniques for SLA violation prediction by using the historic QoS data to predict the future QoS values. However, these approaches do not consider the occurrence of eventsand the impact they will have on SLA violation. Moreover, existing approaches also do not provide any recommendation actions to the SLA manager to prevent violation proactively. These limitations of the current literature need the development of a comprehensive framework that can identify and capture events which impact a services quality/performance and model their effect on QoS attributes to reduce the negative consequences by avoiding SLA violation.In order to address these problems, we propose an SLA violation prevention framework. The proposed framework provides a methodology for recommending suitable actions to the SLA manager for SLA violation prevention. Moreover, the performance and the usefulness of the proposed framework is evaluated and validated by developing a proof of concept and applying it on case studies.

KEYWORDS

Cloud of Things (CoT),Service Level Agreement (SLA), SLA violation, violation prevention,proactive management, Quality of Service (QoS)

Predicting Stock Prices Using Tweet Frequency and Ai: Leveraging Social Media Insights to Forecast Tomorrows Market Trends

Zimo Liu1, Lin Yang2, Tami Takada3, 1Beijing No. 12 High School, No. 15 Yize Road Fengtai District, Beijing, 213711 Somerset Ln SE, Bellevue WA 98006, 3Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

I use the frequency of the tweet counts of the stock ticker to predict the stock price [1]. Using AI to predict the price with today’s tweet count and the highest and lowest stock price to predict tomorrow’s stock price [2]. The benefits of predicting stock prices are minimizing losses and getting a better idea about making money. But since the price of stocks is hard to predict, analyzing the number of price tickers discussed in social media can help people to know more precisely trends. “They analyzed the activity of 150 companies chosen at random from the S&P 500 Index and noticed a correlation between the number of tweets they sent and their share price [3]. Having observed this, the researchers devised a mathematical model, applied it to an imaginary portfolio and outperformed other financial strategies based on financial analysis by as much as 11%” [4]. This indicates the reliability of predicting stock prices with social media. Compared with some popular methods such as Auto-Regressive Conditional Heteroscedastic or Generalized Auto-Regressive Moving Average, using social media to predict price can consider the effect of social trends on the stock price [5]. Using social media to predict the stock price is not subjective and is much cheaper to computerize.

KEYWORDS

Stock Price Prediction, Tweet Frequency Analysis, AI-Based Forecasting, Social Media Trends.

Influence of Wireless Novel Routing Protocol by Using Mdpc Algorithm

Ayad Hasan Adhab1 & Naseer Ali Hussien2, 1Kufa University, Computer Science and Mathematics College, Iraq, 2Alayen University, Iraq

ABSTRACT

This research study investigates the influence of a novel wireless routing protocol that incorporates the MDPC (Multiplicative-Divisive Probabilistic Congestion Control) algorithm. The background of the research stems from the increasing demand for efficient and reliable routing protocols in wireless networks, which face challenges such as limited bandwidth, variable network topologies, and dynamic environmental conditions. The purpose of this study is to evaluate the performance of the proposed routing protocol and assess its effectiveness in addressing these challenges. To achieve this objective, a series of methodologies were employed. First, an in-depth analysis of existing routing protocols was conducted to identify their limitations and areas for improvement. The MDPC algorithm was then integrated into the routing protocol design to enhance its performance in terms of packet delivery ratio, network throughput, and energy efficiency. Extensive simulations were carried out using network simulators, and various performance metrics were measured to assess the efficacy of the proposed protocol. The principal results of this study demonstrate that the wireless routing protocol utilizing the MDPC algorithm exhibits superior performance compared to conventional routing protocols. It achieves higher packet delivery ratio, improved network throughput, and reduced energy consumption, even in challenging network conditions. The MDPC algorithms ability to effectively manage packet routing and mitigate the effects of network congestion and link failures contributes significantly to the overall performance enhancement. The simulations were conducted in controlled environments, and real-world deployment scenarios may introduce additional challenges that need to be addressed. Furthermore, practical implications of implementing the protocol, such as hardware and software compatibility, scalability, and security considerations, should be thoroughly investigated before widespread adoption. The social implications of this research are noteworthy, as the proposed wireless routing protocol has the potential to enhance communication reliability and efficiency in various domains. Improved wireless network performance can enable seamless connectivity and data exchange, leading to advancements in areas such as telemedicine, autonomous vehicles, and remote sensing. Additionally, the protocols energy efficiency benefits contribute to the reduction of carbon footprint, promoting sustainable technological solutions.

