Welcome to BDAP 2020

International Conference on Big Data and
Applications (BDAP 2020)

June 13 ~ 14, 2020, Helsinki, Finland



Accepted Papers
Detection and Characterisation of the Non-periodic Noise Generated by Linear Loads in Power Electric Lines in A PLC –Power Line Communication System

Pablo Emilio Rozo Garcia and Johann Alexander Hernandez, Doctorate in Engineering, Francisco José de Caldas District University

ABSTRACT

In this work the characterisation and modelling of the asynchronous impulsive (non-periodic) noise, which occurs in communication lines (PLC) when used as a communication channel, are performed. A strategy was implemented to detect the noise under different circumstances in a residential electrical environment. The study was conducted on purely linear loads. An implementation was adjusted with appropriate measuring devices and algorithms were designed to process the information recorded. The impulsive noises detected are Burst type, because they are the most critical noises that occur in a communication channel through power lines. Statistical processes are used to characterise and to model the noise. The Middleton model is used to determine its presence under certain conditions. The results are satisfactory. The Burst type non-periodic noise is detected. The results were perfect in relation to reality by applying the characterisation and modelling proposed.

KEYWORDS

Powerline, Communication, Noise, Burst, Middlenton, Model, Characterisation


Enhanced Homograph Attack Detection

Zicong Zhu1, Tran Phuong Thao1, Hoang-Quoc Nguyen-Son2, Rie Shigetomi Yamaguchi1, Toshiyuki Nakata1, 1Graduate School of Information Science and Technology, The University of Tokyo, Japan and 2KDDI Research Inc.

ABSTRACT

The Internationalized Domain Name (IDN) homograph attack is a web security problem in which the attackers deceive the computer users about what websites they access by homologous domain names. Recently the growth of IDN homograph attack has become a severe problem with a significant probability of criminality like frauds for ordinary users. In this paper, we propose a classification method for IDN homograph detection by making use of Structural Similarity Index (SSIM). Compared to the existing approach, the experiment results showed that our improved classification method could increase the accuracy from 95.07% to 96.18% and decrease the false positive rate from 3.92% to 3.23%. We also conducted an empirical analysis of the IDN homograph data and training processes of the SSIM classification approach for discussion that our method takes advantages in homograph detection.

KEYWORDS

Web Security, Internationalized Domain Name, Structural Similarity Index, Homograph Attack, Visual Similarity


A 3D Simulation for the Feedback Loop Between Orbital Debris and Future Space Activities and Economy

Jack Liu1, Emmanuel Reyes2, Yu Sun3, 1Portola High School, Irvine, CA, 2University of California, Irvine and 3California State Polytechnic University, Pomona

ABSTRACT

Since the success of SpaceX’s reusable launch system program, there has been a massive resurgence in interest in space, hundreds of companies and startups are racing to develop cheaper ways of venturing into the vacuum of space. As a result, the sustainability of the space environment will be put under great danger and pressure, threatening all other future space activities. In the study, we attempt to quantify the chain effect of various forms of space activities and orbital debris using Unity3D, followed by proposing the plan to use NASA’s simulation software Orbital Debris Engineering Model (ORDEM) 3.0 and Debris Assessment Software (DAS) 3.0.

KEYWORDS

Orbital Debris, 3D Simulation, Unity3D


Smart Learning Gateways for Omani HEIs: Benefits, Challenges and solutions

Qasim Alajmic1, Amer Abuali2 and Mohammed A. Al-Sharafi3, 1Collegeof Arts & Humanitas, Department of Education, A’ Sharqiah University (ASU), Oman, 2Taibah University, IS Department, KSA and 3Facultyof Computer Systems & Software Engineering, Universiti Malaysia Pahang, Malaysia

ABSTRACT

Globally, the higher education is completely transformed with the growth of information and communication technology. This change is due to the advancement of information technology in the world which has led to the creation of conceptual frameworks that design the smart learning environment across the world. Therefore, a great deal of today's teachings relies heavily on the information and technology resources where mosthigher education institutionsstarting digitize their courses curriculum. The smart learning matter has gain a global trend for past few years, but still did not discussed thoroughly in Omani environment. The purpose of this study is to study the challenges, benefits and offer solutions that the higher education in Oman would benefit of. Finally, this paper gives recommendations on how the universitiesin Omani HEIs can minimize and conquer the challenges that higher education’ students in Oman face in becoming a smart learning environment.


