Accepted Papers

System Design of Receiver Module for Emerging Warning Signal From　Navigation Satellite System Employing Slave Wireless Stations of Emergency Broadcast System

Keiko Shimazu1 Michi Hamashita2, Sora Masaki2, Tomoyo Shibata2, Soma Nishimura2, Taku Yamamoto2, Hiroyuki Yuasa3 and Yuno Sudo3, 1Advanced Institute of Industrial Technology, Tokyo, Japan, 2Tokyo Metropolitan University, Tokyo, Japan and 3Yokohama National University, Yokohama, Japan

ABSTRACT

This paper reports our systems design of GNSS (Global Navigation Satellite System) application system. That’s the first trial of employing GNSS as an emergency report communication service. The system will work for victims abandoned within specific areas where general communication infrastructure is down. This paper consists of 2 parts. The first one presents a structure of the receiving module of the emergency signal from QZSS, which is a Japanese Navigation Satellite System. The other part introduces a message format for this service developed jointly by the EU/ Galileo team. The purpose of developing this format was to solve the challenge of how to manage vary and complicated information in a limited area.

KEYWORDS

GNSS, QZSS, disaster mitigation, EWS.

Golfpro: a Pose-based Golf Coaching System Using Artificial Intelligence and Computer Vision

Andy Yu1 and Yu Sun2, 1Los Osos High School, 6001 Milliken Ave, Rancho Cucamonga, CA91737 and 2California State Polytechnic University, Pomona, CA, 91768, Irvine, CA92620

ABSTRACT

In the sport of golf, there are several main mechanics in each successful golf swing that brings consistency [1]. Inaddition, there are specific nuances in the golf swing that may be dif icult for recreational players to analyze anddetect. The main question is how an app can potentially detect these main techniques and compare themwheninputted two dif erent golf swings. Guided with mediapipe and cv2 technologies, we have built a software to analyzetwo golf swings simultaneously, and to compare them with one another, all into a smartphone application [2][3]. This paper will discuss key technologies that were utilized in order to create the program, the various challengesthat were faced in the process of creating the software, along with our methodologies [4]. The end result was anapplication that would detect various angles created based on certain golf positions, and then utilize themin orderto compare with another video, whether that be a professional player or a friend’s golf swing. Using a Pythonbackend and a Flutter-based frontend, the program can be utilized through a mobile device, and thus makes theprogram accessible to the public [5]. With the publishing of this application, users can start to deconstruct theirown golf mechanics without the complications and the high fee that is generally charged from coach one ononecoaching.

KEYWORDS

Golf, AI, Golf coach, Visual feedback.

Phase-II Validation of Agile Scrum Based Mvp Architecture Framework Model for Android Mobile Application Development Through a Delphi Based Expert Judgment Techniques Applied With Capability Maturity Model Integration

Mr.N.Rajasekaran1 and Dr.S.M.Jagatheesan1, 1Assistant Professor in Computer Applications, Kongu Arts and Science College (Autonomous), Erode, Tamilnadu, India and 1Associate Professor in PG and Research Department of Computer Science, Gobi Arts and Science College, Gobi, Tamilnadu, India

ABSTRACT

The validation is needed for any new methodological software proposals like architectures/frameworks and applications. It demands several real-life implementations. However, the IT industries are afraid to invest the money without the firm guarantee that they will be returned the entire expenditure amount of investment. Accordingly, the industries were using two technicians to pick and use the R&D (Research and Development) software’s. One is the research software models should be applied in real time projects and the second one is the same should be validated through Expert Judgment (EJT) Techniques. Industries may not apply all the research software’s in real time projects because it leads to increase the bugs and defects in the same projects. Hence most of the organizations use the EJT because it provides a less-cost initial validation of particular R&D software’s. The positive comments of Expert Judgments will lead to encourage the software developers and IT industries to pick and use the proposed research software models. Hence, the primary goal of this paper will assess the overall software Quality and outcomes of the Agile Scrum based MVP (Model View Presenter) Architecture Model (ASM-MVP) which is already developed as research software architecture for Android Mobile Application Development. The proposed models are validated through Phase –II Delphi based Expert Judgment Techniques and the Chronbach’s alpha reliability prediction Method which is used to predict the reliability of the proposed model. In this research we can get more positive comments from the Expert judgment team and got reliable alpha value comparing to Phase-I which is validated through us. Therefore, the already proposed Agile Scrum based MVP Architecture Model will give better result for android mobile application development.