KEYWORDS

Wireless Novel Routing Protocol, MDPC, Chunking methods, Data De-duplication.

Internet of Things Network Architecture and Security Challenges

Muhammad R Ahmed1, Ahmed Al Shihimi1, Thirein Myo1 Badar Al Baroomi1 and M Shamim Kaiser2, 1Military Technological College, Muscat, Oman, 2Institute of Information Technology , Jahangirnagar Universiry, Savar, Bangladesh

ABSTRACT

The Internet of Things (IoT) has transformed not only the way we communicate and operate our devices, but it has also brought us significant security challenges. A typical IoT network architecture consists of four levels: a device, a network, an application, and a service, each with its own security considerations. There are three types of IoT networks: Personal Area Networks (PANs), Local Area Networks (LANs), and Wide Area Networks (WANs). Each type has its own security requirements, so it is important to understand their particular security requirements. Several communication protocols that are used in IoT networks, like Wi-Fi and Bluetooth, are also susceptible to vulnerabilities that require the implementation of additional security measures. In addition to physical security challenges, there are numerous security challenges in the form of authentication, encryption, software vulnerabilities, DoS attacks, data privacy, and supply chain security. In order to deal with these challenges, we need to take a multi-layered approach that is comprised of physical, technical, and organizational measures. In this paper, we present an overview of IoT network architecture, along with an analysis of security challenges.

KEYWORDS

Internet of Things, Architecture, Challenges, Security.

An IoT- Based Smart City Model using Packet Tracer Simulator

Shaikha Alhajri, Noura Aljulaidan, Zainab Alramdan, Relam Alkhaldi, Zomord Alshihab, Khaznah Alhajri, Huda Althumali, and Taghreed Balharith, Computer Science Department, College of Science and Humanities, Imam, Abdulrahman Bin Faisal University, P.O.Box 31961, Jubail, Saudi Arabia.

ABSTRACT

The Internet of Things (IoT) is one of the technology trends nowadays. In addition, the IoT is one means of developing a living life. This paper presents a smart city model based on the IoT using Cisco Packet Tracer simulation software. As a starting point, the paper explains smart city architecture that aims to improve life through three aspects. The first aspect is creating a network that allows users to control their smart devices from anywhere and at any time. The second aspect is bypassing the high budget by improving operational efficiency through the managed interconnection between smart devices within the city. Ultimately, the third aspect is increasing security in all city facilities. The simulation showed that the smart city would make life in cities more productive and interactive.

KEYWORDS

IoT, Smart City, Cisco, Packet Tracer, Networks

Extending Common Usability Heuristics List With Learner-centric Strategies for an Exhaustive Elearning Design Assessment

Nadia MENAD, Department of Computer Science, University of Science and Technology, Oran, Algeria

ABSTRACT

The learner-centered approach to e-Learning is an emerging philosophy that has been winning prominence in the educational space in nowadays. This approach emphasizes creating a more engaging e-Learning environments by putting the needs of the learner first and creating an adapted situation where the learner can succeed. In this article we will explore what this new way of thinking looks like in practice, and how this later could be applicable in interface design. According to several research studies, a learner-centric approach to education is far more beneficial than any other method. Such an instructional method encourages learners to adopt a “I can do” mindset. Learners are allowed to learn autonomously, in a positive manner, and be extremely motivated. Psychological researchers believe that motivation is tied to autonomy and the manner of designing interfaces have a direct impact on the learner. For this purpose, elearning application designers should adapt this way of thinking as a part of their conception. Our contribution aims to extend an existing usability evaluation nterface heuristics, these common list has been enriched in our proposal with a learner centric strategies, to give a birth of an exhaustive e-learning interface design assessment questionnaire.

KEYWORDS

User experience, Educational platforms, interface evaluation, Online educational environment, Learnercentric strategies, Remote Teaching quality.

