Papers by Anwaitu Fraser Egba, PhD
International Journal of Advancement in Science and Technology, 2024
This project presents the development and optimization of real-time campus security survillance s... more This project presents the development and optimization of real-time campus security survillance system leveraging Arduino technology and CCTV cameras to enhance campus safety and security. The system integrates hardware components, including Arduino Uno board, Wi-Fi modules cameras, motion sensors and SD card to achieve seamless operation. PIR sensors detect motion and triggers the Arduino to adjust the camera's position and activate recording. Machine algorithm such as kmeans clustering was employed for anomaly detection, enabling the system to identify suspicious activity and send real-time alerts to designated devices. The system's accuracy is consistently high across tests ranging from 94.75% to 98.75%. Precision shows the system is generally good at minimizing false positive, though with some variability. Recall values suggest that the system effectively detect most motion event. The implementation of the system enhances campus security by providing real-time alerts and efficient monitoring.
Multimedia Research, 2024
In the field of poultry science, automation technologies can be highly helpful. Using an automati... more In the field of poultry science, automation technologies can be highly helpful. Using an automatic heating and lighting system for newborn chickens helps to sustain a temperature that is ideal for their development both during the day and during the cold winter nights. A self-regulating temperature device that uses a fixed point or value to regulate the temperature of a lab or room is known as an automatic heat control system. The research study aimed to manage and control heat and lighting system automatically using Arduino. The user will set the desired temperature, which is then compared to the temperature of the poultry house as determined by a temperature sensor, and the device responds by automatically turning on the heater/lamp based on the temperature differential. Time and temperature will be registered on the SD card. The heater will turn on if the temperature falls below the fixed limit. Dip Trace, a circuit modelling program used to create electronic systems and PCBs, was used to create the device. The ATmega328p microcontroller and Arduino software were used to code. To provide a controlled voltage to most of the active devices in the system design circuit, a 5v DC power supply was added. For data recording, an SD card and an RTC are attached to the circuit. This method maintains a warm environment for baby chicks while also providing light. This technology regulates the temperature of the surroundings without the need for human intervention. The android mobile app may be used to monitor and check the temperature status of poultry homes at any time via a Bluetooth connection.
Kasu Journal of Computer Science , 2024
This study has the goal of developing security model that detected and prevented the risks of Dis... more This study has the goal of developing security model that detected and prevented the risks of Distributed Denial of Service (DDoS) attacks in cloud computing systems and IoT devices which are gravely potent and on the increase today, especially with the rapid growth of internet during the last one and a half decades. This is more prevalent because of the several benefits that an organization enjoys after adopting cloud computing and Internet of Things (IoT). However, the harm that may result after a DDoS attack on a cloud computing infrastructure or service and IoT devices can be very huge, and all efforts must be made to secure it. Therefore, the traditional security mechanism cannot satisfy the security requirements of cloud computing and IoT. While several models exist on tackling this menace which operate on a particular layer (mostly layer 3) of the Open System Interconnection (OSI), we have developed a cloud-based hybrid defense and detection mechanism to prevent DDoS attacks in cloud computing environment and IoT that operates in layers 3 (network), 4 (transport) and 7 (application) of the OSI model. This was done using two approaches: analyzing Transmission Control Protocol/Internet Protocol (TCP/IP) header features of incoming packets in cloud computing environment in order to detect and classify spoofed IP address during DDoS attack via a custom-made Web Application Firewall (WAF); and the integration of the cloud resources with Cloudflare. In the first instance, TCP syn flood attacks were targeted to a particular webserver on port 80 through an attacking lab machine. This machine did not have this custom-made WAF (prevention/detection mechanism) against these attacks. There was 100% packet loss as no replies were received, overwhelming the system. The result shows that a total of 1,625,192 packets were transmitted in a short period which were captured and analyzed via Wireshark. Several TCP errors were observed over a very short time interval which indicated successful DDoS attack effectively crashing the system. The result varied when the custom-made WAF was put in place, and the attacking lab machine launched a TCP syn flood attack against the web server on port http port 80. A total of 2,353,585 packets were transmitted in a short period which were captured and analyzed using Wireshark and contained less TCP errors indicating successful mitigation of DDoS attacks. When the resources were hosted online and integrated with Cloudflare, integrity checks were successful before the resources were loaded, indicating complete mitigation of attacks. In the end, an enhanced, cloud-based, hybrid (WAF + Cloudflare) security model that prevented the risks of DDoS attacks on cloud computing and IoT devices was designed and implemented. The methodology adopted for this research work is Open Source Security Testing Methodology Manual (OSSTMM) and programming language used is batch script. The model will be useful in education, healthcare, ecommerce, financial, political/electoral, web hosting providers/ISPs offices, homes and online gaming sites. However, these advancements also make IoT and cloud applications vulnerable to a variety of security threats. To broaden the scope of this research, it is recommended to extend the study to include Man-in-the-Middle (MitM) attacks and routing attacks targeting IoT devices and cloud applications.
