Abraham Evwiekpaefe | Nigerian Defence Academy, Kaduna, Nigeria (original) (raw)
Papers by Abraham Evwiekpaefe
West Science Interdisciplinary Studies, Jan 25, 2024
Implementation of Flipped Classroom as A Supportive and Alternative Approach to Traditional Learning System, 2024
Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped cl... more Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped classrooms has developed as a convincing educational strategy, designed to reshape the traditional teaching and learning models. This study developed a mini LMS platform to empower educators in managing and disseminating instructional materials to engage students before the in-class period. JavaScript, HTML, CSS and MYSQL play vital roles in the design and development mini Learning Management System (LMS) used in this study to create
a functional and user-friendly platform. The integration of these technologies in the design of the mini LMS allows for the creation of a robust, operative, interactive and data-driven learning platform. JavaScript provided the dynamism of the user experience, HTML structured the content, CSS styled the interface and MySQL managed the data. Consequently, a mini Learning Management System was developed. This platform was used in implementing the flipped classroom system.
International Journal of Basic Science and Technology, 2024
Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped cl... more Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped classrooms has developed as a convincing educational strategy, designed to reshape the traditional teaching and learning models. This study developed a mini LMS platform to empower educators in managing and disseminating instructional materials to engage students before the in-class period. JavaScript, HTML, CSS and MYSQL play vital roles in the design and development mini Learning Management System (LMS) used in this study to create a functional and user-friendly platform. The integration of these technologies in the design of the mini LMS allows for the creation of a robust, operative, interactive and data-driven learning platform. JavaScript provided the dynamism of the user experience, HTML structured the content, CSS styled the interface and MySQL managed the data. Consequently, a mini Learning Management System was developed. This platform was used in implementing the flipped classroom system.
The growing demand for university placements has led to inefficiencies and lack of transparency i... more The growing demand for university placements has led to inefficiencies and lack of transparency in existing methods. The study aims to explore the underutilization of AI in these processes to improve efficiency, transparency, and accessibility. The methodology involves extracting and cleaning publication data from Scopus, preparing it for analysis using Google Colab, and visualizing relationships between keywords with VOS viewer. Key findings reveal significant research areas, keyword co-occurrence, and collaborative authorship trends in AI applications within HE admissions and administrative processes. The study highlights the importance of AI applications in university management, human factors, employment outcomes, big data utilization, decision support systems, and educational computing infrastructure. The study highlights gaps in the current literature and calls for ethical and methodological rigor, interdisciplinary approaches, and robust AI systems for fairness and transparency. Future research should incorporate diverse data sources, qualitative analysis, and extend the timeframe to capture ongoing developments in AI applications.
The growing demand for university placements has led to inefficiencies and lack of transparency i... more The growing demand for university placements has led to inefficiencies and lack of transparency in existing methods. The study aims to explore the underutilization of AI in these processes to improve efficiency, transparency, and accessibility. The methodology involves extracting and cleaning publication data from Scopus, preparing it for analysis using Google Colab, and visualizing relationships between keywords with VOS viewer. Key findings reveal significant research areas, keyword co-occurrence, and collaborative authorship trends in AI applications within HE admissions and administrative processes. The study highlights the importance of AI applications in university management, human factors, employment outcomes, big data utilization, decision support systems, and educational computing infrastructure. The study highlights gaps in the current literature and calls for ethical and methodological rigor, interdisciplinary approaches, and robust AI systems for fairness and transparency. Future research should incorporate diverse data sources, qualitative analysis, and extend the timeframe to capture ongoing developments in AI applications.
International Journal of Advances in Intelligent Informatics
Despite tremendous advancements in gender equality, there are still persistent gender disparities... more Despite tremendous advancements in gender equality, there are still persistent gender disparities, especially in important human activities. Consequently, gender inequality and related concerns are serious problems in our global society. Major players in the global economy have identified the gender identity system as a crucial stepping stone for bridging the enormous gap in gender-based problems. Extensive research conducted by forensic scientists has uncovered a unique pattern in the fingerprint, and these distinguishing characteristics of fingerprints can be utilized to determine the gender of individuals. Numerous research has revealed various fingerprint-based approaches to gender recognition. This research aims to present a novel dynamic horizontal voting ensemble model with a hybrid Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) deep learning algorithm as the base learner to determine human gender attributes based on fingerprint patterns automatically. Mor...
