Pub Date : 2022-12-31DOI: 10.1142/s021926592242004x
Huiping Li
Remote sensing image (RSI) segmentation is an effective method to interpret remote sensing information and an important means of remote sensing data information processing. Traditional RSI segmentation methods have some problems such as poor segmentation accuracy and low similarity difference measurement. Therefore, we propose a multi-scale segmentation (MSS) method for remote sensing big data image. First, the segmentation scale of RSI is divided, and the quantitative value of histogram band is used to calculate the similarity index between different objects; Second, the parameters in the same spot are improved based on the maximum area method to determine the shape factor of RSI; Finally, the object closure model is established to clarify the region conversion cost, and the RSI is dynamically segmented based on Multi-scale convolutional neural networks; The MSS algorithm of RSI is designed, and the MSS method of RSI is obtained. The results show that the maximum similarity difference measure of the proposed method is 0.648, and the similarity difference measure always remains the largest. The maximum recall of RSI is 0.954, and the highest recall is 0.988, indicating that the RSI segmentation accuracy of the proposed method is good.
{"title":"Multi-Scale Segmentation Method of Remote Sensing Big Data Image Using Deep Learning","authors":"Huiping Li","doi":"10.1142/s021926592242004x","DOIUrl":"https://doi.org/10.1142/s021926592242004x","url":null,"abstract":"Remote sensing image (RSI) segmentation is an effective method to interpret remote sensing information and an important means of remote sensing data information processing. Traditional RSI segmentation methods have some problems such as poor segmentation accuracy and low similarity difference measurement. Therefore, we propose a multi-scale segmentation (MSS) method for remote sensing big data image. First, the segmentation scale of RSI is divided, and the quantitative value of histogram band is used to calculate the similarity index between different objects; Second, the parameters in the same spot are improved based on the maximum area method to determine the shape factor of RSI; Finally, the object closure model is established to clarify the region conversion cost, and the RSI is dynamically segmented based on Multi-scale convolutional neural networks; The MSS algorithm of RSI is designed, and the MSS method of RSI is obtained. The results show that the maximum similarity difference measure of the proposed method is 0.648, and the similarity difference measure always remains the largest. The maximum recall of RSI is 0.954, and the highest recall is 0.988, indicating that the RSI segmentation accuracy of the proposed method is good.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"18 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79319980","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 : 2022-12-19DOI: 10.1142/s0219265921490025
Ashok Kumar Rai, A. K. Daniel
A wireless sensor network (WSN) can be used for various purposes, including area monitoring, health care, smart cities, and defence. Numerous complex issues arise in these applications, including energy efficiency, coverage, and intruder detection. Intruder detection is a significant obstacle in various wireless sensor network applications. It causes data fusion that jeopardizes the network’s confidentiality, lifespan, and coverage. Various algorithm has been proposed for intruder detection where each node act as an agent, or some monitoring nodes are deployed for intruder detection. The proposed protocol detects intruders by transmitting a known bit from the Cluster Head (CH) to all nodes. The legal nodes must acknowledge their identification to the CH in order to be valid; otherwise, if the CH receives an incorrect acknowledgement from a node or receives no acknowledgement at all, it is an intruder. The proposed protocol assists in protecting sensor data from unauthorized access and detecting the intruder with its location through the identity of other legal nodes. The simulation results show that the proposed protocol delivers better results for identifying intruders for various parameters.