Determination of the Optimal Surface Area of Printed Boards

David Aleksanyan1, Levon Stepanyan2 and David Husikyan3, 1Department of Communication Systems, Marshal Armenak Khamperyants Military Aviation Institute, Yerevan, Armenia, 2Department of Industrial Engineering and Systems Management, American University of Armenia, Yerevan, Armenia and 3Department of Communication Systems, National Polytechnic University of Armenia, Yerevan, Armenia

ABSTRACT

Mathematical model is used in order to determine the surface area of the printed board using its characteristics parameters. The functional dependency of the surface area of the printed board from the quantity of the Integral Schemes (IS), Rent’s coefficient, the average number of outputs of the IS, the minimal width of the metallic wirings is obtained.

KEYWORDS

Integral Schemes, Conduction Layers, Printed Board Surface Area, Rent’s Coefficient.


Machine Learning Approach Towards Road Accident Analysis in India

Shruti Singhal, Bhavini Priyamvada and Dr Rachna Jain, Computer Science Department, Bharati Vidyapeeth’s College of Engineering, Delhi, India

ABSTRACT

This paper aims to study, compare and analyse the performance of six major machine-learning techniques to better understand the occurrence of traffic accidents. The methods considered are Decision trees, Support Vector Machines, Naïve Bayes, Random Forest, K-Nearest Neighbour and, Logistic Regression. For the most realistic and conceivable accident reduction effects with budgetary constraints, the study must be based on objective and scientific surveys to detect and further prevent accidents, understand the causes and the acuteness of injuries.

KEYWORDS

Machine learning, Random Forests Classification, Support Vector Machines, Decision Trees Classification


Parking Assistance Display with Estimated Parking Space Using Stereo Vision

Chi-Cheng Cheng, Chi-Cheng Lee, and Jyun-Han Huang, Department of Mechanical and Electro-Mechanical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan, R.O.C.

ABSTRACT

Inexperienced drivers always suffer from limited spatial information coming from side and review mirrors to complete parking tasks. The major obstacle is that they cannot easily estimate relative position of the parking space with respect to their vehicles. Therefore, this paper aims to develop a parking assistance display system that can continuously provide the top view of both the vehicle and the parking space for drivers. The system applies two wide-angle cameras mounted at the rear of the vehicle. In order to search for two farther corners of the parking space with efficiency, the FAST corner detection technique is employed. Three dimensional spatial coordinates of those corners can therefore be determined by the stereo vision framework. As a result, the position of the parking space relative to the vehicle can be estimated. To verify the effectiveness of the proposed parking assistance display, parking experiments with a golf cart were conducted. Experimental results demonstrate the parking tasks can be successfully accomplished with the help from the presented assistance display.

KEYWORDS

Parking Assistance Display, Stereo Vision, Corner Detection, Parking Space Estimation.


Low-cost automatic fish measuring estimation

Vicent Sanz Marco1, David G. Valcarce2, Marta F. Riesco2, Vanesa Robles3, Olga Rubiera Rodriguez4 and Morito Matsuoka1, 1Cybermedia Centre, Osaka University, Osaka, Japan, 2Spanish Institute of Oceanography, Santander, Spain, 3Department of Molecular Biology, Universidad de Leon, Leon, Spain and 4Lancaster University, Lancaster, United Kingdom

ABSTRACT

For an optimal fish raising under captivity conditions, biomass calculation is usually an essential factor to estimate the ideal amount of food required. Usually, this process implies human-animal interaction, however, fish manipulation can affect their correct growth or even cause their death. In particular, some fish species like Senegalese sole, can easily be stressed when they are manipulated out from their environment. The advances on image recognition systems have opened a new range of possibilities to avoid any kind of human-animal interaction. With a lowest estimation of 0.8 centimetres, and around 95% of accuracy detection, our novel prototype can successfully provide a highly accurate fish measuring estimation based on an image, which can be provided by any kind of device, such as mobile phone.

KEYWORDS

Image Recognition, Neural Networks, Image Reconstruction, Biology, Applications


Grant-free Safe-Scma Based on Detection of Unknown Abnormal Codebooks

Hanyuan Huang, Tao Li and Hui Zhao, College of Cyber Security, Sichuan University, Chengdu, China

