Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051633
Saba Ibrahim David, S. Bashir, Mohammed D. Abdulmalik
Several alarming health challenges are urging medical experts and practitioners to research and develop new approaches to diagnose, detect and control the early spread of deadly diseases. One of the most challenging is Coronavirus Infection (Covid-19). Models have been proposed to detect and diagnose early infection of the virus to attain proper precautions against the Covid-19 virus. However, some researchers adopt parameter optimization to attain better accuracy on the Chest X-ray images of covid-19 and other related diseases. Hence, this research work adopts a hybridized cascaded feature extraction technique (Local Binary Pattern LBP and Histogram of Oriented Gradients HOG) and Convolutional Neural Network CNN for the deep learning classification model. The merging of LBP and HOG feature extraction significantly improved the performance level of the deep-learning CNN classifier. As a result, 95% accuracy, 92% precision, and 93% recall are attained by the proposed model.
{"title":"A Concept-Based Review on Generative Adversarial Network for Generating Super Resolution Medical Image Using SWOT Analysis","authors":"Saba Ibrahim David, S. Bashir, Mohammed D. Abdulmalik","doi":"10.1109/ITED56637.2022.10051633","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051633","url":null,"abstract":"Several alarming health challenges are urging medical experts and practitioners to research and develop new approaches to diagnose, detect and control the early spread of deadly diseases. One of the most challenging is Coronavirus Infection (Covid-19). Models have been proposed to detect and diagnose early infection of the virus to attain proper precautions against the Covid-19 virus. However, some researchers adopt parameter optimization to attain better accuracy on the Chest X-ray images of covid-19 and other related diseases. Hence, this research work adopts a hybridized cascaded feature extraction technique (Local Binary Pattern LBP and Histogram of Oriented Gradients HOG) and Convolutional Neural Network CNN for the deep learning classification model. The merging of LBP and HOG feature extraction significantly improved the performance level of the deep-learning CNN classifier. As a result, 95% accuracy, 92% precision, and 93% recall are attained by the proposed model.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126737829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051260
Umar Abdulkadir, V. O. Waziri, J. Alhassan, I. Ismaila
The electronic health (e-health) systems support a range of electronic devices, wireless links, transmission and storage of data. E-health systems allows communication through a gateway (or central point) in the cloud. Health professionals and teams utilize e-health systems to perform virtual consultations to patients, remote treatment or diagnosis. The success story of e-health systems is often met with problems including: insecure channels of communication, eavesdropping of messages across channels by adversary, profound insider attacks on private information on servers, and healthcare services disruptions. Cryptography or encryption algorithms have been considered as capable of overcoming the privacy and security problems of electronic medical records management. However, certain issues persist with cryptographic-based schemes such as slow processing speed, weak security mechanisms, high computational overheads, and weak public-private keys. In this paper, a lattice-based cryptography, Ring Learning With Error (RLWE) encryption is used to propose a privacy scheme for EMR in cloud environment. The choice of RLWE is due to its provable hardness among conventional lattice problem. The outcomes revealed that, the proposed encryption scheme outperformed comparable asymmetric schemes in terms of elapsed time (0.04sec) against ECDSA (1.11sec), ECC (16.62sec), and RSA (37.95sec). Again, the public key size was better for RLWE (32-bits) only after ECDSA (10-bits), against ECC (97-bits), and RSA (191-bits). Similarly, the private key size for ECC (9-bits) was only better than RLWE(10-bits), against ECDSA (58-bits), and RSA (687-bits) respectively. The proposed encryption scheme is time and memory-efficient; and holds promise for EMRs privacy.
