Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Towards Reducing Convid-19 Spread: A Geo-Location based Attendance Monitoring and Navigation System for Institution
Get PDFThe current pandemic caused by covid-19 has come to stay and has changed many things, including the education sector of the whole world. However, institutions must resume, and academic activities must continue under the precautionary measures for students and staff to stay safe. The question is, how will precautionary measure be observed? This paper provided a geo-location approach in tackling the aspect of attendance management of students and staff in the classroom to maintain social distancing while marking attendance sheets for a large class and minimize time wastage for another lecturer. The developed software also focused in campus area navigation for outsiders or newly admitted students. This research was carried out using smart phones due to its built-in global positioning system (GPS) and can be afforded by all. The developed system was tested online with different smart phones connected to it, 93 feed-backs with 63% correctness were gotten from the system prediction
The Impact of Different Image Thresholding based Mammogram Image Segmentation- A Review
Get PDFImages are examined and discretized numerical capacities. The goal of computerized image processing is to enhance the nature of pictorial data and to encourage programmed machine elucidation. A computerized imaging framework ought to have fundamental segments for picture procurement, exceptional equipment for encouraging picture applications, and a tremendous measure of memory for capacity and info/yield gadgets. Picture segmentation is the field broadly scrutinized particularly in numerous restorative applications and still offers different difficulties for the specialists. Segmentation is a critical errand to recognize districts suspicious of tumor in computerized mammograms. Every last picture have distinctive sorts of edges and diverse levels of limits. In picture transforming, the most regularly utilized strategy as a part of extricating articles from a picture is "thresholding". Thresholding is a prevalent device for picture segmentation for its straightforwardness, particularly in the fields where ongoing handling is required
A Dynamic Level Technical Indicator Model for Oil Price Forecasting
Get PDFInvestment in commodities and stock requires a nearly accurate prediction of price to make profit and to prevent losses. Technical indicators are usually employed on the software platforms for commodities and stock for such price prediction and forecasting. However, many of the available and popular technical indicators have proved unprofitable and disappointing to investors, often resulting not only in ordinary losses but in total loss of investment capital. We propose a dynamic level technical indicator model for the forecasting of commodities prices. The proposed model creates dynamic price supports and resistances levels in different time frames of the price chart using a novel algorithm and employs them for price forecasting. In this study, the proposed model was applied to predict the prices of the United Kingdom (UK) Oil. It was compared with the combination of two popular and widely accepted technical indicators, the Moving Average Convergence and Divergence (MACD) and Stochastic Oscillator. The results showed that the proposed dynamic level technical indicator model outperformed MACD and Stochastic Oscillator in terms of profit
Efficient Network Traffic Classification and Visualizing Abnormal Part Via Hybrid Deep Learning Approach : Xception + Bidirectional GRU
Get PDFDue to a rapid development in the field of information and communication, the information technologies yielded novel changes in both individual and organizational operations. Therefore, the accessibility of information became easier and more convenient than before, and malicious approaches such as hacking or spying aimed at various information kept increasing. With the aim of preventing malicious approaches, both classification and detecting malicious traffic are vital. Therefore, our research utilized various deep learning and machine learning models for better classification. The given dataset consists of normal and malicious data and these data types are png files. In order to achieve precise classification, our experiment consists of three steps. Firstly, only vanilla CNN was used for the classification and the highest score was 86.2%. Second of all, for the hybrid approach, the machine learning classifiers were used instead of fully connected layers from the vanilla CNN and it yielded about 87% with the extra tree classifier. At last, the Xception model was combined with the bidirectional GRU and it attained a 95.6% accuracy score, which was the highest among all
SDWAN (Software Defined-WAN) Technology Evaluation and Implementation
Get PDFMany organizations are struggling to provide high bandwidth and reliable internet connectivity at their branch offices and business locations and getting the most out of their operational expense. The need for internet connectivity at any branch offices and business locations is no longer a luxury but is a necessity. Let us try to understand how to replace the traditional MPLS network with the new SDWAN (Software - Defined- Wide Area Network) technology. We will try to understand why it is essential to implement the latest technology instead of investing in the existing MPLS (Multi- Protocol label switching) by taking an example of a retail organization. We also have a look at how to evaluate the product by using some metrics and how different teams are involved during different phases of the project
