Pub Date : 2022-11-01DOI: 10.1109/ITED56637.2022.10051357
A. Amusan, Yusuf Kolawole Adebakin
Railway system is a kind of transportation where passengers and goods are transported on wheeled vehicles running on rails located on tracks. This form of transportation is usually inexpensive, secure, and often the most convenient. In areas with frequent use of railway transport system, there is need to limit the accidents at the level crossing, mitigate the falling of trains on the rail due to cracks and create an excellent feedback system. The manual management of the system is inconvenient, time wasting and prone to sudden accidents. Hence in this work, an automatic railway system which includes automatic level crossing and crack detection system with an excellent feedback process is developed using ultrasonic sensors and microcontrollers for control. The system is unique because it uses ultrasonic sensors for maximum performance. The developed system detects cracks on the rail, automatically controls the level crossing to avoid collision and send all possible feedbacks to a remote station using the SIM module. The reliability assessment of the system gave 93.3%. The system is reliable, efficient, and convenient and it is recommended for areas where rail transport systems are demanding.
{"title":"An Automatic Railway Level Crossing System with Crack Detection","authors":"A. Amusan, Yusuf Kolawole Adebakin","doi":"10.1109/ITED56637.2022.10051357","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051357","url":null,"abstract":"Railway system is a kind of transportation where passengers and goods are transported on wheeled vehicles running on rails located on tracks. This form of transportation is usually inexpensive, secure, and often the most convenient. In areas with frequent use of railway transport system, there is need to limit the accidents at the level crossing, mitigate the falling of trains on the rail due to cracks and create an excellent feedback system. The manual management of the system is inconvenient, time wasting and prone to sudden accidents. Hence in this work, an automatic railway system which includes automatic level crossing and crack detection system with an excellent feedback process is developed using ultrasonic sensors and microcontrollers for control. The system is unique because it uses ultrasonic sensors for maximum performance. The developed system detects cracks on the rail, automatically controls the level crossing to avoid collision and send all possible feedbacks to a remote station using the SIM module. The reliability assessment of the system gave 93.3%. The system is reliable, efficient, and convenient and it is recommended for areas where rail transport systems are demanding.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"21 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":"127839014","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/ITED56637.2022.10051582
J. B. Awotunde, A. Imoize, Akash Kumar Bhoi, R. Jimoh, Stephen Ojo, R. Panigrahi, N. Faruk
With no associated devices, device-free localization (DFL) uses wireless sensor networks to find a target. DFL has created comprehensive applications, smart cities and the Internet of Things (IoT), among other things. This technique has attracted significant attention from various fields, increasing the demand for tracking indoor location-based services. The critical challenge in DFL is a way to retrieve essential characteristics to illustrate raw signals with various locations linked with diverse patterns. The complexity of an indoor environment with limited space has created low indoor positioning reliability and effectiveness problems. Therefore, this study proposes and formulated an image classification problem for the DFL problem by initially transforming the receiving signal strength (RSS) inputs into picture frames. The feature extraction from raw signals was performed using Deep Feed-Forward Neural Network (DFFNN) and deep auto-encoder (DAE) to fine-turning for classification. The DAE combined DFFNN were used for signal reconstruction and feature learning to present the DFL better. The findings revealed an accuracy of 100% using real-world data collected, and a signal-to-noise ratio over −5dB, 0dB, and 5dB was used to measure the react to noisy data. Moreover, in IoT applications, its time cost is very fast in single activity by 5ms for classification. The proposed method is better in noiseless and noisy situations, localization accuracy, and other related techniques.