The Effect of Improvised Computer-Based Software Package on Secondary School Students’ Achievement and Attitude Towards Mathematics
Innovare journal of education, Jul 1, 2024
The study was conducted to determine the effect of improvised computer-based software on the achi... more The study was conducted to determine the effect of improvised computer-based software on the achievement and attitude of senior secondary school students towards mathematics. Fifteen secondary school mathematics teachers were trained to produce a computer-based software package and use the package to teach ‘graphical solution to quadratic equations’ to senior secondary class one (SSCI) students. A total sample of 1487 SSCI students was used in the study:745 students in the 15 secondary schools purposively selected on the rationale of their closeness to a computer centre, was used as the experimental group, and 742 students from the 15 schools randomly selected for use as the control group. Pre-test, post-test, and quasi-experimental research designs were used to conduct the study. Fifteen intact classes were simultaneously used for treatment in the experimental and control groups. The experimental groups were taught with computers using the computer-based software package to teach graphical solutions to quadratic equations produced by their teacher, while the control groups were taught using the conventional strategy. The result reveals a significant difference in academic achievement between students taught with improvised computer-based software packages and those taught using the conventional strategy. The mean achievement score of 73% and standard deviation of 9% was obtained from the experimental group, while the control group had a mean achievement of 57% and standard deviation of 5%. Similarly, the experimental group had an attitude test score of 82% and a standard deviation of 6%, while the control group had a mean attitude test score of 59% and a standard deviation of 11%. This gave the calculated value of the t-test as t= 42.3 for achievement and t = 50.1 for attitude, showing a significant difference in achievement and attitude between the experimental and control groups. Thus, an improvised computer-based software package is more effective in teaching mathematics than the conventional strategy. Hence, improvising computer-based software for teaching and learning is highly recommended.
Development of a Diabetes Mellitus Diagnostic System Using Self-Organizing Map Algorithm: A Machine Learning Approach
IDOSR Journal of Scientific Research, Mar 11, 2024
Delivery of Health care services in developing nations has posed a huge problem to the world at l... more Delivery of Health care services in developing nations has posed a huge problem to the world at large. The United Nations and the World Health Organization have been on the front burner sorting for ways of improving these problems to abate the yearly mortality rates which are caused largely by inadequate health facilities, poor technical know-how, and poor health care administration. One disease that has a high number of patients is diabetes. In Nigeria, out of a population of 200 million, diabetes kills over 2% yearly. To reduce this menace, early diagnosis and awareness are important. And automation of the medical diagnostic system is one of the sure ways of achieving these feet. This paper explores the potential of a self-organizing map algorithm; a machine learning technique in the development of a diabetes mellitus diagnostic system (DMDS). Data collected from 120 patients from the University of Port Harcourt Teaching Hospital (UPTH) was used in the training and validation of the model. The confusion matrix formula was used in testing the sensitivity and accuracy of the model which yielded 75.63% and 87.2% respectively which are within the accepted range, predefined by expert physicians.
Multimed. Res., Apr 1, 2024
Artificial Neural Networks (ANNs) are a type of machine learning algorithms that are used to solv... more Artificial Neural Networks (ANNs) are a type of machine learning algorithms that are used to solve problems such as medical diagnosis. In recent times, the amount of data that is generated daily is on the increase and the level of the complexity of problems is troubling. ANN algorithms are commonly used to overcome these challenges are further faced with the problem of having fixed data attributes as a dataset for its input layer, the complexity of having heterogeneous datasets instead of homogeneous datasets,and having a single objective output layer instead of a multi-objective output layer that could enable the diagnosis of multiple diseases. This researchproposes an enhanced modular-based Neural Network algorithm that utilizes heterogeneous datasets drawn from multiple sources, decomposed and clustered into independent units, and then trained by ANNs selected according to their learning paradigms-supervised, unsupervised, and reinforcement learning, to provide an effective, efficient and timely medical diagnosis, especially in developing countries where modern facilities are lacking with much dependence on manual methods.Thus an integrated system with multiple ANN techniques modelled into a single unit is developed. The results show that the proposed approach has been significantly successful indealing with the aforesaid problem compared to other methods with a training accuracy of 0.905, Sensitivity of 0.917, and specificity of 0.923.
