International Journal of Advances in Computer Science and Technology, 2024
Strong cybersecurity solutions are becoming more and more important as Internet of Things (IoT) t... more Strong cybersecurity solutions are becoming more and more important as Internet of Things (IoT) technology integration in healthcare settings develops. This study offers a method for feature extraction, selection, and attack classification by fusing the discriminative capacity of feedforward neural networks (FNNs) with the adaptability of fuzzy logic systems. In delicate healthcare database of IoT wearable devices, to reduce false alarm and guaranteeing intrusion detection dependability are the main priorities. The suggested method uses a feature extraction, selection technique, training and testing based on FNN, which allows the model to adjust to the dynamic and varied character of medical data. During the assessment stage, a dataset including a range of healthcare IoT scenarios, including different kinds of attacks, is used to train and evaluate the model, the ToN_IoT dataset was used. Fuzzy logic improves the system's resilience in identifying pertinent features by managing uncertainties and imprecise input. Fuzzy logic is one of the best technique for handling uncertainty, its linguistic representation and rule reasoning helps in better identification and classification. The findings indicate a noteworthy decrease in the frequency of false alarms when juxtaposed with conventional intrusion detection systems. Results obtained from the model are 99.2, 98.8, 99.5, 99.1 & 0.008 for accuracy, precision, recall, F1-Score and False alarm respectively. Promising outcomes in protecting IoT healthcare environments are demonstrated by the suggested system, opening the door to better patient data privacy and system resilience against cyberattacks.
Fire disaster on oil and gas platform has caused serious injuries to people, loss of lives and da... more Fire disaster on oil and gas platform has caused serious injuries to people, loss of lives and damages to properties. This Research work introduces the use of swarm methods (Artificial Bee Colony (ABC) and Particle Swarm Optimization (PSO)) for predicting fire disaster on oil and gas platform caused by electrical faults in Nigeria. Simulation results shows that during the first Experiment (Exp. 1), using different fault resistance, a constant colony size or population size of 20 (area of search) and max Cycles of 5 (maximum number of iteration), at 0.3 ohm-0.0 ohm (fault resistance), all faults will show danger and should be attended to on time before it will lead to fire outbreak for both the ABC and PSO method. For the second experiment, ABC technique results show that from 0.4 ohm-0.00 ohm fault resistance, all faults will show danger and should be attended to on time before it will lead to fire disaster while PSO method results prove that from 0.35 ohm-0.00 ohm fault resistance all faults will show danger, which will lead to fire disaster using max iteration of 50 and population size of 100. So using Particle swarm optimization (PSO) model is quite difficult because of the use of many parameters while Artificial Bee Colony (ABC) model, gives you a more stable result and it uses fewer parameters.
The importance of oil and gas pipeline systems cannot be over emphasized as it remains a reliable... more The importance of oil and gas pipeline systems cannot be over emphasized as it remains a reliable means of transporting oil and gas in Nigeria for the sustenance of Nigeria economy. The failure of these Pipelines can cause environmental damage due to oil spillage as well as economic losses due to productions interruption. In acknowledgement of the importance of the pipeline system the researcher embarked on an action research on the system. This research work aims at developing a predictive decision support system that will support organizational decisions in problem solving using an action research approach. Since the whole purpose of action research is to determine simultaneously an understanding of the social system and the best opportunities for change in any system, the researcher in collaboration with the oil and gas domain operators Shell Petroleum Development Company of Nigeria (SPDC) employs the Action Research approach to studying the kind of activities that goes on around the pipeline environment and collate data of such activities to help avert or minimize repetitive attack to pipeline facility by vandals and the likes by provide an effective and anticipatory heavy security system using artificial neural network Artificial Intelligence technology.
European Journal of Computer Science and Information Technology, 2019
This Research work introduces Particle swarm optimization technique for predicting fire outbreaks... more This Research work introduces Particle swarm optimization technique for predicting fire outbreaks in industrial environment. The Particle swarm optimization (PSO) method is a swarmbased heuristic, which mimics the foraging behavior of bird flocks. Two Experiments were conducted, the first Experiment (Exp. 1) using 26 different test simulations was performed, using different fault resistance, a constant population size of 20 and max iteration of 5. It shows that when the fault resistance is between 0.3 ohm-0.0 ohm, there will be likelihood of danger occurring among all faults at the same time, and none of the faults will be normal. While the second Experiment (Exp. 2) conducted, using 26 different test simulations was performed, using different fault resistance, a constant population size of 100 and max iteration of 50, it proves that when the fault resistance is between 0.35 ohm-0.0-ohm fault resistance, there will be likelihood of danger occurring among all faults at the same time. Results prove that PSO can be used to predict fire outbreak caused by electrical faults.