Queued Combined Guard Channel and Mobile Assisted Handoff Call Admission in 5g Networks

Nagla O. Mohamed, Computer Science and Engineering Department, Yanbu Industrial College, KSA.

ABSTRACT

The combined guard channels and mobile assisted with handoff queueing call admission control is studied. Two customer types, narrowband (voice calls) and wideband (data, video and media) are considered. Matrix algorithmic techniques are used to solve the balance equations to calculate the different performance measures of the system. The results indicate that when handoff call are queued, handoff call dropping is reduced for both types of calls and there is an increase in the bandwidth utilization. There is no noticeable change in the blocking probability of new calls. Increasing the size of the queue, led to further reduction in the handoff call dropping and increase in the bandwidth utilization.

KEYWORDS

Call admission control, handoff, guard channels, mobile assisted handoff.

A Mobile Application to Enable Donation of Devices Within a Community With the Potential Social and Environmental Impact

Shengyu Zhang1, Jonathan Sahagun2, 1Rancho Cucamonga High School, 11801 Lark Dr, Rancho Cucamonga, CA 91701, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768.

ABSTRACT

The project aims to develop a mobile application to increase device donation within a community and evaluate its ef ectiveness in increasing donation and user satisfaction [1]. The background of the problem is presented along with the hypothesis that the mobile application will increase donation by making it more convenient and increasing awareness of the need for donation [2]. The proposed solution involves conducting two studies: one to measure the number of devices donated by participants who have access to the mobile application and one to measure the satisfaction level of users who donate via the mobile application compared to traditional methods. The key technologies and components of the program are outlined, including a user-friendly interface and features such as device compatibility and donation tracking. Challenges encountered during development are discussed, including issues with testing and user feedback. The application is tested in various scenarios to ensure functionality and usability. The results show an increase in the number of devices donated and higher satisfaction levels among users who donate via the mobile application [3]. The projects importance is highlighted by the potential to make a positive impact on the community and improve access to technology for those in need.

KEYWORDS

Digital divide, Device donation, E-waste reduction, Community engagement.

A Comparative Study of Denoising Techniques for Improving 5g Communication at 3.5ghz. Simulation Approach

Seyi E. Olukanni,Department of Physics, Confluence University of Science and Technology, Nigeria

ABSTRACT

This paper presents a comparative study of denoising techniques for improving 5G communication at 3.5GHz. A 5G communication system comprising a transmitter, a channel, and a receiver is simulated with MatLab and three types of noise (thermal noise, intermodulation noise, and external interference) are introduced to the generated signal. The wavelet, PCA, weiner, median filter, and the karmer filter are used to denoised the signal with only thermal noise and also denoise the signal with all the noise present.Their perfomances are measured using signal-to-noise ratio (SNR), mean square error (MSE), and peak signalto-noise ratio (PSNR).The results show that karmer filter outperforms the other techniques in terms of MSE, SNR and PSNR.These findings can be valuable for researchers and practitioners in the field of 5G communication system design and implementation, as they provide insights into the most effective denoising techniques for improving 5G communication performance.

KEYWORDS

5G, communication, Denoising, Wavelet, Wiener Filtering, PCA, Median Filtering, Kalman Filtering.

A Mobile Application to Evaluate the Relationship Between Countries or Areas Based on Twitter

Zimo Jiang1, Yang Liu2, 1Irvine High School, 4321 Walnut Ave, Irvine, CA 92604, 2Computer Science Department, California State Polytechnic University, Pomona, CA91768

ABSTRACT

In recent years, there has been a noticeable deterioration in international relations between various countriesaround the world. This has led to an increase in misunderstandings, cultural clashes, and even conflicts between dif erent nations. Many people are feeling the ef ects of this breakdown in relations, especially those who are trying to navigate interactions with individuals from dif erent countries. To address this problem, an app, which aims to help people understand the relationship between dif erent countries, is designed. The app is called Country Relations and is designed to provide users with a comprehensive understanding of the financial and social relationship between dif erent countries. Country Relations uses an algorithm that automatically collects news keywords to analyze a large database of economic or social information from around the world. By entering two countries into the application, users can obtain an accurate assessment of the relationship between these two countries. It might be useful for those who are planning to travel or work abroad, as well as for individuals who are interested in learning more about dif erent cultures. In conclusion, the breakdown in international relations in recent years has created a need for new tools that can help people understand the relationship between dif erent countries. This app is designed to fill this gap, providing users with a comprehensive understanding of the financial and social relationship between dif erent nations.