{"title":"An Enhanced DFFNN for Location-Based Services of Indoor Device-Free Submissive Localization","authors":"J. B. Awotunde, A. Imoize, Akash Kumar Bhoi, R. Jimoh, Stephen Ojo, R. Panigrahi, N. Faruk","doi":"10.1109/ITED56637.2022.10051582","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051582","url":null,"abstract":"With no associated devices, device-free localization (DFL) uses wireless sensor networks to find a target. DFL has created comprehensive applications, smart cities and the Internet of Things (IoT), among other things. This technique has attracted significant attention from various fields, increasing the demand for tracking indoor location-based services. The critical challenge in DFL is a way to retrieve essential characteristics to illustrate raw signals with various locations linked with diverse patterns. The complexity of an indoor environment with limited space has created low indoor positioning reliability and effectiveness problems. Therefore, this study proposes and formulated an image classification problem for the DFL problem by initially transforming the receiving signal strength (RSS) inputs into picture frames. The feature extraction from raw signals was performed using Deep Feed-Forward Neural Network (DFFNN) and deep auto-encoder (DAE) to fine-turning for classification. The DAE combined DFFNN were used for signal reconstruction and feature learning to present the DFL better. The findings revealed an accuracy of 100% using real-world data collected, and a signal-to-noise ratio over −5dB, 0dB, and 5dB was used to measure the react to noisy data. Moreover, in IoT applications, its time cost is very fast in single activity by 5ms for classification. The proposed method is better in noiseless and noisy situations, localization accuracy, and other related techniques.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"1 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":"127989780","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/ITED56637.2022.10051586
O. A, Okandeji Alexander, Oshevire Patrick
Due to the pervasive use of fossil fuels-based technologies for meeting domestic energy needs such as water heating, space cooling, and lighting, household energy consumption is increasing rapidly. However, these technologies consume enormous energy with huge energy costs. The energy crisis in Nigeria has long been identified as one of the key major obstacles impeding the country's economic growth, resulting in the disproportionate use of biomass for domestic heating. Therefore, fossil fuels-based heating technologies need to be substituted with a clean, eco-friendly, in exhaustible renewable heating technology towards achieving a net-zero energy target in buildings. Water heating with a hybrid system is a promising alternative to reduce energy consumption and costs. This system can be used as an off-grid energy solution to generate hot water in remote areas. This paper examines the techno-economic suitability of using a hybrid solar/heat pump system to address the issue of energy conservation. The methodology considered the initial upfront cost, operating and maintenance costs, grid energy costs, salvage cost, and the inflation rate over the project's economic life as an economic comparative metric. When compared to a baseline heating system, the use of hybrid systems saves about NGN 865,668.80, resulting in a 46.8% cost savings.
{"title":"Hybrid Solar/Heat Pump System for Water Heating in Nigeria: Techno-economic assessment","authors":"O. A, Okandeji Alexander, Oshevire Patrick","doi":"10.1109/ITED56637.2022.10051586","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051586","url":null,"abstract":"Due to the pervasive use of fossil fuels-based technologies for meeting domestic energy needs such as water heating, space cooling, and lighting, household energy consumption is increasing rapidly. However, these technologies consume enormous energy with huge energy costs. The energy crisis in Nigeria has long been identified as one of the key major obstacles impeding the country's economic growth, resulting in the disproportionate use of biomass for domestic heating. Therefore, fossil fuels-based heating technologies need to be substituted with a clean, eco-friendly, in exhaustible renewable heating technology towards achieving a net-zero energy target in buildings. Water heating with a hybrid system is a promising alternative to reduce energy consumption and costs. This system can be used as an off-grid energy solution to generate hot water in remote areas. This paper examines the techno-economic suitability of using a hybrid solar/heat pump system to address the issue of energy conservation. The methodology considered the initial upfront cost, operating and maintenance costs, grid energy costs, salvage cost, and the inflation rate over the project's economic life as an economic comparative metric. When compared to a baseline heating system, the use of hybrid systems saves about NGN 865,668.80, resulting in a 46.8% cost savings.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"12 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":"121052014","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/ITED56637.2022.10051221
Obioma Uchenna Nwogu, U. Nwawelu, C. Ani
With the adoption of IEEE 802.11ah standard, Internet of Things (IoT) and its performance has improved. However, registration time reduction, hidden node problem and efficient channel utilization are issues that have effect on the performance of the IEEE 802.11ah network standard. These issues can be attributed to the failure to allocate appropriate threshold for authentication control and to adjust Restricted Access Window (RAW). These are occasioned by inefficient clustering and station grouping schemes employed. In attempt to address these identified problems, Transitive Grouping (TG) scheme is proposed for the IoT support IEEE 802.11ah network. The TG scheme is a better way of clustering, grouping of stations, and allocation of RAW slot adaptively for an IoT support IEEE 802.11ah network. The TG scheme performance is evaluated in NS-3 environment on the basis of network delay, probability of successful transmission, throughput, channel utilization and registration time metrics. The proposed TG scheme is validated with four popular RAW slot allocation algorithms implemented in 802.11ah namely: RAW Association Identifier (RAd), Traffic Demand-based Stations Grouping (TSG), Hybrid Slotted CSMA/TDMA (HSCT), and M/G/I RAW Slot Allocation (MRA). Simulation results demonstrated that the proposed TG scheme achieved a substantial improvement over the other schemes.
