Accepted Papers

System End-User Actions as a Threat to Information System Security

Paulus Kautwima, Titus Haiduwa, Kundai Sai, Valerianus Hashiyana, School of Computing, University of Namibia, Windhoek, Namibia

ABSTRACT

Information system security is of paramount importance to every institution that deals with digital information. Nowadays, efforts to address cybersecurity issues are mostly software or hardware-oriented. However, the most common types of cybersecurity breaches happen as a result of unintentional human errors also known as end user errors. Thus, this study aimed to identify the end-user errors and the resulting vulnerabilities that could affect the system security requirements, the CIA triad of information assets. The study further present state-of-the-art countermeasures and intellectual ideas on how entities can protect themselves from advent events. Adopted is a mixed-method research approach to inform the study. A closed-ended questionnaire and a semi-structured interview were used as data collection tools. The findings of this study revealed that system end user errors remain the biggest threat to information systems security. Indeed errors make information systems vulnerable to certain cybersecurity attacks and when exploited puts legitimate users at risk.

KEYWORDS

Information security, Information Systems, End-user errors.

A Social-based Gaming System to Motivate the Dog Walking and Community using Internet-Of-Things (IoT) and AI

Ruize Yu¹, and Yu Sun², ¹Santa Margarita Catholic High School, Rancho Santa Margarita, USA, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

In recent years, society has shown an increase in pet ownership, however, only a few companies exist to help pet owners keep track of their pet’s health. This paper designs a tool to help track pet owners measure the amount of steps their dogs have taken to measure their pet’s health. We applied our application to our dogs and conducted a qualitative evaluation of the approach. The results show that the tool indeed works and will track the pet’s steps taken, location, and provides a fun and engaging way to interact with the app.

KEYWORDS

IoT, Gaming System, Machine Learning.

A Lightweight Two-Layer Blockchain Mechanism for Reliable Crossing-Domain Communication in Smart Cities

Xiangyu Xu and Jianfei Peng, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China

ABSTRACT

The smart city is an emerging notion that leveraging the technique of Internet of Things (IoT) to achieve more comfortable, smart and controllable cities. The communications crossing domains between smart cities is indispensable to enhance collaborations. However, crossing-domain communications are more vulnerable since there are in different domains. Moreover, there are huge different devices with different computation capabilities, from sensors to the cloud servers. In this paper, we propose a lightweight twolayer blockchain mechanism for reliable crossing-domain communication in smart cities. Our mechanism provides a reliable communication mechanism for data sharing and communication between smart cities. We defined a two-layer blockchain structure for the communications inner and between smart cities to achieve reliable communications. We present a new block structure for the lightweight IoT devices. Moreover, we present a reputation-based multi-weight consensus protocol in order to achieve efficient communication while resistant to the nodes collusion attack for the proposed blockchain system. We also conduct a secure analysis to demonstrate the security of the proposed scheme. Finally, performance evaluation shows that our scheme is efficient and practical.

KEYWORDS

Smart city, IoT, Lightweight blockchain, Reliable communication.

Privacy as invisibility (by default) Bridging the gap between anarcho-capitalists and cypherpunks

Andrea Togni, Independent researcher (PhD in philosophy), Italy

ABSTRACT

The main thesis of this paper in political philosophy is that privacy as invisibility (by default) is one of the best weapons to defend property rights. Privacy is not something that can be owned, but it is a necessary condition for the preservation of property. Physical and tangible objects behave differently from information, ideas and data with regard to property and privacy: while ownership of the latter is lost as soon as they are seen by adversaries, this is not the case for the former. In both cases, however, making property invisible is crucial to keep it safe. This paper tries to point out why attaining privacy as invisibility is a prerequisite for any free society. In the first paragraph, I recollect some of the main theories on privacy, so that the discussion is contextualized properly. Then, I provide some conceptual clarifications useful to better understand the purpose of this work. In the third section, I address the question why the private sector has not been successful in replacing governments despite being able to provide better services at better prices. Last, I discuss the concept of privacy as invisibility with a special consideration for the digital realm, and in doing so I call for a structural alliance between anarchocapitalists and cypherpunks. To paraphrase Rothbard: the cypherpunk ethos is the fullest expression of anarcho-capitalism, and anarcho-capitalism is the fullest expression of the cypherpunk ethos.

