Pub Date : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377414
Wenyi Xu, Xiaofeng Gao, Yin Sheng, Guihai Chen
Recommendation system is a popular research field. In the age of information explosion, a reliable recommendation system is necessary for users. There are a certain number of approaches to do recommendation work. Reinforcement learning is one of the methods used in recommendation system. In this paper, we use reinforcement learning to recommend items to target users, and achieved a rather good result. To give a better user experience, we have added explanations for recommended items. The explanation is realized by Knowledge Graph. We use TransE to embed target users and items, and it helps manage the information of users and items. Our method KGDQN combines Knowledge Graph and reinforcement learning, which can decide the proper recommendation items, and find the reasoning paths from target users to recommended items. Redundant edges are pruned and the DQN model renders a reward function which gives back the result of recommended items, and the explanation paths of the recommendation. Experiments are conducted on Amazon datasets which show the superior performance of KGDQN
{"title":"Recommendation System with Reasoning Path Based on DQN and Knowledge Graph","authors":"Wenyi Xu, Xiaofeng Gao, Yin Sheng, Guihai Chen","doi":"10.1109/IMCOM51814.2021.9377414","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377414","url":null,"abstract":"Recommendation system is a popular research field. In the age of information explosion, a reliable recommendation system is necessary for users. There are a certain number of approaches to do recommendation work. Reinforcement learning is one of the methods used in recommendation system. In this paper, we use reinforcement learning to recommend items to target users, and achieved a rather good result. To give a better user experience, we have added explanations for recommended items. The explanation is realized by Knowledge Graph. We use TransE to embed target users and items, and it helps manage the information of users and items. Our method KGDQN combines Knowledge Graph and reinforcement learning, which can decide the proper recommendation items, and find the reasoning paths from target users to recommended items. Redundant edges are pruned and the DQN model renders a reward function which gives back the result of recommended items, and the explanation paths of the recommendation. Experiments are conducted on Amazon datasets which show the superior performance of KGDQN","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"239 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131653537","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377431
Md. Nazmus Saadat, Hasibul Kabir, Muhammad Shuaib, R. Nassr, Mohd Nizam Husen, Husna Osman
Event detection is a cutting-edge problem in video image processing which is not that straight forward to solve. Hence, we perform a thorough search for state of the art in solving the issues in this area. There are many applications of event detection in this age of cybercrime. We target to propose a best solution to outperform existing research and make a positive development in it. We have discussed quite a long list of existing literature reviews in this hope that it would help us and anyone else working on the same as a guideline and one stop reading.
{"title":"Research Issues & State of the Art Challenges in Event Detection","authors":"Md. Nazmus Saadat, Hasibul Kabir, Muhammad Shuaib, R. Nassr, Mohd Nizam Husen, Husna Osman","doi":"10.1109/IMCOM51814.2021.9377431","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377431","url":null,"abstract":"Event detection is a cutting-edge problem in video image processing which is not that straight forward to solve. Hence, we perform a thorough search for state of the art in solving the issues in this area. There are many applications of event detection in this age of cybercrime. We target to propose a best solution to outperform existing research and make a positive development in it. We have discussed quite a long list of existing literature reviews in this hope that it would help us and anyone else working on the same as a guideline and one stop reading.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133219023","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377365
Joonhyung Lee, B. Jeon, Seung Hwan Song, Hyoukryeol Choi
By mounting a projector on a soft unmanned aerial vehicle (UAV) called “S-CLOVD”, one can freely move and show visual information on the floor. One practical problem with the UAV-projector is the distortion of the projected image caused by UAV disturbance. In this paper, we propose a geometry-based method of stabilizing the floor projected image using the flight information of the UAV (e.g altitude, roll, pitch, yaw). By visual comparison of the stabilized images, its stabilization performance is shown much improved. In this paper, The UAV-projector system and stabilization algorithm are proposed. And, the performance of proposed idea is validated with experimental data.
