Stephen B Joseph | University of Maiduguri (original) (raw)
Papers by Stephen B Joseph
Heliyon
The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers a... more The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers are some of the reasons for their high popularity and acceptance for control in process industries around the world today. Tuning of PID control parameters has been a field of active research and still is. The primary objectives of PID control parameters are to achieve minimal overshoot in steady state response and lesser settling time. With exception of two popular conventional tuning strategies (Ziegler Nichols closed loop oscillation and Cohen-Coon's process reaction curve) several other methods have been employed for tuning. This work accords a thorough review of state-of-the-art and classical strategies for PID controller parameters tuning using metaheuristic algorithms. Methods appraised are categorized into classical and metaheuristic optimization methods for PID parameters tuning purposes. Details of some metaheuristic algorithms, methods of application, equations and implementation flowcharts/algorithms are presented. Some open problems for future research are also presented. The major goal of this work is to proffer a comprehensive reference source for researchers and scholars working on PID controllers.
The measurement of temperature, relative humidity and light intensity remotely by using the senso... more The measurement of temperature, relative humidity and light intensity remotely by using the sensor is not only important in weather monitoring but also crucial for many other applications such as agriculture and industrial processes. This study proposed a remote weather monitoring system that is based on Arduino Uno Microcontroller that have the ability to monitor, measure and display the temperature, relative humidity and light intensity of the atmosphere, using analogue and digital components. The analogue outputs of the sensors are connected to a microcontroller through an ADC for digital signal conversion and data logging. An LCD display is also connected to the microcontroller to display the measurement. For analysis and archiving purposes, the data can be transferred over GSM and receiver section to a mobile phone. The device has many advantages compared to other weather monitoring system in terms of its smaller size, on-device display, low cost and portability. The major stre...
This study presents a report of our research work on the design, construction and testing of a ce... more This study presents a report of our research work on the design, construction and testing of a cell phone detector. It has become obvious that blocking or jamming of cell phone signals is difficult, expensive, and/or illegal in many situations. A more practical means of controlling cell phones involves detecting their RF signals, followed by confiscation or other intervention. With this, a cell phone detector is a device designed to detect the presence of a cell phone within a certain range of vicinity (from a distance of one anda-half metres.). Our aim is to design a cell phone detector that can be used to prevent the use of mobile phones in examination halls, confidential rooms, banks, petrol filling stations, military intelligent gathering etc. We made use of two signal detectors each with a dipole antenna, choke, and diode. Each dipole antenna is tuned to 900MHz. When the antennas resonate at 900 MHz a charge is induced in the inductor. A diode then demodulates the signal, which...
Illumination of Artificial Intelligence in Cybersecurity and Forensics, 2022
Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from... more Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from large audience around the world. Some application areas include forensics, cyber security and intelligent monitoring. Face recognition attendance system serves as a perfect substitute for the conventional attendance system in organizations and classrooms. The challenges associated with most face recognition techniques is inability to detect faces in situations such as noise, pose, facial expression, illumination, obstruction and low performance accuracy. This necessitated the development of more robust and efficient face recognition systems that will overcome the drawbacks associated with conventional techniques. This paper proposed a parallel faces recognition attendance system based on Convolutional Neural Network a branch of artificial intelligence and OpenCV. Experimental results proved the effectiveness of the proposed technique having shown good performance with recognition accuracy of about 98%, precision of 96% and a recall of 0.96. This demonstrates that the proposed method is a promising facial recognition technology.
Illumination of Artificial Intelligence in Cybersecurity and Forensics
Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from... more Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from large audience around the world. Some application areas include forensics, cyber security and intelligent monitoring. Face recognition attendance system serves as a perfect substitute for the conventional attendance system in organizations and classrooms. The challenges associated with most face recognition techniques is inability to detect faces in situations such as noise, pose, facial expression, illumination, obstruction and low performance accuracy. This necessitated the development of more robust and efficient face recognition systems that will overcome the drawbacks associated with conventional techniques. This paper proposed a parallel faces recognition attendance system based on Convolutional Neural Network a branch of artificial intelligence and OpenCV. Experimental results proved the effectiveness of the proposed technique having shown good performance with recognition accuracy of about 98%, precision of 96% and a recall of 0.96. This demonstrates that the proposed method is a promising facial recognition technology.