Science journal of University of Zakho, May 30, 2024
In the field of breast cancer diagnosis, the precise classification of benign images plays a pivo... more In the field of breast cancer diagnosis, the precise classification of benign images plays a pivotal role in ensuring effective patient care. This research undertakes a detailed examination of EfficientNetV2 models, specifically focusing on their ability to discern benign histopathology breast cancer images. The dataset were carefully curated to include diverse benign cases such as adenosis, fibroadenoma, phyllodes_tumor, and tubular_adenoma of image level for 40X magnification factor underwent thorough preprocessing before being divided into training and testing sets. Various variants of the EfficientNetV2 model-EfficientNetV2B0, EfficientNetV2B1, EfficientNetV2B2, EfficientNetV2B3, EfficientNetV2S, EfficientNetV2M, and EfficientNetV2L-were trained on the designated dataset. The performance evaluation shows the intricacies of the efficiency of each model. Notably, EfficientNetV2L emerged as a standout performer, boasting impressive metrics such as Accuracy (0.97), Precision (0.97), Recall (0.97), F1-score (0.97). These findings underscore the potential of EfficientNetV2L as a robust tool for accurately discerning benign histopathology breast cancer images. This study contributes significant insights to the field of breast cancer diagnostics, particularly addressing the critical task of classifying benign cases accurately. The gained insights pave the way for improved decision-making in assessments, ultimately enhancing the overall efficacy of breast cancer diagnosis.
Nigerian Journal of Technology, May 13, 2022
Road Traffic Crash (RTC) is among the leading causes of death in the world and has a significant ... more Road Traffic Crash (RTC) is among the leading causes of death in the world and has a significant impact on the socioeconomic development in a society. Generally, RTC can be caused by one or a combination of the following factors: Human, environment and vehicle. This study utilized five data mining algorithm classifiers (Decision Tree (DT), K-Nearest Neighbor (KNN), J-Repeated Incremental Pruning to Produce Error Reduction (JRIP), Naïve Bayes (NB), and Multi-layer Perceptron (MLP)) to classify the severity of RTC and identify the significant causes of RTC in Kaduna State, Nigeria. The RTC data used in this study included 26 RTC attributes with 1580 instances from 2016 to 2018 that covered fatal, serious and minor cases obtained from the Federal Road Safety Corps, Kaduna sector command. Two sets of experiments were performed on the classifiers (without and with feature selection). The study results showed that among the five data mining algorithms used, K-NN had the best accuracies of 94.8% and 96.1% respectively for the without and with feature selection experiments.
Social Science Research Network, Apr 2, 2020
Science World Journal, 2014
The paper proposes a framework that integrates Perceived Credibility, Perceived Regulatio... more The paper proposes a framework that integrates Perceived Credibility, Perceived Regulation, Perceived Benefit, Perceived Awareness/Education with the Unified Theory of Acceptance and Use of Technology (UTAUT) concept in users’ adoption of e-commerce in Kaduna State, Nigeria. The findings show that while the original UTAUT model suggests a positive relationship between its variables and Behavioral Intention, it appears that the data do not support a significant relationship between these concepts. However, significant relationships were identified between performance expectancy, effort expectancy, facilitating conditions, perceived regulation on behavioural intention to adopt e-commerce. Unfortunately, no significant relationships were found between social influences, Perceived credibility, Perceived Benefit, Perceived awareness/education with respect to Behavioral Intention.
