Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Towards Optimized K Means Clustering using Nature-inspired Algorithms for Software Bug Prediction
Full text linkIn today s software development environment the necessity for providing quality software products has undoubtedly remained the largest difficulty As a result early software bug prediction in the development phase is critical for lowering maintenance costs and improving overall software performance Clustering is a well-known unsupervised method for data classification and finding related patterns hidden in dataset
Domain Specific Deep Neural Network Model for Classification of Abnormalities on Chest Radiographs
Full text linkThis study collected pre-processed dataset of chest radiographs formulated a deep neural network model for detecting abnormalities It also evaluated the performance of the formulated model and implemented a prototype of the formulated model This was with the view to develop a deep neural network model to automatically classify abnormalities in chest radiographs In order to achieve the overall purpose of this research a large set of chest x-ray images were sourced for and collected from the CheXpert dataset which is an online repository of annotated chest radiographs compiled by the Machine Learning Research group Stanford University The chest radiographs were preprocessed into a format that can be fed into a deep neural network The preprocessing techniques used were standardization and normalization The classification problem was formulated as a multi-label binary classification model which used convolutional neural network architecture for making decision on whether an abnormality was present or not in the chest radiographs The classification model was evaluated using specificity sensitivity and Area Under Curve AUC score as parameter A prototype of the classification model was implemented using Keras Open source deep learning framework in Python Programming Language The AUC ROC curve of the model was able to classify Atelestasis Support devices Pleural effusion Pneumonia A normal CXR no finding Pneumothorax and Consolidation However Lung opacity and Cardiomegaly had probability out of less than 0 5 and thus were classified as absent Precision recall and F1 score values were 0 78 this imply that the number of False Positive and False Negative are the same revealing some measure of label imbalance in the dataset The study concluded that the developed model is sufficient to classify abnormalities present in chest radiographs into present or absen
Socio-Technical Power System Resilience
Full text linkAbstract Power systems serve social communities that consist of residential commercial and industrial customers The social behavior and degree of collaboration of all stakeholders such as consumers prosumers and utilities affect the level of pre- paredness mitigation recovery adaptability and thus power system resilience Nonetheless the literature pays scant attention to stakeholders social characteristics and collaborative efforts when confronted with a disaster and views the problem solely as a cyber-physical system However power system resilience which is not a standalone discipline is inherently a cyber-physical- social problem making it complex to address To this end in this paper we develop a socio-technical power system resilience model based on neuroscience social science and psychological theories and using the threshold model to simulate the behavior of power system stakeholders during a disaste
Blockchain Challenges: Advantages and Algorithms
Full text linkCryptocurrency is the innovation that has changed the way of life most significantly over the past ten years Bitcoins is a term that often comes up when discussing the blockchain system Although they are not identical Ethereum and Cryptocurrency nevertheless remain widely misunderstood Innovative technologies had to be created as a result from rising degrees of globalization These groundbreaking innovations improve the speed of international trade There are many technical experiments some of them were successful whereas others died or required development The decentralized ledger technology its benefits and methods for consensus are described on this articl
Inernet of Everything: A Solution to Mobile Banking using Voice Recognition
Full text linkThe advancement in banking transaction system over the years has been enormous and the needs for identifications of customer s authentication validation and confirmation are of utmost priority and should be dealt with judiciously Mobile banking has emerged as one of the main division in digital world of financial transactions and consists of information inquiry notifications and alerts applications and payment transfer Mobile based application is used for connecting customer handset with bank server for all such services in the banking industry The current trend of Mobile banking as gone beyond the use of One Time Password OTP applications used by banks The problem with current banking applications is that they send data directly to customer in plain text form compromising with security recognised as OTP in most of the online transaction An online banking customer logging in to the bank s website with username and password triggers a request to send an OTP to his or her registered mobile phone or the OTP may not be necessary after one or two transaction There is every likely hold of Mobile phone been stealing access by unauthorised person or being hacked Upon receipt of a text message with the OTP the customer enters it with an additional field on the banking site s login page to complete the login process since your details are already on your phone It could have been fine if the mobile network can act immediately but blocking of network provider involves the presentation of National Identification Number NIN which is a chain reaction The purpose of this research work is to provide cost effective secure fast Mobile banking solution combining features of cryptography as well as behavioural pattern and Interactive Voice Response for final authentication and authorisation of costumer identification in all form of financial transaction