{"title":"Transitive Grouping for Internet of Things Support IEEE 802.11ah using Integrated Approach","authors":"Obioma Uchenna Nwogu, U. Nwawelu, C. Ani","doi":"10.1109/ITED56637.2022.10051221","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051221","url":null,"abstract":"With the adoption of IEEE 802.11ah standard, Internet of Things (IoT) and its performance has improved. However, registration time reduction, hidden node problem and efficient channel utilization are issues that have effect on the performance of the IEEE 802.11ah network standard. These issues can be attributed to the failure to allocate appropriate threshold for authentication control and to adjust Restricted Access Window (RAW). These are occasioned by inefficient clustering and station grouping schemes employed. In attempt to address these identified problems, Transitive Grouping (TG) scheme is proposed for the IoT support IEEE 802.11ah network. The TG scheme is a better way of clustering, grouping of stations, and allocation of RAW slot adaptively for an IoT support IEEE 802.11ah network. The TG scheme performance is evaluated in NS-3 environment on the basis of network delay, probability of successful transmission, throughput, channel utilization and registration time metrics. The proposed TG scheme is validated with four popular RAW slot allocation algorithms implemented in 802.11ah namely: RAW Association Identifier (RAd), Traffic Demand-based Stations Grouping (TSG), Hybrid Slotted CSMA/TDMA (HSCT), and M/G/I RAW Slot Allocation (MRA). Simulation results demonstrated that the proposed TG scheme achieved a substantial improvement over the other schemes.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"1 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":"129006562","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/ITED56637.2022.10051468
A. Musa, Faruk Obasanjo Adekola, N. Faruk
The need for high speed data traffic on mobile devices has risen because of the permeating use of gadgets, such as mobile smart phones, notepads and tablets that are constantly running on data. In order to meet these requirements, mobile network providers must set up both tiny cells, high-capacity and very dense, base stations (BSs). This is to cover not only a vast area but also including hotspots with quick, adaptable, and robust supply. The overall spectral efficiency of 5G networks must be improved, and the operations and deployment costs must be decreased. This paper evaluates and compares the performance of Strict Fractional Frequency Reuse (FFR) and Frequency Reuse Factor-3 (FRF-3) according to the cell throughput and cell spectral efficiency with the theoretical peak throughput and peak spectral efficiency as specified in NR 3GPP specifications. The results from the simulation revealed that the FFR performs much better than the FRF-3, however, it is still not efficient in relation to the peak values.
{"title":"Performance Evaluation of Strict Fractional Frequency Reuse and Frequency Reuse Factor-3 in 5G Networks","authors":"A. Musa, Faruk Obasanjo Adekola, N. Faruk","doi":"10.1109/ITED56637.2022.10051468","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051468","url":null,"abstract":"The need for high speed data traffic on mobile devices has risen because of the permeating use of gadgets, such as mobile smart phones, notepads and tablets that are constantly running on data. In order to meet these requirements, mobile network providers must set up both tiny cells, high-capacity and very dense, base stations (BSs). This is to cover not only a vast area but also including hotspots with quick, adaptable, and robust supply. The overall spectral efficiency of 5G networks must be improved, and the operations and deployment costs must be decreased. This paper evaluates and compares the performance of Strict Fractional Frequency Reuse (FFR) and Frequency Reuse Factor-3 (FRF-3) according to the cell throughput and cell spectral efficiency with the theoretical peak throughput and peak spectral efficiency as specified in NR 3GPP specifications. The results from the simulation revealed that the FFR performs much better than the FRF-3, however, it is still not efficient in relation to the peak values.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"41 1 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":"116640189","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/ITED56637.2022.10051564
A. Kuyoro, Sheriff Alimi, O. Awodele