Diabetes Mellitus (DM) which refers to a metabolic disorder that occurs when the level of blood s... more Diabetes Mellitus (DM) which refers to a metabolic disorder that occurs when the level of blood sugar in the body is considered high, which could be a resulting effect of inadequate availability of insulin in the body. It is a chronic disease which may lead to myriads of complications in the body system. Statistics by the World Health Organization (WHO) in 2013, indicated that DM was the cause of death of over 1.5 million people around the world and in 2016, 8.5% of adults within age seventeen (17) and above were reported to be diabetic and diabetic patients have continued to increase in recent years. It is therefore very glaring that these alarming figures calls for very urgent and effective attention. There has been a recent proliferate increase in studies relating to machine learning in the healthcare sector, hence the motivation for this research work. The research was based on the prevalence of diabetes amongst the masses of Kaduna metropolis using some selected hospitals as a case study after which a predictive model was designed for diabetes, using some selected supervised learning algorithms like Decision tree algorithm, K-Nearest Neighbour algorithm and Artificial Neural Networks on a dataset gotten from 44 Army Reference Hospital and Yusuf Danstoho Memorial Hospital Kaduna which constitutes of nine (9) attributes that was considered. The results indicated that ANN produced the highest accuracy with 97.40% followed by decision tree algorithm with 96.10% accuracy then K-NN algorithm with 88.31% First author's last name and (not &) Second author's last name (use et al. if more than two authors)
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES
Today, there is a fierce rivalry between ethnic groups in Nigeria on a number of issues, such as ... more Today, there is a fierce rivalry between ethnic groups in Nigeria on a number of issues, such as the division of power and resources, aversion to dominance, and uneven growth. Ethnicity as an identity naturally occupies a prominent position in the political arena. It is the simplest and most natural way for people to mobilize around essential human needs such as security, food, shelter, economical well-being, inequity, land distribution, autonomy, and recognition. Recent research has revealed the potential to determine an individual's ethnicity based on biometric data automatically. These studies reported significant advancements in automatically predicting demographics based on facial and iris traits. This success has been ascribed to the availability of a sufficient amount of high-quality data. There needs to be more data about the likelihood that fingerprints can disclose an individual's ethnicity. A need for more data causes this difficulty. This study aims to obtain fingerprint pictures via live scan among the major ethnic groups in Nigeria. For training and classification of the fingerprint images, the proposed Dynamic Horizontal Voting Ensemble (DHVE) deep learning with a Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) as the base learner was employed. Standard performance classification metrics such as Accuracy, Recall, Precision, and F1 score were used to evaluate the performance analysis of the model. This study demonstrated an accuracy of over 98% in predicting a person's ethnicity. Additionally, the proposed model outperformed existing state-of-the-art models.
IJAIT (International Journal of Applied Information Technology)
There is paucity of information regarding the probability that fingerprints may reveal combined s... more There is paucity of information regarding the probability that fingerprints may reveal combined soft biometric trait of human age, gender, and ethnicity. This challenge is due to lack of data. This has however, prompted academics to conduct their demographic classification-related work using the limited fingerprint dataset that is now available. However, complete fingerprint datasets collected under conventional and real-world conditions are not easily available for research reasons. This research aims to design a multi-task Deep Learning model for classifying the combined traits of ethnicity, gender, and age group estimation using fingerprint pattern. The fingerprint database was collected using a live scan method in real-world conditions, with subjects from three most numerous racial groups of Nigeria which are Yoruba, Igbo and Hausa, with consideration of the subject gender and age groups. The proposed method for the fingerprint image classification and training is the novel Dyna...
World Journal of Innovative Research
World Journal of Innovative Research
Most system interfaces do not meet user intuition in terms of both context and the underlying act... more Most system interfaces do not meet user intuition in terms of both context and the underlying actions thereof, hence reducing user's task execution efficiency. This translate into the amount of time taken to learn, recall and complete the procedure for certain task with respect to a given system or device. It was in the light of this that this work took a look at the existing human computer interaction (HCI) usability testing techniques with the intention of empirically establishing which among cognitive walkthrough, heuristic evaluation and user group is the most efficient in identifying and correcting system's usability problems. To create the research pathway a detail review of related work was undertaken to identify the lacuna therein for the research direction. A case study of the Nigerian Defence Academy (NDA) website was used as a specimen for administering the usability test methods and the outcome of each was documented. The research methodology adopted a purposive and stratified sampling technique to reduced biased and increased reliability of the representative sample chosen for this research. The sample chosen was an extract of final year undergraduate students of Federal College of Education (FCE) Pankshin, an affiliate of University of Jos, Plateau State, Nigeria. The students have taken a course in Human Factor in System Design, which provided them with adequate training in usability test techniques, 20 out of the total 30 students with the requisite skill were chosen to undertake the test process. The data collated passed through paired sample T-test procedure of the compare-mean analysis with confidence interval percentage of 95%, using the IBM Statistical Package for the Social Sciences (SPSS) version 26. The outcome of the T-test showed that the respective means of cognitive-walkthrough, heuristic-evaluation and user-group are 5.750, 4.900 and 6.350, with respective correlation coefficients of 0.192, 0.54 and 0.624. This shows a strong relationship between each pair of the test techniques. However, user-group usability test technique with the highest mean accuracy interval of 1.450 is the best in terms of performance relative to the other two techniques. Finally, the result of the analysis as well as charts created and the participant's findings were summarized thus proffering way forward and recommendations for the improvement of system and user interaction.