{"title":"Ring Learning With Error-Based Encryption Scheme for the Privacy of Electronic Health Records Management","authors":"Umar Abdulkadir, V. O. Waziri, J. Alhassan, I. Ismaila","doi":"10.1109/ITED56637.2022.10051260","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051260","url":null,"abstract":"The electronic health (e-health) systems support a range of electronic devices, wireless links, transmission and storage of data. E-health systems allows communication through a gateway (or central point) in the cloud. Health professionals and teams utilize e-health systems to perform virtual consultations to patients, remote treatment or diagnosis. The success story of e-health systems is often met with problems including: insecure channels of communication, eavesdropping of messages across channels by adversary, profound insider attacks on private information on servers, and healthcare services disruptions. Cryptography or encryption algorithms have been considered as capable of overcoming the privacy and security problems of electronic medical records management. However, certain issues persist with cryptographic-based schemes such as slow processing speed, weak security mechanisms, high computational overheads, and weak public-private keys. In this paper, a lattice-based cryptography, Ring Learning With Error (RLWE) encryption is used to propose a privacy scheme for EMR in cloud environment. The choice of RLWE is due to its provable hardness among conventional lattice problem. The outcomes revealed that, the proposed encryption scheme outperformed comparable asymmetric schemes in terms of elapsed time (0.04sec) against ECDSA (1.11sec), ECC (16.62sec), and RSA (37.95sec). Again, the public key size was better for RLWE (32-bits) only after ECDSA (10-bits), against ECC (97-bits), and RSA (191-bits). Similarly, the private key size for ECC (9-bits) was only better than RLWE(10-bits), against ECDSA (58-bits), and RSA (687-bits) respectively. The proposed encryption scheme is time and memory-efficient; and holds promise for EMRs privacy.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121341149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051591
T. Omodunbi, G. E. Alilu, Rhoda Ikono
Drug Recommender Systems (DRSs) which are information systems that recommend drug(s) to users based on their symptoms and other factors, have been gaining a lot of research interest recently. These systems help both patients and medical personnel to determine and decide on the best drug prescription with combination to use. Different approaches ranging from machine learning, statistical methods, artificial intelligent, data mining Ontology, matrix factorization etc. have been applied to build a robust DRSs. This paper presents the review of the state-of-the-art algorithms applied to DRS and also gives a summary of a proposed DRS. Findings shows that most recent DRSs use Machine Learning based algorithms such as clustering, sentiment analysis, association rule mining, stacked Artificial Neural Networks, etc., for recommendations. Just a few use other approaches like the Ontology based approach. The DRS reviewed did not take into consideration the feedback from users and most did not consider the peculiarities of patients such as age and pre-existing medical conditions (like allergies and pregnancy) etc, Based on some of the limitations identified, we propose a DRS that will recommend appropriate drugs by considering patients peculiarities. It will also incorporate a feedback mechanism in order to strengthen the knowledge base of the system.
{"title":"Drug Recommender Systems: A Review of State-of-the-Art Algorithms","authors":"T. Omodunbi, G. E. Alilu, Rhoda Ikono","doi":"10.1109/ITED56637.2022.10051591","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051591","url":null,"abstract":"Drug Recommender Systems (DRSs) which are information systems that recommend drug(s) to users based on their symptoms and other factors, have been gaining a lot of research interest recently. These systems help both patients and medical personnel to determine and decide on the best drug prescription with combination to use. Different approaches ranging from machine learning, statistical methods, artificial intelligent, data mining Ontology, matrix factorization etc. have been applied to build a robust DRSs. This paper presents the review of the state-of-the-art algorithms applied to DRS and also gives a summary of a proposed DRS. Findings shows that most recent DRSs use Machine Learning based algorithms such as clustering, sentiment analysis, association rule mining, stacked Artificial Neural Networks, etc., for recommendations. Just a few use other approaches like the Ontology based approach. The DRS reviewed did not take into consideration the feedback from users and most did not consider the peculiarities of patients such as age and pre-existing medical conditions (like allergies and pregnancy) etc, Based on some of the limitations identified, we propose a DRS that will recommend appropriate drugs by considering patients peculiarities. It will also incorporate a feedback mechanism in order to strengthen the knowledge base of the system.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"7 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113941679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051624
Segun Akintunde, O. R. Vincent, Oreoluwa Tinubu
The electronic auction system has emerged as one of the leading electronic commerce platforms where auctioneers and bidders converge for transactions. With the Internet's proliferation, e-commerce systems' functionalities have greatly been enhanced. Unfortunately, fraudulent activities increasingly hamper the credibility of online auction systems. Shill Bidding is one of the prominent frauds in the e-auction. Due to its similarity with normal bidding behaviors, it is challenging to detect as legitimate bidders could be categorized as fraudulent and vice versa. Several authentic auctioneers have been cheated during online bidding systems because of the diverse ways shill bidding is being perpetrated. It is, therefore, essential to improve the credibility of online bidding systems. In this study, we proposed a machine learning-based prediction system that determines the likelihood of a customer/seller perpetrating shill bidding. Upon deployment, the proposed system would prevent shill bidders from participating in a car action system. A vote ensemble model is trained with public data of 12 attributes comprising Random Forest, Decision Tree, Multi-layer Perceptron (MLP), and Sequential Maximal Optimization (SMO) base learners. An object-oriented Python programming language is used to implement the shill bidding predictive system. Experimental results show the excellence of the proposed system using metrics such as Precision, Accuracy, Recall, F1-score, and Misclassification error.
