Accepted Papers

Blockchain-Resilient Framework for Cloud-based Network Devices within the Architecture of Self-Driving Cars

Mirza Mujtaba Baig, Department of Information Technology, University of the Cumberlands, Williamsburg, KY

ABSTRACT

Artificial Intelligence (AI) is evolving rapidly and one of the areas which this field has influenced is automation. The automobile, healthcare, education and robotic industries deploy AI technologies constantly and the automation of tasks is beneficial to allow time for knowledge-based tasks and also introducing convenience to everyday human endeavors. The paper reviews the challenges faced with the current implementations of autonomous self-driving cars by exploring the machine learning, robotics and artificial intelligence techniques employed for the development of this innovation. The controversy surrounding the development and deployment of autonomous machines e.g., vehicles begs the need for the exploration of the configuration of the programming modules. This paper seeks to add to the body of knowledge of research assisting researchers in decreasing the inconsistencies in current programming modules. Blockchain is a technology of which applications are mostly found within the domains of financial, pharmaceutical, manufacturing, artificial intelligence. The registering of events in a secured manner as well as applying external algorithms required for the data analytics are especially helpful for integrating, adapting, maintaining, and extending to new domains especially predictive analytics applications.

KEYWORDS

Artificial Intelligence, Automation, Big Data, Self-driving Cars, Machine Learning, Neural Networking Algorithm, Blockchain, Business Intelligence.

Clock Gating Flip-Flop using Embedded XoR Circuitry

Peiyi Zhao¹, William Cortes¹, Congyi Zhu² and Tom Springer¹, ¹Fowler School of Engineering, Chapman University, Orange, CA, USA, ²Nangjing University, Nanjing, China

ABSTRACT

In this paper, a novel flip-flop using clock gating circuitry with embedded XOR, GEMFF, is proposed. Using post layout simulation with 45nm technology, GEMFF outperforms prior state-of-the-art flip-flop by 25.1% at 10% data switching activity in terms of power consumption.

KEYWORDS

Dynamic Power, Low Supply Voltage, Flip-Flop.

Design and Implementation of Agricultural Machinery Equipment Scheduling Platform Based on CBR

Wen Li, Zhengyu Bai and Qi Zhang, School of Management, Jiangsu University, Zhenjiang, China

ABSTRACT

The demand for smart scheduling platform in agriculture, particularly in the scheduling process of machinery equipment, is high. With the continuous development of agricultural machinery equipment technology, a large number of agricultural machinery equipment and agricultural machinery cooperative service organizations continue to appear in China. The large area of cultivated land and the large amount of agricultural activities in the central and western regions of China have made the demand for smart and efficient agricultural machinery equipment scheduling platforms more intense. In this study, we design and implement a platform for agricultural machinery equipment scheduling to allocate agricultural machinery equipment resources reasonably. With agricultural machinery equipment scheduling platform taked as the research object, we discuss its research significance and value, use the service blueprint technology to analyze and characterize the agricultural machinery equipment schedule workflow, the network analytic method to obtain the demand platform function requirements, and divide the platform functions through the platform function division diagram. Simultaneously, based on the case-based reasoning(CBR) algorithm, the equipment scheduling module of the agricultural machinery equipment scheduling platform is realized; finally, a design scheme of the agricultural machinery equipment scheduling platform architecture is provided and the visualization interface of the platform is established via VB programming language. It provides design ideas and theoretical support for the construction of modern agricultural equipment information scheduling platform.

KEYWORDS

Case-based Reasoning, Service Blueprint, System Design, AN, VB Programming Language.

What are the Aspects of Adopting Computer-Based Exams and Do they Impact Negatively on Students?

