| 1 |
Author(s):
Ifekanandu Chukwudi Christian, Nico Ebieye Mary, Renner Blessing Awaji-ima.
Page No : 1-13
|
Information Systems and Operational Efficiency of Maritime Firms in Port Harcourt.
Abstract
The study examined the relationship between information systems and operational efficiency of maritime firms’ in Port Harcourt, Rivers State. Three research questions and three research hypotheses were formulated to address the specific objectives of this study. The RBV theory was adopted in this study and also quantitative research design using a correlational method of investigation. The population consists of 16 maritime firms in Port Harcourt. Census sampling was applied with focus on managers. Four managers per firm were sampled; a total of 64 managers were sampled. The reliability of the instrument was determined using Cronbach alpha test and it stood at 0.88 higher than the benchmark of 0.7. The data collected for this study were analyzed through descriptive and inferential statistics. The Spearman Rank-Order Correlation Technique was employed to test the various hypotheses formulated. The result of the analysis revealed that the information system is significantly and positively related to the operational efficiency of maritime firms’ in Port Harcourt, Rivers State. The empirical results of this study confirmed this as a positive and significant relationship was found between processing transaction systems and operational efficiency of maritime firms, and between electronic data interchange and operational efficiency of maritime firms. Based on these findings, it was concluded that the information system with its dimension of processing transaction system and electronic data interchange will improve operational efficiency of maritime firms in Port Harcourt. This study recommends that maritime firms should leverage on information systems as this would ensure reduction in cost and improve operational efficiency; they should use processing transaction system in order to facilitate the recording, tracking, and management of business transactions within the organization and the port, and they should adopt electronic data interchange for processing of documents and timely delivery of same.
| 2 |
Author(s):
Oti Eric Uchenna, Michael O. Olusola.
Page No : 14-23
|
Overview of Agglomerative Hierarchical Clustering Methods.
Abstract
Agglomerative hierarchical clustering methods are the most popular type of hierarchical clustering used to group objects in clusters based on their similarity. The methods uses a bottom-up approach and it starts clustering by treating the individual data points as a single cluster, then it is merged continuously based on similarity until it forms one big cluster containing all objects. In this paper, we reviewed eight agglomerative hierarchical clustering methods namely: single linkage method, complete linkage method, average linkage method, weighted group average method, centroid method, median method, Ward’s method and the flexible beta method; we also discussed measures of similarity and dissimilarity using quantitative data as our reference point.
| 3 |
Author(s):
Ezekiel-Hart James Carr, Blessing Awaji-ima Renner PhD.
Page No : 24-34
|
Electronic Marketing Strategies and Customer Satisfaction of Commercial Banks in Port Harcourt, Rivers State.
Abstract
The study examined the relationship between Electronic Marketing Strategies and Customer Satisfaction of commercial banks in Port Harcourt, Rivers State. The study adopted the correlation survey research design. The target population of this study comprised of 21 registered commercial banks in Port Harcourt, Rivers State gotten through the Central Bank of Nigeria. Given a population of 21 banks which is less than thirty (30), the study adopted a census approach and undertook a study of the entire 21 banks with a focus on the staff (ICT Personals, Service Managers and Business Development Managers). To generate data for the study, sixty three (63) copies of questionnaire were given to the twenty one registered Banks in the frame of three (3) copies per bank. The questionnaire was structured in a four (4) point likert scale. The data collected through the questionnaire were analyzed using Pearson Product Moment Correlation. From the bivariate analysis carried, it was discovered that electronic marketing strategies showed a significant relationship with customer satisfaction of commercial banks in Port Harcourt, Rivers State. It was revealed that content marketing showed a very strong and significant relationship with customer retention of commercial banks in Port Harcourt, Rivers State. Also, e-mail marketing showed moderate and significant relationship with customer retention of commercial banks in Port Harcourt, Rivers State. The study concludes that electronic marketing strategies are significant predictor of customer satisfaction of commercial banks in Port Harcourt, Rivers State. The study recommends that: bank should create contents on various social media platforms as this would increase customer retention and they should adopt e-mail marketing in reaching out to customers. This would increase customer patronage and retention.
| 4 |
Author(s):
Umoh Enoima Essien.
Page No : 35-42
|
Using QR Code and a Smartphone to Provide University of Cross River State (UNICROSS) Certificate Authentication.
