COMPUSOFT: An International Journal of Advanced Computer Technology 2020-09-10T04:58:59+00:00 Editor In Chief Open Journal Systems <p>Computer Science Journals - COMPUSOFT is a monthly computer and engineering science journal that publishes innovative articles which contribute new theoretical results in all areas of engineering and Computer Science, Communication Network, Information Security issues, electrical engineering, electronics engineering etc. COMPUSOFT is high impact journal of information technology having Impact Factor of 4.44 (Self Calculated) with the rejection rate of around 90%. We invite research papers, review articles, thesis in all the fields of engineering &amp; computer science. We are indexed in many renowned indexing agencies. International Computer Science and Engineering Journals have devoted Staff, Reviewers, Editorial Board Members, Experts, and Adviser.</p> Big Data Quality: Factors, Frameworks, and Challenges 2020-08-31T14:27:47+00:00 Mohammad Abdallah Mohammad Muhairat Ahmad Althunibat Ayman Abdalla Big Data applications are widely used in many fields; Artificial Intelligent, Marketing, Commercial applications, and Health care, as we have seen the role of Bid Data in the Convid-19 pandemic. Therefore, to ensure that the Big Data applications are used and generated in good quality for their consumers. It is important to have quality factors that the Big Data applications should satisfy, quality frameworks that applied and tested the quality factors for the Big Data application. However, the quality measurement process has some challenges to be applicable and trustworthy. In this research, we have listed different quality factors and dimensions and quality frameworks that are commonly used to measure the Big Data quality measurement. Also, we listed the frequent challenges that the researchers and data scientists are faced through the Big Data quality measurement process. 2020-08-31T14:27:13+00:00 Copyright (c) 2020 COMPUSOFT: An International Journal of Advanced Computer Technology Generating 3D dataset of Gait and Full body movement of children with Autism spectrum disorders collected by Kinect v2 camera 2020-09-02T04:16:48+00:00 Ahmed AbdulRahman Israa Hadi Yasen Rajihy <p>Until now, a three-dimensional dataset combines gait and body movement analysis of children with Autism Spectrum Disorders (ASD) in controlled environments has not been published. ASD mean disorders of neurodevelopment that last a lifetime which occurs in early childhood and usually associated with unusual movement and gait disturbances. Three-dimensional gait features captured by Kinect v2 can assist clinicians in diagnosing, clinical decision-making, and treatment planning of ASD. In this paper, Kinect v2 uses to build a 3D-skeleton-based gait dataset, which includes joints positions, the corresponding skeleton movement video, joints trajectories video captured by Kinect v2, and color videos captured by Samsung Note 9 rear camera. Besides building dataset, this paper classifies children with ASD from normal children by proposed system comprises four main stages: 1) dataset augmentation based on seven transformations to solve the problem of lack of ASD cases, 2) Extracting features that we think play an important role in classification, 3) Reducing data dimensions using Principal Component Analysis (PCA) and 4) Using Multilayer Perceptron (MLP) to classify data. Classification accuracy when using eleven features result from PCA and MLP is 95% with 0.7 seconds to build the model</p> 2020-09-02T04:16:47+00:00 Copyright (c) 2020 COMPUSOFT: An International Journal of Advanced Computer Technology NEURAL NETWORK VISUAL ODOMETRY BASED FRAMEWORK FOR UAV LOCALIZATION IN GPS DENIED ENVIRONMENT 2020-09-10T04:58:59+00:00 Mohamed Ali SEDRINE Wided SOUIDENE MSEDDI Rabah ATTIA <p>This paper presents a vision-based localization framework based on visual odometry.Visual odometry is a classic approach to incrementally estimate robot motion even in GPS denied environment, by tracking features in successive images. As it is subject to drift, this paper proposes to call&nbsp; a convolutional neural netwok and visual memory to improve process accuracy.</p> <p>In fact, our framework is made of two main steps. First, the robot builds its visual memory by annotating places with their ground truth positions. Dedicated data structures are made to store referenced images and their positions. Then, during navigation step, we use loop closure corrected visual odometry. A siamese convolutional neural network allows us to detect already visited positions. It takes as input current image and an already stored one. If the place is recognized, the drift is then quantified using the stored position. Drift correction is conducted by an original two levels correction process. The first level is directly applied to the&nbsp; estimation by substracting the error. The second level is applied to the graph itself using iterative closest point method, to match the estimated trajectory graph&nbsp; to the ground truth one.</p> <p><strong>Experiments showed that the proposed localization method has a centimetric accuracy.</strong></p> 2020-09-10T00:00:00+00:00 Copyright (c) 2020 COMPUSOFT: An International Journal of Advanced Computer Technology