KEYWORDS

Country Relationship, Twitter, Thunkable, Mobile Application.

A Helpful Mobile Application to Assist the Behaviors of Autistic People Through Mini Games Created Using Unity

Leon Huang1, Moddwyn Andaya2 ,1Germantown Friends School, 31 W Coulter St, Philadelphia, PA 19144 ,2Computer Science Department, California State Polytechnic University, Pomona, CA91768

ABSTRACT

With proliferating rates of people being diagnosed with autism, it has rung the bell for immediate change [7]. In an efort to ring the bell louder — though minimalistically — this app was developed to make life easier for autistic kids through the refining of their comprehension skills, decision-making skills, and restrictive behaviors [8]. This was done through the making of minigames and an adventure story. Some minigames were designed to cater to the restrictive behaviors of autistic kids by making the games more engaging. Other games focused on improving comprehension skills, such as memory or vocabulary. The adventure game tested both comprehension and decision- making skills. Despite the app s positive impact, there were blind spots due to the complex nature of autism. The best solution was to continuously tinker with the app to ensure maximum compatibility with the autistic audience. Although autism is a dif icult diagnosis to cure, such an app can assist in making the lives of autistic kids easier. With increasing rates of autism diagnosis, this app serves as a reminder of the need for more resources to cater to the growing population of autistic individuals [9].

KEYWORDS

Autism, Behavior, Minigames, Development.

Shootpro: an Interactive and Immersive Basketball Shooting Practice Assistance System Using Artificial Intelligence and Computer Vision

Yuetpang Chen1, Lin Yang2, Marisabel Chang3, 1, 2Thayer Academy, 745 Washington St, Braintree, MA 02184,213711 Somerset Ln SE, Bellevue WA 98006,3Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Today, millions of people watch basketball like the NBA and many have a favorite player whom they admire [4]. Some even want to play the sport like their favorite star. However, for those who haven’t tried the sport before, basketball can be very difficult. For example, beginners can miss shots because their shooting form changes every time, but they don’t know that its changed, resulting in repeated misses as they don’t fix it. Also, some people don’t know what a “correct shot” looks like and therefore wouldn’t know how to improve their shots. This paper proposes a software to solve this problem. This software uses mediapipe poses, AI comparison, and cv2 to help users identify the problems above and fix them [5]. We applied our application to the real-world basketball court and conducted a qualitative evaluation of the approach. The results show that with the help of this application, basketball players shoot with a better accuracy and form.

KEYWORDS

Basketball, Corrector, Shooting Form.

How to Use Classical Operation in Digital Bits to Simulate Quantumbits for the Rsa Cryptosystem

Jun-Ya Wang1, Xui-Chengn Chang2, Hung-Ju Wang3, 1National Taiwan University of Science and Technology, 2National Chengchi University, 3Bureau of Standards, Metrology, and Inspection

ABSTRACT

In quantum algorithm, the Shors algorithm can find prime decomposition of very big numbers easily and break RSA encryption much faster and more efficiently than in the classical case. How to complicant the public key to slow down the speed and efficiency of Shors algorithm to secure our RSA encryption scheme is main issue in this study. By using classical random simulation to operation as quantum bits to complicate the RSA cryptosystem, even Shors algorithm can not to find prime decomposition of very big numbers n with qubits random simulation easily.

KEYWORDS

encryption, decryption, key, quantum bits, simulation.