{"title":"Stabilization of Floor Projection Image with Soft Unmanned Aerial Vehicle Projector","authors":"Joonhyung Lee, B. Jeon, Seung Hwan Song, Hyoukryeol Choi","doi":"10.1109/IMCOM51814.2021.9377365","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377365","url":null,"abstract":"By mounting a projector on a soft unmanned aerial vehicle (UAV) called “S-CLOVD”, one can freely move and show visual information on the floor. One practical problem with the UAV-projector is the distortion of the projected image caused by UAV disturbance. In this paper, we propose a geometry-based method of stabilizing the floor projected image using the flight information of the UAV (e.g altitude, roll, pitch, yaw). By visual comparison of the stabilized images, its stabilization performance is shown much improved. In this paper, The UAV-projector system and stabilization algorithm are proposed. And, the performance of proposed idea is validated with experimental data.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123143206","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377368
Areum Kim, Sukhan Lee
Accurate estimation of the State-of-Health (SOH) of a battery in a real-world operation is important for predicting its aging or anomaly status for the condition based maintenance as well as for the safety. Conventional approaches to the SOH estimation based on battery discharging characteristics, such as voltage and charge variations, deal mainly with the constant discharging current at individual cycles. However, it is clear that, in order to have the SOH estimation of a battery viable in real-world applications, the intra- and inter-cycle variation of discharging current should be taken into consideration. This paper shows that the battery SOH can be estimated accurately, with a sufficient generalization power, even under the varying intra- and inter-cycle discharging currents incurred by realtime payload variations. Specifically, first, we propose to represent the discharging characteristics of a battery by the four features: the entropies of the voltage and current distributions as well as the rated amounts of the total charge and the average current within a cycle. A sequence of these four feature values obtained along the progress of cycles are then input to a stacked LSTM for SOH estimation. Experiments are conducted based on CALCE datasets and the datasets collected under the intra-cycle time-varying discharging currents. The results indicate that the proposed method is able to obtain the accuracy of SOH estimation as high as, or even better than, that of the constant discharging current under varying discharging currents.
{"title":"Online State of Health Estimation of Batteries under Varying Discharging Current Based on a Long Short Term Memory","authors":"Areum Kim, Sukhan Lee","doi":"10.1109/IMCOM51814.2021.9377368","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377368","url":null,"abstract":"Accurate estimation of the State-of-Health (SOH) of a battery in a real-world operation is important for predicting its aging or anomaly status for the condition based maintenance as well as for the safety. Conventional approaches to the SOH estimation based on battery discharging characteristics, such as voltage and charge variations, deal mainly with the constant discharging current at individual cycles. However, it is clear that, in order to have the SOH estimation of a battery viable in real-world applications, the intra- and inter-cycle variation of discharging current should be taken into consideration. This paper shows that the battery SOH can be estimated accurately, with a sufficient generalization power, even under the varying intra- and inter-cycle discharging currents incurred by realtime payload variations. Specifically, first, we propose to represent the discharging characteristics of a battery by the four features: the entropies of the voltage and current distributions as well as the rated amounts of the total charge and the average current within a cycle. A sequence of these four feature values obtained along the progress of cycles are then input to a stacked LSTM for SOH estimation. Experiments are conducted based on CALCE datasets and the datasets collected under the intra-cycle time-varying discharging currents. The results indicate that the proposed method is able to obtain the accuracy of SOH estimation as high as, or even better than, that of the constant discharging current under varying discharging currents.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123589295","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377327
M. Hossain, Tangina Sultana, Md. Alamgir Hossain, E. Huh
Multi-Access Edge Computing (MEC) is a promising candidate to handle the enormous computation demands of many emerging applications and the ever-growing user's quality-of-service (QoS) requirements. However, due to the limitation of computing resource capacity of a distinct edge server, most of the previous studies have proposed a collaboration approach. For collaboration, they considered vertical offloading between mobile with edge computing or edge with cloud computing for taking the advantages of both these technologies. Therefore, these approaches ignored the neighboring edge server having spare computing resources in the same tier. This paper thus proposes edge orchestration based computation peer offloading (EOPO) scheme among the edge servers in the same tier. The main objective is to share the computation resources among the edge servers. Our proposed approach selects the optimal computational node for task offloading based on fuzzy rules. Simulation results corroborate that fuzzy decision based computation peer offloading scheme significantly improves the performance of edge computing. Our proposed EOPO scheme outperformed the two reference schemes which can reduce the average task completion time and task failure rate at approximately 36% and 80.5% respectively when compared with the local edge offloading (LEO) scheme; and at approximately 25.4% and 67.2% respectively when compared with two-tier based offloading between edge with cloud (TTO) scheme.