{"title":"Energy-Efficient Model for Intruder Detection Using Wireless Sensor Network","authors":"Ashok Kumar Rai, A. K. Daniel","doi":"10.1142/s0219265921490025","DOIUrl":"https://doi.org/10.1142/s0219265921490025","url":null,"abstract":"A wireless sensor network (WSN) can be used for various purposes, including area monitoring, health care, smart cities, and defence. Numerous complex issues arise in these applications, including energy efficiency, coverage, and intruder detection. Intruder detection is a significant obstacle in various wireless sensor network applications. It causes data fusion that jeopardizes the network’s confidentiality, lifespan, and coverage. Various algorithm has been proposed for intruder detection where each node act as an agent, or some monitoring nodes are deployed for intruder detection. The proposed protocol detects intruders by transmitting a known bit from the Cluster Head (CH) to all nodes. The legal nodes must acknowledge their identification to the CH in order to be valid; otherwise, if the CH receives an incorrect acknowledgement from a node or receives no acknowledgement at all, it is an intruder. The proposed protocol assists in protecting sensor data from unauthorized access and detecting the intruder with its location through the identity of other legal nodes. The simulation results show that the proposed protocol delivers better results for identifying intruders for various parameters.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"54 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80413299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-21DOI: 10.1142/s0219265922420026
Ma Jingze, Zhan Guoye, Yang Fan, Chen Xingpei
Based on the spring, spring MVC and MyBatis structures of the cloud platform SSM framework, an information management platform for power grid material supply chain is built. The data layer uses a variety of sensors to collect power grid material supply chain information, and the information is fed back to the data storage layer after being integrated by the logical reorganization function of the persistence layer. The data storage layer uses the multi-sensor supply chain information fusion method based on paste progress to fuse the information and store it in the database. The business logic layer calls the information in the database and uses the improved k-means clustering algorithm to detect the abnormal supply chain data information. After calculation and data control by the control layer, the data management results are displayed through the presentation layer. The experimental results show that the absolute error of data fusion is very low. It can effectively cluster data information and distinguish outlier anomaly information at the same time, and the effect of information management is good.
{"title":"Data-Driven Information Management Method of Power Supply Chains Using Mobile Cloud Computing","authors":"Ma Jingze, Zhan Guoye, Yang Fan, Chen Xingpei","doi":"10.1142/s0219265922420026","DOIUrl":"https://doi.org/10.1142/s0219265922420026","url":null,"abstract":"Based on the spring, spring MVC and MyBatis structures of the cloud platform SSM framework, an information management platform for power grid material supply chain is built. The data layer uses a variety of sensors to collect power grid material supply chain information, and the information is fed back to the data storage layer after being integrated by the logical reorganization function of the persistence layer. The data storage layer uses the multi-sensor supply chain information fusion method based on paste progress to fuse the information and store it in the database. The business logic layer calls the information in the database and uses the improved k-means clustering algorithm to detect the abnormal supply chain data information. After calculation and data control by the control layer, the data management results are displayed through the presentation layer. The experimental results show that the absolute error of data fusion is very low. It can effectively cluster data information and distinguish outlier anomaly information at the same time, and the effect of information management is good.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"2 11","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72393174","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 : 2022-10-13DOI: 10.1142/s0219265922430010
E. Babu, Ilaiah Kavati, Ramalingaswamy Cheruku, Soumyabrata Nayak, Uttam Ghosh
The Internet of Things refers to billions of devices around us connected to the wireless internet. These IoT devices are memory-constrained devices that can collect and transfer data over the network without human assistance. Recently, IoT is materialized in retail commerce, transforming from recognition service to post-purchase engagement service. IoT examples in retail commerce are smart refrigerators, smart speakers, smart washing machines, smart automobiles, and automatic re-purchase of groceries using RFID tags. Despite the rise, one of the significant inconveniences slowing rapid adaption is the “security” of these devices, which are vulnerable to various attacks. One such attack is Distributed Denial-of-Service (DDoS) attacks targeting offline or online sensitive data. Hence, a lightweight cryptographic mechanism needs to establish secure communication among IoT devices. This paper presents the solution to secure communication among IoT devices using a permissioned blockchain network. Specifically, in this work, we proposed a mechanism for identifying and authenticating the smart devices using the Elliptic-curve cryptography (ECC) protocol. This proposed work uses permissioned blockchain infrastructure, which acts as a source of trust that aids the authentication process using ECC cryptosystem. In addition, lightweight Physical Unclonable Function (PUF) technology is also used to securely store the device’s keys. Using this technology, the private keys need not be stored anywhere, but it is generated on the fly from the trusted zone whenever the private key is required.