Support Vector Machine (SVM) in dealing with a classification problem, separates classes using decision boundaries with the primary objective of establishing a large margin between support vectors of the respective class groups; it utilizes kernels to achieve non-linear decision boundaries. This current work examines the performance of four SVM kernels (Sigmoid, Linear, Radial Basis Function (RBF) and Polynomial kernel functions) in addressing classification problems using two datasets from two domains. The two datasets are the Knowledge Discovery in Dataset (KDD) and a set of features extracted from voiced and unvoiced frames. The Polynomial kernel function had the best classification performance on the KDD dataset with accuracy and precision of 99.77% and 99.8% respectively but recorded the worst performance against the voice-feature dataset with an accuracy of 74.96%. Inductively, the polynomial kernel can be best suited for some classification datasets but can return the worst classification performance on another classification dataset. The RBF shows consistent high performance across the two data domains with accuracies of 96.04% and 99.77% and can be considered a general-purpose kernel guaranteed to yield satisfactory classification performance regardless of the dataset type or data domains. The performance of polynomial kernels over the two separate datasets supports the “No Free Launch Theorem”, which when applied to machine learning, means that if an algorithm performs well over a class of problem, it may have worse performance on other class of problem. This implies that there might not be one specific machine learning algorithm that gives the best possible performance for a set of problems, it is therefore important for researchers to try out various algorithms before concluding on the best possible result on any dataset.
{"title":"Comparative Analysis of the Performance of Various Support Vector Machine kernels","authors":"A. Kuyoro, Sheriff Alimi, O. Awodele","doi":"10.1109/ITED56637.2022.10051564","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051564","url":null,"abstract":"Support Vector Machine (SVM) in dealing with a classification problem, separates classes using decision boundaries with the primary objective of establishing a large margin between support vectors of the respective class groups; it utilizes kernels to achieve non-linear decision boundaries. This current work examines the performance of four SVM kernels (Sigmoid, Linear, Radial Basis Function (RBF) and Polynomial kernel functions) in addressing classification problems using two datasets from two domains. The two datasets are the Knowledge Discovery in Dataset (KDD) and a set of features extracted from voiced and unvoiced frames. The Polynomial kernel function had the best classification performance on the KDD dataset with accuracy and precision of 99.77% and 99.8% respectively but recorded the worst performance against the voice-feature dataset with an accuracy of 74.96%. Inductively, the polynomial kernel can be best suited for some classification datasets but can return the worst classification performance on another classification dataset. The RBF shows consistent high performance across the two data domains with accuracies of 96.04% and 99.77% and can be considered a general-purpose kernel guaranteed to yield satisfactory classification performance regardless of the dataset type or data domains. The performance of polynomial kernels over the two separate datasets supports the “No Free Launch Theorem”, which when applied to machine learning, means that if an algorithm performs well over a class of problem, it may have worse performance on other class of problem. This implies that there might not be one specific machine learning algorithm that gives the best possible performance for a set of problems, it is therefore important for researchers to try out various algorithms before concluding on the best possible result on any dataset.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"52 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":"125632612","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/ITED56637.2022.10051383
B. A. Ajayi, J. Nweke, Muhammad Usman Ogah
Enhancing the interagency collaborative approach to crime management in developing nations cannot be overemphasized. This study presents a computerized system posed to enhance interagency collaboration in combating crime in Nigeria. Interagency Crime Management System (ICMS) is a web-based application that accepts input through an Application Program Interface (API) provided to the individual applications being used by different security agencies under the Federal Government of Nigeria. The system is based on a relational database with schemas very close to those of law enforcement agencies. The system was designed to accept data in the same input format from each of these agencies. These are the criminal code, name of criminal, nationality, state of origin, the local government of origin, age, nature of the crime committed, location of the crime, a section of the penal code violated, current status as at when reporting, officer-in-charge, and reporting agency. To achieve this, the study adopted the Structured System Analysis and Design Methodology (SSADM). The process starts with designing a framework for ICMS, then furthered by developing an algorithm for ICMS, and Laravel was employed for the implementation of the algorithm developed. The database management software employed for the application, PostgreSQL, stores every detail of the crime using a unique reference number for every record stored in the database to facilitate easy retrieval. This system also provides a search facility to query the database about information relating to the various categories of crime, criminals, and crimes that are common in particular geographical location and provide analytics tools such as charts for research and analysis purposes.