Journal of Computing and Social Informatics
This paper presents a comparative analysis of the widely accepted YOLOv5 and the latest version o... more This paper presents a comparative analysis of the widely accepted YOLOv5 and the latest version of YOLO which is YOLOv7. Experiments were carried out by training a custom model with both YOLOv5 and YOLOv7 independently in order to consider which one of the two performs better in terms of precision, recall, mAP@0.5 and mAP@0.5:0.95. The dataset used in the experiment is a custom dataset for Remote Weapon Station which consists of 9,779 images containing 21,561 annotations of four classes gotten from Google Open Images Dataset, Roboflow Public Dataset and locally sourced dataset. The four classes are Persons, Handguns, Rifles and Knives. The experimental results of YOLOv7 were precision score of 52.8%, recall value of 56.4%, mAP@0.5 of 51.5% and mAP@0.5:0.95 of 31.5% while that of YOLOv5 were precision score of 62.6%, recall value of 53.4%, mAP@0.5 of 55.3% and mAP@0.5:0.95 of 34.2%. It was observed from the experiment conducted that YOLOv5 gave a better result than YOLOv7 in terms of...
Dutse Journal of Pure and Applied Sciences, Mar 30, 2023
Diabetes and hypertension are examples of non-communicable diseases that are becoming a severe pr... more Diabetes and hypertension are examples of non-communicable diseases that are becoming a severe problem in the world today. A number of diseases have been connected to unhealthy eating habits. In this study, a recommender system that uses nutritional knowledge to suggest meals that are nutrient-dense to patients suffering from either ailments or one of it. The Study looked into computer models for tailored meal suggestions based on dietary data and user data in recent years. It examined physical traits, physiological data, and other personal information. A general framework for daily eating plan selections is presented in this article. The system used machine learning methodologies and techniques to generate recommendations for the necessary food items. Kmeans clustering and Random Forest classification technique were used which concentrates on providing meal recommendations that help the user maintain and enhance his or her health. The model was able to achieve an accuracy of 95% with 100 decision trees.
International Journal of Intelligent Computing and Information Sciences
The skin is one of the organs of the human body where various internal health problems including ... more The skin is one of the organs of the human body where various internal health problems including cardiovascular diseases tend to show some notable signs and symptoms. The dermatologist may be one of the first clinician to recognize that someone does have cardiovascular disease because warning signs can develop on the skin. The aim of this research is to use the efficientNetV2 model for the classification of dermatologic manifestations of cardiovascular disease based on transfer learning. The EfficientNetV2 model was modified and trained as a classifier for the selected images of dermatologic manifestations of cardiovascular disease. A total of 2665 images consisting of 430 for Cyanosis, 480 for Liverdo reticularis, 780 for Xanthoma, 430 for Stasis dermatitis, 540 for fingernails clubbing, and other 1100 images of both normal skin and general objects were used in the training of the model. Data augmentation was also used to increase the amount of training images and finetuning was employed on the model. Google Collaboratory was used as the platform to train the model. The trained model with fine-tuning was able to obtain a considerable accuracy of 96.04%. The EfficientNetV2 convolutional neural network (CNN) model performed exceptionally well in the image classification.
Nigerian Journal of Technology, 2021
The use of computers to conduct examinations is more effective than traditional paper-based exami... more The use of computers to conduct examinations is more effective than traditional paper-based examinations in terms of immediate availability of results and long term cost effectiveness. This however is faced with identifying and authenticating the real identities of the examinees so as to reduce impersonation. The study examined the existing authentication method available on the Computer-based test system of Air Force Institute of Technology (AFIT), Kaduna, Nigeria and proposed the fingerprint biometric technique as an additional method to authenticate the examinees. The fingerprint biometric authentication was developed using FlexCode SDK and implemented on DigitalPersona 4500 fingerprint reader – the recommended scanner by JAMB for fingerprint enrollment. The system was developed using PHP scripting language on XAMPP local server and MySQL database system. The results obtained showed that there is no need for a middleware to link the authentication module with the CBT because of t...
