Pub Date : 2022-09-26DOI: 10.1108/ijpcc-06-2022-0244
T. P. Fowdur, Lavesh Babooram
Purpose The purpose of this paper is geared towards the capture and analysis of network traffic using an array ofmachine learning (ML) and deep learning (DL) techniques to classify network traffic into different classes and predict network traffic parameters. Design/methodology/approach The classifier models include k-nearest neighbour (KNN), multilayer perceptron (MLP) and support vector machine (SVM), while the regression models studied are multiple linear regression (MLR) as well as MLP. The analytics were performed on both a local server and a servlet hosted on the international business machines cloud. Moreover, the local server could aggregate data from multiple devices on the network and perform collaborative ML to predict network parameters. With optimised hyperparameters, analytical models were incorporated in the cloud hosted Java servlets that operate on a client–server basis where the back-end communicates with Cloudant databases. Findings Regarding classification, it was found that KNN performs significantly better than MLP and SVM with a comparative precision gain of approximately 7%, when classifying both Wi-Fi and long term evolution (LTE) traffic. Originality/value Collaborative regression models using traffic collected from two devices were experimented and resulted in an increased average accuracy of 0.50% for all variables, with a multivariate MLP model.
{"title":"Performance analysis of a cloud-based network analytics system with multiple-source data aggregation","authors":"T. P. Fowdur, Lavesh Babooram","doi":"10.1108/ijpcc-06-2022-0244","DOIUrl":"https://doi.org/10.1108/ijpcc-06-2022-0244","url":null,"abstract":"\u0000Purpose\u0000The purpose of this paper is geared towards the capture and analysis of network traffic using an array ofmachine learning (ML) and deep learning (DL) techniques to classify network traffic into different classes and predict network traffic parameters.\u0000\u0000\u0000Design/methodology/approach\u0000The classifier models include k-nearest neighbour (KNN), multilayer perceptron (MLP) and support vector machine (SVM), while the regression models studied are multiple linear regression (MLR) as well as MLP. The analytics were performed on both a local server and a servlet hosted on the international business machines cloud. Moreover, the local server could aggregate data from multiple devices on the network and perform collaborative ML to predict network parameters. With optimised hyperparameters, analytical models were incorporated in the cloud hosted Java servlets that operate on a client–server basis where the back-end communicates with Cloudant databases.\u0000\u0000\u0000Findings\u0000Regarding classification, it was found that KNN performs significantly better than MLP and SVM with a comparative precision gain of approximately 7%, when classifying both Wi-Fi and long term evolution (LTE) traffic.\u0000\u0000\u0000Originality/value\u0000Collaborative regression models using traffic collected from two devices were experimented and resulted in an increased average accuracy of 0.50% for all variables, with a multivariate MLP model.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43889779","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 : 2022-09-21DOI: 10.1108/ijpcc-06-2022-0245
Gopinath Anjinappa, Divakar Bangalore Prabhakar
Purpose The fluctuations that occurred between the power requirements have shown a higher range of voltage regulations and frequency. The fluctuations are caused because of substantial changes in the energy dissipation. The operational efficiency has been reduced when the power grid is enabled with the help of electric vehicles (EVs) that were created by the power resources. The model showed an active load matching for regulating the power and there occurred a harmonic motion in energy. The main purpose of the proposed research is to handle the energy sources for stabilization which has increased the reliability and improved the power efficiency. This study or paper aims to elaborate the security and privacy challenges present in the vehicle 2 grid (V2G) network and their impact with grid resilience. Design/methodology/approach The smart framework is proposed which works based on Internet of Things and edge computations that managed to perform an effective V2G operation. Thus, an optimum model for scheduling the charge is designed on each EV to maximize the number of users and selecting the best EV using the proposed ant colony optimization (ACO). At the first, the constructive phase of ACO where the ants in the colony generate the feasible solutions. The constructive phase with local search generates an ACO algorithm that uses the heterogeneous colony of ants and finds effectively the best-known solutions widely to overcome the problem. Findings The results obtained by the existing in-circuit serial programming-plug-in electric vehicles model in terms of power usage ranged from 0.94 to 0.96 kWh which was lower when compared to the proposed ACO that showed power usage of 0.995 to 0.939 kWh, respectively, with time. The results showed that the energy aware routed with ACO provided feasible routing solutions for the source node that provided the sensor network at its lifetime and security at the time of authentication. Originality/value The proposed ACO is aware of energy routing protocol that has been analyzed and compared with the energy utilization with respect to the sensor area network which uses power resources effectively.