Rabea Emdas¹ and Ahmed Alruwaili², ¹Faculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, Victoria 3122, Australia, ²Department of Computer Science and Information Technology, La Trobe University, Bundoora, Victoria 3086, Australia

ABSTRACT

Computer-based exams (CBEs) have been used in various courses, such as schools, universities and other training centres. As there are many educational institutions which have chosen to convert from paper test system to computer- based exam. However, adopting computer tests may lead to some difficulties for the students, which relates to technical defects and lake of computer skills of some students when they applying the computer based exams. The purpose of the essay was to determine negative and positive effects on the students of using computer-based exams and focus on some of suggesting solutions to the negative effects, such the exams to make continuous use of computer- based possible. In the first section the computer test, which could cause negative effects on students due to various levels of skills to use computer and some technical problems was examined. The design of the computer examination system requires careful planning and study from several aspects before becoming officially accepted, the computer-based exams still have a few problems which may lead to difficulties in using computer exams. Then the many benefits which could be gained by using computer-based exams, such as the student will be more independent with computer test were described. In addition, the students have accessible to the exams through the internet network. Finally, the effectiveness of certain strategy to solve the negative effects of computer-based exams were argued. developing the solutions of the technical problems are required for computer test, where improving the input methods questions and corrections. It was concluded that the computer exam, with adjustments, is more suitable for students.

KEYWORDS

Computer-Based Exams, Computer Test, Computer System Examinations, Computer Test model.

Evaluating the Potentials of Piezoelectric Energy Harvesters (PEH)

Agwu Abu Paul, Kamil .R. Kehinde, Aliyu .Y. Sharif and Belamo Jessica, Science laboratory and Technology ResearchDepartment, Nigerian Building and Road Research Institute, FCT Abuja, Nigeria

ABSTRACT

Renewable energy demand is at alarming demand thus there is Mechanical energy is available in the environment from vibrations induced by flowing air or water to vibrating structures & moving objects and so on. This energy can be converted to other forms of energy for various applications. One of such applications utilizes electromechanical conversion characteristics of piezoelectric material to capture, store and generate energy at a micro-level. This study presents an assessment of Piezoelectric Energy Harvester (PEH) technology to establish its viability and applicability for energy harvesting. The piezoelectric tiles were inspected for cracks before use and stress was applied on the stacked samples with adhesive in series to determine the electric output of the samplesusing the compressive test machine and 2.5kg proctor compaction rammer. Also, X-ray fluorescence analysis (XRF) was carried out on the samples to ascertain its’ chemical composition. XRF result showed that the PEH samples contained a high percentage of Lead (Pb) and Zirconium (Zr) indicating the samples were ferroelectric material i.e. Lead Zirconate Titanate (PZT). However, a high proportion of silver was observed as a result of the coating applied to the PZT material. It was also observed that there is a direct relationship between stress & voltage and a single PZT tile of 20mm and 35mm diameter depending on the stress applied produced an average voltage of 0.5VAC – 21.9VAC respectively. Lastly, a control circuit was designed and a PEH tile was fabricated on Polyvinylidene Fluoride (PVDF) sheet and tested to map out the average voltage that can be generated to power an LED concerning applied human stress when stepped on.

KEYWORDS

Energy harvesting, Piezoelectric, Electromechanical conversion, Ferroelectric, Electrical output, Electromechanical.

A New Method on Service Description Supporting Customization in Structured Networks

Delin Ding, SEU, china

ABSTRACT

With the growing diversity of new technologies and networked services, the limitations of present layered network are more and more outstanding. The layered structure makes it hard to design a protocol for each new service. An attractive alternative is to construct a structured and modular architecture for the design and implementation of new standards and protocols. Structured networks provide a service through the dynamic composition of generic protocol functions blocks with respect to user requirements. In order to make such mechanism works properly, how to describe networked services becomes one of most important issues. Therefore, this paper presents a new method on service description supporting customization. Firstly this paper presents several new kinds of structured networks which can be divided into two types, and then the categories of atomic services and service instances are summarized. The second part introduces a new description method to networked services. The method includes some formal definitions, and its process model is described by process algebra. The method can be used to provide precise formal description and analysis about network behavior. Furthermore, this paper discusses a study of description rules based on XML schema. Finally, the simulation results have proved its feasibility and effectivity.

KEYWORDS

service description, structured networks, customizable, process algebra.

