Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Performance Analysis of D-MoSK Modulation in Mobile Diffusive-Drift Molecular Communication Relay System
Full text linkMolecular communication (MC) is a new wireless communication technology, which uses molecules as information carriers. Diffusion-based MC is one of the most common MC methods. With the increase of diffusion distance, the molecular signal attenuation is serious, so the traditional communication technology of relay is introduced into the MC system. In this work, a mobile diffusive-drift MC relay model is investigated, in which the depleted molecule shift keying (D-MoSK) modulation is used. The closed-form expression of symbole error rate (SER) and the channel capacity are derived, meanwhile the impacts of several crucial parameters on the performance are discussed comprehensively
Human Tracking and Profiling for Risk Management
Full text linkInfectious viruses are conveyed via respiratory droplets produced by an infected person when they speak, sneeze, or cough. So, to combat virus transmission, the World Health Organization (WHO) has imposed severe regulations such as mandatory face mask use and social segregation in public spaces. The Human Tracking and Profiling for Risk Management System (HTPRM) is an online application that identifies the risk associated with failing to follow proper health practices. This proposed approach, which is divided into four components, utilizes You Only Live Once YOLO (V3) to detect facemask danger, which would be determined based on two factors: wearing the face mask properly and the type of mask (Surgical, k95, homemade, and bare). The second phase is to use Open CV and SSDMobilenet to evaluate the value of a one-meter space (Social Distance) between people. The system recognizes the maximum number of individuals that can be in the vicinity of the specific hall that uses YOLO( V3) and image processing as the third procedure. In the last processing, the system identifies each persons behavior, classifies it as uncommon or not, and calculates the risk associated with each category. Finally, the system computes the overall risk and generates a warning alarm to notify the user that they are in a dangerous scenario
An Analysis of the Potential Risk and Fraud Involved in Mobile Money Transaction in Freetown Sierra Leone
Full text linkThe research work focused on looking at an analysis of the potential risk and fraud involved in mobile money transactions in Sierra Leone with a focus on Orange and Africell mobile telecommunication companies. The implementation of mobile money service like any other financial service faces risks and challenges. This research addresses fraud as a challenge in the provision of mobile money service to customers in Sierra Leone. Mobile money usage for transactions is steadily growing across Africa with the potential to revolutionize the cash-dominant economy of this continent to be cashless. With the increased use of mobile money services and number of business use cases designed each day, it is imperative to design a holistic approach to mobile money risk, security that will reduce security exposures and prevent fraud, as some mobile money service providers have lost millions of Leones to this growing threat. This research, therefore, examines the measures that mobile network operators providing mobile money services can employ to prevent fraud
Blockchain and Smart Contracts as Complex Self-Organizing Frameworks: Theoretical Perspective
Full text linkBlockchain offers unprecedented opportunities for innovation in financial transactions with a whole new world of opportunities for banking, lending, insurance, and money transfers. Through its algorithms, digital security by decentralization, form smart contracts. Smart contracts allow the performance of credible transactions without third parties, the transactions premised by trackable and irreversible processes are superior to traditional contract law and greatly reduce other transaction costs associated with contracting. Globally, enterprises are undergoing a major transformation towards smart businesses that use intelligent systems integrated into planning for their daily routine. Blockchain technology and smart contacts termed disruptive technologies provide innovative solutions that cannot be ignored due to their inherent complexities. Regarded as complex systems, there is a need to have a theoretical view to understanding the hidden order to the evolution of these systems to bring out traits that are common and have a combination of independent actors behaving as a single unit responding and adapting to their existent setting, as self-organizing systems. This study significantly plays a unique role in contemporary science by explaining how blockchain and smart contracts unify run as nonlinearity complex system that adapts to their environment to bring about consistency hence their applicability
Using Unlabeled Data for Increasing Low-Shot Classification Accuracy of Relevant and Open-Set Irrelevant Images
Full text linkIn search exploration and reconnaissance tasks performed with autonomous ground vehicles an image classification capability is needed for specifically identifying targeted objects relevant classes and at the same time recognize when a candidate image does not belong to anyone of the relevant classes irrelevant images In this paper we present an open-set low-shot classifier that uses during its training a modest number less than 40 of labeled images for each relevant class and unlabeled irrelevant images that are randomly selected at each epoch of the training process The new classifier is capable of identifying images from the relevant classes determining when a candidate image is irrelevant and it can further recognize categories of irrelevant images that were not included in the training unseen The proposed low-shot classifier can be attached as a top layer to any pre-trained feature extractor when constructing a Convolutional Neural Networ
Cloud Computing and Other ICT advancements Use in Kenya’s Agricultural Sector