{"title":"Developing an Interoperable Crime Management System","authors":"B. A. Ajayi, J. Nweke, Muhammad Usman Ogah","doi":"10.1109/ITED56637.2022.10051383","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051383","url":null,"abstract":"Enhancing the interagency collaborative approach to crime management in developing nations cannot be overemphasized. This study presents a computerized system posed to enhance interagency collaboration in combating crime in Nigeria. Interagency Crime Management System (ICMS) is a web-based application that accepts input through an Application Program Interface (API) provided to the individual applications being used by different security agencies under the Federal Government of Nigeria. The system is based on a relational database with schemas very close to those of law enforcement agencies. The system was designed to accept data in the same input format from each of these agencies. These are the criminal code, name of criminal, nationality, state of origin, the local government of origin, age, nature of the crime committed, location of the crime, a section of the penal code violated, current status as at when reporting, officer-in-charge, and reporting agency. To achieve this, the study adopted the Structured System Analysis and Design Methodology (SSADM). The process starts with designing a framework for ICMS, then furthered by developing an algorithm for ICMS, and Laravel was employed for the implementation of the algorithm developed. The database management software employed for the application, PostgreSQL, stores every detail of the crime using a unique reference number for every record stored in the database to facilitate easy retrieval. This system also provides a search facility to query the database about information relating to the various categories of crime, criminals, and crimes that are common in particular geographical location and provide analytics tools such as charts for research and analysis purposes.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"39 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121003813","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/ITED56637.2022.10051488
M. Onoja, Abayomi Jegede, Jesse Mazadu, G. Aimufua, Ayodele Oyedele, Kolawole Olibodum
Malware has posed a serious problem in today's world of cyber security. Effective malware detection approaches minimize damages caused by malware attack, while efficient detection strategies reduce the amount of resources required to detect malware. A previous application of LightGBM model to malware detection shows that the technique is suitable for Windows malware detection. However, the study did not compute the training time, detection time and classification accuracy of the model. There is need to evaluate the accuracy of LightGBM algorithm and determine the time required for training it. This is because quality training produces highly reliable model. It is also necessary to compute the classification accuracy and prediction time, to enhance better decision making. This paper applied the generic LightGBM algorithm on Windows malware to determine its efficiency and effectiveness in terms of training time, prediction time and classification accuracy. Performance evaluation based on the Malimg dataset shows a 99.80% training accuracy for binary class, while the accuracy for multi-class is 96.87%. The training time of the generic LightGBM is 179.51s for binary class and 2224.77s for multi-class. The classification accuracy showed a True Positive Rate (TPR) of 99% and False Positive Rate (FPR) of 0.99% for the binary classification, while the prediction time of the model are 0.08s and 0.40s for binary and multi class respectively. The results obtained for training time, detection time and classification accuracy show that LightGBM algorithm is suitable for detecting Windows malware.
{"title":"Exploring the Effectiveness and Efficiency of LightGBM Algorithm for Windows Malware Detection","authors":"M. Onoja, Abayomi Jegede, Jesse Mazadu, G. Aimufua, Ayodele Oyedele, Kolawole Olibodum","doi":"10.1109/ITED56637.2022.10051488","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051488","url":null,"abstract":"Malware has posed a serious problem in today's world of cyber security. Effective malware detection approaches minimize damages caused by malware attack, while efficient detection strategies reduce the amount of resources required to detect malware. A previous application of LightGBM model to malware detection shows that the technique is suitable for Windows malware detection. However, the study did not compute the training time, detection time and classification accuracy of the model. There is need to evaluate the accuracy of LightGBM algorithm and determine the time required for training it. This is because quality training produces highly reliable model. It is also necessary to compute the classification accuracy and prediction time, to enhance better decision making. This paper applied the generic LightGBM algorithm on Windows malware to determine its efficiency and effectiveness in terms of training time, prediction time and classification accuracy. Performance evaluation based on the Malimg dataset shows a 99.80% training accuracy for binary class, while the accuracy for multi-class is 96.87%. The training time of the generic LightGBM is 179.51s for binary class and 2224.77s for multi-class. The classification accuracy showed a True Positive Rate (TPR) of 99% and False Positive Rate (FPR) of 0.99% for the binary classification, while the prediction time of the model are 0.08s and 0.40s for binary and multi class respectively. The results obtained for training time, detection time and classification accuracy show that LightGBM algorithm is suitable for detecting Windows malware.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"155 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":"126928006","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/ITED56637.2022.10051460
S. O. Olukumoro, Cecilia Ajowho Adenusi, Emmanuel Ofoegbunam, Oguns Yetunde Josephine, Opakunle Victor Abayomi
YouTube is a video-sharing website where users may publish, watch, share, and comment on videos and other media. The proliferation of technological gadgets, combined with rapid advancements in technology, has resulted in an increase in trending videos on the platform, where videos and content receive hundreds of thousands, if not millions, of views within minutes of being uploaded and continue to trend throughout the day. This study uses the US YouTube Trending dataset, which includes 130591 occurrences and was acquired from the kaggle repository between August 11, 2020 to May 14, 2022. This study used qualitative and quantitative methods to analyze the YouTube videos dataset, and then performed a predictive analysis on the trending video tags, predicting how a particular video on YouTube might trend in the next two to eight days by predicting the trending of such videos for the next two to eight days and showing their accuracy results using the K-nearest neighbor algorithm (KNN). The model that was utilized to perform the prediction analysis has an accuracy of around 98 percent.