Data Transmission by Ultrasound: Loss of Confidentiality

Clay Schneider Vallejo Pinilla, Carlos Augusto Ruiz Patiño, Héctor Fernando Vargas Montoya, Departamento de Sistemas de Información, Universidad Instituto Tecnológico Metropolitano, Medellín - Colombia

ABSTRACT

Information and data can be breached in different ways and by multiple means; it all depends on the storage and transmission process. Every day, cyber-attackers look for mechanisms and tools to gain access to data and information that may be sensitive for organizations, and new data transmission methods that use ultrasonic waves can allow malicious individuals to obtain data from computer systems by controlling elements as common as their speakers. This poses an important challenge for networks administrators and computer security personnel because they will need to identify possible information leakages in such unconventional means. In this article, the possibility of transmitting information using ultrasound and the peripherals of desktop computers was analyzed, which violates the principle of confidentiality. A technical implementation was made for sending and receiving data by ultrasound using GNU Radio and a self-developed application for data visualization. It was possible to send information at ultrasonic frequencies (above 18,000 Hz) through the speakers of a computer, and the data were successfully received and visualized in another one.

KEYWORDS

Cyberattack, confidentiality, exfiltration, ultrasound.

A Probabilistic-Based Approach for Ads Recommendation

Djalila Boughareb, Hazem Bensalah, Hamid Seridi and Nadir Farah, Labstic Laboratory, University of Guelma, Guelma, Algeria

ABSTRACT

In this paper, we propose a novel ads recommender system that learns the preferences of an online social network users and clusters them in different communities of interests. Then the system suggests interested ads to target users’. The system is based on k-means and probabilistic matrix factorization method. The used dataset is collected explicitly from Hazmit social network developed in order to collect data and evaluate recommendations. The obtained primary results are encouraging where over of 92% of recommended ads are judged interesting for users.

KEYWORDS

Recommender Systems, k-means, probabilistic matrix factorization, ads recommendation.

Detect Text Topics by Semantics Graphs

Alex Romanova, Melenar, LLC, McLean, VA, US, 22101

ABSTRACT

It is beneficial for document topic analysis to build a bridge between word embedding process and graph capacity to connect the dots and represent complex correlations between entities. In this study we examine processes of building a semantic graph model, finding document topics and validating topic discovery. We introduce a novel Word2Vec2Graph model that is built on top of Word2Vec word embedding model. We demonstrate how this model can be used to analyze long documents and uncover document topics as graph clusters. To validate topic discovery method we transfer words to vectors and vectors to images and use deep learning image classification.

KEYWORDS

Graph Mining, Semantics, NLP, Deep Learning, CNN Image Classification.

A Data-Driven Intelligent Application for Youtube Video Popularity Analysis using Machine Learning and Statistics

Wenxi Gao¹, Ishmael Rico², Yu Sun³, ¹University of Toronto, Toronto, ON M5S, Canada, ²University of California, Berkeley, Berkeley, CA, 94720, ³California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

People now prefer to follow trends. Since the time is moving, people can only keep themselves from being left behind if they keep up with the pace of time. There are a lot of websites for people to explore the world, but websites for those who show the public something new are uncommon. This paper proposes an web application to help YouTuber with recommending trending video content because they sometimes have trouble in thinking of the video topic. Our method to solve the problem is basically in four steps:YouTube scraping, data processing, prediction by SVM and the webpage. Users input their thoughts on our web app and computer will scrap the trending page of YouTube and process the data to do prediction. We did some experiments by using different data, and got the accuracy evaluation of our method. The results show that our method is feasible so people can use it to get their own recommendation.

KEYWORDS

Machine Learning, data processing, SVM, topic prediction.

Design and Implementation of an IoT Based LPG and Co Gases Monitoring System

Otoniel Flores-Cortez¹, Ronny Cortez² and Bruno González³, ¹Department of Applied Sciences, Universidad Tecnologica de El Salvador San Salvador, El Salvador, ²Associate researcher Universidad Tecnologica de El Salvador, San Salvador, El Salvador, ³Associate researcher, Universidad Tecnologica de El Salvador, San Salvador, El Salvador

