Pub Date : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998141
Xinying Wang, Jian Yi, Y. Li
Alzheimer’s disease is a degenerative disease of the nervous system. If the doctor can detect the disease early, he can treat the patient in advance to slow down the deterioration of the health. We propose a network 3D_ResNeXt_Bi-LSTM fused with ResNeXt and Bi-LSTM, which uses MRI brain images to classify and recognize AD (Alzheimer disease) and NC (Normal Contrast) from neuroimaging. We use a 3D convolution kernel to replace the 2D convolution kernel and flatten the feature of the final ResNeXt into one-dimensional data and send it to Bi-LSTM. So that the network can thoroughly learn the spatial information of the 3D brain image data, finally we send the features to the classifier for classification. Experiments on the ADNI dataset show that our network’s highest classification accuracy for AD and NC is 98.97%.
{"title":"Application of Fusion Model of 3D-ResNeXt and Bi-LSTM Network in Alzheimer’s Disease Classification","authors":"Xinying Wang, Jian Yi, Y. Li","doi":"10.1109/ICCIS56375.2022.9998141","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998141","url":null,"abstract":"Alzheimer’s disease is a degenerative disease of the nervous system. If the doctor can detect the disease early, he can treat the patient in advance to slow down the deterioration of the health. We propose a network 3D_ResNeXt_Bi-LSTM fused with ResNeXt and Bi-LSTM, which uses MRI brain images to classify and recognize AD (Alzheimer disease) and NC (Normal Contrast) from neuroimaging. We use a 3D convolution kernel to replace the 2D convolution kernel and flatten the feature of the final ResNeXt into one-dimensional data and send it to Bi-LSTM. So that the network can thoroughly learn the spatial information of the 3D brain image data, finally we send the features to the classifier for classification. Experiments on the ADNI dataset show that our network’s highest classification accuracy for AD and NC is 98.97%.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132814366","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998160
Li Xianlong, Zhang Yamiao, Chen Feng, Huang Jingping, Fan Jiangtao, Zhang Chong
With the development of wireless communication, the use of channel resources becomes more extensive, and the ability to transmit useful information as far as possible in the limited spectrum resources can be used to understand and study the characteristics of the wireless channel itself and some of the relevant features.
{"title":"Modeling and Realization of the Channel model for Joint Tactical Communication System","authors":"Li Xianlong, Zhang Yamiao, Chen Feng, Huang Jingping, Fan Jiangtao, Zhang Chong","doi":"10.1109/ICCIS56375.2022.9998160","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998160","url":null,"abstract":"With the development of wireless communication, the use of channel resources becomes more extensive, and the ability to transmit useful information as far as possible in the limited spectrum resources can be used to understand and study the characteristics of the wireless channel itself and some of the relevant features.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128903445","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998144
Jin Jubo, Wan Abdul Malek Wan Abdullah, Zhiyuan Chen, Norizan Binti Anwar
The traditional operation and maintenance platform is dependent on the static rules set manually, which can not better cope with the dynamic and complex changing scene. Nowadays, with the rapid development of machine learning and artificial intelligence, intelligent operation and maintenance system can make more efficient and accurate decisions in the face of dynamic changing scenarios through big data accumulated in business scenarios, and can also automatically monitor services, detect abnormal events, and deal with faults in emergency. This paper carefully analyzes the necessity of constructing an intelligent operation and maintenance system, and the application of machine learning in the analysis and fault detection of intelligent operation and maintenance system.