{"title":"Edge Orchestration Based Computation Peer Offloading in MEC-Enabled Networks: A Fuzzy Logic Approach","authors":"M. Hossain, Tangina Sultana, Md. Alamgir Hossain, E. Huh","doi":"10.1109/IMCOM51814.2021.9377327","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377327","url":null,"abstract":"Multi-Access Edge Computing (MEC) is a promising candidate to handle the enormous computation demands of many emerging applications and the ever-growing user's quality-of-service (QoS) requirements. However, due to the limitation of computing resource capacity of a distinct edge server, most of the previous studies have proposed a collaboration approach. For collaboration, they considered vertical offloading between mobile with edge computing or edge with cloud computing for taking the advantages of both these technologies. Therefore, these approaches ignored the neighboring edge server having spare computing resources in the same tier. This paper thus proposes edge orchestration based computation peer offloading (EOPO) scheme among the edge servers in the same tier. The main objective is to share the computation resources among the edge servers. Our proposed approach selects the optimal computational node for task offloading based on fuzzy rules. Simulation results corroborate that fuzzy decision based computation peer offloading scheme significantly improves the performance of edge computing. Our proposed EOPO scheme outperformed the two reference schemes which can reduce the average task completion time and task failure rate at approximately 36% and 80.5% respectively when compared with the local edge offloading (LEO) scheme; and at approximately 25.4% and 67.2% respectively when compared with two-tier based offloading between edge with cloud (TTO) scheme.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124940602","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377373
Eric Tjon, M. Moh, Teng-Sheng Moh
Advances in generative models and manipulation techniques have given rise to digitally altered videos known as deepfakes. These videos are difficult to identify for both humans and machines. Modern detection methods exploit various weaknesses in deepfake videos, such as visual artifacts and inconsistent posing. In this paper, we describe a novel architecture called Eff-YNet designed to detect visual differences between altered and unaltered areas. The architecture combines an EfficientNet encoder and a U-Net with a classification branch into a model capable of both classifying and segmenting deepfake videos. The task of segmentation helps train the classifier and also produces useful segmentation masks. We also implement ResNet 3D to detect spatiotemporal inconsistencies. To test these models, we run experiments against the Deepfake Detection Challenge dataset and show improvements over baseline classification models. Furthermore, we find that an ensemble of these two approaches improves performance over a single approach alone.
{"title":"Eff-YNet: A Dual Task Network for DeepFake Detection and Segmentation","authors":"Eric Tjon, M. Moh, Teng-Sheng Moh","doi":"10.1109/IMCOM51814.2021.9377373","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377373","url":null,"abstract":"Advances in generative models and manipulation techniques have given rise to digitally altered videos known as deepfakes. These videos are difficult to identify for both humans and machines. Modern detection methods exploit various weaknesses in deepfake videos, such as visual artifacts and inconsistent posing. In this paper, we describe a novel architecture called Eff-YNet designed to detect visual differences between altered and unaltered areas. The architecture combines an EfficientNet encoder and a U-Net with a classification branch into a model capable of both classifying and segmenting deepfake videos. The task of segmentation helps train the classifier and also produces useful segmentation masks. We also implement ResNet 3D to detect spatiotemporal inconsistencies. To test these models, we run experiments against the Deepfake Detection Challenge dataset and show improvements over baseline classification models. Furthermore, we find that an ensemble of these two approaches improves performance over a single approach alone.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126096736","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377418
Md. Ratul Amin, M. Zuhairi, Md. Nazmus Saadat
Blockchain is a decentralized and immutable technology which offers transparency for the digital world, where habitual technology does not. The novel blockchain technology may be employed by many sectors, i.e., healthcare, bank, government services, and supply chain. In particular, Biomedical Engineering Supply Chain (BESC) is a significant part of the medical sector that supplies equipment for the medical sector i.e., Covid-19 testing kit, PPE (Personal Protection Equipment), and medicine. The biomedical product should be able to be traced and the data secured; otherwise, the initial data may be modified and potentially risking patients and the public. Nevertheless, the conventional centralized technology creates a leakage point and as such, compromises data security. This paper proposes a new data dealing approach with using Hyperledger Fabric Blockchain-based BESC to alleviate the centralized controllable and operational issues. The blockchain-based BESC is a novel approach, which can control the users and subsequently eliminate the possibility of tampering within the blockchain system when stored.