{"title":"Trust-Based Permissioned Blockchain Network for Identification and Authentication of Internet of Smart Devices: An E-Commerce Prospective","authors":"E. Babu, Ilaiah Kavati, Ramalingaswamy Cheruku, Soumyabrata Nayak, Uttam Ghosh","doi":"10.1142/s0219265922430010","DOIUrl":"https://doi.org/10.1142/s0219265922430010","url":null,"abstract":"The Internet of Things refers to billions of devices around us connected to the wireless internet. These IoT devices are memory-constrained devices that can collect and transfer data over the network without human assistance. Recently, IoT is materialized in retail commerce, transforming from recognition service to post-purchase engagement service. IoT examples in retail commerce are smart refrigerators, smart speakers, smart washing machines, smart automobiles, and automatic re-purchase of groceries using RFID tags. Despite the rise, one of the significant inconveniences slowing rapid adaption is the “security” of these devices, which are vulnerable to various attacks. One such attack is Distributed Denial-of-Service (DDoS) attacks targeting offline or online sensitive data. Hence, a lightweight cryptographic mechanism needs to establish secure communication among IoT devices. This paper presents the solution to secure communication among IoT devices using a permissioned blockchain network. Specifically, in this work, we proposed a mechanism for identifying and authenticating the smart devices using the Elliptic-curve cryptography (ECC) protocol. This proposed work uses permissioned blockchain infrastructure, which acts as a source of trust that aids the authentication process using ECC cryptosystem. In addition, lightweight Physical Unclonable Function (PUF) technology is also used to securely store the device’s keys. Using this technology, the private keys need not be stored anywhere, but it is generated on the fly from the trusted zone whenever the private key is required.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"108 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73697485","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 : 2022-09-28DOI: 10.1142/s0219265922990018
{"title":"Author Index Volume 22 (2022)","authors":"","doi":"10.1142/s0219265922990018","DOIUrl":"https://doi.org/10.1142/s0219265922990018","url":null,"abstract":"","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"38 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79141598","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: 10.1142/s0219265922420014
Chen Ying, Liao Xianjing, Wang Wei, Wang Jiahao, Zhang Wencheng, Shi Yanjiao, Zhang Qi
Aiming at the problems of insufficient feature extraction ability, many mismatching points and low registration accuracy of some remote sensing image registration algorithms, this study proposes a remote sensing image registration algorithm via cyclic parameter synthesis spatial transformation network. (1) We propose a feature extraction network framework combined with the improved spatial transformation network and improved Densely Connected Networks (DenseNet), which can focus on important areas of images for feature extraction.This framework can effectively improve the feature extraction ability of the model, so as to improve the model accuracy. (2) In the matching stage, we design the coarse filter and fine filter double filter architecture. Thus, the false matching points are effectively filtered out, which not only improves the robustness of the model but also improves the registration accuracy. Compared with the two traditional methods and two deep learning methods, the experimental results of this model are better in many indexes.
{"title":"Remote Sensing Image Registration Via Cyclic Parameter Synthesis and Spatial Transformation Network","authors":"Chen Ying, Liao Xianjing, Wang Wei, Wang Jiahao, Zhang Wencheng, Shi Yanjiao, Zhang Qi","doi":"10.1142/s0219265922420014","DOIUrl":"https://doi.org/10.1142/s0219265922420014","url":null,"abstract":"Aiming at the problems of insufficient feature extraction ability, many mismatching points and low registration accuracy of some remote sensing image registration algorithms, this study proposes a remote sensing image registration algorithm via cyclic parameter synthesis spatial transformation network. (1) We propose a feature extraction network framework combined with the improved spatial transformation network and improved Densely Connected Networks (DenseNet), which can focus on important areas of images for feature extraction.This framework can effectively improve the feature extraction ability of the model, so as to improve the model accuracy. (2) In the matching stage, we design the coarse filter and fine filter double filter architecture. Thus, the false matching points are effectively filtered out, which not only improves the robustness of the model but also improves the registration accuracy. Compared with the two traditional methods and two deep learning methods, the experimental results of this model are better in many indexes.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"31 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78934535","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 : 2022-05-31DOI: 10.1142/s0219265921490013
R. Amutha, G. Sivasankari, K. Venugopal, Thompson Stephan
Owing to uncertainties associated with energy and maintenance of large Wireless Sensor Networks (WSN) during transmission, energy-efficient routing strategies are gaining popularity. A Dynamic Threshold Adaptive Routing Algorithm (DTAR) is proposed for determining the most appropriate node to become a Cluster Head (CH) using adaptive participation criteria. For determining the next Forwarder Node (FN), an adaptive ranking scheme depends on distance ([Formula: see text]) and Residual Energy ([Formula: see text]). However, additional parameters such as Delivery Ratio (DR), End-to-End delay ([Formula: see text] delay), and Message Success Rate (MSR) should be considered to achieve the most optimal approach to achieve energy efficiency. The proposed DTAR algorithm is validated on variable clustered networks in order to investigate the effect of opportunistic routing with increasing network size and energy resources. The proposed algorithm shows a substantial decrease in energy consumption during transmission. Energy Consumption (EC), Packet Delivery Ratio (PDR), End-to-End delay ([Formula: see text] delay), and Message Success Rate (MSR) are used to illustrate the effectiveness of the proposed algorithm for energy efficiency.