{"title":"A secure IoT and edge computing based EV selection model in V2G systems using ant colony optimization algorithm","authors":"Gopinath Anjinappa, Divakar Bangalore Prabhakar","doi":"10.1108/ijpcc-06-2022-0245","DOIUrl":"https://doi.org/10.1108/ijpcc-06-2022-0245","url":null,"abstract":"\u0000Purpose\u0000The fluctuations that occurred between the power requirements have shown a higher range of voltage regulations and frequency. The fluctuations are caused because of substantial changes in the energy dissipation. The operational efficiency has been reduced when the power grid is enabled with the help of electric vehicles (EVs) that were created by the power resources. The model showed an active load matching for regulating the power and there occurred a harmonic motion in energy. The main purpose of the proposed research is to handle the energy sources for stabilization which has increased the reliability and improved the power efficiency. This study or paper aims to elaborate the security and privacy challenges present in the vehicle 2 grid (V2G) network and their impact with grid resilience.\u0000\u0000\u0000Design/methodology/approach\u0000The smart framework is proposed which works based on Internet of Things and edge computations that managed to perform an effective V2G operation. Thus, an optimum model for scheduling the charge is designed on each EV to maximize the number of users and selecting the best EV using the proposed ant colony optimization (ACO). At the first, the constructive phase of ACO where the ants in the colony generate the feasible solutions. The constructive phase with local search generates an ACO algorithm that uses the heterogeneous colony of ants and finds effectively the best-known solutions widely to overcome the problem.\u0000\u0000\u0000Findings\u0000The results obtained by the existing in-circuit serial programming-plug-in electric vehicles model in terms of power usage ranged from 0.94 to 0.96 kWh which was lower when compared to the proposed ACO that showed power usage of 0.995 to 0.939 kWh, respectively, with time. The results showed that the energy aware routed with ACO provided feasible routing solutions for the source node that provided the sensor network at its lifetime and security at the time of authentication.\u0000\u0000\u0000Originality/value\u0000The proposed ACO is aware of energy routing protocol that has been analyzed and compared with the energy utilization with respect to the sensor area network which uses power resources effectively.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43162379","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 : 2022-09-20DOI: 10.1108/ijpcc-05-2022-0213
R. Cyriac, Saleem Durai M.A.
Purpose Routing protocol for low-power lossy network (RPL) being the de facto routing protocol used by low power lossy networks needs to provide adequate routing service to mobile nodes (MNs) in the network. As RPL is designed to work under constraint power requirements, its route updating frequency is not sufficient for MNs in the network. The purpose of this study is to ensure that MNs enjoy seamless connection throughout the network with minimal handover delay. Design/methodology/approach This study proposes a load balancing mobility aware secure hybrid – RPL in which static node (SN) identifies route using metrics like expected transmission count, and path delay and parent selection are further refined by working on remaining energy for identifying the primary route and queue availability for secondary route maintenance. MNs identify route with the help of smart timers and by using received signal strength indicator sampling of parent and neighbor nodes. In this work, MNs are also secured against rank attack in RPL. Findings This model produces favorable result in terms of packet delivery ratio, delay, energy consumption and number of living nodes in the network when compared with different RPL protocols with mobility support. The proposed model reduces packet retransmission in the network by a large margin by providing load balancing to SNs and seamless connection to MNs. Originality/value In this work, a novel algorithm was developed to provide seamless handover for MNs in network. Suitable technique was developed to provide load balancing to SNs in network by maintaining appropriate secondary route.