KEYWORDS

privacy, property, anarcho-capitalism, cypherpunk.

Introduction on Military Supply Chain Management and Blockchain

Syarifah Bahiyah Rahayu^{1, 2}, Sharmelen A/L Vasanthan³, Afiqah M. Azahari^{1, 2}, Joe Chai⁴, ¹Cyber Security and Digital Revolution Industry Centre, National Defence University of Malaysia Kuala Lumpur, Malaysia, ²Fac. of Defence Science & Technology National Defence University of Malaysia Kuala Lumpur, Malaysia, ³Campus SophiaTech, 450 Route des Chappes, 06410 Biot, France, ⁴Joe Chai, ProximaX Malaysia Sdn. Bhd, Lot 3A.09, Level 3A, GLO Damansara, Jalan Damansara, 60000 Kuala Lumpur, Malaysia

ABSTRACT

Blockchain has become a powerful technology and when it comes to supply chain management, blockchain has a lot to offer which could contribute to its development and make the supply chain more effective. The same benefit could be also gained when blockchain is incorporated in Military Supply Chain Management (MSCM). The aim of this paper is to develop a military supply chain management blockchain using ProximaX blockchain technology. Investigate the potential benefits of incorporating blockchain to the MSCM environment. This paper reviews previous works of other researchers which use blockchain technology in supply chain. In this paper, we also delve deeper into ProximaX’s blockchain technology and propose the implementation of smart contracts into MSCM. The findings of this paper show that incorporating blockchain into the MSCM enables transparency thus reducing fraud, improving communication between parties and making end-to-end tracking in MSCM more transparent.

KEYWORDS

Blockchain, distributed ledger technology, smart contract, supply chain, nodes.

Redefining the Data Protection Impact Assessment Methodology to Support the Requirements of the General Protection Regulation in a Big Data Analytics Context – A Delphi Study Approach

Georgios Georgiadis and Geert Poels, Faculty of Economics and Business Administration, Ghent University, Belgium

ABSTRACT

Big Data Analytics (BDA) is a complex ecosystem comprising users, high-capacity infrastructure, services, and applications that store, retrieve, and process large amounts of data from widely scattered sources. Because of their benefits, like in the case of suppressing the spread of COVID-19, there is growing interest from companies and organisations in investing in such technologies. There are, however, several mounting concerns associated with the secure and lawful processing of personal data under the General Data Protection Regulation (GDPR) and whether privacy and data protection risks associated with the overall data handling could be adequately assessed using the Data Protection Impact Assessment (DPIA). In this position paper, we describe our research work in addressing those concerns and our imminent research plan that will lead to the development of an improved DPIA methodology capable of assessing the data protection risks inherent in projects relying on BDA technologies.

KEYWORDS

Big Data, Big Data Analytics, Data Protection Impact Assessment, Delphi Method, General Data Protection Regulation, Privacy, Privacy Impact Assessment.

The Relationships in AI, Big Data and Internet of Things (IOT)

Yew Kee Wong, School of Information Engineering, HuangHuai University, Henan, China

ABSTRACT

In the information era, enormous amounts of data have become available on hand to decision makers. Big data refers to datasets that are not only big, but also high in variety and velocity, which makes them difficult to handle using traditional tools and techniques. Due to the rapid growth of such data, solutions need to be studied and provided in order to handle and extract value and knowledge from these datasets. The Internet of Things, or "IoT" for short, is about extending the power of the internet beyond computers and smartphones to a whole range of other things, processes and environments. IoT is at the epicentre of the Digital Transformation Revolution that is changing the shape of business, enterprise and people’s lives. This transformation influences everything from how we manage and operate our homes to automating processes across nearly all industries. This paper aims to analyse the relationships of AI, big data and IoT, as well as the opportunities provided by the applications in various operational domains.

KEYWORDS

Artificial Intelligence, Big Data, IoT, Digital Transformation Revolution, Machine Learning.