Innovare Journal of Education, 2024
The study was conducted to determine the effect of improvised computer-based software on the achi... more The study was conducted to determine the effect of improvised computer-based software on the achievement and attitude of senior secondary school students towards mathematics. Fifteen secondary school mathematics teachers were trained to produce a computer-based software package and use the package to teach ‘graphical solution to quadratic equations’ to senior secondary class one (SSCI) students. A total sample of 1487 SSCI students was used in the study:745 students in the 15 secondary schools purposively selected on the rationale of their closeness to a computer centre, was used as the experimental group, and 742 students from the 15 schools randomly selected for use as the control group. Pre-test, post-test, and quasi-experimental research designs were used to conduct the study. Fifteen intact classes were simultaneously used for treatment in the experimental and control groups. The experimental groups were taught with computers using the computer-based software package to teach graphical solutions to quadratic equations produced by their teacher, while the control groups were taught using the conventional strategy. The result reveals a significant difference in academic achievement between students taught with improvised computer-based software packages and those taught using the conventional strategy. The mean achievement score of 73% and standard deviation of 9% was obtained from the experimental group, while the control group had a mean achievement of 57% and standard deviation of 5%. Similarly, the experimental group had an attitude test score of 82% and a standard deviation of 6%, while the control group had a mean attitude test score of 59% and a standard deviation of 11%. This gave the calculated value of the t-test as t= 42.3 for achievement and t = 50.1 for attitude, showing a significant difference in achievement and attitude between the experimental and control groups. Thus, an improvised computer-based software package is more effective in teaching mathematics than the conventional strategy. Hence, improvising computer-based software for teaching and learning is highly recommended.
Journal of Computational Mechanics, Power System and Control, 2024
Artificial Neural Networks (ANNs) are a type of machine learning algorithms that are used to solv... more Artificial Neural Networks (ANNs) are a type of machine learning algorithms that are used to solve problems such as medical diagnosis. In recent times, the amount of data that is generated daily is on the increase and the level of the complexity of problems is troubling. ANN algorithms are commonly used to overcome these challenges are further faced with the problem of having fixed data attributes as a dataset for its input layer, the complexity of having heterogeneous datasets instead of homogeneous datasets,and having a single objective output layer instead of a multi-objective output layer that could enable the diagnosis of multiple diseases. This researchproposes an enhanced modular-based Neural Network algorithm that utilizes heterogeneous datasets drawn from multiple sources, decomposed and clustered into independent units, and then trained by ANNs selected according to their learning paradigms-supervised, unsupervised, and reinforcement learning, to provide an effective, efficient and timely medical diagnosis, especially in developing countries where modern facilities are lacking with much dependence on manual methods.Thus an integrated system with multiple ANN techniques modelled into a single unit is developed. The results show that the proposed approach has been significantly successful indealing with the aforesaid problem compared to other methods with a training accuracy of 0.905, Sensitivity of 0.917, and specificity of 0.923.
IDOSR PUBLICATIONS, 2024
Delivery of Health care services in developing nations has posed a huge problem to the world at l... more Delivery of Health care services in developing nations has posed a huge problem to the world at large. The United Nations and the World Health Organization have been on the front burner sorting for ways of improving these problems to abate the yearly mortality rates which are caused largely by inadequate health facilities, poor technical know-how, and poor health care administration. One disease that has a high number of patients is diabetes. In Nigeria, out of a population of 200 million, diabetes kills over 2% yearly. To reduce this menace, early diagnosis and awareness are important. And automation of the medical diagnostic system is one of the sure ways of achieving these feet. This paper explores the potential of a self-organizing map algorithm; a machine learning technique in the development of a diabetes mellitus diagnostic system (DMDS). Data collected from 120 patients from the University of Port Harcourt Teaching Hospital (UPTH) was used in the training and validation of the model. The confusion matrix formula was used in testing the sensitivity and accuracy of the model which yielded 75.63% and 87.2% respectively which are within the accepted range, predefined by expert physicians.