KEYWORDS

Agile Scrum based MVP Architecture Model, Delphi, Expert Judgment and Alpha.

An Application That Combines Learning and Games to Make Learners Keep Interest in Learningm

Larry Zhang1 and Yu Sun2, 11Agoura High School, 28545 W Driver Ave, Agoura Hills, CA 91301 and 2California State Polytechnic University, Pomona, CA, 91768, Irvine, CA 92620

ABSTRACT

Learning a new language and a new culture is always fun and interesting at the beginning. However, when learners get deeper into the learning process, they find that whether it is memorizing vocabulary, learning different types of grammar, or learning a new culture that is completely different from the learners country, it becomes very difficult and learners gradually lose their enthusiasm for learning [1][2]. Also, some of the textbooks right now are published a long time ago. Teaching some 20 or 30 years agos culture wont help the learner and may make them misunderstand the modern culture of that country. So why cant we give the learner more accurate information and keep the learning process as fun as ever? This paper designs a software that combines the games and learning together. By setting up different scenarios, building a variety of representative buildings, adding various characters to communicate with, designing different culturally significant objects, and conceiving an interesting story plot to let people who are learning a new language or culture can learn in a unique and more fun way. After applying the app to language schools, Japanese language learner communities, and the Internet, the results showed that the app makes learners learn in a more relaxed atmosphere and makes them want to learn more [3].

KEYWORDS

2D RPG, Japanese culture and language, Unity, Explore.

An Autochess Game Designed to Improve the Critical Thinking Skills of Its Players

Yinjie Wu1 and Yu Sun2, 1Virginia Episcopal School, 400 VES Rd, Lynchburg, Virginia 24503 and 2California State Polytechnic University, Pomona, CA, 91768, Irvine, CA 92620

ABSTRACT

Providing critical thinking skills to people in an exciting and engaging manner is an issue that can hopefully be resolved with the introduction of a newly created autochess game [1][2]. Because this game only allows player interaction to occur before the battle starts in the preparation phase, the game encourages the player to think ahead and predict how the players team can defeat the enemy team based on which cards are selected to be added. To test the effectiveness of the game at improving the critical thinking skills of its players, an experiment was conducted in which five example questions from the Watson-Glaser test were provided to the participants of the survey to answer, then the participants would play through all three levels of the game [3]. Then, the participants would try the same five questions from the Watson-Glaser test again [4]. The results of the survey indicate that the game only provided a slight improvement in critical thinking skills.

KEYWORDS

Autochess, Critical Thinking, Mythical Creatures, Unity.

A Mobile Application for Analysing and Forecasting Crime using ARIMA with ANN

Gajaanuja Megalathan1 and Banuka Athuraliya2, 1Department of Computing Informatics Institute of Technology, 10 Trelawney Pl, Colombo 04, Sri Lanka, 2Department of Computing Informatics Institute of Technology, 10 Trelawney Pl, Colombo 04, Sri Lanka

ABSTRACT

Crime is one of our societys most intimidating and threatening challenges. With the majority of the population residing in cities, many experts and data provided by local authorities suggest a rapid increase in the number of crimes committed in these cities in recent years. There has been an increasing graph in the crime rates. People living in Sri Lanka has the right to know the exact crime rates and the crime rates in the future of the place they are living in. Due to the current economic crisis the crime rates have spiked. there have been so many thefts murders recorded within last 6-10 months. Although there are many sources to find out there is no solid way of searching and finding out the safety of the place. Due to all these reasons, there is need for the public to feel safe when they are introduced to new places. This mobile application will be a solution for this problem. Mainly for the tourists and people who newly move to a place will gain advantage of this application. Moreover, Arima Model combined with ANN is to be used to predict the crime rates. From the past researchers works it evidently clear that they haven’t used Arima model combined with Artificial Neural Network to forecast crimes.