An Intelligent and Data-Driven Mobile Platform for Youth Volunteer Management using Machine Learning and Big Data Analysis

Serena Wen¹ and Yu Sun², ¹Lewis and Clark High School, 521 W 4th Ave, Spokane, WA 99204, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

In my high school’s Key Club, meetings were always held in a crowded classroom and The upcoming volunteer events would usually be written on the whiteboard. This always leads to information missing between volunteers. A system that can help efficiently manage the volunteers and volunteer opportunities is needed. So to solve this problem, I developed a VolunteerMatch Mobile system using dart and flutter framework. Volunteer opportunity recommendation and matching feature would be the next step.

KEYWORDS

Volunteering support platform, Machine Learning, cloud computing.

Ensuring the Integrity of Cloud Computing Against Account Hijacking using Blockchain Technology

Assia Akamri and Chaimae Saadi, Laboratory Of System Analysis, Information Processing And Industrial Management, High School Of Technology Of Sale, Mohamed V University, Rabat, Morocco

ABSTRACT

Cloud computing is a delivery model of the internet in order to store the data user in a remote server or a data center rather than personal computer, and pay as you go basis .This cloud has several advantage such as : access data from anywhere ,easy to access, elasticity . but anything connected to the internet is not totally secure, even servers with invincible security are vulnerable to attacks .Account hijacking is one of the major attacks in the cloud, and it is considered as one of the most famous technologies that keeps and maintains the integrity of data Blockchain technology is a digital distributed ledger that collects data in the form of blocks that are linked together with a chain. In this paper, we propose a decentralized cloud that combines two technologies: blockchain and Cloud Computing in order to ensuring data integrity.

KEYWORDS

Cloud computing, Blockchain, Security, Session hijacking, Data integrity.

Database Security in a Dynamic IT World (Examine Database Security Fundamentals that Help to make sure High Levels of Flexibility in Data Use, and Effectiveness in Data Protection)

Temitope-Awodiji, California Miramar University, USA

ABSTRACT

Databases are vulnerable. Public statements by Target, Home Depot, and Anthem following their extremely advertised data breaches are each uniform and succinct on how their breaches unfolded: unauthorized access to those systems that ultimately led to the extraction of sensitive information. A comprehensive strategy to secure a database is over data security. Usually, security events will be related to the later action: illegitimate access to data confidentiality damage, injury to the integrity of knowledge, loss of data accessibility (Discover). Loss of privacy of data, creating them accessible to others without a right of access is not visible within the database and does not need changes deductible database. This paper addresses these events to confirm database security.

KEYWORDS

Data Security, Database, Data Integrity, Data Science, Information Technology.

Hadoop Mapreduce as a General Framework for Mining Small Patterns

Ishak H.A MEDDAH, LabRi Laboratory, Ecole Superieure en Informatique Sidi Bel Abbes, Algeria

ABSTRACT

Hadoop MapReduce is an open solution for the big data treatment, it’s used to analyse and process a set of voluminous data. his happens by distributing the computational work across a cluster of virtual servers running in a cloud or a large set of machines. Process Mining provides an important bridge between data mining and business process analysis. Its techniques allow for extracting information from event logs. Generally, there are two steps in process mining, correlation definition or discovery and the inference or composition. First of all, our work consists to mine small patterns from a log traces. Those patterns are the representation of the traces execution from a log file of a business process. In this step, we use existing techniques. The patterns are represented by finite state automaton or their regular expression; and the final model is the combination of only two types of different patterns represented by regular expressions. Second, we compute these patterns in parallel, and then combine those small patterns using the Hadoop framework. We have two steps; the first is the Map Step through which we mine patterns from execution traces, and the second one is the combination of these small patterns as a reduce step.

KEYWORDS

Hadoop, MapReduce, Process Mining Execution traces, Log file.

