Browsing by Author "Abdullahi, M.U."

Now showing 1 - 9 of 9
  • Thumbnail Image
    ItemOpen Access
    Application of Sales Forecasting Model Based on Machine Learning Algorithms
    (Department of Computer Science, Nasarawa State University Keffi, 2021-10-10) Abdullahi, Maimuna A.; Aimufua, Gilbert Imuetinyan Osaze; Abdullahi, M.U.
    Machine learning has been a subject undergoing intense study across many different industries and fortunately, companies are becoming gradually more aware of the various machine learning approaches to solve their problems. However, to fully harvest the potential of different machine learning models and to achieve efficient results, one needs to have a good understanding of the application of the models and the nature of data. This paper aims to investigate different approaches to obtain good results of the machine learning algorithms applied for a given forecasting task. To this end, the paper critically analyzes and investigate the applicability of machine learning algorithm in sales forecasting under dynamic conditions, develop a forecasting model based on the regression model, and evaluate the performance of four machine learning regression algorithms (Random Forest, Extreme Gradient Boosting, Support Vector Machine for Regression and Ensemble Model) using data set from Nigeria retail shops for sales forecasting based on performance matrices such as R-squared, Root Mean Square Error, Mean Absolute Error and Mean Absolute Percentage Error.
  • Thumbnail Image
    ItemOpen Access
    CAREER GUIDANCE AND COUNSELING PORTAL FOR SENIOR SECONDARY SCHOOL STUDENTS
    (Department of Computer Science, Nasarawa State University Keffi, 2022-02-02) Aimufua, Gilbert Imuetinyan Osaze; Abdullahi, M.U.; Ibrahim, Abdullahi Mainuna
    This paper developed a web based Career Guidance and Counselling (CGC) portal to mitigate the problems of traditional counselor-client interaction process, which is a paper-based procedure that has a lot of flaws. These flaws include: poor record management, delay in accessing student’s record and unavailability of central database to manage records electronically. Interviews and observations were used to collect data from both students and the school counselors. The portal enables students to take career guidance independently at their own convenience. It can also enable the students test themselves on some selected questions in the form of a quiz. The system is designed following a sound engineering principle i.e., from requirements gathering, software requirement specification, design and implementation, testing to deployment. Data flow diagrams and use case scenarios are used to demonstrate the functionality of the web portal. Using Hypertext Preprocessor Pages (PHP) programming language, a proof of concept was developed to illustrate the features and functionality of the portal. The outcome is a robust web Portal suitable for Guidance and Counselling that is user friendly.
  • Thumbnail Image
    ItemOpen Access
    Certificate Generation and Verification System Using Blockchain Technology and Quick Response Code
    (Department of Computer Science, Nasarawa State University Keffi, 2022-02-03) Abdullahi, M.U.; Aimufua, Gilbert Imuetinyan Osaze; Adamu, Aminu Muhammad
    The number of certificate counterfeits in our society has become challenging and prevalent. Today, forging certificates has become a business tumbling from the need/want of the people for employment. Graduates with legitimate certificates/degrees are denied job opportunities by the holders of these forged credentials. To address this problem, many researchers have proposed a certificate verification system. Although the existing systems can solve some of the major problems such as accessing student’s records with the provision of a central database to manage these records electronically. However, the system can easily be hacked and manipulated since it is mostly available on centralized servers. This dissertation developed a certificate generation and verification system using blockchain technology and Quick Response (QR) code. Iterative and incremental models were used for the system modelling. Also, Data flow diagrams and use case scenarios are used to demonstrate the functionality of the web application. Consequently, suitable programming languages were chosen to implement the proposed algorithm of the system. Hypertext Preprocessor Pages (PHP) and Spring boot (Java framework) were used for the implementation of frontend and backend respectively. The system was evaluated and show that not only is secure but also protects the student’s identity by providing an anonymous verification setting.
  • Thumbnail Image
    ItemOpen Access
    Development of a Cloud-Based Meteorological Historical Data System
    (Department of Computer Science, Nasarawa State University Keffi, 2022-12-15) Aimufua, Gilbert Imuetinyan Osaze; Gummi, Sulaiman Ammar; Abdullahi, M.U.
    Meteorological data has played a significant role in most developed and developing nations. However, in Nigeria, the storage of meteorological data has been so limited, scattered and without defined structure. The purpose of this paper is to develop a cloud-based meteorological data management system as well as a sales portal to improve the management of meteorological data and associated climate services at the Nigerian Meteorological Agency (NiMet). This agency has indisputable importance in the nation’s economy, but poor management leads to either loss or damage of the data. Additionally, the process of accessing NiMet data and products for research is often long and stressful. To address these problems, this paper adopts the waterfall and descriptive models to develop a new system. This approach divides the project activities into sequential phases, where each phase depends on the deliverables of the previous one and corresponds to a specialization of tasks. The developed system will be the central hub for numerous meteorological services, including statistical reports, graphical analyses, data extractions, climate summaries, and health sectors, which will dramatically improve work flow, data consistency, and integrity beyond previous practices in Nigeria.
  • Thumbnail Image
    ItemOpen Access
    Development of Anti-Polypharmacy Management System
    (Department of Computer Science, Nasarawa State University Keffi, 2021-03-06) Aimufua, Gilbert Imuetinyan Osaze; Onyechi, Nkiruka P.; Abdullahi, M.U.
