Ugboaja Samuel Gregory

Bio: Ugboaja Samuel Gregory is an academic researcher from Michael Okpara University of Agriculture. The author has contributed to research in topics: Machine learning & Artificial intelligence. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.

Prospects and Challenges of Using Machine Learning for Academic Forecasting

Abstract: The study examines the prospects and challenges of machine learning (ML) applications in academic forecasting. Predicting academic activities through machine learning algorithms presents an enhanced means to accurately forecast academic events, including the academic performances and the learning style of students. The use of machine learning algorithms such as K-nearest neighbor (KNN), random forest, bagging, artificial neural network (ANN), and Bayesian neural network (BNN) has potentials that are currently being applied in the education sector to predict future events. Many gaps in the traditional forecasting techniques have greatly been bridged by the use of artificial intelligence-based machine learning algorithms thereby aiding timely decision-making by education stakeholders. ML algorithms are deployed by educational institutions to predict students' learning behaviours and academic achievements, thereby giving them the opportunity to detect at-risk students early and then develop strategies to help them overcome their weaknesses. However, despite the benefits associated with the ML approach, there exist some limitations that could affect its correctness or deployment in forecasting academic events, e.g., proneness to errors, data acquisition, and time-consuming issues. Nonetheless, we suggest that machine learning remains one of the promising forecasting technologies with the power to enhance effective academic forecasting that would assist the education industry in planning and making better decisions to enrich the quality of education.

Exploring a Secured Socket Python Flask Framework in Real Time Communication System

Abstract: Communication networks makes it easier to connect internationally in today's world. Chat systems, such as WhatsApp, Twitter, Instagram and others, enable people to connect and chat over the internet. This chat system has evolved into one of the most important intermediate tools for people to exchange information and materials over the internet, thereby requiring secured socket system. In a social cultural environment, communication with a given network goal system necessitates a stress-free method of knowledge delivery. Surfing websites like "My Room" and "Facebook" has become a common occurrence among the younger generation. Nowadays, social networking websites are an important part of people's social, educational, and professional lives. The aim of Short Research Article Uchenna et al.; AJRCOS, 8(1): 77-87, 2021; Article no.AJRCOS.67890 78 this study is to create a group communication framework that uses a protected socket browser interface. This architecture was created with a server scripting language, a SQLite database model, and Python web application frameworks in mind.

The emergent properties of a dolphin social network

Abstract: Many complex networks, including human societies, the Internet, the World Wide Web and power grids, have surprising properties that allow vertices (individuals, nodes, Web pages, etc.) to be in close contact and information to be transferred quickly between them. Nothing is known of the emerging properties of animal societies, but it would be expected that similar trends would emerge from the topology of animal social networks. Despite its small size (64 individuals), the Doubtful Sound community of bottlenose dolphins has the same characteristics. The connectivity of individuals follows a complex distribution that has a scale-free power-law distribution for large k. In addition, the ability for two individuals to be in contact is unaffected by the random removal of individuals. The removal of individuals with many links to others does affect the length of the information path between two individuals, but, unlike other scale-free networks, it does not fragment the cohesion of the social network. These self-organizing phenomena allow the network to remain united, even in the case of catastrophic death events.

Machine Learning Approaches for Student Performance Prediction

Abstract: India's Education system is very old and due to a large population of students in India, there are some serious issues in analyzing and predicting students' performance. In the Indian Context, every institution has its own set of standards for evaluating student success, there is no proper procedure for monitoring and analyzing a student's performance and progress. One of the major factors is lack of research in existing prediction approaches, making it difficult to determine the optimal prediction methodology for visualizing student academic growth and performance. Another reason could be the lack of research into the areas that can affect students' academic performance and achievement. In this paper, focus is given on additional external factors like geographical location, parent education, health status etc. that can affect a students' performances apart from the grades in any course. That will be more effective in visualizing and analyzing student's performance. For experimental work, data has been collected from UCI repository and results are obtained from two different machine learning algorithms (KNN and Logistic Regression). Performance analysis is also done for these two algorithms based on accuracy level of results as well as with some existing work.

Low-cost Surveillance System using Smartphone and Raspberry Pi4 Based on Real Time Streaming Protocol

Abstract: The development of technology in the field of internet of things (IoT) increase the development of android applications that are used to practically control IoT systems, especially in the field of monitoring. The current surveillance systems that using closed-circuit television (CCTV) are still very popular, but these systems require high costs for installation and their capabilities are not very flexible and scalable. Thus it is considered necessary to build stream and photo applications that low-cost, and more flexible. Therefore, in this study a simple remote application that utilizes video streams using Android with the help of websocket protocol on sending the command is developed. Testing is carried out to measure the performance of the developed system. The test is carried out in two stages, the first test was testing the function of the Android application and web server on raspberry pi with black box testing. The second test, performed a performance test on each feature by looking at the running time of each main software feature to see its real time capability. The low cost and flexibility of the surveillance system are achieved with the use of multi threading and with the usage of websocket making a flexibility at the level of low technical manipulation, although the stream and the device are still not responsive enough due to the encoding of the h264 data stream when it will be sent by the help of the VLC software.

Machine Learning Approaches for Student Performance Prediction

Abstract: India's Education system is very old and due to a large population of students in India, there are some serious issues in analyzing and predicting students' performance. In the Indian Context, every institution has its own set of standards for evaluating student success, there is no proper procedure for monitoring and analyzing a student's performance and progress. One of the major factors is lack of research in existing prediction approaches, making it difficult to determine the optimal prediction methodology for visualizing student academic growth and performance. Another reason could be the lack of research into the areas that can affect students' academic performance and achievement. In this paper, focus is given on additional external factors like geographical location, parent education, health status etc. that can affect a students' performances apart from the grades in any course. That will be more effective in visualizing and analyzing student's performance. For experimental work, data has been collected from UCI repository and results are obtained from two different machine learning algorithms (KNN and Logistic Regression). Performance analysis is also done for these two algorithms based on accuracy level of results as well as with some existing work.