An Intelligent Mobile Floating Application to Aid Seniors in Using the Smartphone Using Machine Learning

Yilin Chen¹ and Yu Sun², ¹Troy High School, 2200 Dorothy Ln, Fullerton, CA 92831, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

The twenty-first century is a century of rapid technological growth, one significant area being the smartphone [4]. By 2021, more than eight percent of US adults own a smartphone. Smartphones are capable of making phone calls, messaging texts, making purchases, taking pictures, playing games, finding roads, and more. However, not everyone is a beneficiary of this technology. Seniors often fall behind in this technology advancement. They often struggle with finding the right button to press or get confused with the variety of functions. This paper develops a floating application that when launched, checks the opening application and displays a list of its functions. Then, the user can select what they want to do, and the application will begin a tutorial to guide the senior in using their phone. We applied our application to Google Play and conducted a qualitative evaluation of the approach. The results show that this application will be effective in facilitating seniors in using the smartphone.

KEYWORDS

Machine Learning, Big Data, Mobile Application.

An Intelligent System to Assist Piano Composition and Chords Generation using AI and Machine Learning

Jiaxuan Zhang¹ and Yu Sun², ¹Arcadia High School, 180 Campus Dr, Arcadia, CA 91006, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

As a musician and producer, I’ve always struggled with finding chords when I first started writing music [5]. It sometimes goes to the extent of me forgetting my melody because I take so long trying to figure out the chords. So I came up with an idea for this app, that will help amateur and beginner musicians save time and provide chord suggestions to them as a booster to start writing songs [6]. It features a recording or a midi input feature, then the app will carefully analyze the given melody and give a selection of the best chord progressions using intelligent AI. As an output, it is able to present it as guitar chords, piano chords, and ukulele chords, enabling more different musicians to use this app.

KEYWORDS

Music, Chords, Melody, Chord Generation.

Pangaea Minds Teacher Leaders: Using Virtual Worlds for Global Collaboration in our Classrooms

Peta Estens, Faculty of Art & Design, University of New South Wales, Sydney, Australia

ABSTRACT

Pangaea Minds is world leading and ground-breaking in connecting primary and secondary schools around the world through a private virtual world campus on an ongoing and long-term basis. Through avatars, teachers team teach and nurture student collaboration all over the world. Teachers, students and their respective wider school communities are committed to working with a range of unique cultures and societies, having diverse histories and politics, on an ongoing and long-term basis. Cooperation and collaboration are fundamental for the success of developing future generations authentic global awareness, global thinking and global leadership. Pangaea Minds teacher leaders recognise they are pioneers and there is a great responsibility in reshaping education to empower our students to have the skills and knowledge for rapidly changing industries and to meet the global challenges. Pangaea Minds teachers are active researchers and designers working together to continuously to reshape the Education system and improve student outcomes.

KEYWORDS

Teacher Leadership, Virtual Worlds, Avatars, Global Awareness.

Learning Styles as a Referential Framework for Classifying Learners who learn online

Pengiran Shaiffadzillah Pengiran Omarali, Educational Technology Centre, Brunei Darussalam

ABSTRACT

Over the last two decades, the online learner demographic is predominantly attributed to higher education students who undertake formal online learning courses from institutions all over the world. Coming from different backgrounds, these learners collectively comprise of already diverse and heterogeneous groups of individuals with different dispositions toward learning in general and learning online or in blended learning environments. More recently however, and abruptly augmented further by the global Covid-19 pandemic, online learning and blended learning have been introduced into K-12 learning. With the higher education online learner demographic being diverse in online learning preferences as it is, the more dynamic profiles of learners in K-12 demand education providers the capacity to identify learners using different types of taxonomies and learner constructs so that their learning environments, whether it be fully online or blended, can supplement if not replicate the teaching and learning that occur in the on-site classrooms. One such construct is ‘learning styles’. This article is a review of learning styles used as a referential framework in the practice of online learner classification, taking into consideration arguments from different perspectives of the Learning Styles discourse including studies that have found evidence in support of learning styles, studies that have found no relationship between learning styles and learning effectiveness, and commentaries by researchers who have questioned the significance of learning styles itself.

KEYWORDS

Learning styles, learner dispositions, online learning, blended learning, K-12 online.