{"title":"Prognosticate Trending Days of Youtube Videos Tags Using K-Nearest Neighbor Algorithm","authors":"S. O. Olukumoro, Cecilia Ajowho Adenusi, Emmanuel Ofoegbunam, Oguns Yetunde Josephine, Opakunle Victor Abayomi","doi":"10.1109/ITED56637.2022.10051460","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051460","url":null,"abstract":"YouTube is a video-sharing website where users may publish, watch, share, and comment on videos and other media. The proliferation of technological gadgets, combined with rapid advancements in technology, has resulted in an increase in trending videos on the platform, where videos and content receive hundreds of thousands, if not millions, of views within minutes of being uploaded and continue to trend throughout the day. This study uses the US YouTube Trending dataset, which includes 130591 occurrences and was acquired from the kaggle repository between August 11, 2020 to May 14, 2022. This study used qualitative and quantitative methods to analyze the YouTube videos dataset, and then performed a predictive analysis on the trending video tags, predicting how a particular video on YouTube might trend in the next two to eight days by predicting the trending of such videos for the next two to eight days and showing their accuracy results using the K-nearest neighbor algorithm (KNN). The model that was utilized to perform the prediction analysis has an accuracy of around 98 percent.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"80 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":"124251220","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/ITED56637.2022.10051257
Sani Galadima Garba, A. Obiniyi, Musa Adeku Ibrahim, B. I. Ahmad
The key schedule, an essential part of the cipher(cryptography), is often neglected during the cipher algorithm design. However, a compromised key schedule leads to the entire cipher's successful attack. In this article, we reviewed the elements to consider when creating an excellent key schedule, proposed a methodology to achieve it, designed a key schedule with the proposed method, implemented the design, and analyzed the result to confirm that it meets the specifications. Our proposed key schedule is specially designed for devices with limited memory size, processing ability, and storage. So, this article's suggested method and design were done to achieve a secure key schedule using minimal resources, especially in hardware implementation.
{"title":"On the Key Schedule of Lightweight Block Cipher","authors":"Sani Galadima Garba, A. Obiniyi, Musa Adeku Ibrahim, B. I. Ahmad","doi":"10.1109/ITED56637.2022.10051257","DOIUrl":"https://doi.org/10.1109/ITED56637.2022.10051257","url":null,"abstract":"The key schedule, an essential part of the cipher(cryptography), is often neglected during the cipher algorithm design. However, a compromised key schedule leads to the entire cipher's successful attack. In this article, we reviewed the elements to consider when creating an excellent key schedule, proposed a methodology to achieve it, designed a key schedule with the proposed method, implemented the design, and analyzed the result to confirm that it meets the specifications. Our proposed key schedule is specially designed for devices with limited memory size, processing ability, and storage. So, this article's suggested method and design were done to achieve a secure key schedule using minimal resources, especially in hardware implementation.","PeriodicalId":246041,"journal":{"name":"2022 5th Information Technology for Education and Development (ITED)","volume":"25 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":"122816562","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：