{"title":"DTAR: A Dynamic Threshold Adaptive Ranking-Based Energy-Efficient Routing Algorithm for WSNs","authors":"R. Amutha, G. Sivasankari, K. Venugopal, Thompson Stephan","doi":"10.1142/s0219265921490013","DOIUrl":"https://doi.org/10.1142/s0219265921490013","url":null,"abstract":"Owing to uncertainties associated with energy and maintenance of large Wireless Sensor Networks (WSN) during transmission, energy-efficient routing strategies are gaining popularity. A Dynamic Threshold Adaptive Routing Algorithm (DTAR) is proposed for determining the most appropriate node to become a Cluster Head (CH) using adaptive participation criteria. For determining the next Forwarder Node (FN), an adaptive ranking scheme depends on distance ([Formula: see text]) and Residual Energy ([Formula: see text]). However, additional parameters such as Delivery Ratio (DR), End-to-End delay ([Formula: see text] delay), and Message Success Rate (MSR) should be considered to achieve the most optimal approach to achieve energy efficiency. The proposed DTAR algorithm is validated on variable clustered networks in order to investigate the effect of opportunistic routing with increasing network size and energy resources. The proposed algorithm shows a substantial decrease in energy consumption during transmission. Energy Consumption (EC), Packet Delivery Ratio (PDR), End-to-End delay ([Formula: see text] delay), and Message Success Rate (MSR) are used to illustrate the effectiveness of the proposed algorithm for energy efficiency.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"71 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85894656","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 : 2022-05-12DOI: 10.1142/s0219265922410018
A. R. Suhas, M. Manoj Priyatham
A physical region can have multiple parts, each part is monitored with the help of a Special DDN (SDDN). In the existing methods, namely, LEACH, the Fuzzy method has a larger path between the initiator DDN to destination DDN. Non-healthy DDNs can occur in the Group-based Detection Data Network (GDDN) when the battery level of the DDN reaches below the threshold. The possibility of more Non-healthy DDNs can be of multiple reasons (i) when the link path is of larger length (ii) Same DDN is used multiple times as an SDDN and (iii) repeated communication between base station to DDNs causes the DDN to lose more battery. If a mechanism is created to recover the DDNs or recharge them, then the number of Non-healthy DDNs can be reduced and DDN performance can be improved a lot. The Proposed Genetic (PGENETIC) method will find the SDDN in a battery-aware manner and also at path will be of minimum length along with regular interval trigger to identify DDNs which are non-healthy and replace or recharge them. PGENETIC is compared with LEACH, Fuzzy method, and Proposed CHEF (PCHEF) and proved that PGENETIC exhibits better performance.
一个物理区域可以包含多个部分，每个部分通过SDDN (Special DDN)进行监控。在现有的方法中，即LEACH，模糊方法在发起者DDN到目的DDN之间的路径更大。当GDDN (Group-based Detection Data Network)的电池电量低于阈值时，可能会出现非健康DDNs。出现更多非健康DDN的可能性有多种原因:(i)链路路径长度较大;(ii)同一DDN作为SDDN多次使用;(iii)基站与DDN之间的重复通信导致DDN消耗更多电池。如果建立恢复DDN或为其充值的机制，则可以减少非健康DDN的数量，并大大提高DDN的性能。提出的遗传(PGENETIC)方法将以电池感知的方式找到SDDN，并且在路径长度最小的情况下，以及定期间隔触发来识别非健康ddn并替换或充电。将PGENETIC算法与LEACH、Fuzzy、Proposed CHEF (PCHEF)算法进行了比较，证明了PGENETIC算法具有更好的性能。
{"title":"Health Ratio Optimization of Group Detection-Based Data Network Using Genetic Algorithm","authors":"A. R. Suhas, M. Manoj Priyatham","doi":"10.1142/s0219265922410018","DOIUrl":"https://doi.org/10.1142/s0219265922410018","url":null,"abstract":"A physical region can have multiple parts, each part is monitored with the help of a Special DDN (SDDN). In the existing methods, namely, LEACH, the Fuzzy method has a larger path between the initiator DDN to destination DDN. Non-healthy DDNs can occur in the Group-based Detection Data Network (GDDN) when the battery level of the DDN reaches below the threshold. The possibility of more Non-healthy DDNs can be of multiple reasons (i) when the link path is of larger length (ii) Same DDN is used multiple times as an SDDN and (iii) repeated communication between base station to DDNs causes the DDN to lose more battery. If a mechanism is created to recover the DDNs or recharge them, then the number of Non-healthy DDNs can be reduced and DDN performance can be improved a lot. The Proposed Genetic (PGENETIC) method will find the SDDN in a battery-aware manner and also at path will be of minimum length along with regular interval trigger to identify DDNs which are non-healthy and replace or recharge them. PGENETIC is compared with LEACH, Fuzzy method, and Proposed CHEF (PCHEF) and proved that PGENETIC exhibits better performance.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"1 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79283778","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 : 2022-01-31DOI: 10.1142/s0219265921430477