A Case Study of Integrating Audio-Visual Aids into English Language Teaching in Indonesian Junior High Schools: A Multiliteracies Pedagogical approach

Salwa, The University of Newcastle Australia

ABSTRACT

With the implementation of the current 2013 curriculum in Indonesian secondary education, the use of multimedia and technology as New Literacies is promoted. The practice of adopting a Multiliteracies Pedagogical approach has become increasingly prominent. Drawing on the framework of Multiliteracies practices which incorporates the four components of situated practice, overt instruction, critical framing, and transformed practice (New London Group,1996), this article presents the findings of a descriptive case study investigating teachers’ perceptions of the use of Audio Visual Aids in English language teaching in Indonesian Junior high schools. Data was collected from semi-structured interviews, focus group discussions and classroom observations with four English teachers, four students’ focus group discussions from four different types of schools. Thematic analysis was used in analysing the qualitative data. The findings indicated that most teachers frequently applied Multiliteracies Pedagogy which focuses on the use of Multimodality in their English language teaching by integrating Audio-Visual materials into their English language teaching. The findings also indicated that the teachers’ enactment in applying the four multiliteracies framework aspects, the situated practice and overt instruction were mostly applied whereas critical framing and transformed practice were not dominantly used. Given that fact, promoting Audio-Visual materials in preservice teachers’ training and teacher professional development training in Indonesian Junior High schools is recommended.

KEYWORDS

Multiliteracies, Multimodality, EFL , Secondary education, teacher training.

An Intelligent and Data Driven Mobile Platform for Early Childhood Development using Machine Learning and Data Mining

Maggie Ding¹ and Yu Sun², ¹Orange County School of the Arts, Santa Ana, CA 92701, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

In China almost 96 million children live in rural areas. Some of these children suffer from malnutrition since parents or guardians do not have knowledge of nutritional plans or how to calculate nutritional values. However, most of the Chinese population has access to a mobile device. This paper proposes a mobile application, which runs on the IOS and Android platforms, to calculate nutritional values and recommend a nutritional menu. EZ Nutrition and Education is a mobile app that targets millions of parents and caregivers in rural China and provides a solution to the regions’ early childhood underdevelopment problems. It provides recommendations for healthy meals and age-appropriate educational activities, measures children’s daily intake of calories and macro-nutrients (protein, carbs, and fats), and provides a way to have fun through activities that teach skills and values so as to prevent the underdevelopment of rural children’s physical, intellectual and mental growth. We applied our application to a group of participants (ages 6-12) and conducted a qualitative evaluation of the approach. The results show that the nutritional calculator feature can help parents improve the nutritional health of their children. Though two of the underweight participants lost weight and two of the overweight participants gained weight while using the recommended nutritional plan, we believe that the recommended nutritional menu could be an excellent feature for this application after we adjust some of the parameters since some parents claimed they could not follow the recommended menus.

KEYWORDS

Computer Science, Game, Art Design.

Fencingestimate: A 3D Game-Based Interactive Driving Simulation Training System Using Artificial Intelligence and Computer Vision

Weixuan Lei¹ and Yu Sun², ¹Irvine, CA 92604, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

Training for fencing during the pandemic has changed from what it was beforehand. Students have been taking lessons online, and instead of fencing with peers, students now train by watching and analyzing fencing videos. Learning fencing from watching videos of world class fencers is an effective way of learning. However, sabre fencing is so fast that many inexperienced fencers are unable to capture the important information by watching short clips. Therefore, they are unable to learn techniques such as sabre fencing just from watching videos. This paper traces the development of an application that can utilize computer vision and pose estimation to analyze fencing video clips and output accurate scored points as well as the techniques used within the given clips. We applied our application to help less experienced fencers improve their ability to recognize points and conduct qualitative evaluations of different fencing techniques.

KEYWORDS

3D simulation, Computer vision, Artificial intelligence, Fencing lessons.

