International Journal of Computer (IJC)

Prediction of Soil Macronutrients Using Machine Learning Algorithm

Umm E Farwa, Ahsan Ur Rehman, Saad Qasim Khan, Muhammad Khurram — Wed, 08 Apr 2020 15:44:52 +0000

In this research work, machine learning algorithms were applied to find the relationship between independent variables and dependent variables for soil data analysis. The independent variables include moisture, temperature, soil pH, Cation Exchange Capacity(CEC) whereas, the dependent variables include Nitrogen, Phosphorus and Potassium (NPK). This research concludes relationships between Phosphorus, Potassium, soil pH and CEC; Nitrogen and soil moisture and temperature using machine learning(ML) algorithms so as to deduce NPK content of soil. A comparative analysis with obtained results from each ML method is also presented. Machine learning algorithms are best performed on data with multiple independent variables. The values computed for nitrogen relationship were more accurate than PK relationship values. The accuracy of data set I was less than data set II. A large data set would produce more accurate results for both data sets.

Neural Network-Based Expression Recognition System for Static Facial Images

Yamin, Khin Khin Oo, Moe Moe Htay — Mon, 13 Apr 2020 09:57:58 +0000

Affective Computing is a field of studying the human effect to interpret, recognize, process, and simulate in computer science, psychology, and cognitive science. Humans express their emotions in a variety of ways such as body gesture, word, vocal, and mainly facial expression. Non-verbal behavior is a significant component of communication, and facial expressions of emotions are the most important complex signal. Facial Expression Recognition (FER) is an interesting and challenging task in artificial intelligence. FER system in the study three steps including preprocessing, feature extraction and expression classification. In the paper, comparative analysis of expression recognition is implemented based on Neural Network (NN) with three feature extraction methods of Sobel Edge, Histogram of Oriented Gradient and Local Binary Pattern. NN-based expression recognition system achieves an accuracy of 95.82% and 97.68% for JAFFE and CK+ dataset respectively. The result has shown that the Edge features are the effected features for recognizing human expression using still images.

An Improved Model for the Implementation of Web-Based Learning in Adult Secondary School Education in Kenya

Ms. Martha Muthoni Ng’ang’a, Prof Stephen Kimani, Dr. Michael W. Kimwele — Sat, 09 May 2020 12:38:04 +0000

The development of technology, which evolves continuously, has led to the transformation of traditional courses into web-based courses. However, as these e-learning systems grow more complex, involving numerous users with different levels of need, there is a need to have web-based learning models that adequately address such users’ needs, taking into consideration their levels of expertise, access and ability to interact with such systems. Most of the existing models present the adult learners with difficulties, as most of them have to concentrate mostly on learning the technology rather than learning the desired content. Most of the difficulties arise from the web-based learning model configurations in use in the country. The majority lack features and capabilities of highly interactive, fast-paced multimedia-supported learning currently demanded by most learners and tutors. Therefore, the main aim of this research was to devise an improved model for implementing a web-based learning programme in adult secondary school education. After analysing the existing models and establishing their operational challenges, an improved model was proposed. The proposed model was statistically tested using sample data. The results showed that recognizing both technological and user attributes along the recognized theoretical frameworks was important in increasing the users’ behavioural inclination to use the improved model.

Therefore, it is recommended that more sensitization to web-based learning should be implemented by the adult education department in the Ministry of Education among adult learners in the country. It is also recommended that system developers should find ways of incorporating additional features into the model without affecting its architecture and function. Finally, there is need for future studies on the causal antecedents of the constructs presented in this research model to provide more precise practical implications.

COVID-19 Outbreak Data Analysis and Prediction Modeling Using Data Mining Technique

Tajebe Tsega Mengistie — Thu, 14 May 2020 22:16:26 +0000

Nowadays, sustainable development is considered a key concept and solution in creating a promising and prosperous future for human societies. Nevertheless, there are some predicted and unpredicted problems that epidemic diseases are real and complex problems. Hence, in this research work, a serious challenge in the sustainable development process was investigated using the classification of confirmed cases of COVID-19 (new version of Coronavirus) as one of the epidemic diseases. Hence, the data mining predictive modeling method of data handling and predictive or forecasting the spread of COVID-19 virus. This research work mainly works on predicting or forecasting by using fbprophet. Prophet it is a python library package used for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonally, plus holiday’s effect. It works best with time series that have a strong seasonal effect and several seasons of historical data. The model helps to interpret patterns of public sentiment on disseminating related health information and assess the political and economic influence of the spread of the virus.