{"title":"LMH-RPL: a load balancing and mobility aware secure hybrid routing protocol for low power lossy network","authors":"R. Cyriac, Saleem Durai M.A.","doi":"10.1108/ijpcc-05-2022-0213","DOIUrl":"https://doi.org/10.1108/ijpcc-05-2022-0213","url":null,"abstract":"\u0000Purpose\u0000Routing protocol for low-power lossy network (RPL) being the de facto routing protocol used by low power lossy networks needs to provide adequate routing service to mobile nodes (MNs) in the network. As RPL is designed to work under constraint power requirements, its route updating frequency is not sufficient for MNs in the network. The purpose of this study is to ensure that MNs enjoy seamless connection throughout the network with minimal handover delay.\u0000\u0000\u0000Design/methodology/approach\u0000This study proposes a load balancing mobility aware secure hybrid – RPL in which static node (SN) identifies route using metrics like expected transmission count, and path delay and parent selection are further refined by working on remaining energy for identifying the primary route and queue availability for secondary route maintenance. MNs identify route with the help of smart timers and by using received signal strength indicator sampling of parent and neighbor nodes. In this work, MNs are also secured against rank attack in RPL.\u0000\u0000\u0000Findings\u0000This model produces favorable result in terms of packet delivery ratio, delay, energy consumption and number of living nodes in the network when compared with different RPL protocols with mobility support. The proposed model reduces packet retransmission in the network by a large margin by providing load balancing to SNs and seamless connection to MNs.\u0000\u0000\u0000Originality/value\u0000In this work, a novel algorithm was developed to provide seamless handover for MNs in network. Suitable technique was developed to provide load balancing to SNs in network by maintaining appropriate secondary route.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43017773","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 : 2022-09-14DOI: 10.1108/ijpcc-05-2022-0197
M. Boopathi, Meena Chavan, J. J, Sanjay Kumar
Purpose The Denial of Service (DoS) attack is a category of intrusion that devours various services and resources of the organization by the dispersal of unusable traffic, so that reliable users are not capable of getting benefit from the services. In general, the DoS attackers preserve their independence by collaborating several victim machines and following authentic network traffic, which makes it more complex to detect the attack. Thus, these issues and demerits faced by existing DoS attack recognition schemes in cloud are specified as a major challenge to inventing a new attack recognition method. Design/methodology/approach This paper aims to detect DoS attack detection scheme, termed as sine cosine anti coronavirus optimization (SCACVO)-driven deep maxout network (DMN). The recorded log file is considered in this method for the attack detection process. Significant features are chosen based on Pearson correlation in the feature selection phase. The over sampling scheme is applied in the data augmentation phase, and then the attack detection is done using DMN. The DMN is trained by the SCACVO algorithm, which is formed by combining sine cosine optimization and anti-corona virus optimization techniques. Findings The SCACVO-based DMN offers maximum testing accuracy, true positive rate and true negative rate of 0.9412, 0.9541 and 0.9178, respectively. Originality/value The DoS attack detection using the proposed model is accurate and improves the effectiveness of the detection.
目的DoS (Denial of Service)攻击是一种入侵行为，它通过分散不可用的流量来吞噬组织的各种服务和资源，使可靠的用户无法从服务中获益。通常，DoS攻击者通过协作多台受害机器并跟踪真实的网络流量来保持其独立性，这使得检测攻击变得更加复杂。因此，指出了现有云环境下DoS攻击识别方案所面临的问题和缺点，这是发明一种新的攻击识别方法所面临的主要挑战。本文旨在检测DoS攻击的检测方案，称为正弦余弦抗冠状病毒优化(SCACVO)驱动的深度最大输出网络(DMN)。该方法在攻击检测过程中考虑记录的日志文件。在特征选择阶段，基于Pearson相关性选择重要特征。在数据增强阶段采用过采样方案，然后利用DMN进行攻击检测。DMN采用SCACVO算法进行训练，该算法结合了正弦余弦优化和抗冠状病毒优化技术形成。结果基于scacvo的DMN检测准确率最高，真阳性率为0.9412，真阴性率为0.9541，真阴性率为0.9178。原创性/价值利用该模型进行的DoS攻击检测准确，提高了检测的有效性。