OpenGame4Kids: A Public Platform for Developing and Recommending Learning-Based Games for Youth

Maggie Ding¹ and Yu Sun², ¹Orange County School of the Arts, Santa Ana, CA 92701, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

In China almost 96 million children live in rural areas. Some of these children suffer from malnutrition since parents or guardians do not have knowledge of nutritional plans or how to calculate nutritional values. However, most of the Chinese population has access to a mobile device. This paper proposes a mobile application, which runs on the IOS and Android platforms, to calculate nutritional values and recommend a nutritional menu. EZ Nutrition and Education is a mobile app that targets millions of parents and caregivers in rural China and provides a solution to the regions’ early childhood underdevelopment problems. It provides recommendations for healthy meals and age-appropriate educational activities, measures children’s daily intake of calories and macro-nutrients (protein, carbs, and fats), and provides a way to have fun through activities that teach skills and values so as to prevent the underdevelopment of rural children’s physical, intellectual and mental growth. We applied our application to a group of participants (ages 6-12) and conducted a qualitative evaluation of the approach. The results show that the nutritional calculator feature can help parents improve the nutritional health of their children. Though two of the underweight participants lost weight and two of the overweight participants gained weight while using the recommended nutritional plan, we believe that the recommended nutritional menu could be an excellent feature for this application after we adjust some of the parameters since some parents claimed they could not follow the recommended menus.

KEYWORDS

Computer Science, Game, Art Design.

Drive2Pass: A 3D Game-based Interactive Driving Simulation System for Improving the Youth Driving Learning and Training using Machine Learning

Charles Yang¹ and Yu Sun², ¹Northwood High, 4515 Portola Pkwy, Irvine CA 92620, ²California State Polytechnic University, Pomona, CA, 91768

ABSTRACT

Youths have a higher car accident rate, so to decrease the percentage, I developed a game that will teach players to practice safer driving behaviors [5]. It is meant to simulate real driving, and teaches the players key individual concepts about road safety. This game puts an emphasis on properly executing blinking, hill parking, and headlights. This addresses the problem in other games where they solely focus on steering and acceleration, as this game also includes other driving elements to promote defensive driving. The intended goal of this game was to teach beginner drivers proper driving etiquette in a safe, risk-free environment and become a potential alternative to the traditional method of driving on real roads.

KEYWORDS

Youth Driving, Machine Learning, 3D Modeling.

Emergency Management System for College Students based on Big Data Processing Technology

Ziyue wang, Tingfang li and Jianxia chen, Major in data science and big data technology, Hubei University of Technology, China

ABSTRACT

With the development of the Internet, China has entered the era of rapid development of information technology. How to respond to natural disasters, emergency traffic accidents, public health emergencies is worth exploring. At present, emergency management system is mainly used in natural disasters, public health, transportation and other fields, but it is rarely used in Colleges and universities. There are still many problems in the actual application of the current emergency management system. This paper introduces the college students emergency management system under the application of big data processing technology, hoping to help college students emergency management.

KEYWORDS

Web System, Stream Data Processing, Data visualization, Internet Worm.

An Intelligent Question Answering Platform for Graduate Enrollment

Mengyuan Zhang, Yuting Wang, Jianxia Chen and Yu Cheng, School of Computer Science, Hubei University of Technology, Wuhan, China

ABSTRACT

To enhance the competitiveness of colleges and universities in the graduate enrollment and reduce the pressure on candidates for examination and consultation, it is necessary and practically significant to develop an intelligent Q&A platform, which can understand and analyze users semantics and accurately return the information they need. However, there are problems such as the low volume and low quality of the corpus in the graduate enrollment, this paper develops a question answering platform based on a novel retrieval model including density-based logistic regression and the combination of convolutional neural networks and bi-directional long short-term memory. The experimental results show that the proposed model can ef ectively alleviate the problem of data sparseness and greatly improve the accuracy of the retrieval performance for the graduate enrollment.

KEYWORDS

Question Answering System, Graduate Enrollment, Deep Learning, Sentence Semantic Similarity.