Efficientfair and Robust Spdz-like Multi-party Computation

Chung-Li Wang, Alibaba Inc., Hangzhou City, Zhejiang Province, China

ABSTRACT

Effective multi-party computation protocols have been developed, but concerns regarding privacy and correctness persist. Classic results demonstrate that guaranteed output delivery can be achieved by assuming fairness and identifiable abort. However, it is still challenging to design an efficient implementation that can deliver correct outputs while maintaining robustness and fairness, if the majority is malicious. To address this issue, we have redesigned the secret-sharing mechanism and employed a semi-trusted third party (TTP) as the key manager to provide optimistic backup for output delivery. The verification and delivery procedures prevent the malicious parties from “stealing” the output, when there is at least one honest party. Furthermore, the TTP has no knowledge of output, so even if he is malicious and colluding, we only lose fairness. The decryption is needed only when misconduct is detected. Our scheme also enables identified abort for offline preprocessing, and the audit of the offline sub-protocols can be publicly performed, holding corrupted parties accountable before receiving private inputs. With fairness and identifiable abort, output delivery is guaranteed by excluding the cheaters.

KEYWORDS

Efficient Multi-Party Computation, Public Verifiability, Robustness, Fairness, Semi-Trusted Third Party.

Performance Analysis Of AODV And DSR Routing Protocols Under Blackhole Attack Using Ns-2

Ferdinand Alifo1 Mustapha Awinsongya Yakubu2 and Prof. Michael Asante3, 1MIS/Computer Dep., Ministry of Local Government, Local Gov’t Service, Sekyere East District Assembly, Ghana, 2University of Cincinnati Ohio, USA, 3Department of Computer Science, Kwame Nkrumah University of Science and Technology, Ghana

ABSTRACT

Mobile Ad-Hoc Networks (MANETs) are wireless networks without a fixed infrastructure, allowing nodes to move freely and act as both routers and hosts. Nodes establish virtual links and use routing protocols like AODV, DSR, and DSDV for connections. Security is a concern, with the Blackhole attack being a notable threat where a malicious node drops packets instead of forwarding them. The paper used NS-2.35 ns-allinone-2.35 version for simulating the impact of Blackhole nodes and implementing AODV and DSR protocols. The study analyzed average throughput, packet delivery ratio, and residual energy as metrics, observing that AODV showed better energy efficiency and delivery than DSR, but DSR performed better in throughput. Environmental factors and data sizes were also considered in the analysis.

KEYWORDS

Performance Analysis, AODV, DSR, MANET, Protocols, Security, Blackhole, Metrics, Attack, NS2

An Informational Hub That Utilizes Modern Application User Interfaces to Encourage Healthy Lifestyles

Weibo Jin1, Megan Liu2, 1University High School, 4771 Campus Drive, Irvine, CA 92612, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

The idea for this app is a platform for people and especially athletes to know proper dieting, exercising, and how to recover from workout-related accidents [2]. I had to go online and search up everything I needed to know and sometimes I would get false information from the wrong websites. Athletes should be able to see what is good for them to eat, what kinds of workouts they should do everyday, as well as how to recover from certain injuries that they may sustain. When the user logs in to the app they will see options that say recovery exercise news and nutrition pages that contain all the information they will need.The nutrition page will display some common good foods to eat and their data such as calories, carbs, and more. The exercises page will list several important exercises vital to a good workout. Lastly, the injury page, also referred to as the recovery page, will show users a picture of the human body and allow them to select certain parts of the body to read up on relevant information pertaining to injuries around that area [3]. I also made 2 experiments to help me know and fix the app’s blindspot, the first one is a survey i give to my friends to try my app and fill it out, the second one is i follow the workouts and foods on my app for one day and compare to american’s daily nutrition and workout plans.

KEYWORDS

Fitness, Exercise, Database, Injuries.

An Emotion Detection Mobile Application to Decrease Potential Mental Disorder Among Seniors Using Sentiment Analysis From Audio Data

Tengjie Qiu1, Daniel Carter2, 1Mater Dei High School, 1202 W Edinger Ave, Santa Ana, CA 92707, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

