D. Mane, P. Kumbharkar, Nirupama Earan, Komal Patil, Sakshi Bonde, Nilesh J. Uke
Nowadays, it is crucial to continuously monitor and provide real-time analysis to reduce traffic-related accidents and practices such as vehicle overloading on the roads daily. As a result, we reviewed the literature's numerous methods and techniques for vehicle detection, recognition, identification, speed estimation, and license plate recognition. In this analysis, we examined 42 articles published in the last ten years, from 2012 to 2022. Based on our research, we found that the Deep CNN is the optimum method for vehicle categorization. The motivation of this review is that none of the aforementioned models are combined into a single model, so we present a comprehensive list of all these models that may be helpful to anyone conducting the study in this area. Therefore, after reviewing the chosen research publications, we propose 20+ datasets that might be used in the field for more research. We also discovered 15+ different ML models used to detect and identify vehicles. Finally, we observed that combining machine learning and AI (Artificial Intelligence) to create intelligent traffic control systems is a promising research area.
{"title":"A Research Survey on Real-Time Intelligent Traffic System","authors":"D. Mane, P. Kumbharkar, Nirupama Earan, Komal Patil, Sakshi Bonde, Nilesh J. Uke","doi":"10.46338/ijetae0423_05","DOIUrl":"https://doi.org/10.46338/ijetae0423_05","url":null,"abstract":"Nowadays, it is crucial to continuously monitor and provide real-time analysis to reduce traffic-related accidents and practices such as vehicle overloading on the roads daily. As a result, we reviewed the literature's numerous methods and techniques for vehicle detection, recognition, identification, speed estimation, and license plate recognition. In this analysis, we examined 42 articles published in the last ten years, from 2012 to 2022. Based on our research, we found that the Deep CNN is the optimum method for vehicle categorization. The motivation of this review is that none of the aforementioned models are combined into a single model, so we present a comprehensive list of all these models that may be helpful to anyone conducting the study in this area. Therefore, after reviewing the chosen research publications, we propose 20+ datasets that might be used in the field for more research. We also discovered 15+ different ML models used to detect and identify vehicles. Finally, we observed that combining machine learning and AI (Artificial Intelligence) to create intelligent traffic control systems is a promising research area.","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122858138","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}
M. H. Misran, M. A. M. Said, M. Othman, A. Jaafar, Redzuan Abd Manap, S. Suhaimi, N. I. Hassan
—5G technology is leverages advanced antenna technology and wider bandwidth to improve the potential of wireless communication that enables a significant increase in the amount of information that can be transmitted through the wireless system. With its ability to deliver higher data rates and lower latency, 5G promises to support a wide range of applications, from immersive virtual reality to autonomous vehicles.However, 5G communication systems are characterized by poor radiation features, which limit their usefulness in wider operational ranges. To overcome these issues, this project will focus on designing a high-gain array antenna operating at 3.5GHz specifically for 5G communication. A directional patch antenna will be designed for a specific base station to provide high radiation network connectivity and superior communication quality. Moreover, the high-gain array antenna at 3.5GHz will be optimized for long-distance point-to-point connections. In this project, a 4x4 patch antenna will be designed and fabricated using FR4 epoxy material to achieve high gain for long-distance signal transmission.