The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers a... more The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers are some of the reasons for their high popularity and acceptance for control in process industries around the world today. Tuning of PID control parameters has been a field of active research and still is. The primary objectives of PID control parameters are to achieve minimal overshoot in steady state response and lesser settling time. With exception of two popular conventional tuning strategies (Ziegler Nichols closed loop oscillation and Cohen-Coon's process reaction curve) several other methods have been employed for tuning. This work accords a thorough review of state-of-the-art and classical strategies for PID controller parameters tuning using metaheuristic algorithms. Methods appraised are categorized into classical and metaheuristic optimization methods for PID parameters tuning purposes. Details of some metaheuristic algorithms, methods of application, equations and implementation flowcharts/algorithms are presented. Some open problems for future research are also presented. The major goal of this work is to proffer a comprehensive reference source for researchers and scholars working on PID controllers.
Peer-to-Peer (P2P) applications are bandwidth-heavy and lead to network congestion. The masquerad... more Peer-to-Peer (P2P) applications are bandwidth-heavy and lead to network congestion. The masquerading nature of P2P traffic makes conventional methods of its identification futile. In order to manage and control P2P traffic efficiently preferably in the network, it is necessary to identify such traffic online and accurately. This paper proposes a technique for online P2P identification based on traffic events signatures. The experimental results show that it is able to identify P2P traffic on the fly with an accuracy of 97.7%, precision of 98% and recall of 99.2%.
Jurnal Teknologi, 2015
Malware is a computer security problem that can morph to evade traditional detection methods base... more Malware is a computer security problem that can morph to evade traditional detection methods based on known signature matching. Since new malware variants contain patterns that are similar to those in observed malware, machine learning techniques can be used to identify new malware. This work presents a comparative study of several feature selection methods with four different machine learning classifiers in the context of static malware detection based on n-grams analysis. The result shows that the use of Principal Component Analysis (PCA) feature selection and Support Vector Machines (SVM) classification gives the best classification accuracy using a minimum number of features.
The susceptible characteristics of email spams allow them to undergo changes that can make them t... more The susceptible characteristics of email spams allow them to undergo changes that can make them to easily evade spam filters. This necessitates the need to develop more effective spam filters. Machine learning approaches have proved to be an efficient method for solving the problem of several spam emails wreaking havoc on email users. The conventional techniques of spam filtering like black lists and white lists (using domains, IP addresses, mailing addresses, etc.) have not been able to effectively curb the hazards posed by spam emails. In this paper, we applied the Logistic Model Tree machine learning algorithm for efficient classification of email spam messages. The aim of this study is to develop an email spam filter with superior prediction accuracy and fewer number of features. From the Enron public dataset consisting of 5,180 emails of both ham, spam, and normal emails, some features were extracted and used by the Logistic Model Tree Induction algorithm. Our technique has a classification accuracy of 99.305%, very low false positive rate (0.05), and very high true positive rate of 0.995. All experiments are conducted on WEKA data mining and machine learning simulation environment.
PROPORTIONAL-INTEGRAL-DERIVATIVE (PID) CONTROLLER TUNING FOR AN INVERTED PENDULUM USING PARTICLE SWARM OPTIMISATION (PSO) ALGORITHM , 2018
Linear control systems can be easily tuned using conventional tuning techniques such as the Ziegl... more Linear control systems can be easily tuned using conventional tuning techniques such as the Ziegler-Nichols and Cohen-Coon tuning formulae. Empirical studies have found that these conventional tuning methods result in an unsatisfactory control performance when they are used for industrial processes. It is for this reason that control practitioners often prefer to tune most nonlinear systems using trial and error tuning, or intuitive tuning. A need therefore exists for the development of a suitable automatic tuning technique that is applicable for a wide range of control processes that do not respond satisfactorily to conventional tuning. The balancing of an inverted pendulum by moving a cart along a horizontal track is a classic problem in the area of control. The encouraging results obtained from the simulation of the PID Controller parameters-tuning using the PSO when compared with the performance of PID and Ziegler-Nichols (Z-N) makes PSO-PID a good addition to solving PID Controller tuning problems using metaheuristic techniques as will reduce the time and cost of tuning these parameters and improve the overall system performance.
Automatic Tuning of Proportional Integral Derivative Controller using Genetic Algorithm, 2018
The application of intelligent approaches for tuning the gains of Proportional-Integral-Derivativ... more The application of intelligent approaches for tuning the gains of Proportional-Integral-Derivative (PID) controller parameters has been growing recently. The flexibility ability of evolutionary procedures have elevated its acceptability for adjusting the gains PID controllers. This work presents an automatic strategy for adjusting the gains of a PID controller parameters of systems with scarce initial information and integrative and unstable dynamics, using evolutionary Genetic Algorithm (GA), an Evolutionary Computation (EC) technique strategy. The advantages of the proposed approach were highlighted through the comparison with classical Ziegler-Nichols closed loop approach. Experiments with different processes indicate that the gains obtained through genetic algorithms may provide better responses than those obtained by the classical Ziegler-Nichols approach in terms of time domain specification and performance indices.