{"title":"An approach for DoS attack detection in cloud computing using sine cosine anti coronavirus optimized deep maxout network","authors":"M. Boopathi, Meena Chavan, J. J, Sanjay Kumar","doi":"10.1108/ijpcc-05-2022-0197","DOIUrl":"https://doi.org/10.1108/ijpcc-05-2022-0197","url":null,"abstract":"\u0000Purpose\u0000The Denial of Service (DoS) attack is a category of intrusion that devours various services and resources of the organization by the dispersal of unusable traffic, so that reliable users are not capable of getting benefit from the services. In general, the DoS attackers preserve their independence by collaborating several victim machines and following authentic network traffic, which makes it more complex to detect the attack. Thus, these issues and demerits faced by existing DoS attack recognition schemes in cloud are specified as a major challenge to inventing a new attack recognition method.\u0000\u0000\u0000Design/methodology/approach\u0000This paper aims to detect DoS attack detection scheme, termed as sine cosine anti coronavirus optimization (SCACVO)-driven deep maxout network (DMN). The recorded log file is considered in this method for the attack detection process. Significant features are chosen based on Pearson correlation in the feature selection phase. The over sampling scheme is applied in the data augmentation phase, and then the attack detection is done using DMN. The DMN is trained by the SCACVO algorithm, which is formed by combining sine cosine optimization and anti-corona virus optimization techniques.\u0000\u0000\u0000Findings\u0000The SCACVO-based DMN offers maximum testing accuracy, true positive rate and true negative rate of 0.9412, 0.9541 and 0.9178, respectively.\u0000\u0000\u0000Originality/value\u0000The DoS attack detection using the proposed model is accurate and improves the effectiveness of the detection.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46641449","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 : 2022-09-01DOI: 10.1108/ijpcc-05-2022-0200
A. R., Nayana J. S., Rajarshee Mondal
Purpose The purpose of optimal protocol prediction and the benefits offered by quantum key distribution (QKD), including unbreakable security, there is a growing interest in the practical realization of quantum communication. Realization of the optimal protocol predictor in quantum key distribution is a critical step toward commercialization of QKD. Design/methodology/approach The proposed work designs a machine learning model such as K-nearest neighbor algorithm, convolutional neural networks, decision tree (DT), support vector machine and random forest (RF) for optimal protocol selector for quantum key distribution network (QKDN). Findings Because of the effectiveness of machine learning methods in predicting effective solutions using data, these models will be the best optimal protocol selectors for achieving high efficiency for QKDN. The results show that the best machine learning method for predicting optimal protocol in QKD is the RF algorithm. It also validates the effectiveness of machine learning in optimal protocol selection. Originality/value The proposed work was done using algorithms like the local search algorithm or exhaustive traversal, however the major downside of using these algorithms is that it takes a very long time to revert back results, which is unacceptable for commercial systems. Hence, machine learning methods are proposed to see the effectiveness of prediction for achieving high efficiency.
{"title":"Real-time optimal protocol prediction of quantum key distribution using machine learning","authors":"A. R., Nayana J. S., Rajarshee Mondal","doi":"10.1108/ijpcc-05-2022-0200","DOIUrl":"https://doi.org/10.1108/ijpcc-05-2022-0200","url":null,"abstract":"\u0000Purpose\u0000The purpose of optimal protocol prediction and the benefits offered by quantum key distribution (QKD), including unbreakable security, there is a growing interest in the practical realization of quantum communication. Realization of the optimal protocol predictor in quantum key distribution is a critical step toward commercialization of QKD.\u0000\u0000\u0000Design/methodology/approach\u0000The proposed work designs a machine learning model such as K-nearest neighbor algorithm, convolutional neural networks, decision tree (DT), support vector machine and random forest (RF) for optimal protocol selector for quantum key distribution network (QKDN).\u0000\u0000\u0000Findings\u0000Because of the effectiveness of machine learning methods in predicting effective solutions using data, these models will be the best optimal protocol selectors for achieving high efficiency for QKDN. The results show that the best machine learning method for predicting optimal protocol in QKD is the RF algorithm. It also validates the effectiveness of machine learning in optimal protocol selection.\u0000\u0000\u0000Originality/value\u0000The proposed work was done using algorithms like the local search algorithm or exhaustive traversal, however the major downside of using these algorithms is that it takes a very long time to revert back results, which is unacceptable for commercial systems. Hence, machine learning methods are proposed to see the effectiveness of prediction for achieving high efficiency.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46475330","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 : 2022-08-30DOI: 10.1108/ijpcc-05-2022-0181