International Journal of Computer Applications , 2018
In Nigeria, there have been increases in damages due to fire outbreaks particularly in industrial... more In Nigeria, there have been increases in damages due to fire outbreaks particularly in industrial and busy environments. Fire outbreak has caused serious injuries to people, loss of lives, damage of properties etc. Methods usually used in predicting fire outbreaks are fire alarm, flame detection, smoke detection algorithm, real-time fire, flame detection etc. This Research work introduces an artificial bee colony heuristic for predicting fire outbreaks in industrial environment in Nigeria. The artificial bee colony heuristic is a swarm-based heuristic, which mimics the foraging behavior of a honey bee swarm. In this paper, artificial bee colony technique was used for predicting fire outbreaks caused by electrical faults. Two Experiments were conducted, the first Experiment (Exp. 1) using 26 different test simulations was performed using different fault resistance, a constant colony size of 20 (area of search) and max Cycles of 5 (maximum number of iteration). It shows that when the fault resistance is between 0.3 ohms-0.0 ohms, there will be likelihood of danger occurring among all faults at the same time, and none of the faults will be normal. While the second Experiment (Exp. 2) conducted, using 26 different test simulations was performed using different fault resistance, a constant colony size of 100 (area of search) and max Cycles of 50 (maximum number of iteration), it proves that when the fault resistance is between 0.4 ohms-0.0 ohms, there will be likelihood of danger occurring among all faults at the same time. The results also prove good performance of the predictive ABC system for average convergence at 2.25 at 26 trials and its unique capability to make multiple predictions. The system was simulated and modeled using Matlab 7.5.0(R2007b) program.
International Journal of Advances in Computer Science and Technology, 2024
Strong cybersecurity solutions are becoming more and more important as Internet of Things (IoT) t... more Strong cybersecurity solutions are becoming more and more important as Internet of Things (IoT) technology integration in healthcare settings develops. This study offers a method for feature extraction, selection, and attack classification by fusing the discriminative capacity of feedforward neural networks (FNNs) with the adaptability of fuzzy logic systems. In delicate healthcare database of IoT wearable devices, to reduce false alarm and guaranteeing intrusion detection dependability are the main priorities. The suggested method uses a feature extraction, selection technique, training and testing based on FNN, which allows the model to adjust to the dynamic and varied character of medical data. During the assessment stage, a dataset including a range of healthcare IoT scenarios, including different kinds of attacks, is used to train and evaluate the model, the ToN_IoT dataset was used. Fuzzy logic improves the system's resilience in identifying pertinent features by managing uncertainties and imprecise input. Fuzzy logic is one of the best technique for handling uncertainty, its linguistic representation and rule reasoning helps in better identification and classification. The findings indicate a noteworthy decrease in the frequency of false alarms when juxtaposed with conventional intrusion detection systems. Results obtained from the model are 99.2, 98.8, 99.5, 99.1 & 0.008 for accuracy, precision, recall, F1-Score and False alarm respectively. Promising outcomes in protecting IoT healthcare environments are demonstrated by the suggested system, opening the door to better patient data privacy and system resilience against cyberattacks.
Fire disaster on oil and gas platform has caused serious injuries to people, loss of lives and da... more Fire disaster on oil and gas platform has caused serious injuries to people, loss of lives and damages to properties. This Research work introduces the use of swarm methods (Artificial Bee Colony (ABC) and Particle Swarm Optimization (PSO)) for predicting fire disaster on oil and gas platform caused by electrical faults in Nigeria. Simulation results shows that during the first Experiment (Exp. 1), using different fault resistance, a constant colony size or population size of 20 (area of search) and max Cycles of 5 (maximum number of iteration), at 0.3 ohm-0.0 ohm (fault resistance), all faults will show danger and should be attended to on time before it will lead to fire outbreak for both the ABC and PSO method. For the second experiment, ABC technique results show that from 0.4 ohm-0.00 ohm fault resistance, all faults will show danger and should be attended to on time before it will lead to fire disaster while PSO method results prove that from 0.35 ohm-0.00 ohm fault resistance all faults will show danger, which will lead to fire disaster using max iteration of 50 and population size of 100. So using Particle swarm optimization (PSO) model is quite difficult because of the use of many parameters while Artificial Bee Colony (ABC) model, gives you a more stable result and it uses fewer parameters.