{"title":"An Ensemble-based Shill Billing Prediction Model in Car Auction System","authors":"Segun Akintunde, O. R. Vincent, Oreoluwa Tinubu","doi":"10.1109/ITED56637.2022.10051624","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051624","url":null,"abstract":"The electronic auction system has emerged as one of the leading electronic commerce platforms where auctioneers and bidders converge for transactions. With the Internet's proliferation, e-commerce systems' functionalities have greatly been enhanced. Unfortunately, fraudulent activities increasingly hamper the credibility of online auction systems. Shill Bidding is one of the prominent frauds in the e-auction. Due to its similarity with normal bidding behaviors, it is challenging to detect as legitimate bidders could be categorized as fraudulent and vice versa. Several authentic auctioneers have been cheated during online bidding systems because of the diverse ways shill bidding is being perpetrated. It is, therefore, essential to improve the credibility of online bidding systems. In this study, we proposed a machine learning-based prediction system that determines the likelihood of a customer/seller perpetrating shill bidding. Upon deployment, the proposed system would prevent shill bidders from participating in a car action system. A vote ensemble model is trained with public data of 12 attributes comprising Random Forest, Decision Tree, Multi-layer Perceptron (MLP), and Sequential Maximal Optimization (SMO) base learners. An object-oriented Python programming language is used to implement the shill bidding predictive system. Experimental results show the excellence of the proposed system using metrics such as Precision, Accuracy, Recall, F1-score, and Misclassification error.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124921905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051449
Maudlyn I. Victor-Ikoh, B. R. Japheth
Due to tragic losses caused by preventable home fires, it is imperative to have technological advancement toward more fire safety measures. Cooking fires are one of the most prevalent types of house fires, accounting for more of all residential fires; and cooking left unattended, is by far the most common cause of home fires. This paper proposes an early detection of home fire outbreaks by sound parameter analysis. The sounds produced by cooking - boiling, frying, simmering is a result of the dynamics of the cooking components. By automatically detecting the state of cooking liquids by their sounds, such changes as occurring can be used to diagnose the condition of the cooking item before a possible onset of fire. This work made use of water, a common cooking liquid, for an empirical study. Python programming with google colab was the software tool used to display and analyze key parameters obtained from sound signals of boiling water; and sound signals of water that have boiled but still heated until the water dried out completely (heated water-dried-out). The analysis made in the time-domain view showed a marked difference in sound signal between boiling water and a heated water-dried-out. Relatively, the signal levels (amplitude) of boiling water are higher than that of a heated water-dried-out. Hence, we conclude that sounds made from cooking, if collected by embedded systems and analysed in real-time, is one safety measure to averting the incidences of home fire outbreak.