ABSTRACT

Nowadays use of liquefied petroleum gas (LPG) has increased. LPG is an asphyxiating, volatile and highly flammable gas. In a LPG leak situation, potential health accidents are increased either by inhalation or by combustion of the gas. On the other hand, carbon monoxide (CO) is a toxic gas that comes mainly from combustion in car engines. Breathing CO-polluted air can cause dizziness, fainting, breathing problems, and sometimes death. To prevent health accidents, including explosions, in open or closed environments, remote and real-time monitoring of the concentration levels of CO and LPG gases has become a necessity. The aim of this work is to demonstrate the use of Internet of Things (IoT) techniques to design and build a telemetry system to monitor in real-time the concentration of GLP and CO gases in the surrounding air. To implement this work, as central hardware there is a microcontroller, CO and PLG sensors on the electronic station. Besides, Amazon Web Services (AWS) was used as an IoT platform and data storage in the cloud. The main result was a telematics system to monitor in real time the concentrations of both GLP and CO gases, whose data is accessible from any device with internet access through a website. Field tests have been successful and have shown that the proposed system is an efficient and low-cost option.

KEYWORDS

Internet of things, Microcontroller, Remote sensing, LPG, CO.

Empirical Study of Blockchain and IoT Solutions for Supply Chain Management (SCM)

R. Leela Velusamy, Shivani Chander, Swathi Dhamodaran, Vikram Kumaresan, Department of Computer Engineering, National Institute of Technology, Tiruchirappalli, India

ABSTRACT

This paper explores the use of Distributed Ledger Technologies and IoT-based applications for the Supply Chain Management of perishable assets using empirical evidence. The intention of this research is to understand the feasibility of using these technologies in complex and real-time ecosystems like those of the supply chain. With the advent of distributed ledger technologies, there has been an increased interest in using it for solving key issues concerning traceability. Telemetry when used with Blockchain technologies also allows us to create a secure and shared economy that allows for real-time tracking, pricing, and distribution mechanisms. But these nascent technologies come with issues concerning scalability, latency, and mining time which we attempt to quantify in this paper.

KEYWORDS

SCM, IoT, Blockchain, Telemetry.

An IoT based Door Lock System for the Application in Smart Cities in Developing Countries

Nusrat Sultana and Dr. Farruk Ahmed, School of Computer Science and Engineering, Independent University, Bangladesh Dhaka, Bangladesh

ABSTRACT

The new technologies characterizing the Internet of Things allows real smart environments able to provide advanced services to the users. The project presents a low-cost and flexible smart door control and monitoring system using an embedded microprocessor and microcontroller discussing computational offloading and cloud computing for face recognition in mobile device. Computer vision and face recognition is a widely researched subject nowadays due to the technological advancement in computational power of low powered embedded processors making it feasible to deploy image processing algorithms. This project proposes remote access to home and office by Face Recognition and Image Processing. Part of this project consists of three main sub-systems namely face detection, face recognition and automatic door access control which has been implemented and verified successfully. The face recognition and detection process were implemented by modifying Principal Component Analysis (PCA) approach to Fast Based Principal Component Analysis (FBPCA) approach using both Haar Cascade and LBP for face detection implemented on the captured image using a pi-camera and compared with the images in the dataset. If the image matches with the corresponding image of the dataset the door will unlock automatically. This projects also highlights the advantages and limitations of three types of face recognition methods and among them applying the best method regarding the project.

KEYWORDS

Internet of Things (IoT), Raspberry pi, Open CV, Python, Face Detection, Face Recognition, Cloud Computing, Computation Offloading etc.

Blockchain Decentralized Voting for Verified Users with Focus on Anonymity

Piotr Pospiech, Aleksander Marianski and Michal Kedziora, Department of Computer Science and Management, Wroclaw University of Science and Technology, Wroclaw, Poland

ABSTRACT

The paper presents decentralized voting scheme for verified users while maintaining their anonymity. A blockchain network was applied, which is a decentralized and distributed database based on the Peer-to-Peer architecture. During the implementation, the Ethereum network was used. Thanks to this, it is possible to code the terms of the contract required to perform the transaction. Ethereum and the use of smart contracts were also discussed in paper. The implementation uses the blind signature protocol by David Chaum and encryption with the Rivest-Shamir-Adleman (RSA) algorithm. Presented in this paper scheme for blockchain decentralized voting for verified users with focus on anonymity is then fully implemented and identified potential issues are analysed and discussed.