D. E, S. A.
Purpose Intelligent prediction of node localization in wireless sensor networks (WSNs) is a major concern for researchers. The huge amount of data generated by modern sensor array systems required computationally efficient calibration techniques. This paper aims to improve localization accuracy by identifying obstacles in the optimization process and network scenarios. Design/methodology/approach The proposed method is used to incorporate distance estimation between nodes and packet transmission hop counts. This estimation is used in the proposed support vector machine (SVM) to find the network path using a time difference of arrival (TDoA)-based SVM. However, if the data set is noisy, SVM is prone to poor optimization, which leads to overlapping of target classes and the pathways through TDoA. The enhanced gray wolf optimization (EGWO) technique is introduced to eliminate overlapping target classes in the SVM. Findings The performance and efficacy of the model using existing TDoA methodologies are analyzed. The simulation results show that the proposed TDoA-EGWO achieves a higher rate of detection efficiency of 98% and control overhead of 97.8% and a better packet delivery ratio than other traditional methods. Originality/value The proposed method is successful in detecting the unknown position of the sensor node with a detection rate greater than that of other methods.
{"title":"Enhanced gray wolf optimization for estimation of time difference of arrival in WSNs","authors":"D. E, S. A.","doi":"10.1108/ijpcc-05-2022-0181","DOIUrl":"https://doi.org/10.1108/ijpcc-05-2022-0181","url":null,"abstract":"Purpose\u0000Intelligent prediction of node localization in wireless sensor networks (WSNs) is a major concern for researchers. The huge amount of data generated by modern sensor array systems required computationally efficient calibration techniques. This paper aims to improve localization accuracy by identifying obstacles in the optimization process and network scenarios.\u0000\u0000\u0000Design/methodology/approach\u0000The proposed method is used to incorporate distance estimation between nodes and packet transmission hop counts. This estimation is used in the proposed support vector machine (SVM) to find the network path using a time difference of arrival (TDoA)-based SVM. However, if the data set is noisy, SVM is prone to poor optimization, which leads to overlapping of target classes and the pathways through TDoA. The enhanced gray wolf optimization (EGWO) technique is introduced to eliminate overlapping target classes in the SVM.\u0000\u0000\u0000Findings\u0000The performance and efficacy of the model using existing TDoA methodologies are analyzed. The simulation results show that the proposed TDoA-EGWO achieves a higher rate of detection efficiency of 98% and control overhead of 97.8% and a better packet delivery ratio than other traditional methods.\u0000\u0000\u0000Originality/value\u0000The proposed method is successful in detecting the unknown position of the sensor node with a detection rate greater than that of other methods.","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46316328","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 : 2022-08-22DOI: 10.1108/ijpcc-05-2022-0184
R. Bhimanpallewar, S. Khan, K. Joshil Raj, K. Gulati, N. Bhasin, Roop Raj
Purpose Federation analytics approaches are a present area of study that has already progressed beyond the analysis of metrics and counts. It is possible to acquire aggregated information about on-device data by training machine learning models using federated learning techniques without any of the raw data ever having to leave the devices in the issue. Web browser forensics research has been focused on individual Web browsers or architectural analysis of specific log files rather than on broad topics. This paper aims to propose major tools used for Web browser analysis. Design/methodology/approach Each kind of Web browser has its own unique set of features. This allows the user to choose their preferred browsers or to check out many browsers at once. If a forensic examiner has access to just one Web browser's log files, he/she makes it difficult to determine which sites a person has visited. The agent must thus be capable of analyzing all currently available Web browsers on a single workstation and doing an integrated study of various Web browsers. Findings Federated learning has emerged as a training paradigm in such settings. Web browser forensics research in general has focused on certain browsers or the computational modeling of specific log files. Internet users engage in a wide range of activities using an internet browser, such as searching for information and sending e-mails. Originality/value It is also essential that the investigator have access to user activity when conducting an inquiry. This data, which may be used to assess information retrieval activities, is very critical. In this paper, the authors purposed a major tool used for Web browser analysis. This study's proposed algorithm is capable of protecting data privacy effectively in real-world experiments.