We wanted to create a better, more trustworthy solution for caretakers to determine the emotion and feelings their patients are experiencing. This is useful for caretakers to adjust how they go about caring for their patients.To solve this, we decided to create a mobile consumer application. Architecturally, the user (caretaker) will be using this mobile app as a front end which will record and send audio of the patient to a backend service. The service will be hosted on AWS and it will be a sentiment analysis algorithm written in Python. The service will analyze and determine the feeling of the patient and send it back to the front end for the caretaker to see. The front end was written in Flutter. To evaluate the effectiveness of the proposed mobile application, we conducted testing focused on two key aspects: accuracy and response speed. The accuracy of the sentiment analysis algorithm was assessed by comparing the analysis results of pre-recorded audio with predetermined feelings. This evaluation aimed to measure the algorithms ability to correctly identify and classify emotions. Additionally, we tested the speed of response by sending audio samples of varying lengths, ranging from 2 seconds to 60 seconds. The objective was to determine the optimal response time for providing feedback on the users mood. Our findings revealed that the algorithm demonstrated high accuracy in detecting emotions within the tested audio samples. Moreover, the ideal response time for generating feedback was identified as 5 seconds, striking a balance between promptness and accuracy. These testing results validate the efficacy of the proposed application in accurately analyzing sentiment and providing timely responses, supporting its potential as an effective tool for monitoring and addressing the mental well-being of elderly individuals. This proposed mobile app, utilizing sentiment analysis, offers a convenient and accurate means of monitoring and addressing the mental well-being of elderly individuals. Its potential to combat loneliness and provide timely support makes it a valuable tool for improving their overall quality of life.

KEYWORDS

Sentiment Analysis, Audio Data, Mobile Application, Mental Disorder.

An End-to-end Gsm/sms Encrypted Approach for Smartphone Employing Advanced Encryption Standard (Aes)

Wasim Abbas1, Salaki Reynaldo Joshua2, Asim Abbas3, Je-Hoon Lee4 and Seong Kun Kim5, 1, 2, 4 Department of Electronics, Information and Communication Engineering, Kangwon National University, Samcheok-si, Republic of Korea, 3Division of Computer Science, Mathematics and Science, St. John’s University, Queens NY 11439, USA, 5Department of Liberal Studies, Kangwon National University, Samcheok-si, Republic of Korea

ABSTRACT

Encryption is crucial for securing sensitive data during transmission over networks. Various encryption techniques exist, such as AES, DES, and RC4, with AES being the most renowned algorithm. We proposed methodology that enables users to encrypt text messages for secure transmission over cellular networks. This approach utilizes the AES algorithm following the proposed protocols for encryption and decryption, ensuring fast and reliable data protection. This approach ensures secure text encryption and enables users to enter messages that are encrypted using a key at the senders end and decrypted at the recipients end, which is compatible with any Android device. SMS are encrypted with the AES algorithm, making them resistant to brute-force attempts. As SMS has become a popular form of communication, protecting personal data, email alerts, banking details, and transactions information. It addresses security concerns by encrypting messages using AES and cryptographic techniques, providing an effective solution for protecting sensitive data during SMS exchanges.

KEYWORDS

AES, SMS, Android, Privacy, Encryption, Decryption, communication systems .

Precision Pick-up of Micro Objects Using String-based Soft Robotic Grippers

Byung Jun Kwon1 and Gyu Tae Bae2, 1Byung Jun Kwon, Cornerstone Collegiate Academy of Seoul, Seoul, Republic of Korea, 2Gyu Tae Bae, University of California, Berkeley, Berkeley, United States

ABSTRACT

We introduce a novel string-based soft robotic gripper, capable of gentle and precise manipulation of delicate and small objects. The primary challenge lies in delicately handling objects of varying shapes and sizes without causing damage, a prevalent issue with traditional hard grippers. Our solution employs a string-based design, where the strings envelop the object, providing secure and damage-free grip. A motor torque sensor is utilized to optimally control the gripping pressure, preventing over-gripping and ensuring object integrity. We have successfully tested our soft gripper on delicate items ranging from grains of rice to strawberries. This innovative approach presents a solution to two pressing problems: the labor-intensive and potentially damaging manual picking of delicate items, and the inability of conventional robotic grippers to handle small and delicate objects effectively. Furthermore, the versatility and delicate handling of our soft gripper opens up potential applications in various fields such as agriculture, healthcare, and manufacturing. The design and performance of the soft gripper, its advantages over traditional grippers, and its potential applications are explored in this paper. We demonstrate the efficacy of our design through experimental results, confirming the robustness and adaptability of the string-based soft gripper.