{"title":"5G Communication: High Gain Array Antenna Operating at 3.5GHz","authors":"M. H. Misran, M. A. M. Said, M. Othman, A. Jaafar, Redzuan Abd Manap, S. Suhaimi, N. I. Hassan","doi":"10.46338/ijetae0423_06","DOIUrl":"https://doi.org/10.46338/ijetae0423_06","url":null,"abstract":"—5G technology is leverages advanced antenna technology and wider bandwidth to improve the potential of wireless communication that enables a significant increase in the amount of information that can be transmitted through the wireless system. With its ability to deliver higher data rates and lower latency, 5G promises to support a wide range of applications, from immersive virtual reality to autonomous vehicles.However, 5G communication systems are characterized by poor radiation features, which limit their usefulness in wider operational ranges. To overcome these issues, this project will focus on designing a high-gain array antenna operating at 3.5GHz specifically for 5G communication. A directional patch antenna will be designed for a specific base station to provide high radiation network connectivity and superior communication quality. Moreover, the high-gain array antenna at 3.5GHz will be optimized for long-distance point-to-point connections. In this project, a 4x4 patch antenna will be designed and fabricated using FR4 epoxy material to achieve high gain for long-distance signal transmission.","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130238063","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}
A. V, Shuklin G, Pepa Y, Lehominova S, Muzhanova T, Dzyuba T, Yakymenko Y
At present, there are no quantitative studies of the dependence of the index of protection of personal data of actors in social medias on the parameters of its centrality, so this article presents the results of such researches in this area. Since the system of information protection of a social media network is nonlinear and depends on the parameters of a specific indicator of its centrality, mathematical equations have been developed to study the quantitative indicators of such a system, and the stability of the system has been investigated, which is graphically illustrated. The results obtained allow network administrators to analyze the behavior of the security system stability and take technical actions (operating system, firewall, network filter, etc.) that will keep the security indicator within the specified limits.
{"title":"Methodology for Calculating the Index of Protection of a Social Media from its Centrality","authors":"A. V, Shuklin G, Pepa Y, Lehominova S, Muzhanova T, Dzyuba T, Yakymenko Y","doi":"10.46338/ijetae0423_03","DOIUrl":"https://doi.org/10.46338/ijetae0423_03","url":null,"abstract":"At present, there are no quantitative studies of the dependence of the index of protection of personal data of actors in social medias on the parameters of its centrality, so this article presents the results of such researches in this area. Since the system of information protection of a social media network is nonlinear and depends on the parameters of a specific indicator of its centrality, mathematical equations have been developed to study the quantitative indicators of such a system, and the stability of the system has been investigated, which is graphically illustrated. The results obtained allow network administrators to analyze the behavior of the security system stability and take technical actions (operating system, firewall, network filter, etc.) that will keep the security indicator within the specified limits.","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129146996","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}
The primary aim of recommender system is to predict items which are of most interest to the users and today recommender systems play a vital role in boosting the sales in any e-commerce based platform. The present paper proposes an approach for recommending movies to the users on the basis on their choices. A novel technique for evaluation of collaborative filtering using SVD and hit ratio as a metric is taken in our proposed approach. We attempted to build a model-based Collaborative filtering technique. The proposed paper makes use of matrix factorization techniques like SVD & SVD++ for filtering movie recommendation system based on latent features. It makes better recommendations based on choice of user because it captures the underlying features driving the raw data. In this paper we are proposing a hybrid recommender system fusion of Content Based and SVD to get a new hybrid recommender system. Our proposed model gives the value of RMSE 0.87 for SVD model and RMSE 0.938 for SVD++ model. Keywords-- Collaborative filtering, movie recommendation, SVD, content based filtering