West Science Interdisciplinary Studies, Jan 25, 2024
Implementation of Flipped Classroom as A Supportive and Alternative Approach to Traditional Learning System, 2024
Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped cl... more Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped classrooms has developed as a convincing educational strategy, designed to reshape the traditional teaching and learning models. This study developed a mini LMS platform to empower educators in managing and disseminating instructional materials to engage students before the in-class period. JavaScript, HTML, CSS and MYSQL play vital roles in the design and development mini Learning Management System (LMS) used in this study to create
a functional and user-friendly platform. The integration of these technologies in the design of the mini LMS allows for the creation of a robust, operative, interactive and data-driven learning platform. JavaScript provided the dynamism of the user experience, HTML structured the content, CSS styled the interface and MySQL managed the data. Consequently, a mini Learning Management System was developed. This platform was used in implementing the flipped classroom system.
International Journal of Basic Science and Technology, 2024
Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped cl... more Integrating a mini-Learning Management System (MLMS) into the pedagogical structure of flipped classrooms has developed as a convincing educational strategy, designed to reshape the traditional teaching and learning models. This study developed a mini LMS platform to empower educators in managing and disseminating instructional materials to engage students before the in-class period. JavaScript, HTML, CSS and MYSQL play vital roles in the design and development mini Learning Management System (LMS) used in this study to create a functional and user-friendly platform. The integration of these technologies in the design of the mini LMS allows for the creation of a robust, operative, interactive and data-driven learning platform. JavaScript provided the dynamism of the user experience, HTML structured the content, CSS styled the interface and MySQL managed the data. Consequently, a mini Learning Management System was developed. This platform was used in implementing the flipped classroom system.
The growing demand for university placements has led to inefficiencies and lack of transparency i... more The growing demand for university placements has led to inefficiencies and lack of transparency in existing methods. The study aims to explore the underutilization of AI in these processes to improve efficiency, transparency, and accessibility. The methodology involves extracting and cleaning publication data from Scopus, preparing it for analysis using Google Colab, and visualizing relationships between keywords with VOS viewer. Key findings reveal significant research areas, keyword co-occurrence, and collaborative authorship trends in AI applications within HE admissions and administrative processes. The study highlights the importance of AI applications in university management, human factors, employment outcomes, big data utilization, decision support systems, and educational computing infrastructure. The study highlights gaps in the current literature and calls for ethical and methodological rigor, interdisciplinary approaches, and robust AI systems for fairness and transparency. Future research should incorporate diverse data sources, qualitative analysis, and extend the timeframe to capture ongoing developments in AI applications.
The growing demand for university placements has led to inefficiencies and lack of transparency i... more The growing demand for university placements has led to inefficiencies and lack of transparency in existing methods. The study aims to explore the underutilization of AI in these processes to improve efficiency, transparency, and accessibility. The methodology involves extracting and cleaning publication data from Scopus, preparing it for analysis using Google Colab, and visualizing relationships between keywords with VOS viewer. Key findings reveal significant research areas, keyword co-occurrence, and collaborative authorship trends in AI applications within HE admissions and administrative processes. The study highlights the importance of AI applications in university management, human factors, employment outcomes, big data utilization, decision support systems, and educational computing infrastructure. The study highlights gaps in the current literature and calls for ethical and methodological rigor, interdisciplinary approaches, and robust AI systems for fairness and transparency. Future research should incorporate diverse data sources, qualitative analysis, and extend the timeframe to capture ongoing developments in AI applications.
International Journal of Advances in Intelligent Informatics
Despite tremendous advancements in gender equality, there are still persistent gender disparities... more Despite tremendous advancements in gender equality, there are still persistent gender disparities, especially in important human activities. Consequently, gender inequality and related concerns are serious problems in our global society. Major players in the global economy have identified the gender identity system as a crucial stepping stone for bridging the enormous gap in gender-based problems. Extensive research conducted by forensic scientists has uncovered a unique pattern in the fingerprint, and these distinguishing characteristics of fingerprints can be utilized to determine the gender of individuals. Numerous research has revealed various fingerprint-based approaches to gender recognition. This research aims to present a novel dynamic horizontal voting ensemble model with a hybrid Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) deep learning algorithm as the base learner to determine human gender attributes based on fingerprint patterns automatically. Mor...