Full text linkAccording to the latest World Economic Forum study agriculture provides a living for over 70 of Kenya s people As a result agriculture is a crucial sector in Kenya Agricultural productivity is still low and food poverty remains a problem This has resulted in a number of projects in recent years to use ICT advancements to boost agricultural output Cloud computing is one of the advancement that can be used by organizations that still have the traditional on premise IT systems Agriculture is one of the most important areas that has shaped the socioeconomic growth of most countries Over time the benefits of widespread adoption and usage of information and communication technologies in agriculture have included improved agricultural productivity and linkages to remunerative markets food security and national economies among other things E-agriculture is a branch of activity that involves the use of information and communication tools and technology to boost agricultural productivity and make information pertinent to agricultural research planning extension production monitoring marketing and trade available The goal of this desktop review research is to look into how ICT advancements have been used in Kenya s agriculture sector Cloud computing as an advancement was reviewed Cloud computing saves money by removing the need for costly infrastructure and it also gives businesses an easy-to-use cost-effective adaptable dynamic and secure environment in which to do business Radios are still commonly utilized to disseminate agriculture information to rural farmers according to the analysis while computers are primarily used by researchers Despite the fact that mobile-based services aimed to improve access to accurate and timely agriculture information previous literatures show that adoption is hampered by poor technological infrastructure ineffective ICT policies and low user capacity particularly among farmers to use the technologie
Comparative Analysis of Selected Filtered Feature Rankers Evaluators for Cyber Attacks Detection
Full text linkAn increase in global connectivity and rapid expansion of computer usage and computer networks has made the security of the computer system an important issue with the industries and cyber communities being faced with new kinds of attacks daily The high complexity of cyberattacks poses a great challenge to the protection of cyberinfrastructures Confidentiality Integrity and availability of sensitive information stored on it Intrusion detection systems monitors network traffic for suspicious Intrusive activity and issues alert when such activity is detected Building Intrusion detection system that is computationally efficient and effective requires the use of relevant features of the network traffics packets identified by feature selection algorithms This paper implemented K-Nearest Neighbor and Na ve Bayes Intrusion detection models using relevant features of the UNSW-NB15 Intrusion detection dataset selected by Gain Ratio Information Gain Relief F and Correlation rankers feature selection technique
Crop Production Modeling System for Diverse Physiographical Areas in Nueva Vizcaya
Full text linkThe wide range of environmental factors affecting cropping is very difficult to ascertain most especially with the absence of climate monitoring equipment and dissemination of an up-to-date weather data forecasting Due to climate change irregular weather patterns cause major disruptions in agricultural activities and heavy damage to crop yields There is limited data available to anticipate and adapt to climatic changes due to insufficiency of monitoring systems The proposed system entitled Crop Production Modeling System then integrates the use of available state-of-the art climate sensing and monitoring system to gather and interpret data and establish current pattern of weather Portable and unique Field Monitoring Systems FMS installed in strategic locations of the different municipalities of Nueva Vizcaya will be utilize to effectively monitor variations in the weather patterns These weather patterns will be used as a tool to determine the optimal cropping season In addition the system provides different graphical presentations as reports readable and understandable to the users especially to the agricultural sectors Moreover the said system will be accessible and portable to the users in all cases because its internet dependability The present system can be customized to address not only agriculture concerns but also health and safety and disaster and risk management The system has the potential for up scaling and adoption by other provinces or municipalities due to its very promising capabilitie
Design of Machine Learning Framework for Products Placement Strategy in Grocery Store
Full text linkThe well-known and most used support-confidence framework for Association rule mining has some drawbacks when employ to generate strong rules, this weakness has led to its poor predictive performances. This framework predict customers buying behavior based on the assumption of the confidence value, which limits its competent at making good business decision. This work presents a better Association Rule Mining conceptualized framework for mining previous customers transactions dataset of grocery store for the optimal prediction of products placement on the shelves, physical shelf arrangement and identification of products that needs promotion. Sampled transaction records were used to demonstrate the proposed framework. The proposed framework leverage on the ability of lift metric at improving the predictive performance of Association Rule Mining. The Lift discloses how much better an association rule is at predicting products to be placed together on the shelve rather than assuming. The proposed conceptualized framework will assist retailers and grocery stores owners to easily unlock the latent knowledge or patterns in their large day to day stored transaction dataset to make important business decision that will make them competitive and maximized their profit margin
Acoustic Features Based Accent Classification of Kashmiri Language using Deep Learning
Full text linkAutomatic identification of accents is important in todays world, where we are souranded by ASR systems. Accent classification is the problem of knowing the native place of a person from the way He/She speaks the language into consideration. Accents are present in almost all the languages and it forms an important part of the language. Accents are produced from prosodic and articulation characteristics; in this research the aim is to classify accents of Kashmir Language. We have considered using the MFCC and Mel spectrograms for our research. A lot of research has been done for languages like English and is being done in this field and many models of machine learning and deep learning have shown state of the art results, but this problem is new for Kashmiri Language. The accents in Kashmir, vary from area to area and we have chosen 6 areas as our classes. We extracted the features from the audio data, converted those features into Images and then used the CNN architectures as our model. This research can be taken as base research for further researches in this language. Our custom models achieved the loss of 0.12 and accuracy of 98.66% on test data using Mel spectrograms, which is our best for our features