{"title":"Design of a Hybrid Movie Recommender System Using Machine Learning","authors":"Vishal Paranjape, Neelu Nihalani, Nishchol Mishra","doi":"10.46338/ijetae0323_17","DOIUrl":"https://doi.org/10.46338/ijetae0323_17","url":null,"abstract":"The primary aim of recommender system is to predict items which are of most interest to the users and today recommender systems play a vital role in boosting the sales in any e-commerce based platform. The present paper proposes an approach for recommending movies to the users on the basis on their choices. A novel technique for evaluation of collaborative filtering using SVD and hit ratio as a metric is taken in our proposed approach. We attempted to build a model-based Collaborative filtering technique. The proposed paper makes use of matrix factorization techniques like SVD & SVD++ for filtering movie recommendation system based on latent features. It makes better recommendations based on choice of user because it captures the underlying features driving the raw data. In this paper we are proposing a hybrid recommender system fusion of Content Based and SVD to get a new hybrid recommender system. Our proposed model gives the value of RMSE 0.87 for SVD model and RMSE 0.938 for SVD++ model. Keywords-- Collaborative filtering, movie recommendation, SVD, content based filtering","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128240678","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}
M. H. Hassan, Ameer Mohammed Al-obaidi, Sameer Alani, F. Abbas, A. Alkhayyat, S. Mahmood, Hayder Muayad Al-Maawi, R. R. Ali
—Vehicular Ad-Hoc Network (VANETs) is a trending modelthat plays maximum role inall the application of Intelligent Transport Systems (ITS). In general, VANETs are based on two communication types such as among vehicles and vehicles to infrastructure Roadside Units(RSU) based communication. In this paper, HACOGO approach is developedbased on ahybrid bio inspired optimization with the combination of Ant Colony Optimization (ACO) with Grasshopper Optimization Algorithm (GOA). The HACOGO is used to perform stable RSU distribution in VANETs. The ACO algorithm is used to help the vehicle to select the optimal path toward the destination and GOA algorithm highly magnificent vehicle is chosen as RSU. The Performance analysis of HACOGO is done by calculating the common parameters such as packet delivery ratio, end-to-end delay, packet loss and routing overhead. To analysis the effectiveness of the proposed model its results are compared with the earlier works. From the outcome it is proven using the HACOGO approach the end-to-end delay, packet loss and routing overhead is reduced as well as the packet delivery ratio of the network is increased than others. Keywords—Vehicular Ad-Hoc Network,Roadside Units, Ant Colony Optimization.
{"title":"A Hybrid Bio-Inspired Optimization Scheme for RSU Distribution in Vehicular Ad-Hoc Network","authors":"M. H. Hassan, Ameer Mohammed Al-obaidi, Sameer Alani, F. Abbas, A. Alkhayyat, S. Mahmood, Hayder Muayad Al-Maawi, R. R. Ali","doi":"10.46338/ijetae0323_16","DOIUrl":"https://doi.org/10.46338/ijetae0323_16","url":null,"abstract":"—Vehicular Ad-Hoc Network (VANETs) is a trending modelthat plays maximum role inall the application of Intelligent Transport Systems (ITS). In general, VANETs are based on two communication types such as among vehicles and vehicles to infrastructure Roadside Units(RSU) based communication. In this paper, HACOGO approach is developedbased on ahybrid bio inspired optimization with the combination of Ant Colony Optimization (ACO) with Grasshopper Optimization Algorithm (GOA). The HACOGO is used to perform stable RSU distribution in VANETs. The ACO algorithm is used to help the vehicle to select the optimal path toward the destination and GOA algorithm highly magnificent vehicle is chosen as RSU. The Performance analysis of HACOGO is done by calculating the common parameters such as packet delivery ratio, end-to-end delay, packet loss and routing overhead. To analysis the effectiveness of the proposed model its results are compared with the earlier works. From the outcome it is proven using the HACOGO approach the end-to-end delay, packet loss and routing overhead is reduced as well as the packet delivery ratio of the network is increased than others. Keywords—Vehicular Ad-Hoc Network,Roadside Units, Ant Colony Optimization.","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115151582","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}
As blockchain technology makes rapid progress, attempts to use it in various environments are also increasing. Especially home networks and smart factories consisting of a small network of Internet of Things (IoT) devices with singlehop or a few hops are trying to adopt blockchain systems to guarantee the integrity of data and to protect privacy. However, in such low-bandwidth network environments, they encounter challenges because of the network cost for block consensus. This study proposes a lightweight blockchain consensus protocol suitable for these environments. The proposed protocol improves the existing PBFT protocol to reduce the network cost required for consensus. The main innovation is to reduce the number of phases for consensus from three phases to two phases while preserving Byzantine failure tolerance. These two phases guarantee the total order of clients’ transactions in the same view. And the simple viewchange process in the proposed protocol enables the change of the primary node for new block generation. The experimental result shows a significant performance improvement of block consensus over the PBFT. Using the proposed protocol can contribute to operating blockchain systems in various lowbandwidth network environments. Keywords—blockchain, consensus protocol, lightweight protocol, low bandwidth network, PBFT