International Digital Organization for Scientific Research, 2024
Delivery of Health care services in developing nations has posed a huge problem to the world at l... more Delivery of Health care services in developing nations has posed a huge problem to the world at large. The United Nations and the World Health Organization have been on the front burner sorting for ways of improving these problems to abate the yearly mortality rates which are caused largely by inadequate health facilities, poor technical know-how, and poor health care administration. One disease that has a high number of patients is diabetes. In Nigeria, out of a population of 200 million, diabetes kills over 2% yearly. To reduce this menace, early diagnosis and awareness are important. And automation of the medical diagnostic system is one of the sure ways of achieving these feet. This paper explores the potential of a self-organizing map algorithm; a machine learning technique in the development of a diabetes mellitus diagnostic system (DMDS). Data collected from 120 patients from the University of Port Harcourt Teaching Hospital (UPTH) was used in the training and validation of the model. The confusion matrix formula was used in testing the sensitivity and accuracy of the model which yielded 75.63% and 87.2% respectively which are within the accepted range, predefined by expert physicians.
International Journal of Research, 2021
The classical traveling salesman problem(TSP) is simple to state but difficult a problem to solve... more The classical traveling salesman problem(TSP) is simple to state but difficult a problem to solve. TSP seeks to determine the total distance or cost of visiting (n-1) cities or points and returning to the starting city or point. In this research, the Genetic Algorithm (GA) technique is utilized for solving the problem of finding the optimal tour around the nine Niger Delta state capitals in Nigeria which is an example of a traveling salesman problem. The partially mapped(PMX) crossover operator and the inversion mutation operator techniques were employed due to their simplicity. Genetic algorithms are evolutionary techniques used in solving optimization problems according to the survival of the fittest. The method does not provide an optimal exact solution, rather, it gives an approximated result in time. Data required for the tour were obtained from an online google map website where the distances between the state capitals and their coordinates (longitude and latitudes) were obtai...
The traveling salesman problem (TSP) is a classical simple optimization problem that aims at dete... more The traveling salesman problem (TSP) is a classical simple optimization problem that aims at determining the total distance or cost of visiting (n-1) points and returning to the starting point. This research uses the Genetic Algorithm (GA) technique to ind an optimal tour around the nine Niger Delta state capitals cities in Nigeria. The partially mapped (PMX) crossover operator and the inversion mutation operator techniques were employed. The method provides an approximated optimal result in time. The data for the research was obtained through an online google map where the distances between the cities and their coordinates (longitude and latitudes) were obtained. The MATLAB software was used in coding the results show that the BB algorithm yielded an optimal tour of 1351km with a cyclic tour of (X 3,1), (X 1,9), (X 9,6), (X 6,8), (X 8,4), (X 4,7), (X 7,5), (X 5,2), (X 2,3) and then (X 3,1) in 9 iteration circles. While the GA with the population size, maximum iteration, crossover probability, and mutation probability set to 30, 10, 0.8, and 0.1 respectively, yielded an optimal path and an optimal tour 8476125398, that is and 1124.0kms respectively. An improved result was achieved using the GA technique.
International Journal of Research - Granthaalayah, 2021
The traveling salesman problem (TSP) is a classical simple optimization problem that aims at dete... more The traveling salesman problem (TSP) is a classical simple optimization problem that aims at determining the total distance or cost of visiting (n-1) points and returning to the starting point. This research uses the Genetic Algorithm (GA) technique to ind an optimal tour around the nine Niger Delta state capitals cities in Nigeria. The partially mapped (PMX) crossover operator and the inversion mutation operator techniques were employed. The method provides an approximated optimal result in time. The data for the research was obtained through an online google map where the distances between the cities and their coordinates (longitude and latitudes) were obtained. The MATLAB software was used in coding the results show that the BB algorithm yielded an optimal tour of 1351km with a cyclic tour of (X 3,1), (X 1,9), (X 9,6), (X 6,8), (X 8,4), (X 4,7), (X 7,5), (X 5,2), (X 2,3) and then (X 3,1) in 9 iteration circles. While the GA with the population size, maximum iteration, crossover probability, and mutation probability set to 30, 10, 0.8, and 0.1 respectively, yielded an optimal path and an optimal tour 8476125398, that is and 1124.0kms respectively. An improved result was achieved using the GA technique.
