Pub Date : 2021-12-17DOI: 10.1109/ICECE54449.2021.9674507
Yan Wang, Qinglin Wu
Online learning is an important way for learners to acquire knowledge. It helps learners to choose time and place flexibly and improve the efficiency and autonomy of learning. Based on the analysis of the current situation of online learning and user portrait, the general process of online learning user portrait is proposed. Through the data collection of an online course, five dimensions of online learners are selected to cluster the online learners. The experimental results show that the clustering results are satisfactory when the learners of the course are clustered into four categories, Help to improve the effect of online learning. Through the in-depth analysis of the characteristics of online learning group portrait, it provides a reference basis for improving the effect of online learning.
{"title":"Research on Online Learning User Profile Based on K-means Algorithm","authors":"Yan Wang, Qinglin Wu","doi":"10.1109/ICECE54449.2021.9674507","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674507","url":null,"abstract":"Online learning is an important way for learners to acquire knowledge. It helps learners to choose time and place flexibly and improve the efficiency and autonomy of learning. Based on the analysis of the current situation of online learning and user portrait, the general process of online learning user portrait is proposed. Through the data collection of an online course, five dimensions of online learners are selected to cluster the online learners. The experimental results show that the clustering results are satisfactory when the learners of the course are clustered into four categories, Help to improve the effect of online learning. Through the in-depth analysis of the characteristics of online learning group portrait, it provides a reference basis for improving the effect of online learning.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115275594","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}
Password guessing plays an important role in studying the vulnerability of passwords to improve security. In modern password guessing methods, the patterns of passwords from users in specific regions are discovered from a large number of leaked passwords. Most traditional methods, such as PCFG, Markov process, and other deep learning methods rely only on the training set. Different from other application areas of machine learning, the training set of password guessing comes from leaked real password sets, such as Rockyou, CSDN, and VK. Traditional approaches of password guessing are effective for large-scale training sets. However, the size of leaked password sets leaked by users of small languages or users of specific organizations is very small, which makes it difficult for current password guessing methods which relying only on training sets to discover enough words in passwords. In order to solve this problem, this paper proposed a corpus-based password guessing method. First, we analyzed the common words and their categories in the leaked password sets from users in three different countries. On this basis, we proposed an organization method for multiple language corpora, and constructed corpora of more than 3 million words. Secondly, we improved the traditional PCFG password segmentation method and described password structure based on corpora. Third, we evaluated the probability of words in the corpora which are not appearing in the training set based on the Lapalace smoothing. Actual tests show that our method can produce a finer structure than the PCFG. When the size of the training set decreases, the cracking rate of the PCFG decreases significantly, while the impact of our method is not significant, and the cracking rate is significantly higher than that of the PCFG.
{"title":"Corpora-based Password Guessing: An Efficient Approach for Small Training Sets","authors":"Xiaochun Gan, Meng Chen, Dong Li, Zongyan Wu, Weili Han, Hu Chen","doi":"10.1109/ICECE54449.2021.9674437","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674437","url":null,"abstract":"Password guessing plays an important role in studying the vulnerability of passwords to improve security. In modern password guessing methods, the patterns of passwords from users in specific regions are discovered from a large number of leaked passwords. Most traditional methods, such as PCFG, Markov process, and other deep learning methods rely only on the training set. Different from other application areas of machine learning, the training set of password guessing comes from leaked real password sets, such as Rockyou, CSDN, and VK. Traditional approaches of password guessing are effective for large-scale training sets. However, the size of leaked password sets leaked by users of small languages or users of specific organizations is very small, which makes it difficult for current password guessing methods which relying only on training sets to discover enough words in passwords. In order to solve this problem, this paper proposed a corpus-based password guessing method. First, we analyzed the common words and their categories in the leaked password sets from users in three different countries. On this basis, we proposed an organization method for multiple language corpora, and constructed corpora of more than 3 million words. Secondly, we improved the traditional PCFG password segmentation method and described password structure based on corpora. Third, we evaluated the probability of words in the corpora which are not appearing in the training set based on the Lapalace smoothing. Actual tests show that our method can produce a finer structure than the PCFG. When the size of the training set decreases, the cracking rate of the PCFG decreases significantly, while the impact of our method is not significant, and the cracking rate is significantly higher than that of the PCFG.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126605191","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}
Brain tumor segmentation in multi-modal magnetic resonance images is an essential step in brain cancer diagnosis and treatment. Although the recent multi-modal fusion network has achieved impressive performance in brain tumor segmentation, we usually encounter the situations where certain acquired modalities cannot be obtained in advance in clinical practice. In this paper, we propose an advanced network composed of dual residual multi variational auto-encoder and the sub-model distribution loss, which is robust to the absence of any one modality in brain tumor segmentation. This network implements the information merging in both encoder and decoder through this dual residual multi variational auto-encoder and embeds it in latent space, and decodes the features in a residual form. In this way, the features as the input of the decoder will be consistent and the difficulty of learning will be reduced. We evaluate this network on BraTS2018 using subsets of the imaging modalities as input. The experimental results show that our method could achieve better segmentation accuracy compared with the current state-of-the art method UHVED.