KEYWORDS

Arima model, ANN, crime prediction, data analysis.

MVMNET: Graph Classification Pooling Method With Maximum Variance Mapping

Lingang Wang and Lei Sun, Sun Yat-sen University, China.

ABSTRACT

Graph Neural Networks (GNNs) have been shown to effectively model graph-structured data for tasks such as graph node classification, link prediction, and graph classification. The graph pooling method is an indispensable structure in the graph neural network model. The traditional graph neural network pooling methods all employ downsampling or node aggregating to reduce graph nodes. However, these methods do not fully consider spatial distribution of nodes of different classes of graphs, and making it difficult to distinguish the class of graphs with spatial locations close to each other. To solve such problems, this article proposes a Maximum Variance graph feature Multistructure graph classification method (MVM), which extracts graph information from the perspective of graph nodes feature and graph topology. From the nodes feature perspective, we enlarge the variance between different classes while maintaining the variance between the same class of data. Then the hierarchical graph convolution and pooling are performed from a topological perspective and combined with a CNN readout mechanism to preserve more graph information to obtain a graph-level representation with strong discrimination. Experiments demonstrate that our method outperforms several number of state-of-the-art graph classification methods on multiple publicly available datasets.

KEYWORDS

Double-view Graph Pooling, Constrained Maximum Variance, Hierarchical Graph Structure.

Smartyoutuber: a Data-driven Analytical Platform to Improve the Subscriber Growth and Sustainability Using Artificial Intelligence and Big Data Analysis

Muyang Li1, Erik Serbicki2 and Yu Sun3, 1Shanghai Jiaotong University, Shanghai, China, 200240, 2University of California, Irvine, CA 92620, and 3California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

Youtuber is a new type of freelancer, whose economic profit and personal reputation are highly decided by their own popularity on the Internet, which can be reflected directly by the number of subscribers accumulated. In order to develop the management of YouTube channels and get more advertisement benefits, youtubers need to maintain the current subscriber group and appeal to more new followers by making attractive videos. But they lack efficient methods to analyze their video quality and their communication with subscribers so that they can predict their future development and adjust present strategies. In this paper, we applied several machine learning algorithm and models to study the prediction of short and long term future subscriber increase (we call them as growth and sustainability of youtubers) by analyzing youtuber-related information including video content(e.g. topic type, video tags, etc.) and subscriber interaction(e.g. views, likes, comments, etc.). One highest-scoring regression algorithm is proposed to make the out-performing prediction for certain youtubers, and we have proven its rationality and high accuracy in predicting the growth and sustainability of YouTube subscribers with suitable configuration. Apart from establishing algorithms, a relevant website, which offers services for future prediction and improvement suggestions, is created based on the established random forest regression algorithm. This application allows youtubers to completely analyze their current management situation and assists them to increase popularity for both social and economic benefits.

KEYWORDS

Machine Learning, Video Sharing Platform, Artificial Intelligence, Big Data.

Global Stability Indices of the Transmission and Bilinear Control Functions for Tobacco Smoking Epidemic

Bassey Echeng Bassey1* and Delphine Rexson Bassey2, *1Department of Mathematics, University of Cross River State(Unicross), Calabar, Nigeria, 2Department of Plant and Ecological Studies, University of Calabar, Calabar, Nigeria

ABSTRACT

The seeming insurmountable effect of tobacco-smoking, coupled with intense laxity by society towards the avalanche consequential effects of tobacco-smoking consumption and the yet-to-be-available mathematical model for comprehensive treatment of the aforementioned multiple effects of tobacco-smoking, have necessitated this present investigation. That is, this present research arguably presented an insight into the global stability indices of not just the impact of smoking transmission but explicitly demonstrated the methodological application of designated bilinear control functions in the presence of screening techniques for the eradication of consequential effects of smoking and tobacco consumption..