Comparing the Performance of Machine Learning Algorithms for Human Activities Recognition using WISDM Dataset

Ya Min, Yin Yin Htay, Khin Khin Oo — Wed, 20 May 2020 22:07:19 +0000

Human activity recognition is an important area of machine learning research as it has much utilization in different areas such as sports training, security, entertainment, ambient-assisted living, and health monitoring and management. Studying human activity recognition shows that researchers are interested mostly in the daily activities of the human. Mobile phones are used to be more than luxury products, it has become a kind of urgent need for a fast-moving world with rapid development. Nowadays mobile phone is well equipped with advanced processor, more memory, powerful battery and built-in sensors. This provides an opportunity to open up new areas of data mining for activity recognition of human’s daily living. In this paper, we tested experiment using Tree based Classifiers (Decision Tree, J48, JRIP, and Random Forest) and Rule based algorithms Classifiers (Naive Bayes and AD1) to classify six activities of daily life by using Weka tool. According to the tested results Random Forest classifier is more accurate than other classifiers.

Infection Severity Detection of CoVID19 from X-Rays and CT Scans Using Artificial Intelligence

Nimai Chand Das Adhikari — Fri, 22 May 2020 16:03:29 +0000

December 2019, marked with a widespread infection due to a new matured member of SARs Virus named as SARS-CoV2 (Novel Corona Virus-2019) infecting more than 20 lakhs people across the globe. This effect made the World Health Organization to declare COVID-19 (Corona Virus Disease, 2019) as a pandemic situation and called a worldwide lockdown to dampen and flatten the infectious curve and diminish the infection growth. With Limited number of COVID-19 test kits in hospitals and the increasing daily cases has asked for an immediate measure for the development towards the Automatic COVID-19 Detection and Alternative Diagnosis Systems (ACD-ADS). This research presents a two-staged DenseNet architecture to diagnose the COVID19 infections from X-rays and CT-scans images to decrease the turnaround time of the doctors and check more patients during that point of time. This research work talks about the end to end solution for the diagnosis to extract and mark the most infectious regions on the imaging pictures to help the doctors and medical practitioners in this pandemic situation. The system achieved an accuracy of 99% and specificity of 94.1% using the DenseNet network on the X-rays images and an accuracy of 87% and specificity of 86.5% for the CT Scans in the Validation Sets. In a sample of 22 images for the CT-Scans of the reported patients having the COVID-19 infections in a real-time analysis, the model performed with detecting correctly for all the 22 patients. Any model can never replace a doctor nor can decide like a doctor who takes many other factors into the account that impacts a decision at a particular point of time. Hence, I propose a network called Automatic Diagnostic Medical Analysis for the COVID-19 Detection System (ADMCDS) that takes the images and tries to find the infectious regions to help the doctor better identifying the diseased part if any.

Machine Learning for Handwriting Recognition

Preetha S, Afrid I M, Karthik Hebbar P, Nishchay S K — Wed, 03 Jun 2020 20:36:59 +0000

With the knowledge of current data about particular subject, machine learning tries to extract hidden information that lies in the data. By applying some mathematical functions and concepts to extract hidden information, machine learning can be achieved and we can predict output for unknown data. Pattern recognition is one of the main application of ML. Patterns are usually recognized with the help of large image data-set. Handwriting recognition is an application of pattern recognition through image. By using such concepts, we can train computers to read letters and numbers belonging to any language present in an image. There exists several methods by which we can recognize hand-written characters. We will be discussing some of the methods in this paper.