The importance of oil and gas pipeline systems cannot be over emphasized as it remains a reliable... more The importance of oil and gas pipeline systems cannot be over emphasized as it remains a reliable means of transporting oil and gas in Nigeria for the sustenance of Nigeria economy. The failure of these Pipelines can cause environmental damage due to oil spillage as well as economic losses due to productions interruption. In acknowledgement of the importance of the pipeline system the researcher embarked on an action research on the system. This research work aims at developing a predictive decision support system that will support organizational decisions in problem solving using an action research approach. Since the whole purpose of action research is to determine simultaneously an understanding of the social system and the best opportunities for change in any system, the researcher in collaboration with the oil and gas domain operators Shell Petroleum Development Company of Nigeria (SPDC) employs the Action Research approach to studying the kind of activities that goes on around the pipeline environment and collate data of such activities to help avert or minimize repetitive attack to pipeline facility by vandals and the likes by provide an effective and anticipatory heavy security system using artificial neural network Artificial Intelligence technology.
European Journal of Computer Science and Information Technology, 2019
This Research work introduces Particle swarm optimization technique for predicting fire outbreaks... more This Research work introduces Particle swarm optimization technique for predicting fire outbreaks in industrial environment. The Particle swarm optimization (PSO) method is a swarmbased heuristic, which mimics the foraging behavior of bird flocks. Two Experiments were conducted, the first Experiment (Exp. 1) using 26 different test simulations was performed, using different fault resistance, a constant population size of 20 and max iteration of 5. It shows that when the fault resistance is between 0.3 ohm-0.0 ohm, there will be likelihood of danger occurring among all faults at the same time, and none of the faults will be normal. While the second Experiment (Exp. 2) conducted, using 26 different test simulations was performed, using different fault resistance, a constant population size of 100 and max iteration of 50, it proves that when the fault resistance is between 0.35 ohm-0.0-ohm fault resistance, there will be likelihood of danger occurring among all faults at the same time. Results prove that PSO can be used to predict fire outbreak caused by electrical faults.
International Journal of Computer Applications , 2018
In Nigeria, there have been increases in damages due to fire outbreaks particularly in industrial... more In Nigeria, there have been increases in damages due to fire outbreaks particularly in industrial and busy environments. Fire outbreak has caused serious injuries to people, loss of lives, damage of properties etc. Methods usually used in predicting fire outbreaks are fire alarm, flame detection, smoke detection algorithm, real-time fire, flame detection etc. This Research work introduces an artificial bee colony heuristic for predicting fire outbreaks in industrial environment in Nigeria. The artificial bee colony heuristic is a swarm-based heuristic, which mimics the foraging behavior of a honey bee swarm. In this paper, artificial bee colony technique was used for predicting fire outbreaks caused by electrical faults. Two Experiments were conducted, the first Experiment (Exp. 1) using 26 different test simulations was performed using different fault resistance, a constant colony size of 20 (area of search) and max Cycles of 5 (maximum number of iteration). It shows that when the fault resistance is between 0.3 ohms-0.0 ohms, there will be likelihood of danger occurring among all faults at the same time, and none of the faults will be normal. While the second Experiment (Exp. 2) conducted, using 26 different test simulations was performed using different fault resistance, a constant colony size of 100 (area of search) and max Cycles of 50 (maximum number of iteration), it proves that when the fault resistance is between 0.4 ohms-0.0 ohms, there will be likelihood of danger occurring among all faults at the same time. The results also prove good performance of the predictive ABC system for average convergence at 2.25 at 26 trials and its unique capability to make multiple predictions. The system was simulated and modeled using Matlab 7.5.0(R2007b) program.
Uploads
Papers