Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Sub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier
The text extraction from the natural scene image is still a cumbersome task to perform. This paper presents a novel contribution and suggests the solution for cursive scene text analysis notably recognition of Arabic scene text appeared in the unconstrained environment. The hierarchical sub-sampling technique is adapted to investigate the potential through sub-sampling the window size of the given scene text sample. The deep learning architecture is presented by considering the complexity of the Arabic script. The conducted experiments present 96.81% accuracy at the character level. The comparison of the Arabic scene text with handwritten and printed data is outlined as well
ESL University Students2019; Attitudes Towards Using WhatsApp in Academic Writing
This study examined the relationship between behavioural intention and the Technology Acceptance Model (TAM) variables: Perceived usefulness, ease of use and attitudes towards WhatsApp tool in teaching and learning academic writing skills in Botswana. This study accurately hypothesized a positive and significant relationship between behavioural intention to use WhatsApp in academic writing and dimensions of usefulness, and extent of use of WhatsApp. However, there was no significant relationship between ease of use and behavioural intention (0.436); and perceived web based privacy (0.878). 120 questionnaires were distributed with a response rate of 85%. 70 questionnaires were administered at the University of Botswana and 50 at Botho University also in Botswana. The questionnaire consisted of a 5-Point Likert Scale. The data were subjected to validity and reliability in order to explicate the psychometric competence of the scale items in the Botswana context. Correlation and regression analysis established the association and relationship of the hypothesized sub-constructs in this study. Simple random probability sampling technique was adopted in this empirical study. Scale items were adapted from Davis2019;s (1989) TAM model. The findings thus provide a strategic platform for understanding learners in Synchronous and Asynchronous discussion in Digital Learning mode of the 21st Century
Accident Detection in Live Surveillance
With the increase in number of vehicles in the country vehicle detection is an important in road traffic management system. Different traffic accident causes such as vehicle overspeeding, wrong way driving, collision and accident can be detected by CCTV installed on roads. The results obtained from traffic parameters can be applied for vehicle tracking, vehicle classification, parking area monitoring, road traffic monitoring and management etc. The main objective of this project is to decrease the deaths caused by accident occurring because over speeding, wrong war driving by ensuring public safety and also a building a better system for managing the traffic on the roads. The aim of this paper is to develop a system that can detect the vehicle accident which are caused by overspeeding, wrong way driving and collision detection on city roads. A prototype system is developed and tested
Performance Evaluation of Encrypted Text Message Transmission in 5G Compatible Frequency-domain Subband Superposed Scheme Implemented MIMO OFDM Wireless Communication System
In this paper, an investigative study has been made on the performance evaluation of encrypted text message transmission in 5G compatible multiuser frequency-domainsubband superposed (FDSS) scheme implemented MIMO OFDM wireless communication system. The 2D7;2 multiantenna configured simulated system under consideration incorporates modern channel coding (LDPC and Repeat and Accumulate (RA)) and signal detection (Cholesky decomposition based ZF detection, Group Detection (GD) approach aided Efficient Zero-Forcing (ZF) and Lanczos method based efficient signal detection) techniques. In the scenario of transmitting encrypted text message over AWGN and Rayleigh fading channels, it is noticeable that implementation of Repeat and Accumulate channel coding and Group Detection (GD) approach aided Efficient Zero- Forcing (ZF) signal detection techniques is very much robust and effective in retrieving transmitted text messages for all users
On Application of Artificial Neural Networks to Control Quality of Protection Environment
The principles of constructing artificial neural networks for a quality control system for the operation of ship equipment related to environmental protection are considered. The concentration of harmful substances in exhaust gases and bilge waters depends on many factors related to both the condition of the equipment and external conditions. Analytically describing this dependence is extremely difficult, therefore, it is proposed to use artificial neural networks to monitor the state of equipment. The paper describes how to create a neural network such as a self-organizing feature map and methods for its training
A Systematic Review of Security in Electronic Commerce- Threats and Frameworks