{"title":"Federate learning on Web browsing data with statically and machine learning technique","authors":"R. Bhimanpallewar, S. Khan, K. Joshil Raj, K. Gulati, N. Bhasin, Roop Raj","doi":"10.1108/ijpcc-05-2022-0184","DOIUrl":"https://doi.org/10.1108/ijpcc-05-2022-0184","url":null,"abstract":"\u0000Purpose\u0000Federation analytics approaches are a present area of study that has already progressed beyond the analysis of metrics and counts. It is possible to acquire aggregated information about on-device data by training machine learning models using federated learning techniques without any of the raw data ever having to leave the devices in the issue. Web browser forensics research has been focused on individual Web browsers or architectural analysis of specific log files rather than on broad topics. This paper aims to propose major tools used for Web browser analysis.\u0000\u0000\u0000Design/methodology/approach\u0000Each kind of Web browser has its own unique set of features. This allows the user to choose their preferred browsers or to check out many browsers at once. If a forensic examiner has access to just one Web browser's log files, he/she makes it difficult to determine which sites a person has visited. The agent must thus be capable of analyzing all currently available Web browsers on a single workstation and doing an integrated study of various Web browsers.\u0000\u0000\u0000Findings\u0000Federated learning has emerged as a training paradigm in such settings. Web browser forensics research in general has focused on certain browsers or the computational modeling of specific log files. Internet users engage in a wide range of activities using an internet browser, such as searching for information and sending e-mails.\u0000\u0000\u0000Originality/value\u0000It is also essential that the investigator have access to user activity when conducting an inquiry. This data, which may be used to assess information retrieval activities, is very critical. In this paper, the authors purposed a major tool used for Web browser analysis. This study's proposed algorithm is capable of protecting data privacy effectively in real-world experiments.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41697076","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 : 2022-08-19DOI: 10.1108/ijpcc-02-2022-0034
A. More, Dipti P Rana
Purpose Referred data set produces reliable information about the network flows and common attacks meeting with real-world criteria. Accordingly, this study aims to focus on the use of imbalanced intrusion detection benchmark knowledge discovery in database (KDD) data set. KDD data set is most preferably used by many researchers for experimentation and analysis. The proposed algorithm improvised random forest classification with error tuning factors (IRFCETF) deals with experimentation on KDD data set and evaluates the performance of a complete set of network traffic features through IRFCETF. Design/methodology/approach In the current era of applications, the attention of researchers is immersed by a diverse number of existing time applications that deals with imbalanced data classification (ImDC). Real-time application areas, artificial intelligence (AI), Industrial Internet of Things (IIoT), etc. are dealing ImDC undergo with diverted classification performance due to skewed data distribution (SkDD). There are numerous application areas that deal with SkDD. Many of the data applications in AI and IIoT face the diverted data classification rate in SkDD. In recent advancements, there is an exponential expansion in the volume of computer network data and related application developments. Intrusion detection is one of the demanding applications of ImDC. The proposed study focusses on imbalanced intrusion benchmark data set, KDD data set and other benchmark data set with the proposed IRFCETF approach. IRFCETF justifies the enriched classification performance on imbalanced data set over the existing approach. The purpose of this work is to review imbalanced data applications in numerous application areas including AI and IIoT and tuning the performance with respect to principal component analysis. This study also focusses on the out-of-bag error performance-tuning factor. Findings Experimental results on KDD data set shows that proposed algorithm gives enriched performance. For referred intrusion detection data set, IRFCETF classification accuracy is 99.57% and error rate is 0.43%. Research limitations/implications This research work extended for further improvements in classification techniques with multiple correspondence analysis (MCA); hierarchical MCA can be focussed with the use of classification models for wide range of skewed data sets. Practical implications The metrics enhancement is measurable and helpful in dealing with intrusion detection systems–related imbalanced applications in current application domains such as security, AI and IIoT digitization. Analytical results show improvised metrics of the proposed approach than other traditional machine learning algorithms. Thus, error-tuning parameter creates a measurable impact on classification accuracy is justified with the proposed IRFCETF. Social implications Proposed algorithm is useful in numerous IIoT applications such as health care, machinery automation etc. Originalit