Heliyon (ISI & Scopus indexed), 2019
The upsurge in the volume of unwanted emails called spam has created an intense need for the deve... more The upsurge in the volume of unwanted emails called spam has created an intense need for the development of more dependable and robust antispam filters. Machine learning methods of recent are being used to successfully detect and filter spam emails. We present a systematic review of some of the popular machine learning based email spam filtering approaches. Our review covers survey of the important concepts, attempts, efficiency, and the research trend in spam filtering. The preliminary discussion in the study background examines the applications of machine learning techniques to the email spam filtering process of the leading internet service providers (ISPs) like Gmail, Yahoo and Outlook emails spam filters. Discussion on general email spam filtering process, and the various efforts by different researchers in combating spam through the use machine learning techniques was done. Our review compares the strengths and drawbacks of existing machine learning approaches and the open research problems in spam filtering. We recommended deep leaning and deep adversarial learning as the future techniques that can effectively handle the menace of spam emails.
Heliyon, 2019
The upsurge in the volume of unwanted emails called spam has created an intense need for the deve... more The upsurge in the volume of unwanted emails called spam has created an intense need for the development of more dependable and robust antispam filters. Machine learning methods of recent are being used to successfully detect and filter spam emails. We present a systematic review of some of the popular machine learning based email spam filtering approaches. Our review covers survey of the important concepts, attempts, efficiency, and the research trend in spam filtering. The preliminary discussion in the study background examines the applications of machine learning techniques to the email spam filtering process of the leading internet service providers (ISPs) like Gmail, Yahoo and Outlook emails spam filters. Discussion on general email spam filtering process, and the various efforts by different researchers in combating spam through the use machine learning techniques was done. Our review compares the strengths and drawbacks of existing machine learning approaches and the open research problems in spam filtering. We recommended deep leaning and deep adversarial learning as the future techniques that can effectively handle the menace of spam emails.
Heliyon
The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers a... more The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers are some of the reasons for their high popularity and acceptance for control in process industries around the world today. Tuning of PID control parameters has been a field of active research and still is. The primary objectives of PID control parameters are to achieve minimal overshoot in steady state response and lesser settling time. With exception of two popular conventional tuning strategies (Ziegler Nichols closed loop oscillation and Cohen-Coon's process reaction curve) several other methods have been employed for tuning. This work accords a thorough review of state-of-the-art and classical strategies for PID controller parameters tuning using metaheuristic algorithms. Methods appraised are categorized into classical and metaheuristic optimization methods for PID parameters tuning purposes. Details of some metaheuristic algorithms, methods of application, equations and implementation flowcharts/algorithms are presented. Some open problems for future research are also presented. The major goal of this work is to proffer a comprehensive reference source for researchers and scholars working on PID controllers.
The measurement of temperature, relative humidity and light intensity remotely by using the senso... more The measurement of temperature, relative humidity and light intensity remotely by using the sensor is not only important in weather monitoring but also crucial for many other applications such as agriculture and industrial processes. This study proposed a remote weather monitoring system that is based on Arduino Uno Microcontroller that have the ability to monitor, measure and display the temperature, relative humidity and light intensity of the atmosphere, using analogue and digital components. The analogue outputs of the sensors are connected to a microcontroller through an ADC for digital signal conversion and data logging. An LCD display is also connected to the microcontroller to display the measurement. For analysis and archiving purposes, the data can be transferred over GSM and receiver section to a mobile phone. The device has many advantages compared to other weather monitoring system in terms of its smaller size, on-device display, low cost and portability. The major stre...
This study presents a report of our research work on the design, construction and testing of a ce... more This study presents a report of our research work on the design, construction and testing of a cell phone detector. It has become obvious that blocking or jamming of cell phone signals is difficult, expensive, and/or illegal in many situations. A more practical means of controlling cell phones involves detecting their RF signals, followed by confiscation or other intervention. With this, a cell phone detector is a device designed to detect the presence of a cell phone within a certain range of vicinity (from a distance of one anda-half metres.). Our aim is to design a cell phone detector that can be used to prevent the use of mobile phones in examination halls, confidential rooms, banks, petrol filling stations, military intelligent gathering etc. We made use of two signal detectors each with a dipole antenna, choke, and diode. Each dipole antenna is tuned to 900MHz. When the antennas resonate at 900 MHz a charge is induced in the inductor. A diode then demodulates the signal, which...