Development of an Ontology-Based Personalised E-Learning Recommender System

Oluwatoyin Catherine Agbonifo, Motunrayo Akinsete — Sat, 06 Jun 2020 17:56:42 +0000

E-learning has become an active field of research with a lot of investment towards web-based delivery of personalised learning contents to learners. Some issues of e-learning arise from the heterogeneity and interoperability of learning content to suit learner’s style and preferences in order to improve the e-learning environment. Hence, this paper developed an ontology-based personalised recommender system that is needed to recommend suitable learning contents to learners using collaborative filtering and ontology. A pre-test is carried out for users in order to segment them in learning categories to suit their skill level. The learning contents are structured using ontology; and collaborative filtering is used to collects preferences from many users and then recommending the highest rated contents to users. The system is implemented using JAVA programming language with Structured Query Language (MySQL) as database management system. Performance evaluation of the system is carried out using survey and standard metrics such as precision, recall and F1-Measrure. The results from the two performance evaluation models showed that the system is suitable for recommending the required learning contents to learners.

Observational Discoveries in Agile Methodologies and Extreme Programming

Thu, 11 Jun 2020 18:13:12 +0000

The In this study we have focused on various methodologies of nimble programming advancement, for example, Extreme Programming, Crystal Clear, Scrum, Lean programming improvement and some others methods related to category. As there are several methods related to agile development, but we have mainly focused on some of the important methodologies, discovered so far []. This study also reveals the criticism over some of the agile methodologies, based on some of its parameters, while in some situations favor is given to the traditional methodologies. We have adopted quantitative and qualitative approaches to carry out this work, the major audience involved were professionals, software developers who were working in the industry, and were the real practitioners of these methodologies, by taking advantage of their experiences we have considered their suggestions, ideas and experiences. Any software development project involves certain parameters: productivity, quality, cost and schedule. These project parameter are at the main theme of our study, based on it we have discovered that how agile methods may influence the software development industry.

An Improved Rapid Response Model for University Admission Enquiry System Using Chatbot

Olusegun Gbenga, Temilola Okedigba, Halleluyah Oluwatobi — Mon, 15 Jun 2020 07:02:05 +0000

A model for real-time response on admission related enquiries was developed in this research with the aim of bridging the lag usually experienced through the conventional approach of phone call and email. The model was implemented using IBM Watson to design a Chatbot for rapid response to admission enquiries. Botium was used to evaluate the performance of the Chatbot which gave an accuracy of 95.9% with instance of 212successful test cases and 9failed test cases. The approach introduces users to new and emerging technological solutions for optimal and rapid response in the educational sector.

An Efficient Feature Selection Algorithm for Health Care Data Processing

Zahoor Ahmed, Talat Saeed, Umair Ahmed, Faiz Ullah — Wed, 01 Jul 2020 06:35:06 +0000

The researcher used to study the tides depends on a qualitative approach that takes into account the review of past works and studies of various authors and researchers. The service sector is an explosive part of the economy in many countries. Its development is fraught with difficulties, including increased costs, wasteful aspects, poor quality, and the expansion of multifaceted nature. AI systems can be deployed in health programs they want to be qualified using statistics obtained from clinical activities, consisting of screening, diagnosis, corrective measures, etc. The advantage is due to proactive behavior and specialized medical services. Stimulates e-health and electronic monitoring at the forefront of research. AI systems can be deployed in health programs they want to be “qualified” using statistics obtained from clinical activities, consisting of screening, diagnosis, corrective measures, etc. On the other hand, among the various classes in a study in medical services, the use of data mining is usually used as an aid in clinical choice (42%) and for managerial purposes (32%). This segment examines the use of data mining in these territories, and the main points of these checks, performance holes, and key points are different.

RWMSI (Read Exclusive Write Exclusive Modified Shared Invalid) Cache Coherence Protocol

Luma F. Jalil, Abeer D. Al-Nakshabandi — Sat, 04 Jul 2020 04:40:37 +0000

This paper proposes a novel coherence protocol RWMSI (Read exclusive Write exclusive Modified Shared Invalid) that merges “snooping and directory – based coherence protocols “and enhanced them depending on the state of “MESI snooping protocol “. “ Coherence” is implemented with “snooping or directory based protocols “. Because of the shared bus the “ Snooping protocols “ are not scalable , while directory protocols incur directory storage overhead , frequent indirections , and are more prone to design bugs.