Abstract
In the modern world, people frequently fabricate their credentials in order to secure a job or to show up where and when it is necessary. Verification is the most effective approach to identify those fraudulent certificates. Despite this, the paper verification method requires a drawn-out and time-consuming process to handle certificate verification because the certificates must be returned to the institutions who awarded them. As a result, the certificates either fail to pass verification or are delayed by the lengthy process. As a result, a certificate verification method using QR codes is developed in this study for quick verification of University of Cross River State (UNICROSS) certificate genuineness. A Smartphone and 3D Printed QR Code were employed for the enhancement of UNICROSS certificate mobile authentication services. ScanTrust anti-counterfeiting services was used to secured and hosting of the encrypted information. Results shows that our framework is effective for creating mobile authentication services with high user satisfaction rate and having reasonably low computing requirement.
| 5 |
Author(s):
Ofut Ogar Tumneayu, Awuna Kile.
Page No : 43-48
|
Nollywood Movie Sequences Summarization Dataset for Machine Learning Applications
Abstract
Summarization in recent time has become one of most exploited area of natural language processing task, due to significant increase in data volume which is more than terabytes and petabytes. In this article, we present a custom dataset for Nollywood movie sequences, an extensive collection of 13 Nollywood movies representing various genres, including drama, comedy, action. This custom dataset was impendent into pre-train benchmark dataset TVSum following the same file format, frame size and others in order to suit our purpose. Fast Forward Moving Picture Expert Group (FFMPEG) were used for video encoding during pre-processing and final skimming. The proposed framework is effective for creating movie summary with high user satisfaction rate and having reasonably low computing requirement.
| 6 |
Author(s):
Fumlack Kingsley George, Yusuf Musa Malgwi (Ph.D.), Caleb Marcus, Okpalaifeako lydea Chikaodiri.
Page No : 49-67
|
An Efficient Security Routing Protocol for Cloud-Based Networks Using Cisco Packet Tracer.
Abstract
In light of growing cloud computing usage, this study is designed and implemented on an efficient security routing protocol for cloud-based networks using Cisco Packet Tracer. Cloud computing's shared resources and dynamic scalability make cloud-based networks vulnerable to unwanted access, data breaches, and insider assaults, prompting the research. The research objectives is to identify and categorize security threats, evaluate existing security solutions, propose an enhanced security measures, and validate these solutions through simulations in Cisco Packet Tracer. A mixed-methods approach was adopted, integrating quantitative and qualitative research designs. Primary data were collected through surveys using Google form and network analysis tools within Cisco Packet Tracer, while secondary data is derived from a comprehensive literature review. The study employed a random sampling technique to select participants with relevant expertise in cloud security. Data analysis involved thematic analysis to identify patterns in the literature and content analysis to extract insights from survey responses. Statistical tests were used to analyze quantitative data, and network analysis was conducted on data obtained from Cisco Packet Tracer simulations. Key findings revealed that data breaches, unauthorized access, insider threats, malware, ransomware attacks, and Denial of Service (DoS) attacks were significant security concerns. The survey results indicated a consensus on the importance of specific features in efficient security routing protocols but also highlighted skepticism regarding the effectiveness of existing protocols. The proposed security measures, including the Three-Level Enabled Secret protocol, Encryption protocol, Secure Shell protocol (SSH), and various routing protocols such as EIGRP, RIP, BGP, and OSPF, Trunk protocol, switch-port security protocol were validated through simulations and showed effectiveness in mitigating security threats. The study has both theoretical and practical implications, contributing to the body of knowledge in cloud computing security and providing practical recommendations for organizations to strengthen their cloud security posture. Limitations include the simulation-based approach and the focus on specific security protocols, suggesting areas for further research in real-world implementation and integration with emerging technologies.
| 7 |
Author(s):
Olusegun James Adigun, Adebayo Ola Afolaranmi (Ph.D.).
Page No : 68-85
|
Curbing the Effect of Climate Change for Sustainable Development through Digital Transformation and Environmental Sustainability.
Abstract
Climate change has posed a lot of dangers on economic growth and development. Such dangers include hotter temperatures, severe storms, increased drought, inadequate food supply, poverty, displacement of people and many risks to human life. These dangers occur on earth through human activities which release greenhouse gas emissions. Consequently, this paper aimed to look at the environmental sustainability through digital transformation, in order to reduce the effect of climate change on economies, businesses, governance, and socio-political outcomes in the 21st century. It also identified how digital transformation plays an increasingly significant role in promoting environmental sustainability. The paper adopted a systematic literature review, qualitative approach, and a historical analysis. Findings revealed that non-conformity with environmental best practices has gross adverse effects on achieving sustainable development. It was also discovered that non-enforcement of environmental laws and regulations posed danger to environmental sustainability. The paper concluded that adopting digital transformation will be of great advantage to environmental sustainability thus reducing the impact of climate change and accelerate sustainable development in our economies. This paper recommended strict enforcement of environmental laws and regulations. There should be a paradigm shift in the approach to achieving environmental sustainability by improving the circular economy through digital devices (enabling reuse and recycling), extending the lifespan of software and devices, and promoting technologies that help reduce carbon emissions and energy consumption. Also, the importance of less usage of energy by switching to LED light bulbs and energy-efficient electric appliances in our various homes and offices cannot be overemphasized.
| 8 |
Author(s):
Ekoro, Ekoro igo (Ph.D.), Bassey Isaac Rajuno (Ph.D.).