{"title":"DRM-VAE: A Dual Residual Multi Variational Auto-Encoder for Brain Tumor Segmentation with Missing Modalities","authors":"Yian Zhu, Shaoyu Wang, Yun Hu, Xiao Ma, Yanxia Qin, Jianyun Xie","doi":"10.1109/ICECE54449.2021.9674673","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674673","url":null,"abstract":"Brain tumor segmentation in multi-modal magnetic resonance images is an essential step in brain cancer diagnosis and treatment. Although the recent multi-modal fusion network has achieved impressive performance in brain tumor segmentation, we usually encounter the situations where certain acquired modalities cannot be obtained in advance in clinical practice. In this paper, we propose an advanced network composed of dual residual multi variational auto-encoder and the sub-model distribution loss, which is robust to the absence of any one modality in brain tumor segmentation. This network implements the information merging in both encoder and decoder through this dual residual multi variational auto-encoder and embeds it in latent space, and decodes the features in a residual form. In this way, the features as the input of the decoder will be consistent and the difficulty of learning will be reduced. We evaluate this network on BraTS2018 using subsets of the imaging modalities as input. The experimental results show that our method could achieve better segmentation accuracy compared with the current state-of-the art method UHVED.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122689623","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 : 2021-12-17DOI: 10.1109/ICECE54449.2021.9674455
Mengyao Yang, K. Xie, Tong Li, Zepeng Yang
The purpose of color constancy algorithm is to eliminate the influence of illumination on the color of objects in the scene, so that the computer has the same color constancy ability as human visual system. In order to further improve the accuracy and robustness of the color constancy algorithm, this paper proposes a illumination estimation method based on deep residual learning, which fully extracts the illumination feature information in the image by deepening the number of network layers, and uses the residual module to prevent over fitting of the network model, At the same time, the local illumination estimates are integrated to obtain the global illumination estimation of the whole image. The experimental results on ColorChecker data set show that the estimation accuracy and robustness of this method are good, and can be applied to the fields of image processing and computer vision requiring color correction.
{"title":"Color Constancy Based on Deep Residual Learning","authors":"Mengyao Yang, K. Xie, Tong Li, Zepeng Yang","doi":"10.1109/ICECE54449.2021.9674455","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674455","url":null,"abstract":"The purpose of color constancy algorithm is to eliminate the influence of illumination on the color of objects in the scene, so that the computer has the same color constancy ability as human visual system. In order to further improve the accuracy and robustness of the color constancy algorithm, this paper proposes a illumination estimation method based on deep residual learning, which fully extracts the illumination feature information in the image by deepening the number of network layers, and uses the residual module to prevent over fitting of the network model, At the same time, the local illumination estimates are integrated to obtain the global illumination estimation of the whole image. The experimental results on ColorChecker data set show that the estimation accuracy and robustness of this method are good, and can be applied to the fields of image processing and computer vision requiring color correction.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116875119","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 : 2021-12-17DOI: 10.1109/ICECE54449.2021.9674640
Zichao Chai, Wei Liu, Mao Li, Jing Lei
The 5G-TSN integrated network can effectively support time-critical industrial applications and realize real-time communication between all industrial equipment. However, the 5G-TSN integrated network involves different clock domains and the end-to-end cross domain clock synchronization problem needs to be solved. Based on detailed analysis of the synchronization process between 5G and TSN networks, this paper proposes a cross domain clock synchronization method based on data packet relay. The proposed method regards 5G network as logical TSN bridge which is only responsible for the forwarding of timestamped data packets. The clock domain compensation technology is introduced to estimate the residence time of 5G timing messages. The simulation results demonstrate that synchronization accuracy is significantly improved and complexity is reduced.