Artificial Intelligence Assisted Consumer Privacy and Electrical Energy Management
Get PDFSmart metering infrastructure brings unique benefits for Utility Companies as well as consumers, however, massive consumer data collected and transmitted by the smart meters have raised consumers2019; privacy concerns. This paper presents a novel solution that is based on Artificial Intelligence Agent that continuously computes the gap between 201C;Average Daily Demand201D; and 201C;Instantaneous Demand201D; of a consumer, and allows the Battery Banks to discharge just enough to fill the gaps and eliminate kinks in the energy usage graph to mask the energy usage. This novel approach offers several benefits, such as, it conceals the utility usage patterns and thus ensures privacy, eliminates excessive discharging and charging of batteries that lifts operational constraints of the batteries, employs scheduling that renders utility bill reduction as an add-on
The Current State of Fake News in the D.R. Congo and Socials Impacts
Get PDFIn the media industry, the propagation of fake news is becoming a booming topic and challenge. On social media, website and written press the spread of this is so fast to keep track of confusing reader on what is fake and also causing damage in different sector of life [1] in response, social media platforms have announced actions to limit the spread of false content. Rapid speed of fake news poses an increasing risk to society2019;s worldwide to counter this more need to done. The lack of digital literacy may play a big role in spread of fake news in the DRC were less than 20% have access to internet never less access to social media is also low few how have access don2019;t have computer literacy skills to distinguish and decide what to share. With growing number for the last decade, the challenge will be more complicated with a population estimated to 80 million in 2017, if 75% will be able to access social media platform in 2030 the problem will far great than what it is now
Monitoring Social Distancing by Smart Phone App in the effect of COVID-19
Get PDFSocial distancing measures are necessary for many infectious diseases that spreads through droplets and microdroplets. According to WHO, the preventive measure for COVID-19 is to follow strict social distancing. It is not easy to enforce social distance easily in a crowded region and people often not maintain sufficient distance with neighbours. Driven by the need for energy-efficient and cost-effective social distancing monitoring, this paper proposes Smart Social Distancing (SSD) mobile application based monitoring, which can predict the social distancing between two people assisted by mobile bluetooth and mobile camera. SSD involves two major steps to predict the social distance: first the pedestrian in the video frames is identified with the aid of Deep Learning (DL) and in the second step, distance between the two pedestrian is estimated through image processing techniques. The application can also be configured to calculate the distance using Bluetooth Low Energy (BLE) by calculating its received signal strength. The application demonstrates 85% accuracy on predicting the social distancing and alert the user using beep sound or alert messag
A Comparison between Agile and Traditional Software Development Methodologies
Get PDFAgile and Traditional software development methodologies, both are being used in different projects of software development industry. Agile software development technology is an incremental software development process. On the other hand, Traditional software development methodologies or plan-driven software can be explained as a more formal approach to software development. These methodologies come with a fully completed set of systems requirements followed by an architectural and high leveldesign development and inspiration. This research focuses on the software development life cycle, role and responsibilities of agile and traditional software development methodologies and their technical practices. It performs a comparison between both the software development methodologies. Here a questionnaire is used to collect data from the various experts of different IT related organizations of Bangladesh. In the questionnaire, there are three sections to bring out the individual knowledge from different organization, methodology knowledge of the respondents and software development experience of the respondents. The respondents are mainly software engineer, system analyst, software developer etc. A comparison is also performed between this survey result and a survey done by Ambler
Introduction to Computer-Aided Learning
Get PDFIn modern times, technology has taken on a dominant role in many aspects of human life, and computeraided learning (CAL) is an educational tool that makes learning easier. By employing user interface (UI) design it is easy for students to access learning materials and relevant courses. UI design is an important factor for designing useful and usable CAL to appeal to a wide range of users by making the system flexible, attractive, interactive and easy to use