Page No : 86-96
|
Design and Implementation of a Robust Web-based Clearance System for Students in Nigerian Colleges of Education.
Abstract
Online graduating student clearance systems are important platform that greatly reduce the tedious processes involved in getting graduating students cleared for certification. These platforms are hardly available in most colleges of education and other tertiary institutions in Nigeria. The existing trends in the student clearance method is that the processes are done by moving from one office to another and having records on paper. Most existing clearance tasks are done manually. This scenario creates a system that is unreliable and confusing to keep the correct track of the records and can be very overwhelming and stressful to say the least. At the conclusion of the academic session, a clearance form is issued to students. Students apply for the clearance form to their respective department if the students need to exit the College. The consequences of this type of clearance system is that at most times most of the personnel required for the signing of the graduating students form are often not accessible and this creates serious challenges to the students. Also in most cases some of the paper issued to the students got missing in the course of their study and they are asked to pay for dues that have being originally paid. This research presents an automated and robust clearance system that generates students’ clearance per session and final clearance to graduating students. Developing an online customs clearance system called a Robust Web-based Clearance System is the major contribution of this research. The system was developed using java as a programming language. The system was hosted using Xampp as a local server. The system was tested and validated by management and students. The results from the test showed high level of acceptability of the developed system
| 9 |
Author(s):
Anthony Edet, Blessing Ekong, Uduakobong Udonna, Anietie Uwah, Ndueso Udoetor.
Page No : 97-114
|
Machine Learning Model for Adverse Drug Reaction Detection Based on Naive Bayes and XGBoost Algorithm.
Abstract
Adverse drug effects, commonly referred to as adverse drug reactions (ADRs), represent undesirable and unintended responses to medications or pharmaceutical products when used at recommended doses for therapeutic purposes. These effects can range from mild, tolerable symptoms to severe, life-threatening conditions and can manifest in various ways, affecting different organ systems within the human body. ADE analysis plays a pivotal role in prioritizing patient safety. By meticulously examining the relationship between drug administration and patient responses, healthcare providers can tailor medications to individual profiles, minimizing risks of adverse reactions. This ensures a patient-centric approach to treatment, where prescriptions are finely tuned to maximize efficacy while minimizing potential harm. This research aims to address this challenge by developing a machine learning system utilizing the Naive Bayes and XGBoost algorithms to enhance the categorization of drugs with adverse effects, ultimately contributing to improved patient safety and healthcare decision-making. In our approach, we made a system that detects ADR to effectively combine and collate patient medical history and drug information to detect if a patient would suffer adverse effects or reaction after taking the medication in its correct expert prescribed dose. The XGBoost algorithm gave a 75% accuracy score while Naive Bayes algorithm gave 99%.
| 10 |
Author(s):
Rosemary Ngozi Ariwa, Caleb Markus, Nora Terna Godwin, Shehu Adamu, Fumlack Kingsley George.
Page No : 115-129
|
Plant Disease Detection Using Yolo Machine Learning Approach.
Abstract
Artificial intelligence and deep learning models are utilised in health, IT, animal and plant research, and more. Maize, one of the most widely eaten crops globally, is susceptible to a wide variety of disease that impede its development and reduce its output. The objective of this research work is to develop a deep learning-based model for detection of illnesses affecting maize leaves. Furthermore, the model that has been constructed not only forecasts illness but also furnishes illustrative visuals of leaf diseases, so facilitating the identification of disease types. To do this, a dataset including specified illnesses, including blight, common rust, gray leaf spot, and a healthy leaf, was obtained from Kaggle, a secondary source (Pant village). For data analysis, the cross-platform Anaconda Navigator was used, while the programming languages Python and Jupiter Notebook were implemented. The acquired data was used for both training and evaluating the models. The study presents a novel approach to plant disease detection using the YOLO deep learning model, implemented in Python and associated libraries. The Yolov8 algorithm was employed to develop a maize leaf detection system, which outperformed algorithms such as CNN (84%), KNN (81%), Random Forest (85%), and SVM (82%), achieving an impressive accuracy of 99.8%. Limitations of the study include the focus on only three maize leaf diseases and the reliance on single-leaf images for detection. Future research should address environmental elements like temperature and humidity, include numerous leaves in a frame for disease identification, and create disease stage detection methods.
Keyword: Yolov8, Maize Leaf Detection, Machine Learning, Artificial Intelligence, Model.