{"title":"Sound Parameter Analysis for Early Detection and Prevention of Home Fire Outbreak","authors":"Maudlyn I. Victor-Ikoh, B. R. Japheth","doi":"10.1109/ITED56637.2022.10051449","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051449","url":null,"abstract":"Due to tragic losses caused by preventable home fires, it is imperative to have technological advancement toward more fire safety measures. Cooking fires are one of the most prevalent types of house fires, accounting for more of all residential fires; and cooking left unattended, is by far the most common cause of home fires. This paper proposes an early detection of home fire outbreaks by sound parameter analysis. The sounds produced by cooking - boiling, frying, simmering is a result of the dynamics of the cooking components. By automatically detecting the state of cooking liquids by their sounds, such changes as occurring can be used to diagnose the condition of the cooking item before a possible onset of fire. This work made use of water, a common cooking liquid, for an empirical study. Python programming with google colab was the software tool used to display and analyze key parameters obtained from sound signals of boiling water; and sound signals of water that have boiled but still heated until the water dried out completely (heated water-dried-out). The analysis made in the time-domain view showed a marked difference in sound signal between boiling water and a heated water-dried-out. Relatively, the signal levels (amplitude) of boiling water are higher than that of a heated water-dried-out. Hence, we conclude that sounds made from cooking, if collected by embedded systems and analysed in real-time, is one safety measure to averting the incidences of home fire outbreak.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122534267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051387
Chigoziem Andrew Iheanacho, O. R. Vincent
A fascinating area with many applications is that of food item recognition from images. Food recognition is becoming more important in our daily lives because it plays a major part in health-related issues. In this study, a method for categorizing food-related photos using convolutional neural networks has been provided. Convolutional neural networks, in contrast to conventional artificial neural networks, are able to estimate the score function directly from picture pixels. A tensor of outputs is generated by a 2D convolution layer's em ployment of a convolution kernel, which is convolved with the l ayer's input. There are numerous such layers, and the results are concatenated in portions to achieve the final tensor of outputs. The data is also processed using the Max-Pooling function, and the features that result from that processing are employed to train the network. The accuracy of the suggested technique again for classes with in FOOD-101 dataset is 85.78 percent.
{"title":"Classification and recommendation of food intake in West Africa for healthy diet using Deep Learning","authors":"Chigoziem Andrew Iheanacho, O. R. Vincent","doi":"10.1109/ITED56637.2022.10051387","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051387","url":null,"abstract":"A fascinating area with many applications is that of food item recognition from images. Food recognition is becoming more important in our daily lives because it plays a major part in health-related issues. In this study, a method for categorizing food-related photos using convolutional neural networks has been provided. Convolutional neural networks, in contrast to conventional artificial neural networks, are able to estimate the score function directly from picture pixels. A tensor of outputs is generated by a 2D convolution layer's em ployment of a convolution kernel, which is convolved with the l ayer's input. There are numerous such layers, and the results are concatenated in portions to achieve the final tensor of outputs. The data is also processed using the Max-Pooling function, and the features that result from that processing are employed to train the network. The accuracy of the suggested technique again for classes with in FOOD-101 dataset is 85.78 percent.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126980839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051420
Mustapha Deji Dere, Roshidat Oluwabukola Dere, Adewale Adesina, A. Yauri
Communication is essential for individuals to convey feelings and emotions. Persons with speech impairment, on the other hand, find it challenging to share their thoughts, especially during medical emergencies. In this study, we propose a low-cost embedded device that allows individuals with a speech impairment to communicate during medical emergencies. A 1D-convolution neural network (CNN) model extracting features from an onboard inertial measurement unit (IMU) for the classification of selected American sign language (ASL) medical emergencies word. The model was trained offline before deployment to a resource-constrained embedded device for real-time ASL word classification. A pilot test on two volunteers resulted in an offline accuracy of 91.2% and an average online accuracy of 92% for the 8-bit optimized model. The results demonstrate the feasibility to aid individuals with a speech impairment to communicate during medical emergencies. Furthermore, an extended application of the proposed design is for the intuitive learning of sign languages using artificial intelligence.