{"title":"Novel Lightweight Consensus Protocol for Reaching Blockchain Consensus in Low Bandwidth Network Environment","authors":"Minsung Son, Heeyoul Kim","doi":"10.46338/ijetae0323_12","DOIUrl":"https://doi.org/10.46338/ijetae0323_12","url":null,"abstract":"As blockchain technology makes rapid progress, attempts to use it in various environments are also increasing. Especially home networks and smart factories consisting of a small network of Internet of Things (IoT) devices with singlehop or a few hops are trying to adopt blockchain systems to guarantee the integrity of data and to protect privacy. However, in such low-bandwidth network environments, they encounter challenges because of the network cost for block consensus. This study proposes a lightweight blockchain consensus protocol suitable for these environments. The proposed protocol improves the existing PBFT protocol to reduce the network cost required for consensus. The main innovation is to reduce the number of phases for consensus from three phases to two phases while preserving Byzantine failure tolerance. These two phases guarantee the total order of clients’ transactions in the same view. And the simple viewchange process in the proposed protocol enables the change of the primary node for new block generation. The experimental result shows a significant performance improvement of block consensus over the PBFT. Using the proposed protocol can contribute to operating blockchain systems in various lowbandwidth network environments. Keywords—blockchain, consensus protocol, lightweight protocol, low bandwidth network, PBFT","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126123081","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}
The purpose of this study is to explore the trends of the Z and Alpha generation user groups on the metaverse for each unique topic by using LDA topic modeling based on big data analysis. This study seeks a new sustainability direction for the metaverse by discovering the internal and experiential value of users' experiences beyond the technical perspective of the metaverse. The worldwide enthusiasm for the metaverse was driven by the impact of the COVID-19 pandemic, technological advances in computer graphics and infrastructure, and the expansion of the digital generation user base such as generation Z and Alpha. Research on the metaverse has been increasing since 2021, but theoretical approaches by generational subgroups of nextgeneration digital users on the metaverse are still insufficient. Considering the timeliness of the research topic, this study subdivides the next-generation users into two groups, the Z generation and the Alpha generation, to discover the characteristics of each generation regarding the metaverse. In the process of analysis, the importance and relevance of words were identified by text mining analysis of unstructured big data. Next, through LDA topic modeling and visualization analysis, the meaning of each topic group was interpreted based on word pockets, which are related words that have mutually exclusive uniqueness for each topic. Python 3.10 and Textom 6 version software were used for analysis. This study will present meaningful academic and practical insights into the sustainability and utilization of the metaverse by a diverse user base. Keywords—Big data, Data mining, LDA Topic Modeling, Metaverse, Digital Generation
{"title":"LDA Topic Modeling on the Trends of the Next Digital Generation on the New Internet Revolution, Metaverse","authors":"Kiyoung Kim","doi":"10.46338/ijetae0323_15","DOIUrl":"https://doi.org/10.46338/ijetae0323_15","url":null,"abstract":"The purpose of this study is to explore the trends of the Z and Alpha generation user groups on the metaverse for each unique topic by using LDA topic modeling based on big data analysis. This study seeks a new sustainability direction for the metaverse by discovering the internal and experiential value of users' experiences beyond the technical perspective of the metaverse. The worldwide enthusiasm for the metaverse was driven by the impact of the COVID-19 pandemic, technological advances in computer graphics and infrastructure, and the expansion of the digital generation user base such as generation Z and Alpha. Research on the metaverse has been increasing since 2021, but theoretical approaches by generational subgroups of nextgeneration digital users on the metaverse are still insufficient. Considering the timeliness of the research topic, this study subdivides the next-generation users into two groups, the Z generation and the Alpha generation, to discover the characteristics of each generation regarding the metaverse. In the process of analysis, the importance and relevance of words were identified by text mining analysis of unstructured big data. Next, through LDA topic modeling and visualization analysis, the meaning of each topic group was interpreted based on word pockets, which are related words that have mutually exclusive uniqueness for each topic. Python 3.10 and Textom 6 version software were used for analysis. This study will present meaningful academic and practical insights into the sustainability and utilization of the metaverse by a diverse user base. Keywords—Big data, Data mining, LDA Topic Modeling, Metaverse, Digital Generation","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125274708","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}