{"title":"Transparent Data Dealing: Hyperledger Fabric Based Biomedical Engineering Supply Chain","authors":"Md. Ratul Amin, M. Zuhairi, Md. Nazmus Saadat","doi":"10.1109/IMCOM51814.2021.9377418","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377418","url":null,"abstract":"Blockchain is a decentralized and immutable technology which offers transparency for the digital world, where habitual technology does not. The novel blockchain technology may be employed by many sectors, i.e., healthcare, bank, government services, and supply chain. In particular, Biomedical Engineering Supply Chain (BESC) is a significant part of the medical sector that supplies equipment for the medical sector i.e., Covid-19 testing kit, PPE (Personal Protection Equipment), and medicine. The biomedical product should be able to be traced and the data secured; otherwise, the initial data may be modified and potentially risking patients and the public. Nevertheless, the conventional centralized technology creates a leakage point and as such, compromises data security. This paper proposes a new data dealing approach with using Hyperledger Fabric Blockchain-based BESC to alleviate the centralized controllable and operational issues. The blockchain-based BESC is a novel approach, which can control the users and subsequently eliminate the possibility of tampering within the blockchain system when stored.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128138501","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377420
Yoga Pristyanto, A. F. Nugraha, Irfan Pratama, Akhmad Dahlan, Lucky Adhikrisna Wirasakti
In the field of machine learning, the existence of class imbalances in the dataset will make the resulting model have less than optimal performance. Theoretically, the single classifier has a weakness for class imbalance conditions in the datasets because of the majority of single classifiers tend to work by recognizing patterns in the majority class the datasets are not balanced. So, the performance cannot be maximized. In this study, two approaches were introduced to deal with class imbalance conditions in the dataset. The first approach uses ADASYN as resampling while the second approach uses the Stacking algorithm as meta-learning. After conducting a test using 5 datasets with different imbalanced ratios, it shows that the proposed method produced the highest g-mean and AUC score compared to the other classification algorithms. The proposed method in this study is the stacking algorithm between the SVM and Random Forest algorithms and the addition of ADASYN in the resampling process. Hence, the proposed method can be a solution for handling class imbalance in datasets. However, this study has limitations such as the dataset used is a dataset with a binary class category. For this reason, for the future work, testing will be suggested using the imbalanced class dataset with the multiclass datasets.
{"title":"Dual Approach to Handling Imbalanced Class in Datasets Using Oversampling and Ensemble Learning Techniques","authors":"Yoga Pristyanto, A. F. Nugraha, Irfan Pratama, Akhmad Dahlan, Lucky Adhikrisna Wirasakti","doi":"10.1109/IMCOM51814.2021.9377420","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377420","url":null,"abstract":"In the field of machine learning, the existence of class imbalances in the dataset will make the resulting model have less than optimal performance. Theoretically, the single classifier has a weakness for class imbalance conditions in the datasets because of the majority of single classifiers tend to work by recognizing patterns in the majority class the datasets are not balanced. So, the performance cannot be maximized. In this study, two approaches were introduced to deal with class imbalance conditions in the dataset. The first approach uses ADASYN as resampling while the second approach uses the Stacking algorithm as meta-learning. After conducting a test using 5 datasets with different imbalanced ratios, it shows that the proposed method produced the highest g-mean and AUC score compared to the other classification algorithms. The proposed method in this study is the stacking algorithm between the SVM and Random Forest algorithms and the addition of ADASYN in the resampling process. Hence, the proposed method can be a solution for handling class imbalance in datasets. However, this study has limitations such as the dataset used is a dataset with a binary class category. For this reason, for the future work, testing will be suggested using the imbalanced class dataset with the multiclass datasets.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126718195","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 : 2021-01-04DOI: 10.1109/IMCOM51814.2021.9377357
Teresia Ankome, G. Lusilao-Zodi
In the recent years, mobile ad hoc wireless networks (MANETs) have experienced a tremendous rise in popularity and usage due to their flexibility and ability to provide connectivity from anywhere at any time. In general, MANETs provide mobile communication to participating nodes in situation where nodes do not need access to an existing network infrastructure. MANETs have a network topology that changes over time due to lack of infrastructure and mobility of nodes. Detection of a malicious node in MANETs is hard to achieve due to the dynamic nature of the relationships between moving node and the nature of the wireless channel. Most traditional Intrusion Detection System (IDS) are designed to operate in a centralized manner; and do not operate properly in MANET because data in MANETs is distributed in different network devices. In this paper, we present an Hierarchical Cooperative Intrusion Detection Method (HCIDM) to secure packets routing in MANETs. HCIDM is a distributed intrusion detection mechanism that uses collaboration between nodes to detect active attacks against the routing table of a mobile ad hoc network. HCIDM reduces the effectiveness of the attack by informing other nodes about the existence of a malicious node to keep the performance of the network within an acceptable level. The novelty of the mechanism lies in the way the responsibility to protect the networks is distributed among nodes, the trust level is computed and the information about the presence of a malicious is communicated to potential victim. HCIDM is coded using the Network Simulator (NS-2) in an ad hoc on demand distance vector enable MANET during a black hole attack. It is found that the HCIDM works efficiently in comparison with an existing Collaborative Clustering Intrusion Detection Mechanism (CCIDM), in terms of delivery ratio, delay and throughput.