KEYWORDS

Blockchain, e-voting, Ethereum.

An Applicability of Blockchain Model in Business use Case - A Technical Approach

Anitha Premkumar, Department of Computer Science and Engineering, Presidency University Rajankunde, Bangalore, Karnataka, India

ABSTRACT

Business network brings many organizations close together to achieve their desired goals and profit from it. People from different organizations may or may not know each other but still can be part of a business network. A major challenge with these business networks is how to provide trust among people and data security. Blockchain is another means through which many organizations in the current digital age are overcoming these problems with ease. Blockchains have also changed the way the business transactions with clients take place. Blockchain is a decentralized distributed ledger in a peer to peer network which can be public or private, and it enables individuals or companies to collaborate with each other to achieve trust and transparency between business and its clients. Many implementations of blockchain technology are widely available today. Each of them have their own strengths for a specific application domain. They can fundamentally alter electronic communications with a potential to affect all sorts of transaction processing systems. However, there are still many challenges of blockchain technology waiting to be solved such as scalability and adoptability. In this paper, we provide the knowledge on Blockchain technology and we present the applicability of blockchain in the business models and also discuss the relevant use cases for Banking and Supply Chain models.

KEYWORDS

Blockchain, Secure Web Transaction, Decentralized Distributed Ledger, Peer to Peer Network.

Studying the Applicability of Proof of Reputation(PoR) as an Alternative Consensus Mechanism for Distributed Ledger Systems

Oladotun Aluko¹ and Anton Kolonin², ¹Novosibirsk State University, Novosibirsk, Russia, ²Aigents Group, Novosibirsk, Russia

ABSTRACT

Blockchains combine several other technologies like cryptography, networking, and incentive mechanisms in order to support the creation, validation, and recording of transactions between participating nodes. A blockchain system relies on a consensus algorithm to determine the shared state among distributed nodes. An important component underlying any blockchain-based system is its consensus mechanism, which determines the characteristics of the overall system. This thesis proposes a reputation-based consensus mechanism for blockchain-based systems which we term Proof-of-Reputation (PoR) that uses the liquid rank algorithm where the reputation of a node is calculated by blending the normalized ratings by other nodes in the network for a given period with the reputation values of the nodes giving the ratings. The nodes with the highest reputation values eventually become part of the consensus group that determines the state of the blockchain.

KEYWORDS

Consensus, Distributed Ledger Technology, Blockchain,Reputation, Social Computing.

LEA-DNS:DNS Resolution Validity and Timeliness Guarantee Local Authentication Extension with Public Blockchain

TingXiong¹, Shaojin Fu¹, Xiaochun Luo² and Tao Xie¹, ¹National University of Defense Technology, Hunan, China, ²PLANews Media Center, Beijin, China

ABSTRACT

While the Domain Name System(DNS) is an infrastructureof the current network, it still faces the problemofcentralizationanddata authentication according to its concept and practice. Decentralizedstorage of domain names and user local verification using blockchainmay be effective solutions. However, since the blockchain is an add-onlytype database, domain name changes will cause out of date records tostill be correct when using the Simplified Payment Verification(SPV)mechanism locally. This paper mainly introduces Local Enhanced Authentication DNS(LEA-DNS), which allows domain names to be storedin public blockchain database to provide decentralization feature andiscompatible with the existing DNS. It achieves the validity and timelinessof local domain name resolution results to ensure correct and up to datewiththeMerkleMountainRangeandRSAaccumulator technologies.Experiments show that less than 3.052Kb is needed for each DNS request to be validated, while the validation time is negligible, and only9.44Kb of data need to be stored locally by the web client. Its compatibility with the existing DNS system and the lightness of the validationprotocols indicate that this is a system suitable for deployment widely.

KEYWORDS

Domain name system, Blockchain, RSA accumulator, Merkle Mountain Range.