A. Madhuri, V. E. Jyothi, S. Praveen, S. Sindhura, V. S. Srinivas, D. L. S. Kumar
One of the important technologies in present days is Intrusion detection technology. By using the machine learning techniques, researchers were developed different intrusion systems. But, the designed models toughness is affected by the two parameters, in that first one is, high network traffic imbalance in several categories, and another is, non-identical distribution is present in between the test set and training set in feature space. An artificial neural network (ANN) multi-level intrusion detection model with semi-supervised hierarchical [Formula: see text]-means method (HSK-means) is presented in this paper. Error rate of intrusion detection is reduced by the ANN’s accurate learning so it uses the Grasshopper Optimization Algorithm (GOA) which is analysed in this paper. Based on selection of important and useful parameters as bias and weight, error rate of intrusion detection system is reduced in the GOA algorithm and this is the main objective of the proposed system. Cluster based method is used in the pattern discovery module in order to find the unknown patterns. Here the test sample is treated as unlabelled unknown pattern or the known pattern. Proposed approach performance is evaluated by using the dataset as KDDCUP99. It is evident from the experimental findings that the projected model of GOA based semi supervised learning approach is better in terms of sensitivity, specificity and overall accuracy than the intrusion systems which are existed previously.
{"title":"A New Multi-Level Semi-Supervised Learning Approach for Network Intrusion Detection System Based on the ‘GOA’","authors":"A. Madhuri, V. E. Jyothi, S. Praveen, S. Sindhura, V. S. Srinivas, D. L. S. Kumar","doi":"10.1142/s0219265921430477","DOIUrl":"https://doi.org/10.1142/s0219265921430477","url":null,"abstract":"One of the important technologies in present days is Intrusion detection technology. By using the machine learning techniques, researchers were developed different intrusion systems. But, the designed models toughness is affected by the two parameters, in that first one is, high network traffic imbalance in several categories, and another is, non-identical distribution is present in between the test set and training set in feature space. An artificial neural network (ANN) multi-level intrusion detection model with semi-supervised hierarchical [Formula: see text]-means method (HSK-means) is presented in this paper. Error rate of intrusion detection is reduced by the ANN’s accurate learning so it uses the Grasshopper Optimization Algorithm (GOA) which is analysed in this paper. Based on selection of important and useful parameters as bias and weight, error rate of intrusion detection system is reduced in the GOA algorithm and this is the main objective of the proposed system. Cluster based method is used in the pattern discovery module in order to find the unknown patterns. Here the test sample is treated as unlabelled unknown pattern or the known pattern. Proposed approach performance is evaluated by using the dataset as KDDCUP99. It is evident from the experimental findings that the projected model of GOA based semi supervised learning approach is better in terms of sensitivity, specificity and overall accuracy than the intrusion systems which are existed previously.","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"29 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2022-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76894161","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 : 2021-12-01DOI: 10.1142/s0219265921990012
{"title":"Author Index Volume 21 (2021)","authors":"","doi":"10.1142/s0219265921990012","DOIUrl":"https://doi.org/10.1142/s0219265921990012","url":null,"abstract":"","PeriodicalId":53990,"journal":{"name":"JOURNAL OF INTERCONNECTION NETWORKS","volume":"18 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87644479","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：