{"title":"SmartCall: A Real-time, Sign Language Medical Emergency Communicator","authors":"Mustapha Deji Dere, Roshidat Oluwabukola Dere, Adewale Adesina, A. Yauri","doi":"10.1109/ITED56637.2022.10051420","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051420","url":null,"abstract":"Communication is essential for individuals to convey feelings and emotions. Persons with speech impairment, on the other hand, find it challenging to share their thoughts, especially during medical emergencies. In this study, we propose a low-cost embedded device that allows individuals with a speech impairment to communicate during medical emergencies. A 1D-convolution neural network (CNN) model extracting features from an onboard inertial measurement unit (IMU) for the classification of selected American sign language (ASL) medical emergencies word. The model was trained offline before deployment to a resource-constrained embedded device for real-time ASL word classification. A pilot test on two volunteers resulted in an offline accuracy of 91.2% and an average online accuracy of 92% for the 8-bit optimized model. The results demonstrate the feasibility to aid individuals with a speech impairment to communicate during medical emergencies. Furthermore, an extended application of the proposed design is for the intuitive learning of sign languages using artificial intelligence.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132919038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051504
E. A. Jiya, F. Ibikunle, Ilesanmi Banjo Oluwafemi, Aaron Banji Adedayo, Akorede Kola-Junior, Kareem Sunday Babatunde
Communications technologies are becoming the driving force behind social, economic, and political advancements in recent times. Fifth-generation (5G) cellular networks are a revolutionary idea that connects a wide range of machines and devices in a different way than earlier technologies. The design and implementation of the many technical models, on the other hand, have resulted in intolerable signal interference. The total network performance has been considerably harmed by these vulnerable interferences. Communications system interference is an unwelcome annoyance. A number of these interferences have grown to be a significant source of barriers to increased cell throughput. The development of effective interference control strategies is a major enabler given the rise in interference in cellular networks. Additionally, as networks get denser, interference mitigation becomes more difficult. Despite this, interference management has the potential to increase the efficiency of the spectrum used by present and future wireless devices. To combat interference in a broad category of wireless networks, new paradigms for interference control have recently arisen. This review paper looks at the concerns of interferences that have been discovered and researched in various network topologies and techniques. It also pays attention to recent advances in its management: Advanced receiver, Joint Scheduling, and network information theory among others. Potential advantages of each interference management technique are illustrated, and it is proven that if 5G cellular networks use intricate joint scheduling, the advantages of sophisticated receivers can be effectively utilized.
{"title":"Overview of Interference Management Techniques in 5G Cellular Networks","authors":"E. A. Jiya, F. Ibikunle, Ilesanmi Banjo Oluwafemi, Aaron Banji Adedayo, Akorede Kola-Junior, Kareem Sunday Babatunde","doi":"10.1109/ITED56637.2022.10051504","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051504","url":null,"abstract":"Communications technologies are becoming the driving force behind social, economic, and political advancements in recent times. Fifth-generation (5G) cellular networks are a revolutionary idea that connects a wide range of machines and devices in a different way than earlier technologies. The design and implementation of the many technical models, on the other hand, have resulted in intolerable signal interference. The total network performance has been considerably harmed by these vulnerable interferences. Communications system interference is an unwelcome annoyance. A number of these interferences have grown to be a significant source of barriers to increased cell throughput. The development of effective interference control strategies is a major enabler given the rise in interference in cellular networks. Additionally, as networks get denser, interference mitigation becomes more difficult. Despite this, interference management has the potential to increase the efficiency of the spectrum used by present and future wireless devices. To combat interference in a broad category of wireless networks, new paradigms for interference control have recently arisen. This review paper looks at the concerns of interferences that have been discovered and researched in various network topologies and techniques. It also pays attention to recent advances in its management: Advanced receiver, Joint Scheduling, and network information theory among others. Potential advantages of each interference management technique are illustrated, and it is proven that if 5G cellular networks use intricate joint scheduling, the advantages of sophisticated receivers can be effectively utilized.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133424824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051398