KEYWORDS

Tobacco-smoking, global-stability-index, bilinear-control-function, smoking-generation-number, Lozinski-measure, asymptomatic-saddle-period.

De-biasing Rating Propensity Algorithm in Group Recommendation

JUNJIE JIA , TIANYUE SHANG and SI CHEN, Northwest Normal University, China

ABSTRACT

In recent years, group recommendation systems have gradually attracted attention with the increasing phenomenon of people s group activities. Nonetheless, most research focuses on optimizing machine learning models to fit user behavior data better. However, user behavior data is observational rather than experimental. Due to the different psychological benchmarks of user ratings, the training data evaluated by the algorithm cannot fully represent the real preferences of the target group. A De-Biasing Rating Propensity Algorithm in group recommendation is proposed. The proposed algorithm identifies user groups with similar behavior preferences through the Predict&AHC algorithm based on cosine similarity, and calculates user bias information by group and user preference tendency for different user groups. The De-Biasing Proportion on different items is used to build a rating bias consistency model, which effectively adjusts the users predicted rating. The experimental results show that the algorithm can significantly improve the quality and fairness of recommendation.

KEYWORDS

Preference propensity, Evaluation bias, Fairness, Group recommendation.

Privacy-preserving Federated Learning, Deep Learning, and Machine Learning IoT and IoTs Solutions (A Literature Review)

Victor Obarafor, Department of Cyber Security and Digital Forensics, Canterbury Christ Church University, Kent, UK, N Holmes Rd, Canterbury CT1 1QU

ABSTRACT

Internet of Things (IoT) is a growing computing trend that encompasses every connected thing. Over the recent years, IoT has recorded an exponential growth, leading to billions of smart devices, and still increasing. In contrast to other computing devices, some IoTs generate large amount of data, however, this has become a source of concern as data could contain users’ privacy which should be protected at all costs against any potential security breach incident. Securing IoT is very significant with its continuous adoption and use, hence, researchers have proposed several security mechanisms and techniques to safeguard and protect IoT systems and devices. Notwithstanding, there are some research gaps that are yet to be addressed irrespective of the relevant contributions made in protection of users’ privacy and confidentiality using IoTs. In this paper, the researcher solely focused on a review of AI approaches leveraged by researchers in protecting the device and data security aspects of privacy specifically for de-centralised architecture based industrial IoT systems (IIOTs) as they are generating large amount of data and are safety critical. The results achieved, unresolved issues and recommendations for future research are contained in this review.

KEYWORDS

Internet of Things, Data Security, Federated Learning, Decentralised IoT architecture, Privacy.

Practical Applications to Prevent Cyberattacks on Internet on Battlefield Things (IoBT)

Pawankumar Sharma1, Lotfollah Najjar2 and Sriram Srinivasan3, 1School of Computer and Information Science, University of the Cumberlands, KY, 2Information Systems and Quantitative analysis, University of Nebraska, NE and 3Department of Radiation Oncology, Virginia Commonwealth University, VA

ABSTRACT

Technological advancement has contributed to the Internet of Things (IoT), resultingin the Internet of Battlefields (IoBT). The IoBT has contributed to the advancement in coordinating various military operations and improving the equipment and battlefield operations. IoBT has overcome the challenges on the battlefield by overcoming the challenges within communication infrastructure and device heterogeneity. The stochastic geometry and mathematical formulas form the effective model of the coordination of security within the network. The architectural model contains the network geometry coordinated within the intra and inter-layers of the network. The network coordinationutilizes the various algorithms necessary for the build-up of the technology as characterized by the heuristic algorithm.

KEYWORDS

Internet of Battlefield Things (IoBT), IoT, network layers, network geometry, network model architecture, heuristic algorithm.