Shengguo Ge, S. Rum, Hamidah Ibrahim, Erzam Marsilah, Thinagaran Perumal
Source number estimation is one of the important research directions in array signal processing. To solve the difficulty of estimating the number of signal sources under a low signal-to-noise ratio (SNR), a source number enumeration method based on ensemble learning is proposed. This method first preprocesses the signal data. The specific process is to decompose the original signal into several intrinsic mode functions (IMF) by using Complementary Ensemble Empirical Mode Decomposition (CEEMD), and then construct a covariance matrix and perform eigenvalue decomposition to obtain samples. Finally, the source number enumeration model based on ensemble learning is used to predict the number of sources. This model is divided into two layers. First, the primary learner is trained with the dataset, and then the prediction result on the primary learner is used as the input of the secondary learner for training, and then the prediction result is obtained. Computer theoretical signals and real measured signals are used to verify the proposed source number enumeration method, respectively. Experiments show that this method has better performance than other methods at low SNR, and it is more suitable for real environment. Keywords—Source number estimation; Array signal processing; SNR; IMF; CEEMD; Ensemble learning.
{"title":"A Source Number Enumeration Method at Low SNR Based on Ensemble Learning","authors":"Shengguo Ge, S. Rum, Hamidah Ibrahim, Erzam Marsilah, Thinagaran Perumal","doi":"10.46338/ijetae0323_08","DOIUrl":"https://doi.org/10.46338/ijetae0323_08","url":null,"abstract":"Source number estimation is one of the important research directions in array signal processing. To solve the difficulty of estimating the number of signal sources under a low signal-to-noise ratio (SNR), a source number enumeration method based on ensemble learning is proposed. This method first preprocesses the signal data. The specific process is to decompose the original signal into several intrinsic mode functions (IMF) by using Complementary Ensemble Empirical Mode Decomposition (CEEMD), and then construct a covariance matrix and perform eigenvalue decomposition to obtain samples. Finally, the source number enumeration model based on ensemble learning is used to predict the number of sources. This model is divided into two layers. First, the primary learner is trained with the dataset, and then the prediction result on the primary learner is used as the input of the secondary learner for training, and then the prediction result is obtained. Computer theoretical signals and real measured signals are used to verify the proposed source number enumeration method, respectively. Experiments show that this method has better performance than other methods at low SNR, and it is more suitable for real environment. Keywords—Source number estimation; Array signal processing; SNR; IMF; CEEMD; Ensemble learning.","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129596220","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}
O. Olaniyan, A. Olusesi, B. Omodunbi, W. Wahab, Olusogo Julius Adetunji, Bamidele Musiliu Olukoya
Mobile Ad Hoc network (MANET) is a connection of mobile nodes that are joined together to communicate and share information using a wireless link.Some of the MANET in use include mobile smart phones, laptops, personal digital assistant (PDAs), among others.However, MANET has been known for the major challenge of being vulnerable to malicious attacks within the network. One of the techniques which have been used by several research works is the cryptographic approach using advanced encryption technique (AES). AES has been found suitable in the MANET domain because it does not take much space in mobile nodes which are known for their limited space resources. But one of the challenges facing AES which has not been given much attention is the optimal generation of its secret keys. So, therefore, this research work presents a symmetric cryptography technique by developing a model for the optimal generation of secret keys in AES using the linear function mayfly AES (LFM-AES) algorithm. The developed model was simulated in MATLAB 2020 programming environment. LFM-AES was compared with mayfly-AES, particle swarm optimization AES (PSO-AES) using encryption time, computational time, encryption throughput, and mean square error. The simulation results showed that LFM-AES has lower encryption, computational, mean square error, and higher encryption throughput. Keywords-- MANET, Data Security, Key Management, LFM-AES, Mayfly-AES, PSO-AES, AES