Curriculum Semantic Retrieval System based on Distant Supervision

Qingwen Tian, Shixing Zhou, Jianxia Chen, Yi Gao and Shuijing Zhang, School of computer science, Hubei University of Technology, Hubei, China

ABSTRACT

Knowledge Graph is a semantic network that reveals the relationship between entities, which construction is to describe various entities, concepts and their relationships in the real world. Since knowledge graph can effectively reveal the relationship between the different knowledge items, it has been widely utilized in the intelligent education. In particular, relation extraction is the critical part of knowledge graph and plays a very important role in the construction of knowledge graph. According to the different magnitude of data labeling , entity relationship extraction tasks of deep learning can be divided into two categories: supervised and distant supervised. Supervised learning approaches can extract effective entity relationships. However, these approaches rely on labeled data heavily resulting in the time-consuming and labor-consuming. The distant supervision approach is widely concerned by researchers because it can generate the entity relation extraction automatically. However, the development and application of the distant supervised approach has been seriously hindered due to the noises, lack of information and disequilibrium in the relation extraction tasks. Inspired by the above analysis, the paper proposes a novel curriculum points relationship extraction model based on the distant supervision. In particular, firstly the research of the distant supervised relationship extraction model based on the sentence bag attention mechanism to extract the relationship of curriculum points. Secondly, the research of knowledge graph construction based on the knowledge ontology. Thirdly, the development of curriculum semantic retrieval platform based on Web. Compared with the existing advanced models, the AUC of this system is increased by 14.2%; At the same time, taking "big data processing" course in computer field as an example, the relationship extraction result with F1 value of 88.1% is realized. The experimental results show that the proposed model provides an effective solution for the development and application of knowledge graph in the field of intelligent education.

KEYWORDS

Knowledge Graph, Curriculum Points, Distant Supervision, Relation Extraction, Sentence Bag Attention Mechanism, Ontology Construction.

The Optimized Cell Configuration Method of Avoiding SRS Inter-Cell Interference

Shin-Hwan Kim¹, Kyung-Yup Kim², Jae-Hyung Koo³, Young-Soo Seo⁴, ¹Access Network Technology Team, Korea Telecom, Seoul, Korea, ²Access Network Technology Team, Korea Telecom, Seoul, Korea, ³Access Network Technology Department, Korea Telecom, Seoul, Korea, ⁴Network Research Technology Unit, Korea Telecom, Seoul, Korea

ABSTRACT

The issue of cell-to-cell interferences is a serious problem that has always been raised in digital communication system such as NR. The communication method of NR and LTE is OFDM. OFDM has many advantages, but has fatal disadvantage called ICI(Inter-Cell Interference) because resources among cells are overlapped always. For example, NR’s typical interferences are ICIs among PDSCH(Physical Downlink Shared Channel), PDCCH(Physical Downlink Control Channel), PUSCH(Physical Uplink Shared Channel), PUCCH(Physical Uplink Control Channel, CSI-RS(Channel State Information-Reference Signal) and SRS(Sounding Reference Signal). Among them, it is important to determine the correct beamforming weight factor value by estimating the channel with SRS. Therefore, the ICI of SRS degrades the performance of downlink throughput. This paper analyses the impact of SRS’s ICI in conventional scheme, introduces the proposed AC-CS(Auto-Correlation Cyclic Shift) schemes by the Zadoff-Chu sequence to overcome the ICI of SRS and analyses theirs performance. The method used for performance analysis is determined by the detection abilities, which are missing probability and false alarm probability.

KEYWORDS

SRS, beamforming, auto-correlation, missing probability, false alarm probability.

Using Big Data for Machine Learning Applications

Yew Kee Wong, School of Information Engineering, HuangHuai University, Henan, China

ABSTRACT

In the information era, enormous amounts of data have become available on hand to decision makers.Big data refers to datasets that are not only big, but also high in variety and velocity, which makes them difficult to handle using traditional tools and techniques. Due to the rapid growth of such data, solutionsneed to be studied and provided in order to handle and extract value and knowledge from these datasets. Machine learning is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention. Such minimal human intervention can be provided using big data analytics, which is the application of advanced analytics techniques on big data. This paper aims to analyse some of the different machine learning algorithms and methods which can be applied to big data analysis, as well as the opportunities provided by the application of big data analytics in various decision making domains.

KEYWORDS

Artificial Intelligence, Machine Learning, Big Data Analysis.

