Open Access Original Research Article

The Direct Simulation of Third Order Linear Problems on Single Step Block Method

J. Sabo, Y. Skwame, T. Y. Kyagya, J. A. Kwanamu

Asian Journal of Research in Computer Science, Volume 12, Issue 2, Page 1-12
DOI: 10.9734/ajrcos/2021/v12i230277

In this article, the direct simulation of third order linear problems on single step block method has been proposed. In order to overcoming the setbacks in reduction method, direct method has been proposed using power series to reduce computational burden that occur in the reduction method. Numerical properties for the block method are established and the method developed is consistent, convergent and zero-stable. To validate the accuracy of the block method, certain numerical test problems were considered, the results shown that the accuracy of our method are more accurate over the existing method in literature.

Open Access Original Research Article

Topic Modeling and Sentiment Analysis of Electric Vehicles of Twitter Data

H. P. Suresha, Krishna Kumar Tiwari

Asian Journal of Research in Computer Science, Volume 12, Issue 2, Page 13-29
DOI: 10.9734/ajrcos/2021/v12i230278

Twitter is a well-known social media tool for people to communicate their thoughts and feelings about products or services. In this project, I collect electric vehicles related user tweets from Twitter using Twitter API and analyze public perceptions and feelings regarding electric vehicles. After collecting the data, To begin with, as the first step, I built a pre-processed data model based on natural language processing (NLP) methods to select tweets. In the second step, I use topic modeling, word cloud, and EDA to examine several aspects of electric vehicles. By using Latent Dirichlet allocation, do Topic modeling to infer the various topics of electric vehicles. The topic modeling in this study was compared with LSA and LDA, and I found that LDA provides a better insight into topics, as well as better accuracy than LSA.In the third step, the “Valence Aware Dictionary (VADER)” and “sEntiment Reasoner (SONAR)” are used to analyze sentiment of electric vehicles, and its related tweets are either positive, negative, or neutral. In this project, I collected 45000 tweets from Twitter API, related hashtags, user location, and different topics of electric vehicles. Tesla is the top hashtag Twitter users tweeted while sharing tweets related to electric vehicles. Ekero Sweden is the most common location of users related to electric vehicles tweets. Tesla is the most common word in the tweets related to electric vehicles. Elon-musk is the common bi-gram found in the tweets related to electric vehicles. 47.1% of tweets are positive, 42.4% are neutral, and 10.5% are negative as per VADER Finally, I deploy this project work as a fully functional web app.

Open Access Original Research Article

Jaundice Detection System Using Physiological Characteristics

Ekereke, Layefa, Prince O. Asagba

Asian Journal of Research in Computer Science, Volume 12, Issue 2, Page 30-39
DOI: 10.9734/ajrcos/2021/v12i230279

Jaundice is the abnormal accumulation of Bilirubin in the blood, constant checking of their content level in the blood of new born children is vital as going for Anti-natal because its effect is dangerous and irreversible. At the moment, the standard method to determining the concentration of bilirubin in neonates is Laboratory Blood Test (TSB) test and this method can be traumatic for babies due to the constant blood extraction. Our goal in this research is to use hybridized machine learning techniques to develop a jaundice detection system using all the possible physiological characteristics or symptoms. The developed jaundice detection system is capable of detecting the presence of jaundice in neonate non-invasively, it also has a 0.07% standard error coefficient and a Percentage Value of 0.001 when the outcome was compared to TSB of all Test and Validation samples.

Open Access Original Research Article

Efficient Data Mining Techniques for Heart Disease Prediction and Comparative Analysis of Classification Algorithms

Md. Ashikur Rahman Khan, Masudur Rahman, Jayed Us Salehin, Md. Saiful Islam, Md. Fazle Rabbi

Asian Journal of Research in Computer Science, Volume 12, Issue 2, Page 57-68
DOI: 10.9734/ajrcos/2021/v12i230281

Data mining techniques are used to extract interesting patterns and discover meaningful knowledge from huge amount of data. There has been increasing in usage of data mining techniques on medical data for determining useful trends and patterns that are used in analysis and decision making. About eighty percent of human deaths occurred in low and middle-income countries due to heart diseases. The healthcare industry generates large amount of heart disease data which are not organized. These data make the prediction process more complicated and voluminous. Data mining provides the techniques for fast and accurate transformation of data into useful information for heart diseases prediction. The main objectives of this research is to predict heart diseases more accurately using Naïve Bayes, J48 Decision Tree, Neural Network, Random Forest classification algorithms and compare the performance of classifiers. The research uses raw dataset for performance analysis and the analysis is based on Weka Tool. This research also shows best technique from them which is Random Forest on the basis of accuracy and execution time.

Open Access Review Article

Assessing the Performance Analysis of OSPFV3 and EIGRP in Applications in IPV6 Analysis for Articles Published in Scopus between 2016 and 2021

Richard Essah, Isaac Ampofo Atta Senior, Darpan Anand

Asian Journal of Research in Computer Science, Volume 12, Issue 2, Page 40-56
DOI: 10.9734/ajrcos/2021/v12i230280

The Analysis of common conceptual frameworks associated with Performance analysis of OSPFV3 and EIGRP in applications in IPV6 for analysis of articles published in Scopus between 2016 and 2021 by applying the Corresponding method analysis. The number of times an article is downloaded is also being considered as a measurement instrument or method of analysis. The Corresponding analysis method has analysis 117 articles from 2016 to 2021. All the articles are based on performance analysis of OSPFV3 AND IPV6.IPv6 has gained legitimacy and inevitability as a result of the internet's expansion, which has resulted in IPv4 address space exhaustion. An internet next-generation protocol that will replace eventually IPv4 is IPv6. Using Riverbed Modeler Academic Edition, 2state link protocols’ performance for IPv6, IS–IS and OSPFv3 was compared and tested for the greatest commonly utilized applications enterprise for example remote login, database query, file transfer, web surfing, and email. The major characteristics used to assess performance include IPv6 packets dropped, network convergence time, link utilization, throughput, remote login response time, file upload/download response times, http page response times, email, and database query response time,. The primary goal of this dissertation is to compare, simulate, and assess both routing protocols’ performance in order to decide which one is best for routing IPv6 network traffic. Based on the parameters utilized, the protocol that performed better than the others would be suggested for routing network traffic in IPv6. The study was separated into two scenarios to achieve this goal: the IS–IS and OSPFv3 scenario. After the simulation for the IS–IS scenario was completed, the data from both scenarios were compared and examined using the provided parameters to see which protocol worked better. Based on the majority of the simulation parameters employed, the simulation results showed that OSPFv3 was performed as compared toIS–IS.