Illumination of Artificial Intelligence in Cybersecurity and Forensics, 2022
Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from... more Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from large audience around the world. Some application areas include forensics, cyber security and intelligent monitoring. Face recognition attendance system serves as a perfect substitute for the conventional attendance system in organizations and classrooms. The challenges associated with most face recognition techniques is inability to detect faces in situations such as noise, pose, facial expression, illumination, obstruction and low performance accuracy. This necessitated the development of more robust and efficient face recognition systems that will overcome the drawbacks associated with conventional techniques. This paper proposed a parallel faces recognition attendance system based on Convolutional Neural Network a branch of artificial intelligence and OpenCV. Experimental results proved the effectiveness of the proposed technique having shown good performance with recognition accuracy of about 98%, precision of 96% and a recall of 0.96. This demonstrates that the proposed method is a promising facial recognition technology.
Illumination of Artificial Intelligence in Cybersecurity and Forensics
Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from... more Face recognition which is a sub-discipline of computer vision is gaining a lot of attraction from large audience around the world. Some application areas include forensics, cyber security and intelligent monitoring. Face recognition attendance system serves as a perfect substitute for the conventional attendance system in organizations and classrooms. The challenges associated with most face recognition techniques is inability to detect faces in situations such as noise, pose, facial expression, illumination, obstruction and low performance accuracy. This necessitated the development of more robust and efficient face recognition systems that will overcome the drawbacks associated with conventional techniques. This paper proposed a parallel faces recognition attendance system based on Convolutional Neural Network a branch of artificial intelligence and OpenCV. Experimental results proved the effectiveness of the proposed technique having shown good performance with recognition accuracy of about 98%, precision of 96% and a recall of 0.96. This demonstrates that the proposed method is a promising facial recognition technology.
The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers a... more The simplicity, transparency, reliability, high efficiency and robust nature of PID controllers are some of the reasons for their high popularity and acceptance for control in process industries around the world today. Tuning of PID control parameters has been a field of active research and still is. The primary objectives of PID control parameters are to achieve minimal overshoot in steady state response and lesser settling time. With exception of two popular conventional tuning strategies (Ziegler Nichols closed loop oscillation and Cohen-Coon's process reaction curve) several other methods have been employed for tuning. This work accords a thorough review of state-of-the-art and classical strategies for PID controller parameters tuning using metaheuristic algorithms. Methods appraised are categorized into classical and metaheuristic optimization methods for PID parameters tuning purposes. Details of some metaheuristic algorithms, methods of application, equations and implementation flowcharts/algorithms are presented. Some open problems for future research are also presented. The major goal of this work is to proffer a comprehensive reference source for researchers and scholars working on PID controllers.
Peer-to-Peer (P2P) applications are bandwidth-heavy and lead to network congestion. The masquerad... more Peer-to-Peer (P2P) applications are bandwidth-heavy and lead to network congestion. The masquerading nature of P2P traffic makes conventional methods of its identification futile. In order to manage and control P2P traffic efficiently preferably in the network, it is necessary to identify such traffic online and accurately. This paper proposes a technique for online P2P identification based on traffic events signatures. The experimental results show that it is able to identify P2P traffic on the fly with an accuracy of 97.7%, precision of 98% and recall of 99.2%.
Jurnal Teknologi, 2015
Malware is a computer security problem that can morph to evade traditional detection methods base... more Malware is a computer security problem that can morph to evade traditional detection methods based on known signature matching. Since new malware variants contain patterns that are similar to those in observed malware, machine learning techniques can be used to identify new malware. This work presents a comparative study of several feature selection methods with four different machine learning classifiers in the context of static malware detection based on n-grams analysis. The result shows that the use of Principal Component Analysis (PCA) feature selection and Support Vector Machines (SVM) classification gives the best classification accuracy using a minimum number of features.