KEYWORDS

Soft robotics,Gripping technology,Manipulation techniques,Object handling Material science,Robotics engineering,Precision control,Damage prevention, Object integrity preservation.

An Intelligent Mobile Application to Help Students with Problems Between their Peers using Machine Learning

Audrey Chen1, Victor Phan2, 1West Windsor-Plainsboro High School North, 90 Grovers Mill Rd, Plainsboro Township, NJ 08536, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Tutoring is not a commonly available service for middle and high school students who often have to learn the toughest subjects in the K-12 education system [1][2]. This can negatively impact their learning and cause losses in opportunities that could have been avoided. In response, we suggest a mobile application that is able to assist students in their learning as well as help them educate others so that all students can learn together [3]. This application uses the Flutter framework as well as Google’s Firebase service to store user-generated data [4]. An AI recommender system as well as a subject assignment system is hosted on a Python Flask backend server [5]. It will determine what questions someone should look at, as well as what kind of subject a question seems to be, respectively. These systems rely on an AI that uses natural language processing. To test the effectiveness of our application, we devise two experiments. In the first experiment, we determine the accuracy of our subject assigner by giving it several mock questions. In our second experiment, we compare and contrast different recommender systems. Ultimately, our subject assigner is at 50% accuracy and the recommenders we used were roughly the same in accuracy. Overall, this application is polished and with some more improvements to the backend and AI integration, it will be a useful tool for students who need an extra boost in school.

KEYWORDS

Education, Database, Natural Language Processing, Machine Learning

An Intelligent System to Assist Students in Engagement with their Studying using Generative Artificial Intelligence Models

Haozhe Yu1, Lin Yang2 and Tami Takada3, 1Pacific Academy, 4947 Alton Pkwy, Irvine, CA 92604, 213711 Somerset Ln SE, Bellevue, WA 98006, 3Computer Science Department, California State Polytechnic University, Pomona, CA 91768

ABSTRACT

Oftentimes students in the high school system tend to have the least amount of studying assistance despite being in the most rigorous curriculums that the K-12 education system has to offer. Students need someone to guide them on how to complete their homework. TeachNow is a proposed application that would help these students by allowing them to post to a global message board and help out each other. The app centrally relies on a ChatGPT API, to be used by students when no one has responded to their question yet [1]. It works by converting the user’s question into a prompt and then sending it over to the ChatGPT API for processing [2]. Students are able to get these responses from ChatGPT as soon as their question is posed. To test the effectiveness of this system, we perform a test of the ChatGPT API by asking it several mock questions, to which the results were generally desirable [3]. With further revisions, this application would be a perfect fit for students struggling with their education.

KEYWORDS

ChatGPT, Tutoring, Education, Database, Artificial Intelligence

Utilisation of Open Intent Recognition Models for Customer Support Intent Detection

Dr.Rasheed Mohammad, Oliver Favell, Shariq Shah, Emmett Cooper, Edlira, School of computing and digital technology, Birmingham City University, United Kingdom

ABSTRACT

Businesses have sought out new solutions to provide support and improve customer satisfaction as more products and services have become interconnected digitally. There is an inherent need for businesses to provide or outsource fast, efficient and knowledgeable support toremain competitive. Support solutions are also advancing with technologies, including use of social media, Artificial Intelligence (AI), Machine Learning (ML) and remote device connectivity to better support customers. Customer support operators are trained to utilise these technologies to provide better customer outreach and support for clients in remote areas. Interconnectivity of products and support systems provide businesses with potential international clients to expand their product market and business scale. This paper reports the possible AI applications in customer support, done in collaboration with the Knowledge Transfer Partnership (KTP) program between Birmingham City University and a company that handles customer service systems for businesses outsourcing customer support across a wide variety of business sectors. This study explored several approaches to accurately predict customers' intent using both labelled and unlabelled textual data. While some approaches showed promise in specific datasets, the search for a single, universally applicable approach continues. The development of separate pipelines for intent detection and discovery has led to improved accuracy rates in detecting known intents, while further work is required to improve the accuracy of intent discovery for unknown intents.

KEYWORDS

Intent Recognition, Customer Support, Intent Detection