Hierarchical Scheduling for Real-Time Periodic Tasks in Symmetric Multiprocessing

Tom Springer and Peiyi Zhao, Fowler School of Engineering, Chapman University, Orange, CA. USA

ABSTRACT

In this paper, we present a new hierarchical scheduling framework for periodic tasks in symmetric multiprocessor (SMP) platforms. Partitioned and global scheduling are the two main approaches used by SMP based systems where global scheduling is recommended for overall performance and partitioned scheduling is recommended for hard real-time performance. Our approach combines both the global and partitioned approaches of traditional SMP-based schedulers to provide hard real-time performance guarantees for critical tasks and improved response times for soft real-time tasks. Implemented as part of VxWorks, the results are confirmed using a real-time benchmark application, where response times were improved for soft real-time tasks while still providing hard real-time performance.

KEYWORDS

Real-time systems, hierarchical scheduling, symmetric multiprocessing, operating systems.

Facial Expression Recognition for Enabling Interaction with Individuals Affected by Profound Intellectual and Multiple Disabilities

Carmen Campomanes-Álvarez¹ and B. Rosario Campomanes-Álvarez², ¹Department of Computer Vision, CTIC Technological Centre, Gijón, Spain, ²Department of Artificial Intelligence, CTIC Technological Centre, Gijón, Spain

ABSTRACT

Individuals affected by profound intellectual and multiple disabilities remain immobile, have severe restricted mobility or are subject to multiple sensory and intellectual impairments. They are therefore unable to produce conventional behaviours that may serve to communicate a particular need. Consequently, they cannot develop the skills to use existing technological devices, as these tools require the understanding of conventional symbols. Within the INSENSION project, an intelligent platform for enabling the interaction of this kind of people with others is being developed. The system will identify the individuals, recognize their facial expressions, body gestures, vocalizations, physiological parameters, and context information, and then, associate these signals with a communication intent. In this work, a new facial expression recognition method is developed and properly configured to be included in the INSENSION platform, for the specific use by people with profound intellectual and multiple disabilities.

KEYWORDS

Facial Expression Recognition, Machine Learning, Computer Vision, Smart Assistive Technologies.

Development of the stock market trend forecasting system using multiple regression

Shaik Sameeruddin, Department of Computer Engineering, VIT-AP University, Amaravati, India

ABSTRACT

Stock market trend forecasting is an efficient medium for investors, public companies, and governments to invest money, taking into account profit and risk. Current studies on the development of stock-based prediction systems rely on data from social media (sentiment-based) and secondary data sources (financial-sites). However, the data obtained from these sources is usually scarce in nature. In addition, the selection of predictor variables is also low, which ultimately degrades the performance of the predictor model. The challenges associated with current methods can be solved. Propose an efficient prediction model with improved input data quality and revised predictor variables collection/inclusion. This work presents the results of the stock forecast by applying a multi-regression model using R software. The results show that 95% for the KSE 100 index data set, 89% for the Lucky cement and 97% for the Abbot company data set were expected by the proposed system. In addition, an easy-to-use interface is provided to help individuals and companies invest or not in specific stocks.

KEYWORDS

stock market, prediction, data sparse, multiple regression, stock predictors.

Ensemble Model for Chunking

Nilamadhaba Mohapatra, Namrata Sarraf, SwapnaSarit Sahu, Department of Data Science, Zeotap, Bangalore, India

ABSTRACT

Transformer Models have taken over most of the Natural language Inference tasks. In recent times they have proved to beat several benchmarks. Chunking means splitting the sentences into tokens and then grouping them in a meaningful way. Chunking is a task that has gradually moved from POS tag-based statistical models to neural nets using Language models such as LSTM, Bidirectional LSTMs, attention models, etc. Deep neural net Models are deployed indirectly for classifying tokens as different tags defined under Named Recognition Tasks. Later these tags are used in conjunction with pointer frameworks for the final chunking task. In our paper, we propose an Ensemble Model using a fine-tuned Transformer Model and a recurrent neural network model together to predict tags and chunk substructures of a sentence. We analyzed the shortcomings of the transformer models in predicting different tags and then trained the BILSTM+CNN accordingly to compensate for the same.

KEYWORDS

Natural Language Processing- Named Entity Recognition, Chunking, Recurrent Neural networks, Transformer Model.