ABSTRACT

Non orthogonal multiple access (NOMA) can support massive accesses in 5G. Sparse code multiple access (SCMA) is a typical NOMA technology. Basic principle of SCMA is that multi-user bit data directly map into multi-dimensional complex sequences through the codebook. Grant-free SCMA allows users to select codebook from codebook pool to send data instantly, reducing the cost of overhead and delay of granting process. When the receiver and the sender use same codebook information, the data can be transmitted correctly. But in current SCMA researches, the problem of asymmetric codebook information between sender and receiver caused by the intrusion of codebook pool is not considered. In this paper, abnormal codebook detection is proposed in the grant-free SCMA. Because most of intrusion is unknown, detection is realised by comparing test codebooks with normal states. In this paper, without being focus on the whole normal codebook set, the process of detection is generated by extracting characteristics of normal codebooks. Tested objects in the process can include but not limit to codebook structure, constellations, relationship of constellations, overall feature of codebook pool. Detection can be executed step by step until discovering error state or accomplishing all steps to avoid facing high computational complexity caused by directly comparing with all normal codebooks. Besides, tested abnormal codebooks are saved and evolved to act as detectors. Future detection for unknown abnormal codebooks will do match with detectors which are evolved from those known abnormal codebooks.

KEYWORDS

Grant-free SCMA, SCMA codebooks, abnormal codebooks detection, codebook features extraction, abnormal codebook evolution


The Parallel HTM Spatial Pooler with Actor Model

Damir Dobric1, Andreas Pech2, Bogdan Ghita1 and Thomas Wennekers1, 1University of Plymouth, Faculty of Sciences and Engineering and 2Frankfurt University of Applied Sciences, Dept. Of Computer Science and Engineering

ABSTRACT

The Hierarchical Temporal Memory Cortical Learning Algorithm is an algorithm inspired by the biological functioning of the neo-cortex, which combines spatial pattern recognition and temporal sequence learning. It organizes neurons in layered column-units built from many neurons connected in the more complex structure called regions (areas). Such hierarchically organized structures can also be connected in networks, which provides more cognitive capabilities like invariant representation. Complex topology and a high number of neurons in its structure require wide more compute power than a single machine with multicore processors and GPU. This paper aims to improve the HTM CLA by enabling it for horizontal scale on multiple nodes in a highly distributed system by using the Actor Programming Model. The proposed concept also makes use of existing cloud and serverless technology and it enables easy setup and operation of cortical algorithm in a distributed environment.The Proposed model is based on a mathematical theory and computation model, which targets massive concurrency. Using this model drives different reasoning about concurrent execution and should enable flexible distribution of cortical computation logic across multiple physical nodes. This work is the first one about parallel HTM Spatial Pooler on multiple nodes with named computational model.With the increasing popularity of cloud computing and serverless architecture, this work is the first step towards proposing interconnected independent HTM CLA units in an elastic cognitive network and can provide an alternative to deep neuronal networks, with theoretically unlimited scale in a distributed cloud environment. This paper specifically targets the redesign of a single Spatial Pooler unit.

KEYWORDS

Hierarchical Temporal Memory, Cortical Learning Algorithm, HTM CLA, Actor Programming Model, AI, Parallel, Spatial Pooler


An Investigation to Choose the Proper Therapy Technique in the Management of Autism Spectrum Disorder

Ilker Ozsahin1,2, Mubarak Taiwo Mustapha1,2, Safa Ameen Albarwary1,2 and Dilber Uzun Ozsahin1,2, 1Department of Biomedical Engineering, Faculty of Engineering, Near East University, Nicosia, Mersin-10 TRNC, 99138 Turkey and 2DESAM Institute, Near East University, Nicosia, Mersin-10 TRNC, 99138 Turkey

ABSTRACT

Autism spectrum disorder (ASD) is a group of neurodevelopmental conditions in which the individuals face challenges with social engagement, age-appropriate pay and fail to develop appropriate peer relationship according to their developmental level. This study aims to evaluate, compare and rank the therapy techniques used in the management of ASD using the fuzzy preference ranking organization method for enrichment evaluation (PROMETHEE), a multi-criteria decision-making approach. Fuzzy PROMETHEE utilizes a pair-wise comparison of alternatives using preference function and weight. These parameters were prioritized based on their importance for the survivability of the patient. The techniques we selected are as follows: Applied behavioral analysis (ABA), cognitive behavioral therapy (CBT), speech therapy, and pharmacological therapy such as risperidone and aripiprazole. The result indicates that CBT is the most preferred technique, followed by ABA, aripiprazole, speech therapy, and risperidone. Nonetheless, new criteria and parameters could be considered and weights could be assigned based on the interests of the decision maker. We showed the applicability of the proposed technique in informing decision makers in choosing the right therapy technique for the management of ASD.

KEYWORDS

Autism Spectrum Disorders, Therapy, Decision-Making, Fuzzy, PROMETHEE