A. Aniedu, Sandra C. Nwokoye, Chukwunenye S. Okafor, Kingley U. Anyanwu
Non-technical losses (NTL) have rightly been identified as losses arising from energy generated but unaccounted for. They basically occur because of theft and other fraudulent activities surrounding illegal consumption of energy. This loss accounts for massive loss in revenue to utility companies and government and there has been concerted efforts to mitigate such abnormalities thereby saving cost. Although advanced metering infrastructure (AMI) incorporating smart meters have provided some basic organization around management of smart grids and monitoring usage information, it still fails to accurately detect NTL. In this paper therefore a solution to NTL is presented involving the deployment of support vector machines (SVM) as an underlying classifier and integrated with a real-time application interface termed Electricity Usage Classifier interface (ELUCI) for monitoring and pre-processing instantaneous electricity usage time-series data. With this configuration, a classification accuracy of 98.48% was achieved which was a 17.02% improvement over the initial classification models and with a root mean squared error (RMSE) of 0.0894 and an f-measure of 0.979. The developed system can assist governments and utilities to actively monitor and track down energy theft thereby improving revenue and avoiding economic wastages accruing from these activities.
{"title":"Modelling Machine Learning-based Energy Loss Detection and Monitoring System for Advanced Metering Infrastructure","authors":"A. Aniedu, Sandra C. Nwokoye, Chukwunenye S. Okafor, Kingley U. Anyanwu","doi":"10.1109/ITED56637.2022.10051398","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051398","url":null,"abstract":"Non-technical losses (NTL) have rightly been identified as losses arising from energy generated but unaccounted for. They basically occur because of theft and other fraudulent activities surrounding illegal consumption of energy. This loss accounts for massive loss in revenue to utility companies and government and there has been concerted efforts to mitigate such abnormalities thereby saving cost. Although advanced metering infrastructure (AMI) incorporating smart meters have provided some basic organization around management of smart grids and monitoring usage information, it still fails to accurately detect NTL. In this paper therefore a solution to NTL is presented involving the deployment of support vector machines (SVM) as an underlying classifier and integrated with a real-time application interface termed Electricity Usage Classifier interface (ELUCI) for monitoring and pre-processing instantaneous electricity usage time-series data. With this configuration, a classification accuracy of 98.48% was achieved which was a 17.02% improvement over the initial classification models and with a root mean squared error (RMSE) of 0.0894 and an f-measure of 0.979. The developed system can assist governments and utilities to actively monitor and track down energy theft thereby improving revenue and avoiding economic wastages accruing from these activities.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115177387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051202
R. O. Oveh, G. Aziken
Social engineering is a security concern that can be mitigated most efficiently from the most neglected aspect in the security ecosystem which is humans. Technological advancement focused at devices cannot prevent psychological human manipulation. This paper sort to determine the security practices and disposition of humans in a situation of vulnerability to social engineering attacks. Interview was used for data collection. 70 persons were interviewed using structured questions. The result showed that being a former victim of social engineering activity is not enough to prevent being another victim which is a consequence of security practices by the human. It is recommended that security practices against social engineering should be institutionalised in everyday human living.
{"title":"Mitigating Social Engineering Attack: A Focus on the Weak Human Link","authors":"R. O. Oveh, G. Aziken","doi":"10.1109/ITED56637.2022.10051202","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051202","url":null,"abstract":"Social engineering is a security concern that can be mitigated most efficiently from the most neglected aspect in the security ecosystem which is humans. Technological advancement focused at devices cannot prevent psychological human manipulation. This paper sort to determine the security practices and disposition of humans in a situation of vulnerability to social engineering attacks. Interview was used for data collection. 70 persons were interviewed using structured questions. The result showed that being a former victim of social engineering activity is not enough to prevent being another victim which is a consequence of security practices by the human. It is recommended that security practices against social engineering should be institutionalised in everyday human living.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115702505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：