{"title":"Cross Domain Clock Synchronization Based on Data Packet Relay in 5G-TSN Integrated Network","authors":"Zichao Chai, Wei Liu, Mao Li, Jing Lei","doi":"10.1109/ICECE54449.2021.9674640","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674640","url":null,"abstract":"The 5G-TSN integrated network can effectively support time-critical industrial applications and realize real-time communication between all industrial equipment. However, the 5G-TSN integrated network involves different clock domains and the end-to-end cross domain clock synchronization problem needs to be solved. Based on detailed analysis of the synchronization process between 5G and TSN networks, this paper proposes a cross domain clock synchronization method based on data packet relay. The proposed method regards 5G network as logical TSN bridge which is only responsible for the forwarding of timestamped data packets. The clock domain compensation technology is introduced to estimate the residence time of 5G timing messages. The simulation results demonstrate that synchronization accuracy is significantly improved and complexity is reduced.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"2031 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129774312","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 : 2021-12-17DOI: 10.1109/ICECE54449.2021.9674394
Yong Zhang, Zhenyu Zhang, Di Wu, Jie Bao
Sparse code multiple access (SCMA) is a non-orthogonal multiple-access technique, and how to apply it to enhanced mobile broadband (eMBB) and ultrareliable low latency communication (URLLC) coexisting multiservice network slices is a serious challenge. The correlation among subcarriers, codebooks, users and power allocation are all issues that need to be solved by this system. Thus, we propose a SCMA-based slicing model for multi-service networks, and design a heuristic greedy algorithm and a power allocation algorithm based on Karush-Kuhn-Tucker conditions (KKT). The former obtains a sub-optimal solution of the problem by assigning codebooks to users and performing subcarrier matching, and the latter obtains the optimal solution of power allocation by the KKT condition. The simulation results demonstrate the feasibility of the algorithm and show that the SCMA scheme can achieve higher energy efficiency compared with the Orthogonal Multiple Access (OMA) scheme.
{"title":"Resource allocation of Multi-service Network Slicing based on SCMA","authors":"Yong Zhang, Zhenyu Zhang, Di Wu, Jie Bao","doi":"10.1109/ICECE54449.2021.9674394","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674394","url":null,"abstract":"Sparse code multiple access (SCMA) is a non-orthogonal multiple-access technique, and how to apply it to enhanced mobile broadband (eMBB) and ultrareliable low latency communication (URLLC) coexisting multiservice network slices is a serious challenge. The correlation among subcarriers, codebooks, users and power allocation are all issues that need to be solved by this system. Thus, we propose a SCMA-based slicing model for multi-service networks, and design a heuristic greedy algorithm and a power allocation algorithm based on Karush-Kuhn-Tucker conditions (KKT). The former obtains a sub-optimal solution of the problem by assigning codebooks to users and performing subcarrier matching, and the latter obtains the optimal solution of power allocation by the KKT condition. The simulation results demonstrate the feasibility of the algorithm and show that the SCMA scheme can achieve higher energy efficiency compared with the Orthogonal Multiple Access (OMA) scheme.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121916564","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 : 2021-12-17DOI: 10.1109/ICECE54449.2021.9674498
Chunlan Luo, Xiaoxia Zhu
In the context of informatization and big data, the demands for the reliability and real-time of information transmission in wireless communication channels are increasing. Quadratic residue (QR) codes have a high prospect on error correction for reliable data conveyance over channel with noise. This paper proposes an optimized algebraic scheme for decoding (71, 36, 11) QR code for correcting up to 5 errors on one-case-by-one-case basis. This scheme is mainly to improve its algebraic decoding algorithm based on the Lin’s algorithm, only in this paper, the Lin’s algorithm is called LTC71 algorithm. The key technology is to use the algebraic structure of QR code and give a new discriminant condition by mathematical derivation, which can quickly detect whether there are four errors in the code. Simulation results show that the proposed decoding scheme achieves the same bit error-rate performance as LTC71 algorithm, and the decoding time is reduced by about 28.72% owing to the reduced complexity of the decoder when there are four errors in the code.
{"title":"The Improved Decoding Algorithm of the (71, 36, 11) Quadratic Residue Code","authors":"Chunlan Luo, Xiaoxia Zhu","doi":"10.1109/ICECE54449.2021.9674498","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674498","url":null,"abstract":"In the context of informatization and big data, the demands for the reliability and real-time of information transmission in wireless communication channels are increasing. Quadratic residue (QR) codes have a high prospect on error correction for reliable data conveyance over channel with noise. This paper proposes an optimized algebraic scheme for decoding (71, 36, 11) QR code for correcting up to 5 errors on one-case-by-one-case basis. This scheme is mainly to improve its algebraic decoding algorithm based on the Lin’s algorithm, only in this paper, the Lin’s algorithm is called LTC71 algorithm. The key technology is to use the algebraic structure of QR code and give a new discriminant condition by mathematical derivation, which can quickly detect whether there are four errors in the code. Simulation results show that the proposed decoding scheme achieves the same bit error-rate performance as LTC71 algorithm, and the decoding time is reduced by about 28.72% owing to the reduced complexity of the decoder when there are four errors in the code.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125062367","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 : 2021-12-17DOI: 10.1109/ICECE54449.2021.9674321
Di Wang, Tiehu Li
A high-level model of the read-write system for a synchronous-pipelined static random access memory (SRAM) was designed using Verilog hardware description language (HDL). The system is comprised of the host, the main controller and the SRAM chip, with the main controller further consisted of the signal source generator and the data transceiver controller. Three read-write modes, non-burst (regular), linear burst and interleaved burst, were realized in this model. The model was validated by behavioral simulations, which showed that the SRAM chip can be written and read correctly in all the operation modes. The SRAM read-write procedure is greatly simplified as the requirements for the source control signals are minimized. The stability and reliability of the system is improved by maximizing the timing margins of the data transmissions.