Science journal of University of Zakho, May 30, 2024
In the field of breast cancer diagnosis, the precise classification of benign images plays a pivo... more In the field of breast cancer diagnosis, the precise classification of benign images plays a pivotal role in ensuring effective patient care. This research undertakes a detailed examination of EfficientNetV2 models, specifically focusing on their ability to discern benign histopathology breast cancer images. The dataset were carefully curated to include diverse benign cases such as adenosis, fibroadenoma, phyllodes_tumor, and tubular_adenoma of image level for 40X magnification factor underwent thorough preprocessing before being divided into training and testing sets. Various variants of the EfficientNetV2 model-EfficientNetV2B0, EfficientNetV2B1, EfficientNetV2B2, EfficientNetV2B3, EfficientNetV2S, EfficientNetV2M, and EfficientNetV2L-were trained on the designated dataset. The performance evaluation shows the intricacies of the efficiency of each model. Notably, EfficientNetV2L emerged as a standout performer, boasting impressive metrics such as Accuracy (0.97), Precision (0.97), Recall (0.97), F1-score (0.97). These findings underscore the potential of EfficientNetV2L as a robust tool for accurately discerning benign histopathology breast cancer images. This study contributes significant insights to the field of breast cancer diagnostics, particularly addressing the critical task of classifying benign cases accurately. The gained insights pave the way for improved decision-making in assessments, ultimately enhancing the overall efficacy of breast cancer diagnosis.
Nigerian Journal of Technology, May 13, 2022
Road Traffic Crash (RTC) is among the leading causes of death in the world and has a significant ... more Road Traffic Crash (RTC) is among the leading causes of death in the world and has a significant impact on the socioeconomic development in a society. Generally, RTC can be caused by one or a combination of the following factors: Human, environment and vehicle. This study utilized five data mining algorithm classifiers (Decision Tree (DT), K-Nearest Neighbor (KNN), J-Repeated Incremental Pruning to Produce Error Reduction (JRIP), Naïve Bayes (NB), and Multi-layer Perceptron (MLP)) to classify the severity of RTC and identify the significant causes of RTC in Kaduna State, Nigeria. The RTC data used in this study included 26 RTC attributes with 1580 instances from 2016 to 2018 that covered fatal, serious and minor cases obtained from the Federal Road Safety Corps, Kaduna sector command. Two sets of experiments were performed on the classifiers (without and with feature selection). The study results showed that among the five data mining algorithms used, K-NN had the best accuracies of 94.8% and 96.1% respectively for the without and with feature selection experiments.
Social Science Research Network, Apr 2, 2020
Science World Journal, 2014
The paper proposes a framework that integrates Perceived Credibility, Perceived Regulatio... more The paper proposes a framework that integrates Perceived Credibility, Perceived Regulation, Perceived Benefit, Perceived Awareness/Education with the Unified Theory of Acceptance and Use of Technology (UTAUT) concept in users’ adoption of e-commerce in Kaduna State, Nigeria. The findings show that while the original UTAUT model suggests a positive relationship between its variables and Behavioral Intention, it appears that the data do not support a significant relationship between these concepts. However, significant relationships were identified between performance expectancy, effort expectancy, facilitating conditions, perceived regulation on behavioural intention to adopt e-commerce. Unfortunately, no significant relationships were found between social influences, Perceived credibility, Perceived Benefit, Perceived awareness/education with respect to Behavioral Intention.