Machine Learning Algorithms for Predicting Reservoir Porosity using Stratigraphic-dependent Parameters
Full text linkPredicting reservoir porosity, permeability and other reservoir parameters are very important but arduous task in formation evaluation, reservoir geophysics and reservoir engineering. Recent successes in machine learning and data analytics in different geoscience disciplines provides the opportunity to offer cheaper and faster techniques of predicting reservoir properties. This study used gross depositional environments, reservoir depth, diagenetic impact, permeability and stratigraphic heterogeneity from a database of 93 reservoir to predict reservoir porosity. The data for this study includes numeric and categorical descriptions of 93 reservoirs across the UK and Norwegian sector of the North Sea. Five models were trained using linear regression, support vector machine (SVM), boosted tree, bagged tree and random forest algorithms. The performance of the different models was evaluated using R-squared (R2), root mean square error (RMSE) and mean absolute error (MAE). Model trained using random forest algorithm with R2 score of 0.75, RMSE of 0.118 and MAE of 0.0028 outperformed other models. A comparison between predicted porosity and the actual porosity in training data and testing data show a good match, indicating the ability of the random forest model to make prediction on unseen data. The machine learning technique presented in this study represents a pragmatic approach to the classical log conversion problem that over the years has caused dilemmas to generations of geoscientists and petroleum engineers. The method requires no underlying mathematical models or costly assumptions of linearity among variables. Predicting porosity by using sedimentological parameters can effectively reduce the high cost of using petrophysical methods such as nuclear magnetic resonance and other logging methods
Application of Decision Trees in the Identification of Fraudulent Websites
Full text linkComputer security is a very important area in any system that has an internet connection, because there are fraudulent websites that can carry out criminal actions towards a person, organization or other entity. Therefore, it is necessary to be able to detect which websites are fraudulent before being able to enter it, for this an implementation was developed through Decision Trees with the Python language to detect and classify them as Legitimate, Suspicious and Fraudulent through 1353 cases that they rank websites
Data Science and Management : A Study of Theoretical Approaches to computer System with Organisation using Advanced Analytics
Full text linkA firm's Data Management department is in charge of the corporate data capture, retention, security, management, and safety, as well as the formulation and execution of all datarelated regulations inside that company. The Data Management team, on the other hand, merely maintains the data resources; it is underrecognized in the fundamental technological uses of the material. All data is owned by the Data Function of management. The Data Science department in an organisation, on either extreme, conceptualises, develops, executes, and practises all "terms of improving" of information assets. In this context, "technical implementations" refer to the research, technologies, skill, and business practises that use corporate data
Synthesis of Low-Profile Antennas using Fractal Analysis
Full text linkThe results of the synthesis of low-profile antennas based on taking into account the very similarity of their elements are presented. The main disadvantages of low-profile antennas and promising ways to overcome them are considered. The results of calculating their characteristics in the MMANA-GAL and CST Microwave Studio modeling environment are presented. Possibilities of fractal types of low-profile antennas are investigated. The prospects for their application have been determined
Information and Communication Technology (ICT) as a Tool in Revenue Generation and Tax Administration, A Study of Firs Abakaliki,Ebonyi State-Nigeria
Full text linkInformation and Communication Technology ICT has opened a new visage to globalization in revenue generation and tax administration The deployment and integration of ICT facilities into revenue generation and tax administration for internet access and a web portal implementation that enable the organizations in charge of revenue generation and tax administration in Nigeria federal inland revenue service FIRS to carry out most of its activities ubiquitously on the internet is steadily growing in Nigeria This has enabled many financial operations such as Pay-direct E-tax M-banking E-banking E-fiiling E-assessment E-auditing among others In Nigeria quite a large number of revenue generation and tax administration organizations in different state have either developed their portal or have had one deployed for the purpose of ICT-related operation