    The prevalence of adverse drug reactions, adverse drug effects, avoidable deaths, and other drug-related problems arising from multiple drug administration is a wake-up call to our medical practitioners and the world at large, hence prompt action is required to this effect. In this paper, a computerized web-based system called “Anti-Polypharmacy Module” (APM) is being proposed which is geared towards checking the menace of polypharmacy by highlighting its adverse effect and drug-drug interactions. The drug library which contains most of the required information will be used to accomplish this task. The application is designed to be a user-friendly one. The system methodology for this work is the System Development Life Cycle (SDLC). This system is implemented using Java-servlet (JSP), JQuery, and SQL as a collection of software development tools. It is also a web-based application hence HTML5 and CSS3 are carefully crafted together for maximum user-friendliness. Apache Maven and Tomcat 7 are deployed for the back-end server technology. For database query optimization, the basic rules are strictly followed as discussed in the methodology.
  • Thumbnail Image
    ItemOpen Access
    Development of blockchain technology-based electronic voting system
    (Department of Computer Science, Nasarawa State University Keffi, 2021-06-06) Okposhi, Musa Ibrahim; Aimufua, Gilbert Imuetinyan Osaze; Abdullahi, M.U.
    Abstract: Voting has always been an important part of a democratic election since it allows the citizens to voice their opinions on whom they want to lead them. A major problem with traditional voting systems is that the citizens find it difficult to trust the electoral processes. To address the problem of traditional voting, many researchers have proposed an e-voting system. But it also has its major flaws since it is mostly available on centralised servers and can be hacked. This paper designs a working proof of concept decentralised e-voting system using block-chain systems. The blockchain system allows us to design a decentralised voting system that requires the consensus of many participants and so becomes inherently difficult to manipulate or hack. We also evaluate this system and show that not only is it secure, but it also protects the voter’s identity by providing an anonymous voting environment.
  • Thumbnail Image
    ItemOpen Access
    Development of Computerized Warehouse Management System
    (Department of Computer Science, Nasarawa State University Keffi, 2022-01-06) Aimufua, Gilbert Imuetinyan Osaze; Abdullahi, M.U.; Ibrahim, Muazu Auwal
    warehouse is a storage facility for products and commodities awaiting clearance. The manual clearance of these commodities is in used in most organizations. It involves physically transporting billing paperwork from one port to another, which delays the clearance of products. Furthermore, creating a reference to a specific transaction takes a lengthy time. In view of this, this paper developed a computerized warehouse management system to address these issues. It will electronically maintain records of Good Inwards (GI), check-in and check-out, as well as simplify warehouse operations by eliminating the rate of defects in the present manual method. For software implementation, observation and the internet will be employed as data collection techniques. As a result, the waterfall model is used to develop the new system. While PHP programming language is also used for the coding of the client-model application in order to achieve the aims and objectives of the system.
  • Thumbnail Image
    ItemOpen Access
    MACHINE LEARNING APPROACH FOR BREAST CANCER CLASSIFICATION
    (Department of Computer Science, Nasarawa State University Keffi, 2022-06-20) Aimufua, Gilbert Imuetinyan Osaze; Mbanaso, Uche M.; Abdullahi, M.U.
    Breast cancer is the most common cancer among women in Africa. These facts have led researchers to continue studying how to treat and detect breast cancer in women, especially older women, who are at higher risk. Achieving satisfactory cancer classification accuracy with the complete set of genes remains a great challenge (most especially with microarray datasets), due to the high dimensions, small sample size, and presence of noise in gene expression data. Feature reduction is critical and sensitive to the classification task. One of the major drawbacks of cancer studies is recognizing informative genes (features) among the thousands of others in the dataset. A large number of features (genes) against a small sample size and redundancy in expressed data are the main two reasons that lead to poor classification accuracy in machine learning and data mining processes. Therefore, dimensionality reduction is an exciting research area in the fields of pattern recognition, machine learning, data mining, and statistics. The purpose of dimensionality reduction is to improve classification performance through the removal of redundant or irrelevant features. Furthermore, feature selection is typically useful in reducing computation time and memory complexity, which have always been challenges in big data tasks. Besides, the high complexity of the memory space or time as a result of high dimension, noise effect, and outliers but it also has adverse impacts on the performance of the algorithms This paper tends to improve the low general accuracy and minimize memory space and execution time in classification models of machine learning algorithms; hence, the system will employ InfoGain for dimensional reduction and the Random Forest algorithm for classification.
  • Thumbnail Image
    ItemOpen Access
    Protein secondary structure prediction using deep neural network and particle swarm optimization algorithms
    (Department of Computer Science, Nasarawa State University Keffi, 2022-12-04) Abimiku, Aka Patience; Aimufua, Gilbert Imuetinyan Osaze; Abdullahi, M.U.
    Protein secondary structure prediction from its amino acids is purposely used to evaluate and improve the accuracy of performance as well as drug design and cell functionality. Various approaches for predicting protein secondary structure have been used, each with varying accuracy, vulnerabilities, and strengths. In view of this, this paper is aimed at training a deep neural network with particle swarm optimization and comparing the results with the state of accuracy. Also, the methodology used is basic particle swarm optimization for training a 20-15-15-15-3 deep neural network. The Java programming language and the Spring Boot framework were employed to implement the various application programming interfaces of the model. The dataset acquired after the training of JPred Server 1.2, which included 1349 training sets and 149 test sets, was used in training the model. Following the training, it was discovered that the model had a highest accuracy of 53.18 percent on epoch 140, indicating that this model is not a best fit or an alternative to the current state of the art for the prediction of protein secondary structure.