Diabetes Mellitus (DM) which refers to a metabolic disorder that occurs when the level of blood s... more Diabetes Mellitus (DM) which refers to a metabolic disorder that occurs when the level of blood sugar in the body is considered high, which could be a resulting effect of inadequate availability of insulin in the body. It is a chronic disease which may lead to myriads of complications in the body system. Statistics by the World Health Organization (WHO) in 2013, indicated that DM was the cause of death of over 1.5 million people around the world and in 2016, 8.5% of adults within age seventeen (17) and above were reported to be diabetic and diabetic patients have continued to increase in recent years. It is therefore very glaring that these alarming figures calls for very urgent and effective attention. There has been a recent proliferate increase in studies relating to machine learning in the healthcare sector, hence the motivation for this research work. The research was based on the prevalence of diabetes amongst the masses of Kaduna metropolis using some selected hospitals as a case study after which a predictive model was designed for diabetes, using some selected supervised learning algorithms like Decision tree algorithm, K-Nearest Neighbour algorithm and Artificial Neural Networks on a dataset gotten from 44 Army Reference Hospital and Yusuf Danstoho Memorial Hospital Kaduna which constitutes of nine (9) attributes that was considered. The results indicated that ANN produced the highest accuracy with 97.40% followed by decision tree algorithm with 96.10% accuracy then K-NN algorithm with 88.31% First author's last name and (not &) Second author's last name (use et al. if more than two authors)
INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES
Today, there is a fierce rivalry between ethnic groups in Nigeria on a number of issues, such as ... more Today, there is a fierce rivalry between ethnic groups in Nigeria on a number of issues, such as the division of power and resources, aversion to dominance, and uneven growth. Ethnicity as an identity naturally occupies a prominent position in the political arena. It is the simplest and most natural way for people to mobilize around essential human needs such as security, food, shelter, economical well-being, inequity, land distribution, autonomy, and recognition. Recent research has revealed the potential to determine an individual's ethnicity based on biometric data automatically. These studies reported significant advancements in automatically predicting demographics based on facial and iris traits. This success has been ascribed to the availability of a sufficient amount of high-quality data. There needs to be more data about the likelihood that fingerprints can disclose an individual's ethnicity. A need for more data causes this difficulty. This study aims to obtain fingerprint pictures via live scan among the major ethnic groups in Nigeria. For training and classification of the fingerprint images, the proposed Dynamic Horizontal Voting Ensemble (DHVE) deep learning with a Hybrid of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) as the base learner was employed. Standard performance classification metrics such as Accuracy, Recall, Precision, and F1 score were used to evaluate the performance analysis of the model. This study demonstrated an accuracy of over 98% in predicting a person's ethnicity. Additionally, the proposed model outperformed existing state-of-the-art models.
IJAIT (International Journal of Applied Information Technology)
There is paucity of information regarding the probability that fingerprints may reveal combined s... more There is paucity of information regarding the probability that fingerprints may reveal combined soft biometric trait of human age, gender, and ethnicity. This challenge is due to lack of data. This has however, prompted academics to conduct their demographic classification-related work using the limited fingerprint dataset that is now available. However, complete fingerprint datasets collected under conventional and real-world conditions are not easily available for research reasons. This research aims to design a multi-task Deep Learning model for classifying the combined traits of ethnicity, gender, and age group estimation using fingerprint pattern. The fingerprint database was collected using a live scan method in real-world conditions, with subjects from three most numerous racial groups of Nigeria which are Yoruba, Igbo and Hausa, with consideration of the subject gender and age groups. The proposed method for the fingerprint image classification and training is the novel Dyna...
World Journal of Innovative Research
World Journal of Innovative Research
Most system interfaces do not meet user intuition in terms of both context and the underlying act... more Most system interfaces do not meet user intuition in terms of both context and the underlying actions thereof, hence reducing user's task execution efficiency. This translate into the amount of time taken to learn, recall and complete the procedure for certain task with respect to a given system or device. It was in the light of this that this work took a look at the existing human computer interaction (HCI) usability testing techniques with the intention of empirically establishing which among cognitive walkthrough, heuristic evaluation and user group is the most efficient in identifying and correcting system's usability problems. To create the research pathway a detail review of related work was undertaken to identify the lacuna therein for the research direction. A case study of the Nigerian Defence Academy (NDA) website was used as a specimen for administering the usability test methods and the outcome of each was documented. The research methodology adopted a purposive and stratified sampling technique to reduced biased and increased reliability of the representative sample chosen for this research. The sample chosen was an extract of final year undergraduate students of Federal College of Education (FCE) Pankshin, an affiliate of University of Jos, Plateau State, Nigeria. The students have taken a course in Human Factor in System Design, which provided them with adequate training in usability test techniques, 20 out of the total 30 students with the requisite skill were chosen to undertake the test process. The data collated passed through paired sample T-test procedure of the compare-mean analysis with confidence interval percentage of 95%, using the IBM Statistical Package for the Social Sciences (SPSS) version 26. The outcome of the T-test showed that the respective means of cognitive-walkthrough, heuristic-evaluation and user-group are 5.750, 4.900 and 6.350, with respective correlation coefficients of 0.192, 0.54 and 0.624. This shows a strong relationship between each pair of the test techniques. However, user-group usability test technique with the highest mean accuracy interval of 1.450 is the best in terms of performance relative to the other two techniques. Finally, the result of the analysis as well as charts created and the participant's findings were summarized thus proffering way forward and recommendations for the improvement of system and user interaction.