{"title":"AI federated learning based improvised random Forest classifier with error reduction mechanism for skewed data sets","authors":"A. More, Dipti P Rana","doi":"10.1108/ijpcc-02-2022-0034","DOIUrl":"https://doi.org/10.1108/ijpcc-02-2022-0034","url":null,"abstract":"\u0000Purpose\u0000Referred data set produces reliable information about the network flows and common attacks meeting with real-world criteria. Accordingly, this study aims to focus on the use of imbalanced intrusion detection benchmark knowledge discovery in database (KDD) data set. KDD data set is most preferably used by many researchers for experimentation and analysis. The proposed algorithm improvised random forest classification with error tuning factors (IRFCETF) deals with experimentation on KDD data set and evaluates the performance of a complete set of network traffic features through IRFCETF.\u0000\u0000\u0000Design/methodology/approach\u0000In the current era of applications, the attention of researchers is immersed by a diverse number of existing time applications that deals with imbalanced data classification (ImDC). Real-time application areas, artificial intelligence (AI), Industrial Internet of Things (IIoT), etc. are dealing ImDC undergo with diverted classification performance due to skewed data distribution (SkDD). There are numerous application areas that deal with SkDD. Many of the data applications in AI and IIoT face the diverted data classification rate in SkDD. In recent advancements, there is an exponential expansion in the volume of computer network data and related application developments. Intrusion detection is one of the demanding applications of ImDC. The proposed study focusses on imbalanced intrusion benchmark data set, KDD data set and other benchmark data set with the proposed IRFCETF approach. IRFCETF justifies the enriched classification performance on imbalanced data set over the existing approach. The purpose of this work is to review imbalanced data applications in numerous application areas including AI and IIoT and tuning the performance with respect to principal component analysis. This study also focusses on the out-of-bag error performance-tuning factor.\u0000\u0000\u0000Findings\u0000Experimental results on KDD data set shows that proposed algorithm gives enriched performance. For referred intrusion detection data set, IRFCETF classification accuracy is 99.57% and error rate is 0.43%.\u0000\u0000\u0000Research limitations/implications\u0000This research work extended for further improvements in classification techniques with multiple correspondence analysis (MCA); hierarchical MCA can be focussed with the use of classification models for wide range of skewed data sets.\u0000\u0000\u0000Practical implications\u0000The metrics enhancement is measurable and helpful in dealing with intrusion detection systems–related imbalanced applications in current application domains such as security, AI and IIoT digitization. Analytical results show improvised metrics of the proposed approach than other traditional machine learning algorithms. Thus, error-tuning parameter creates a measurable impact on classification accuracy is justified with the proposed IRFCETF.\u0000\u0000\u0000Social implications\u0000Proposed algorithm is useful in numerous IIoT applications such as health care, machinery automation etc.\u0000\u0000\u0000Originalit","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42555185","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 : 2022-08-16DOI: 10.1108/ijpcc-10-2021-0248
A. Gona, Subramoniam M.
Purpose Biometric scans using fingerprints are widely used for security purposes. Eventually, for authentication purposes, fingerprint scans are not very reliable because they can be faked by obtaining a sample of the fingerprint of the person. There are a few spoof detection techniques available to reduce the incidence of spoofing of the biometric system. Among them, the most commonly used is the binary classification technique that detects real or fake fingerprints based on the fingerprint samples provided during training. However, this technique fails when it is provided with samples formed using other spoofing techniques that are different from the spoofing techniques covered in the training samples. This paper aims to improve the liveness detection accuracy by fusing electrocardiogram (ECG) and fingerprint. Design/methodology/approach In this paper, to avoid this limitation, an efficient liveness detection algorithm is developed using the fusion of ECG signals captured from the fingertips and fingerprint data in Internet of Things (IoT) environment. The ECG signal will ensure the detection of real fingerprint samples from fake ones. Findings Single model fingerprint methods have some disadvantages, such as noisy data and position of the fingerprint. To overcome this, fusion of both ECG and fingerprint is done so that the combined data improves the detection accuracy. Originality/value System security is improved in this approach, and the fingerprint recognition rate is also improved. IoT-based approach is used in this work to reduce the computation burden of data processing systems.