{"title":"A Data Security Model for Mobile Ad Hoc Network Using Linear Function Mayfly Advanced Encryption Standard","authors":"O. Olaniyan, A. Olusesi, B. Omodunbi, W. Wahab, Olusogo Julius Adetunji, Bamidele Musiliu Olukoya","doi":"10.46338/ijetae0323_10","DOIUrl":"https://doi.org/10.46338/ijetae0323_10","url":null,"abstract":"Mobile Ad Hoc network (MANET) is a connection of mobile nodes that are joined together to communicate and share information using a wireless link.Some of the MANET in use include mobile smart phones, laptops, personal digital assistant (PDAs), among others.However, MANET has been known for the major challenge of being vulnerable to malicious attacks within the network. One of the techniques which have been used by several research works is the cryptographic approach using advanced encryption technique (AES). AES has been found suitable in the MANET domain because it does not take much space in mobile nodes which are known for their limited space resources. But one of the challenges facing AES which has not been given much attention is the optimal generation of its secret keys. So, therefore, this research work presents a symmetric cryptography technique by developing a model for the optimal generation of secret keys in AES using the linear function mayfly AES (LFM-AES) algorithm. The developed model was simulated in MATLAB 2020 programming environment. LFM-AES was compared with mayfly-AES, particle swarm optimization AES (PSO-AES) using encryption time, computational time, encryption throughput, and mean square error. The simulation results showed that LFM-AES has lower encryption, computational, mean square error, and higher encryption throughput. Keywords-- MANET, Data Security, Key Management, LFM-AES, Mayfly-AES, PSO-AES, AES","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130935341","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}
The hotel industry effectively supports the wider national economy. The sector supports the nation's efforts to promote cultural events and improve visitor amenities. The primary issue this sector is currently dealing with is a hotel booking cancellation. Because of the impact this issue has on the hotel industry's resource allocation, labour needs, customers’ satisfaction, and overall decision-making process. In result, the hotel's reputation, business processes, and financial performance may also suffer. The major goal of this research is to create a model that will help the hotel industry make wise decisions. We completed the necessary data preprocessing and transformation procedures using the Kaggle hotel bookings dataset. Furthermore, we employed a number of machine learning methods to predict the cancellation requests in the future. Additionally, this study used a number of ensemble techniques, including voting, stacking, and bagging, to improve the model's accuracy. The findings showed that the stacking strategy outperformed all other models and had an accuracy rate of 86.76%. The proposed model and analysis discussed in this paper may help the hotel sector forecast the kinds of requests that will likely be cancelled in the future. Keywords—Hotel Booking Cancellation, Machine Learning, Ensemble Machine Learning, Classification
{"title":"Implementation of Ensemble Machine Learning Techniques on Hotel Reservation System","authors":"F. Alotaibi","doi":"10.46338/ijetae0323_03","DOIUrl":"https://doi.org/10.46338/ijetae0323_03","url":null,"abstract":"The hotel industry effectively supports the wider national economy. The sector supports the nation's efforts to promote cultural events and improve visitor amenities. The primary issue this sector is currently dealing with is a hotel booking cancellation. Because of the impact this issue has on the hotel industry's resource allocation, labour needs, customers’ satisfaction, and overall decision-making process. In result, the hotel's reputation, business processes, and financial performance may also suffer. The major goal of this research is to create a model that will help the hotel industry make wise decisions. We completed the necessary data preprocessing and transformation procedures using the Kaggle hotel bookings dataset. Furthermore, we employed a number of machine learning methods to predict the cancellation requests in the future. Additionally, this study used a number of ensemble techniques, including voting, stacking, and bagging, to improve the model's accuracy. The findings showed that the stacking strategy outperformed all other models and had an accuracy rate of 86.76%. The proposed model and analysis discussed in this paper may help the hotel sector forecast the kinds of requests that will likely be cancelled in the future. Keywords—Hotel Booking Cancellation, Machine Learning, Ensemble Machine Learning, Classification","PeriodicalId":169403,"journal":{"name":"International Journal of Emerging Technology and Advanced Engineering","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121208031","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：