Journal of Computing and Social Informatics
This paper presents a comparative analysis of the widely accepted YOLOv5 and the latest version o... more This paper presents a comparative analysis of the widely accepted YOLOv5 and the latest version of YOLO which is YOLOv7. Experiments were carried out by training a custom model with both YOLOv5 and YOLOv7 independently in order to consider which one of the two performs better in terms of precision, recall, mAP@0.5 and mAP@0.5:0.95. The dataset used in the experiment is a custom dataset for Remote Weapon Station which consists of 9,779 images containing 21,561 annotations of four classes gotten from Google Open Images Dataset, Roboflow Public Dataset and locally sourced dataset. The four classes are Persons, Handguns, Rifles and Knives. The experimental results of YOLOv7 were precision score of 52.8%, recall value of 56.4%, mAP@0.5 of 51.5% and mAP@0.5:0.95 of 31.5% while that of YOLOv5 were precision score of 62.6%, recall value of 53.4%, mAP@0.5 of 55.3% and mAP@0.5:0.95 of 34.2%. It was observed from the experiment conducted that YOLOv5 gave a better result than YOLOv7 in terms of...
Dutse Journal of Pure and Applied Sciences, Mar 30, 2023
Diabetes and hypertension are examples of non-communicable diseases that are becoming a severe pr... more Diabetes and hypertension are examples of non-communicable diseases that are becoming a severe problem in the world today. A number of diseases have been connected to unhealthy eating habits. In this study, a recommender system that uses nutritional knowledge to suggest meals that are nutrient-dense to patients suffering from either ailments or one of it. The Study looked into computer models for tailored meal suggestions based on dietary data and user data in recent years. It examined physical traits, physiological data, and other personal information. A general framework for daily eating plan selections is presented in this article. The system used machine learning methodologies and techniques to generate recommendations for the necessary food items. Kmeans clustering and Random Forest classification technique were used which concentrates on providing meal recommendations that help the user maintain and enhance his or her health. The model was able to achieve an accuracy of 95% with 100 decision trees.
International Journal of Intelligent Computing and Information Sciences
The skin is one of the organs of the human body where various internal health problems including ... more The skin is one of the organs of the human body where various internal health problems including cardiovascular diseases tend to show some notable signs and symptoms. The dermatologist may be one of the first clinician to recognize that someone does have cardiovascular disease because warning signs can develop on the skin. The aim of this research is to use the efficientNetV2 model for the classification of dermatologic manifestations of cardiovascular disease based on transfer learning. The EfficientNetV2 model was modified and trained as a classifier for the selected images of dermatologic manifestations of cardiovascular disease. A total of 2665 images consisting of 430 for Cyanosis, 480 for Liverdo reticularis, 780 for Xanthoma, 430 for Stasis dermatitis, 540 for fingernails clubbing, and other 1100 images of both normal skin and general objects were used in the training of the model. Data augmentation was also used to increase the amount of training images and finetuning was employed on the model. Google Collaboratory was used as the platform to train the model. The trained model with fine-tuning was able to obtain a considerable accuracy of 96.04%. The EfficientNetV2 convolutional neural network (CNN) model performed exceptionally well in the image classification.
Nigerian Journal of Technology, 2021
The use of computers to conduct examinations is more effective than traditional paper-based exami... more The use of computers to conduct examinations is more effective than traditional paper-based examinations in terms of immediate availability of results and long term cost effectiveness. This however is faced with identifying and authenticating the real identities of the examinees so as to reduce impersonation. The study examined the existing authentication method available on the Computer-based test system of Air Force Institute of Technology (AFIT), Kaduna, Nigeria and proposed the fingerprint biometric technique as an additional method to authenticate the examinees. The fingerprint biometric authentication was developed using FlexCode SDK and implemented on DigitalPersona 4500 fingerprint reader – the recommended scanner by JAMB for fingerprint enrollment. The system was developed using PHP scripting language on XAMPP local server and MySQL database system. The results obtained showed that there is no need for a middleware to link the authentication module with the CBT because of t...