GSVD: Common Vulnerability Dataset for Smart Contracts on BSC and Polygon

Ziniu Shen, Yunfang Chen and Wei Zhang, School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China

ABSTRACT

The blockchain 2.0, marked by smart contract and Ethereum, has expanded the application scenarios of blockchain technology and driven the boom of decentralized Finance. However, smart contract vulnerabilities and security issues are also emerging one after another. Hackers have exploited these vulnerabilities to cause huge economic losses. In recent years, a large amount of research on the analysis and detection of smart contract vulnerabilities has emerged, but there has been no common detection tool and corresponding test dataset. In this paper, we build GSVD dataset (Generalized Smart Contract Vulnerability Dataset) consisting four offline datasets using smart contracts on two chains, Polygon and BSC: two small Solidity datasets consisting of 153 labeled smart contract source codes, which can be used to test the performance of vulnerability mining tools; two large Solidity datasets consisting of 52,202 un labeled real smart contract source codes that can be used to verify the correctness of various theoriesand tools under a large number of real data conditions. At the same time, this paper integrates the scripting framework accompanying the GSVD dataset, which can execute a variety of popular automated vulnerability detection tools on top of these datasets and generate analysis results of contracts and potential vulnerabilities. We tested the Minor dataset under GSVD using three tools that are kept up to date and found that the combined use of all tools detected 61.1% of labeled vulnerabilities, of which Mythril has the highest detection rate of 42.6%.

KEYWORDS

Smart Contract, Blockchain, Security, Vulnerability Detection, Dataset

Principles and Mechanisms for Digital Transformation in the Education and Healthcare Industries Utilizing Decentralized Self-sovereign Identity

Gregory H. Jackson and Karaitiana Taiuru,The University of Buckingham, U.K. and Adayge Inc., Utah, U.S.A, University of Auckland, Faculty of Engineering, Department of Electrical, Computer and Software Engineering, Auckland New Zealand and Taiuru & Associates Limited, Christchurch, New Zealand

ABSTRACT

This paper argues for the consideration of a decentralized, open, interoperable identity framework as a secure, scalable, user-centered meta-platform capable of leveraging many aggregate network advantages and delivery options in today’s digital world. An overview of the shortfalls and vulnerabilities of the current Internet and systems for identity management is first explained, followed by a summary of the status of development and primary proponents of decentralized, blockchain-enabled, self-sovereign identification (SSI) systems. An examination of the Key Event Receipt Infrastructure (KERI) open-source decentralized key management infrastructure (DKMI) and its primary root-of-trust in self-certifying identifiers (SCID) is evaluated. This paper recommends KERI for consideration as a potential meta-platform overlay and solution for both the education and health industries as a means of attaining their primary goal of being more user versus institution-centric in their core interactions and processes. Finally, some pathways for future research are recommended ideas for future improvements.

KEYWORDS

Distributed ledger technology, digital transformation, self-sovereign identity, education, healthcare.

Markov Chains Applied to Parrondo’s Paradox: the Coin Tossing Problem

Xavier Molinero1 and Camille Mégnien2, 1Department of Mathematics, Universitat Politècnica de Catalunya · BarcelonaTECH, Terrassa, Spain, 2School of Mathematics and Statistics, Barcelona, Spain

ABSTRACT

Parrondo’s paradox was introduced by Juan Parrondo in 1996. In game theory, this paradox is described as: A combination of losing strategies becomes a winning strategy. At first glance, this paradox is quite surprising, but we can easily explain it by using simulations and mathematical arguments. Indeed, we first consider some examples with the Parrondo’s paradox and, using the software R, we simulate one of them, the coin tossing. Actually, we see that specific combinations of losing games become a winning game. Moreover, even a random combination of these two losing games leads to a winning game. Later, we introduce the major definitions and theorems over Markov chains to study our Parrondo’s paradox applied to the coin tossing problem. In particular, we represent our Parrondo’s game as a Markov chain and we find its stationary distribution. In that way, we exhibit that our combination of two losing games is truly a winning combination. We also deliberate possible applications of the paradox in some fields such as ecology, biology, finance or reliability theory.

KEYWORDS

Parrondo’s paradox, Markov chain, Engineering Decision Making, Maintenance and Evolution.