Speech Accuracy Diagnosis using Psychophysiological Signals based on Nonlinear Methods

Hengameh Ghasrani¹ and Elias Mazrooei Rad², ¹Graduated of Bachelors Khavaran Institute of Higher Education, Electrical and Computer Engineering Department, Mashhad, Iran, ²Department of Electrical and Computer Engineering, Khavaran Institute of Higher Education, Mashhad, Iran

ABSTRACT

One of the issues that many judicial and security authorities are concerned about is the speech accuracy confirmation. All of the designed lie detection systems have not been able to confirm the speech accuracy completely. These methods include sound stress measurement, thermal imaging, and deception detection which use blinking. The drawback of the above methods is that they are costly, and difficult to registration, analysis and interpretation. According to the results of various experiments on polygraph data, Photo Plethysmography signals and skin electrical resistance are mostly depend on mental states, especially stress. Also, the variations of these signals have the most weight in the general conclusion of the parameters changes. In this paper, lie detection data recorded at the Intelligent Signal Processing Research Institute were used to show that the ELMAN classifier has a proper percentage of accuracy.

KEYWORDS

Lie detector systems, Normalization systems Photo Plethysmography signal, Skin electrical resistance signal, linear separator.

A Border Perspective on Remote Sensing Technology in Today’s World

Er. Aditya Singh, School of Civil Engineering, Lovely Professional University, Phagwara, Punjab, India

ABSTRACT

In this paper, remote sensing technology is being highlighted and discussed in detail. The paper also describes remote sensing and its beginning. The evolution of remote sensing technology and the current status of remote sensing technology are being mentioned here. The various advantages and limitations of remote sensing technology is also described in the paper. Plus, the numerous applications of remote sensing technology in various fields are mentioned briefly. The reason behind the popularity of remote sensing technology is also written here and the various software that are used to incorporate remote sensing technology are briefly highlighted.

KEYWORDS

Passive Sensors, Active Sensors, Satellite, Infrared, RADAR, LiDAR.

Transfer Learning using Convolutional Neural Network Architectures for Image Recognition

Vishwanath Mahalle and Dhanraj Dhotre, Department of Computer Science and Engineering, SSGMCE, Shegaon (M.S.), India

ABSTRACT

This paper presents an analysis of the performance of popular convolutional neural network (CNN) architectures on Image Recognition. The performances of different types of CNN’s are compared on a single dataset. The CNN’s are already pre-trained on imagenet data, so their performances will give a measure of which type of CNN to use for quick fine tuning with greater accuracy. This study focuses on analysing the performance of four popular networks: Alex Net, VGGNet, Inception and ResNet50. Four different CNN’s are taken and fine tuned them on furniture images. The analysis shows that ResNet50 and Inception are able to recognize objects with much better accuracy than AlexNet and VGG16 with less number of epochs.

KEYWORDS

Transfer learning, Pre-trained Convolutional Neural Networks, Image Recognition, Fine-tuning.

A Q-learning based Fault-Tolerant Controller with application to CSTH system

Seyed Ali Hosseini and Karim Salahshoor, Department of Automation and Instrumentation Engineering Petroleum University of Technology Ahwaz, Iran

ABSTRACT

Systems are continually subjected to faults or malfunctions because of age or sudden events, which might degrade the operation performance and even result in operation failure that is a quite important issue in safety-critical systems. Thus, this vital problem is the main reason to use the Fault-Tolerant strategy to improve the performance of the system with the presence of faults. A fascinating property in Fault-Tolerant Controllers (FTCs) is adaptability to system changes as they evolve throughout system operations. In this paper, a Q-learning algorithm with greedy policy is used to realize the FTC adaptability. Then, some fault scenarios are introduced in a Continuous Stirred Tank Reactor (CSTR) to compare closed-loop performance of the developed Q-learning based FTC with respect to conventional PID controller and a RL-based FTC. The obtained results show the effectiveness of Q-learning-based FTC in different fault scenarios.

KEYWORDS

Reinforcement Learning, Q-learning Algorithm, Fault-Tolerant controller, Adaptive Controller.