{"title":"A High-Level Model of the Read-Write Control System of a SRAM Chip","authors":"Di Wang, Tiehu Li","doi":"10.1109/ICECE54449.2021.9674321","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674321","url":null,"abstract":"A high-level model of the read-write system for a synchronous-pipelined static random access memory (SRAM) was designed using Verilog hardware description language (HDL). The system is comprised of the host, the main controller and the SRAM chip, with the main controller further consisted of the signal source generator and the data transceiver controller. Three read-write modes, non-burst (regular), linear burst and interleaved burst, were realized in this model. The model was validated by behavioral simulations, which showed that the SRAM chip can be written and read correctly in all the operation modes. The SRAM read-write procedure is greatly simplified as the requirements for the source control signals are minimized. The stability and reliability of the system is improved by maximizing the timing margins of the data transmissions.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116102401","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}
In this paper, we propose a novel multi-dimensional spectrum data denoising scheme from the perspective of tensor theory. The spectrum data is organized into spectrum tensor comprehensively from multiple dimensions. The optimal low rank approximation of the noisy spectrum tensor can be calculated by TUCKALS3 algorithm to reduce noise. Estimating the n-rank of tensor more accurately is necessary to improve the denoising performance of the TUCKALS3 algorithm. Therefore, we further improve the existing minimum description length (MDL) algorithm. Experimental results show that the signal-to-noise ratio (SNR) of the spectrum tensor can be increased by 15dB averagely by applying the enhanced algorithm, even at a higher noise level. The enhanced TUCKALS3 algorithm can effectively denoise multi-dimensional spectrum data and improve the corresponding system performance.
{"title":"Multi-Dimensional Spectrum Data Denoising Based on Tensor Theory","authors":"Chengkai Zhai, Wensheng Zhang, Jian Sun, Weihong Zhu, Piming Ma, Zhiquan Bai, Lei Zhang","doi":"10.1109/ICECE54449.2021.9674642","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674642","url":null,"abstract":"In this paper, we propose a novel multi-dimensional spectrum data denoising scheme from the perspective of tensor theory. The spectrum data is organized into spectrum tensor comprehensively from multiple dimensions. The optimal low rank approximation of the noisy spectrum tensor can be calculated by TUCKALS3 algorithm to reduce noise. Estimating the n-rank of tensor more accurately is necessary to improve the denoising performance of the TUCKALS3 algorithm. Therefore, we further improve the existing minimum description length (MDL) algorithm. Experimental results show that the signal-to-noise ratio (SNR) of the spectrum tensor can be increased by 15dB averagely by applying the enhanced algorithm, even at a higher noise level. The enhanced TUCKALS3 algorithm can effectively denoise multi-dimensional spectrum data and improve the corresponding system performance.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"40 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114350567","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 : 2021-12-17DOI: 10.1109/ICECE54449.2021.9674722
Cheng Ma, Xiaohui Yang
Aiming at the problems of poor detection performance and high model complexity of existing detection algorithms in wireless sensor networks (WSNs), a hierarchical intrusion detection model for wireless sensor networks is proposed. Firstly, the traffic data is preprocessed at ordinary nodes, and the chi-square test is used for feature selection to reduce the amount of data storage and calculation; secondly, the improved random forest classifier is deployed to the cluster head nodes; finally, the base station uses Light Gradient Boosting Machine to detect suspicious traffic data. Experimental results show that compared with the existing detection models, this model has lower model complexity and good detection performance.
{"title":"A Hierarchical Intrusion Detection Model in Wireless Sensor Networks","authors":"Cheng Ma, Xiaohui Yang","doi":"10.1109/ICECE54449.2021.9674722","DOIUrl":"https://doi.org/10.1109/ICECE54449.2021.9674722","url":null,"abstract":"Aiming at the problems of poor detection performance and high model complexity of existing detection algorithms in wireless sensor networks (WSNs), a hierarchical intrusion detection model for wireless sensor networks is proposed. Firstly, the traffic data is preprocessed at ordinary nodes, and the chi-square test is used for feature selection to reduce the amount of data storage and calculation; secondly, the improved random forest classifier is deployed to the cluster head nodes; finally, the base station uses Light Gradient Boosting Machine to detect suspicious traffic data. Experimental results show that compared with the existing detection models, this model has lower model complexity and good detection performance.","PeriodicalId":166178,"journal":{"name":"2021 IEEE 4th International Conference on Electronics and Communication Engineering (ICECE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115300917","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：