There is a remarkable scope for more streamlined living through an increase of e-platforms specially ecommerce but this coincides with an increase in security concerns since the global market place is virtual and anonymous Therefore users have to blindly trust the online providers In order to overcome this physiological barrier the eplatforms should ensure utmost security If not the ecommerce industry is unableto perform in the market effectively Thereby arises the need to perform a systematic review of security issues in the e-commerce industry and to discover how different frameworks address these problems This paper aims to identifythe main security problems faced by both customers and vendors when interacting with ecommerce platforms and to evaluate general security management frameworks based on the main security areas identifie
An Analytic Real-Time Framework for IoT based Home Automation System
The Internet of Things or IoT means the ability to connect billions of physical devices around the world that are now linking to the internet for collecting and sharing data. Internet of Things (IoT) technologies is used to sense the real-time primordial manufacture data and included the energy alliance data and the provision circumstance data. The Internet of Things (IoT) will approve any contents to be sensed or monitored remotely wherever there any remaining network infrastructure, making amenities for the integration of the actual world into computer-based systems. Real-time narrates the path of flowing media is processing. In the real-time procedure, anyone can entrance information barring to narrate for it and save our time. In our proposed system, we build a system where we calculate real-time. To compute real-time, we need an IoT based automated system. And here we use an IoT based home automation system. We are passing data through the system for collecting data with the help of Cisco Packet Tracer simulator. For calculating real-time performance, we use six performance metrics to evaluate the event detection system performance. They are sensitivity, specificity, precision, accuracy, F1-score, and G-mean
A Review of Mobile Application Development in the Agile Software Development Environment
With the ever changing dynamic environment in mobile devices, mobile software applications need to cope with some particular performance environment that include the limited resources, high autonomy requirements and mark et regulations among other constraints [1]. To provide a software development process that responds to these challenges, adoption of Agile methodology that follows an iterative approach to build software rapidly where the entire software development lifecycle is brok en down into smaller iterations helps to minimize overall risk s. This allows software projects developed though agile methodologies to be easily modified rapidly to meet the users/customers2019; requirements. This paper assesses the development of mobile applications in the agile software development environment
A Smart Baby Cradle
A small baby needs parents' attention for whole day and 7 days a week, which is impossible due to other priorities like house hold activities, official works and personal works. Day care centre or nanny is the two options available which involves lot of passion. We all live in a world where technologies are sournded all around us. The new generations of parents were raised up with this amazing technology. There are lots of things or items present on these earth that parents will buy to help them care for their baby (Cradle, Crib, Baby Monitor, etc.). So, there is a need for safe and secure place to take good care of the children2019;s need with minimum human intervention and care, which can be accomplished with the help of a 201C;Smart Baby Cradle201D;. A 201C;Smart Baby Cradle201D; provides parents a smart automatic cradle system which help these parents monitor and comfort the baby. The Smart Baby Cradle allows them to monitoring their babies, the cradle, play soothing music, even speak to the baby, observing the temperature of the infant, bed wet sensor which will caution the attendants for bunk wetting of the infant. The mother where so ever she is can have a look on the baby through camera inserted in the cradle. All the fittings are done through Arduino and PIR sensor. Additionally, we provide a predefined nutrition food chart to help baby remain healthy
Study and Optimized Simulation of OSPFv3 Routing Protocol in IPv6 Network
Routing is a design way to pass the data packet. User is assigns the path in a routing configuration. A significant role played by the router for providing the dynamic routing in the network. Structure and Configuration are different for each routing protocols. Next generation internet protocol IPv6 which provides large address space, simple header format. It is mainly effective and efficient routing. It is also ensure good quality of service and also provide security. Routing protocol (OSPFv3) in IPv6 network has been studied and implemented using 2018;cisco packet tracer2019;. 2018;Ping2019; the ping command is used to check the results. The small virtual network created in Cisco platform .It is also used to test the OSPFv3 protocol in the IPv6 network. This paper also contains step by step configuration and explanation in assigning of IPv6 address in routers and end devices. The receiving and sending the packet of data in a network is the responsibility of the internet protocol layer. It also contains the data analysis of packet forwarding through IPv6 on OSPFv3 in simulation mode of cisco packet virtual environment to make the decision eventually secure and faster protocol in IPv6 environment