{"title":"IoT-based multimodal liveness detection using the fusion of ECG and fingerprint","authors":"A. Gona, Subramoniam M.","doi":"10.1108/ijpcc-10-2021-0248","DOIUrl":"https://doi.org/10.1108/ijpcc-10-2021-0248","url":null,"abstract":"\u0000Purpose\u0000Biometric scans using fingerprints are widely used for security purposes. Eventually, for authentication purposes, fingerprint scans are not very reliable because they can be faked by obtaining a sample of the fingerprint of the person. There are a few spoof detection techniques available to reduce the incidence of spoofing of the biometric system. Among them, the most commonly used is the binary classification technique that detects real or fake fingerprints based on the fingerprint samples provided during training. However, this technique fails when it is provided with samples formed using other spoofing techniques that are different from the spoofing techniques covered in the training samples. This paper aims to improve the liveness detection accuracy by fusing electrocardiogram (ECG) and fingerprint.\u0000\u0000\u0000Design/methodology/approach\u0000In this paper, to avoid this limitation, an efficient liveness detection algorithm is developed using the fusion of ECG signals captured from the fingertips and fingerprint data in Internet of Things (IoT) environment. The ECG signal will ensure the detection of real fingerprint samples from fake ones.\u0000\u0000\u0000Findings\u0000Single model fingerprint methods have some disadvantages, such as noisy data and position of the fingerprint. To overcome this, fusion of both ECG and fingerprint is done so that the combined data improves the detection accuracy.\u0000\u0000\u0000Originality/value\u0000System security is improved in this approach, and the fingerprint recognition rate is also improved. IoT-based approach is used in this work to reduce the computation burden of data processing systems.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44441132","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 : 2022-08-10DOI: 10.1108/ijpcc-03-2022-0123
Shoayee Alotaibi
Purpose Be that as it may, BC is computationally costly, has restricted versatility and brings about critical transmission capacity upward and postpones, those seems not to be fit with Internet of Things (IoT) setting. A lightweight scalable blockchain (LSB) which is improved toward IoT necessities is suggested by the authors and investigates LSB within brilliant house setup like an agent model to enable more extensive IoT apps. Less asset gadgets inside brilliant house advantage via any unified chief which lays out common units for correspondence also cycles generally approaching and active solicitations. Design/methodology/approach Federated learning and blockchain (BC) have drawn in huge consideration due to the unchanging property and the relevant safety measure and protection benefits. FL and IoT safety measures’ difficulties can be conquered possibly by BC. Findings LSB accomplishes fragmentation through shaping any overlaid web with more asset gadgets mutually deal with a public BC and federated learning which assures complete protection also security. Originality/value This overlaid is coordinated as without error bunches and reduces extra efforts, also batch leader will be with answer to handle commonly known BCs. LSB joins some of advancements which also includes computations related to lesser weighing agreement, optimal belief also throughput regulatory body.
{"title":"A novel Internet of Things and federated learning-based privacy protection in blockchain technology","authors":"Shoayee Alotaibi","doi":"10.1108/ijpcc-03-2022-0123","DOIUrl":"https://doi.org/10.1108/ijpcc-03-2022-0123","url":null,"abstract":"\u0000Purpose\u0000Be that as it may, BC is computationally costly, has restricted versatility and brings about critical transmission capacity upward and postpones, those seems not to be fit with Internet of Things (IoT) setting. A lightweight scalable blockchain (LSB) which is improved toward IoT necessities is suggested by the authors and investigates LSB within brilliant house setup like an agent model to enable more extensive IoT apps. Less asset gadgets inside brilliant house advantage via any unified chief which lays out common units for correspondence also cycles generally approaching and active solicitations.\u0000\u0000\u0000Design/methodology/approach\u0000Federated learning and blockchain (BC) have drawn in huge consideration due to the unchanging property and the relevant safety measure and protection benefits. FL and IoT safety measures’ difficulties can be conquered possibly by BC.\u0000\u0000\u0000Findings\u0000LSB accomplishes fragmentation through shaping any overlaid web with more asset gadgets mutually deal with a public BC and federated learning which assures complete protection also security.\u0000\u0000\u0000Originality/value\u0000This overlaid is coordinated as without error bunches and reduces extra efforts, also batch leader will be with answer to handle commonly known BCs. LSB joins some of advancements which also includes computations related to lesser weighing agreement, optimal belief also throughput regulatory body.\u0000","PeriodicalId":43952,"journal":{"name":"International Journal of Pervasive Computing and Communications","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2022-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42345909","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：