{"title":"Hierarchical Cooperative Intrusion Detection Method for MANETs (HCIDM)","authors":"Teresia Ankome, G. Lusilao-Zodi","doi":"10.1109/IMCOM51814.2021.9377357","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377357","url":null,"abstract":"In the recent years, mobile ad hoc wireless networks (MANETs) have experienced a tremendous rise in popularity and usage due to their flexibility and ability to provide connectivity from anywhere at any time. In general, MANETs provide mobile communication to participating nodes in situation where nodes do not need access to an existing network infrastructure. MANETs have a network topology that changes over time due to lack of infrastructure and mobility of nodes. Detection of a malicious node in MANETs is hard to achieve due to the dynamic nature of the relationships between moving node and the nature of the wireless channel. Most traditional Intrusion Detection System (IDS) are designed to operate in a centralized manner; and do not operate properly in MANET because data in MANETs is distributed in different network devices. In this paper, we present an Hierarchical Cooperative Intrusion Detection Method (HCIDM) to secure packets routing in MANETs. HCIDM is a distributed intrusion detection mechanism that uses collaboration between nodes to detect active attacks against the routing table of a mobile ad hoc network. HCIDM reduces the effectiveness of the attack by informing other nodes about the existence of a malicious node to keep the performance of the network within an acceptable level. The novelty of the mechanism lies in the way the responsibility to protect the networks is distributed among nodes, the trust level is computed and the information about the presence of a malicious is communicated to potential victim. HCIDM is coded using the Network Simulator (NS-2) in an ad hoc on demand distance vector enable MANET during a black hole attack. It is found that the HCIDM works efficiently in comparison with an existing Collaborative Clustering Intrusion Detection Mechanism (CCIDM), in terms of delivery ratio, delay and throughput.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264960","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}
Object storage systems are widely used for unstructured data such as video data and music data. As these data are increasing its amount, the performance improvement of these object storage systems is increasing their importance. However, understanding their behaviors and finding the bottleneck process in them are difficult because these are distributed systems composed of multiple server computers. In this paper, we evaluate the file uploading performance of the Swift, which is a popular object storage implementation, and show that each uploading takes a long time in some cases. We then propose an analyzing system that visualizes packet transmissions and method calls. The analyzing system identifies the reasons why uploading takes a long time. For evaluating the proposed system, we apply this analyzing method to the Swift and reveal that a process in the Identity Server takes a long time and a hashing function $bcrypt$ is the bottleneck process. Finally, we present a discussion on performance importance based on this analyzing result.
{"title":"Performance Analyzing System Based on Visualization of Packet Transfers and Method Calls on Object Storage System","authors":"Makoto Nakagami, Shunpei Hayakawa, Saneyasu Yamaguchi","doi":"10.1109/IMCOM51814.2021.9377394","DOIUrl":"https://doi.org/10.1109/IMCOM51814.2021.9377394","url":null,"abstract":"Object storage systems are widely used for unstructured data such as video data and music data. As these data are increasing its amount, the performance improvement of these object storage systems is increasing their importance. However, understanding their behaviors and finding the bottleneck process in them are difficult because these are distributed systems composed of multiple server computers. In this paper, we evaluate the file uploading performance of the Swift, which is a popular object storage implementation, and show that each uploading takes a long time in some cases. We then propose an analyzing system that visualizes packet transmissions and method calls. The analyzing system identifies the reasons why uploading takes a long time. For evaluating the proposed system, we apply this analyzing method to the Swift and reveal that a process in the Identity Server takes a long time and a hashing function $bcrypt$ is the bottleneck process. Finally, we present a discussion on performance importance based on this analyzing result.","PeriodicalId":275121,"journal":{"name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129330333","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：