Multi-view Three-dimensional Reconstruction Based on a Two-stage Multi-level Depth Network for Agriculture Applications

Li Guo, Yinyin Shi, Dinfei Jin, Mingjun Deng, and Xu Zhang, School of Automation and Electronic Information, Xiangtan University, Xiangtan, 411105, China

ABSTRACT

To address the problems appearing in multi-view three-dimensional (3D) reconstruction, such as the improvement of the completeness and the accuracy of the 3D reconstructed images, a two-stage multi-level depth network is proposed. In the stage 1 of the proposed network, several convolutional block attention modules (CBAMs) are applied in the lateral connections of the feature pyramid network (FPN). This is targeted to enhance the spatial and channel relativity of the different hierarchical feature maps so as to bring more semantic information. In the stage 2, the obtained multi-scale feature maps in the stage 1 are tackled by a set of cascaded processing procedures, such as adaptive propagation, single-trees transform, and matching cost computation. As a result, a depth map could be generated and then be further refined in the processing. Comparing with other state-of-the-art methods, the subjective and objective experiments based on the DTU dataset show that our method performs good result in completeness. The investigation of applying the proposed method for reconstructing agricultural crop images was carried out, which is based on a set of self-collected images. The experiment shows that a suitable human visual perception for the images could be obtained.

KEYWORDS

Multi-view Stereo, Three-dimensional Reconstruction, Deep Learning, Attention Mechanism, Intelligent Agriculture .

Advanced Clutter Mitigation Method for Surveillance Radar Using Machine Learning

Malwinder Singh, Shashi Ranjan Kumar and Bhukya Soumya Mishra, Product Development & Innovation Center, Bharat Electronics Limited, Bengaluru, India

ABSTRACT

CA-CFAR and Doppler processing are used for target detection in traditional signal processing unit for most of the perimeter surveillance radars. In such radar, ground clutter mitigation is the major challenge. With the advancement in machine learning techniques, radar researchers started integrating machine leaning methods to traditional signal processors for clutter mitigation. Among these methods, discriminative machine learning methods has the ability to learn without the knowledge of distribution type. In this paper, we proposed a method to improve the clutter mitigation by integrating the discriminative ML methods with traditional signal processing methods (CA-CFAR and Doppler) for X-band perimeter surveillance radar. The paper focuses on the raw IQ radar data collection, data labelling, and feature generation, statistical significance of these features, model (DT, SVM and ANN) training and model evaluation. The paper also discusses the future work related to this research.

KEYWORDS

Artificial Neural Network(ANN), Constant False Alarm Rate(CFAR), Digital Down Conversion( DDC), Decision Tree (DT), Fast Fourier Transform (FFT), false negatives (FN), false positives (FP), Field Programmable Gate Arrays (FPGAs), In Phase-Quadrature Phase (IQ), Machine leaning (ML), Radio Detection and Ranging (RADAR), Support Vector Machine (SVM), true negatives (TN), true positives (TP), User Datagram Protocol (UDP), Very High Speed Integrated Circuit Hardware Description Language (VHDL) .

Arabic Text Summarization Using Statistical Features and Word2vector

Khaled Omar1 and Mohamad AlShaar2, 1Department of Artificial intelligence, Damascus University, Damascus, Syria ,2Master of web science, Syrian virtual university, Damascus, Syria

ABSTRACT

Arabic text summarization is a field of natural language processing, and many algorithms for Arabic texts summarization have been developed, but these algorithms faces many weakness points which generated from the specifications of the Arabic language manipulation. In this research we have developed new algorithm for Arabic text summarization that the developed algorithm contains two main models of summarization, the statistical model and the semantic model ,that the statistical model was employed to generate the candidate sentences for summary, and the semantic model was used to select and generate the final summary , in the statistical model we have used sentences statistical features, and in semantic model we have used word2vector technology which convert words to number and keeping the context of text, the developed algorithm has been tested on The Essex Arabic Summaries Corpus (EASC) dataset, and the tests approved the efficiency and the accuracy of the developed algorithm , that the developed algorithm summarization Precision reached to 75%.

KEYWORDS

Arabic text summarization, Arabic word2vector, Arabic WordNet.