The traveling salesman problem (TSP) is a classical simple optimization problem that aims at dete... more The traveling salesman problem (TSP) is a classical simple optimization problem that aims at determining the total distance or cost of visiting (n-1) points and returning to the starting point. This research uses the Genetic Algorithm (GA) technique to ind an optimal tour around the nine Niger Delta state capitals cities in Nigeria. The partially mapped (PMX) crossover operator and the inversion mutation operator techniques were employed. The method provides an approximated optimal result in time. The data for the research was obtained through an online google map where the distances between the cities and their coordinates (longitude and latitudes) were obtained. The MATLAB software was used in coding the results show that the BB algorithm yielded an optimal tour of 1351km with a cyclic tour of (X 3,1), (X 1,9), (X 9,6), (X 6,8), (X 8,4), (X 4,7), (X 7,5), (X 5,2), (X 2,3) and then (X 3,1) in 9 iteration circles. While the GA with the population size, maximum iteration, crossover probability, and mutation probability set to 30, 10, 0.8, and 0.1 respectively, yielded an optimal path and an optimal tour 8476125398, that is and 1124.0kms respectively. An improved result was achieved using the GA technique.
The traveling salesman problem (TSP) is a classical simple optimization problem that aims at dete... more The traveling salesman problem (TSP) is a classical simple optimization problem that aims at determining the total distance or cost of visiting (n-1) points and returning to the starting point. This research uses the Genetic Algorithm (GA) technique to ind an optimal tour around the nine Niger Delta state capitals cities in Nigeria. The partially mapped (PMX) crossover operator and the inversion mutation operator techniques were employed. The method provides an approximated optimal result in time. The data for the research was obtained through an online google map where the distances between the cities and their coordinates (longitude and latitudes) were obtained. The MATLAB software was used in coding the results show that the BB algorithm yielded an optimal tour of 1351km with a cyclic tour of (X 3,1), (X 1,9), (X 9,6), (X 6,8), (X 8,4), (X 4,7), (X 7,5), (X 5,2), (X 2,3) and then (X 3,1) in 9 iteration circles. While the GA with the population size, maximum iteration, crossover probability, and mutation probability set to 30, 10, 0.8, and 0.1 respectively, yielded an optimal path and an optimal tour 8476125398, that is and 1124.0kms respectively. An improved result was achieved using the GA technique.
Artificial neural networks for medical diagnosis using biomedical dataset
International Journal of Behavioural and Healthcare Research, 2013
ABSTRACT Artificial neural networks are a promising field in medical diagnostic applications. The... more ABSTRACT Artificial neural networks are a promising field in medical diagnostic applications. The goal of this study is to propose a neural network for medical diagnosis. A feed-forward back propagation neural network with tan-sigmoid transfer functions is used in this paper. The dataset is obtained from UCI machine learning repository. The results of applying the proposed neural network to distinguish between healthy patients and patients with disease based upon biomedical data in all cases show the ability of the network to learn the patterns corresponding to symptoms of the person. Three cases are studied. In the diagnosis of acute nephritis disease; the percent correctly classified in the simulation sample by the feed-forward back propagation network is 100% while in the diagnosis of heart disease; the percent correctly classified in the simulation sample by the feed-forward back propagation network is approximately 88%. On the other hand, in the diagnosis of disk hernia or spondylolisthesis; the percent correctly classified in the simulation sample is approximately 82%. Receiver operating characteristics (ROCs) curve are used to evaluate diagnosis for decision support.
The study investigates the perceived influence of social networking on the learning habit of stu... more The study investigates the perceived influence of social networking on the learning habit of students in Nigeria. The study specifically examined students’ activities online, the effect of SN usage on their study habit and its influence on students’ socialization habit. To achieve results, four research questions were formulated and the descriptive survey design was adopted for this study. Five (5) tertiary institutions were randomly selected in Rivers state while the stratified random sampling technique was used to select Two Hundred and Fifty (250) respondents from the schools. A thirty two (32) item questionnaire was developed and validated by experts in the department of measurement and evaluation in Federal College of Education (Technical), Omoku, Rivers state. The reliability of the instrument stood at 0.86 and data collected was analyzed using the mean ( ). The findings of the study show that most of the students invest large amount of their quality time on social networking, and the influence of social networking on study habit and socialization habit of students is more negative than positive.
Keyword: Social Networking, Social Media, Addiction, study habit, socialization habit
Uploads
Papers by Anwaitu Fraser Egba, PhD
Keyword: Social Networking, Social Media, Addiction, study habit, socialization habit