The susceptible characteristics of email spams allow them to undergo changes that can make them t... more The susceptible characteristics of email spams allow them to undergo changes that can make them to easily evade spam filters. This necessitates the need to develop more effective spam filters. Machine learning approaches have proved to be an efficient method for solving the problem of several spam emails wreaking havoc on email users. The conventional techniques of spam filtering like black lists and white lists (using domains, IP addresses, mailing addresses, etc.) have not been able to effectively curb the hazards posed by spam emails. In this paper, we applied the Logistic Model Tree machine learning algorithm for efficient classification of email spam messages. The aim of this study is to develop an email spam filter with superior prediction accuracy and fewer number of features. From the Enron public dataset consisting of 5,180 emails of both ham, spam, and normal emails, some features were extracted and used by the Logistic Model Tree Induction algorithm. Our technique has a classification accuracy of 99.305%, very low false positive rate (0.05), and very high true positive rate of 0.995. All experiments are conducted on WEKA data mining and machine learning simulation environment.
PROPORTIONAL-INTEGRAL-DERIVATIVE (PID) CONTROLLER TUNING FOR AN INVERTED PENDULUM USING PARTICLE SWARM OPTIMISATION (PSO) ALGORITHM , 2018
Linear control systems can be easily tuned using conventional tuning techniques such as the Ziegl... more Linear control systems can be easily tuned using conventional tuning techniques such as the Ziegler-Nichols and Cohen-Coon tuning formulae. Empirical studies have found that these conventional tuning methods result in an unsatisfactory control performance when they are used for industrial processes. It is for this reason that control practitioners often prefer to tune most nonlinear systems using trial and error tuning, or intuitive tuning. A need therefore exists for the development of a suitable automatic tuning technique that is applicable for a wide range of control processes that do not respond satisfactorily to conventional tuning. The balancing of an inverted pendulum by moving a cart along a horizontal track is a classic problem in the area of control. The encouraging results obtained from the simulation of the PID Controller parameters-tuning using the PSO when compared with the performance of PID and Ziegler-Nichols (Z-N) makes PSO-PID a good addition to solving PID Controller tuning problems using metaheuristic techniques as will reduce the time and cost of tuning these parameters and improve the overall system performance.
Automatic Tuning of Proportional Integral Derivative Controller using Genetic Algorithm, 2018
The application of intelligent approaches for tuning the gains of Proportional-Integral-Derivativ... more The application of intelligent approaches for tuning the gains of Proportional-Integral-Derivative (PID) controller parameters has been growing recently. The flexibility ability of evolutionary procedures have elevated its acceptability for adjusting the gains PID controllers. This work presents an automatic strategy for adjusting the gains of a PID controller parameters of systems with scarce initial information and integrative and unstable dynamics, using evolutionary Genetic Algorithm (GA), an Evolutionary Computation (EC) technique strategy. The advantages of the proposed approach were highlighted through the comparison with classical Ziegler-Nichols closed loop approach. Experiments with different processes indicate that the gains obtained through genetic algorithms may provide better responses than those obtained by the classical Ziegler-Nichols approach in terms of time domain specification and performance indices.
Heliyon (ISI & Scopus indexed), 2019
The upsurge in the volume of unwanted emails called spam has created an intense need for the deve... more The upsurge in the volume of unwanted emails called spam has created an intense need for the development of more dependable and robust antispam filters. Machine learning methods of recent are being used to successfully detect and filter spam emails. We present a systematic review of some of the popular machine learning based email spam filtering approaches. Our review covers survey of the important concepts, attempts, efficiency, and the research trend in spam filtering. The preliminary discussion in the study background examines the applications of machine learning techniques to the email spam filtering process of the leading internet service providers (ISPs) like Gmail, Yahoo and Outlook emails spam filters. Discussion on general email spam filtering process, and the various efforts by different researchers in combating spam through the use machine learning techniques was done. Our review compares the strengths and drawbacks of existing machine learning approaches and the open research problems in spam filtering. We recommended deep leaning and deep adversarial learning as the future techniques that can effectively handle the menace of spam emails.
Heliyon, 2019
The upsurge in the volume of unwanted emails called spam has created an intense need for the deve... more The upsurge in the volume of unwanted emails called spam has created an intense need for the development of more dependable and robust antispam filters. Machine learning methods of recent are being used to successfully detect and filter spam emails. We present a systematic review of some of the popular machine learning based email spam filtering approaches. Our review covers survey of the important concepts, attempts, efficiency, and the research trend in spam filtering. The preliminary discussion in the study background examines the applications of machine learning techniques to the email spam filtering process of the leading internet service providers (ISPs) like Gmail, Yahoo and Outlook emails spam filters. Discussion on general email spam filtering process, and the various efforts by different researchers in combating spam through the use machine learning techniques was done. Our review compares the strengths and drawbacks of existing machine learning approaches and the open research problems in spam filtering. We recommended deep leaning and deep adversarial learning as the future techniques that can effectively handle the menace of spam emails.