{"title":"Application Analysis of Machine Learning in Intelligent Operation and Maintenance System","authors":"Jin Jubo, Wan Abdul Malek Wan Abdullah, Zhiyuan Chen, Norizan Binti Anwar","doi":"10.1109/ICCIS56375.2022.9998144","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998144","url":null,"abstract":"The traditional operation and maintenance platform is dependent on the static rules set manually, which can not better cope with the dynamic and complex changing scene. Nowadays, with the rapid development of machine learning and artificial intelligence, intelligent operation and maintenance system can make more efficient and accurate decisions in the face of dynamic changing scenarios through big data accumulated in business scenarios, and can also automatically monitor services, detect abnormal events, and deal with faults in emergency. This paper carefully analyzes the necessity of constructing an intelligent operation and maintenance system, and the application of machine learning in the analysis and fault detection of intelligent operation and maintenance system.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117119271","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998136
Xing-Yu Hu, Chao Bai, Hai-Peng Ren
A Chaotic Pseudo Orthogonal Covert (CPOC) communication system is proposed. The Chaotic Pseudo Orthogonal (CPO) signals is proposed to improve the Low Probability of Detection (LPD) performance in the covert communication system. The LPD performance of CPOC system is verified by the cepstrum and Spectral Correlation Function (SCF). The Bit Error Ratio (BER) performance of the proposed CPOC system is compared to the conventional Differential Chaos Shift Keying (DCSK) communication system in Additive Gaussian White Noise (AWGN) and multipath channels. The experiment test has been carried out based on a Software Defined Electronical (SDE) platform to show the feasibility of the covert communication system based on CPOC.
{"title":"A Chaotic Pseudo Orthogonal Covert Communication System","authors":"Xing-Yu Hu, Chao Bai, Hai-Peng Ren","doi":"10.1109/ICCIS56375.2022.9998136","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998136","url":null,"abstract":"A Chaotic Pseudo Orthogonal Covert (CPOC) communication system is proposed. The Chaotic Pseudo Orthogonal (CPO) signals is proposed to improve the Low Probability of Detection (LPD) performance in the covert communication system. The LPD performance of CPOC system is verified by the cepstrum and Spectral Correlation Function (SCF). The Bit Error Ratio (BER) performance of the proposed CPOC system is compared to the conventional Differential Chaos Shift Keying (DCSK) communication system in Additive Gaussian White Noise (AWGN) and multipath channels. The experiment test has been carried out based on a Software Defined Electronical (SDE) platform to show the feasibility of the covert communication system based on CPOC.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126248580","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998162
Priti Shaw, Suresh Sankaranarayanan, P. Lorenz
Esophageal malignancy is a rare form of cancer that starts in the esophagus and spreads to the other parts of the body, impacting a severe risk on the liver, lungs, lymph nodes, and stomach. Studies have shown that esophageal cancer is one of the most prevalent causes of cancer mortality. In 2020, 604100 individuals have been diagnosed with this deadly disease. There are a good number of medical studies, carried out on this topic, every year. A similar focus is also imparted on the AI-based deep learning models for the classification of malignancy. But the challenge is that the AI models are all complex and lack transparency. There is no available information to explain the opacity of such models. And as AI-based medical research seeks reliability, it becomes very important to bring in explainability. So we, through this research, have used Explainable AI(XAI) entitled LIME for creating trust-based models for the early detection of esophageal malignancy. We have used a simple CNN model and several transfer learning-based models, for this study. We have taken the actual endoscopic images from the Kvasir-v2 dataset resulting in an accuracy of 88.75%. with the DenseNet-201 model followed by the usage of an Explainable AI model, Lime, for giving an explanation for the images classified. The deep learning model, combined with explainable AI, helps in getting a clear picture of the regions contributing toward the malignancy prediction and promotes confidence in the model, without the intervention of a domain expert.
{"title":"Early Esophageal Malignancy Detection Using Deep Transfer Learning and Explainable AI","authors":"Priti Shaw, Suresh Sankaranarayanan, P. Lorenz","doi":"10.1109/ICCIS56375.2022.9998162","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998162","url":null,"abstract":"Esophageal malignancy is a rare form of cancer that starts in the esophagus and spreads to the other parts of the body, impacting a severe risk on the liver, lungs, lymph nodes, and stomach. Studies have shown that esophageal cancer is one of the most prevalent causes of cancer mortality. In 2020, 604100 individuals have been diagnosed with this deadly disease. There are a good number of medical studies, carried out on this topic, every year. A similar focus is also imparted on the AI-based deep learning models for the classification of malignancy. But the challenge is that the AI models are all complex and lack transparency. There is no available information to explain the opacity of such models. And as AI-based medical research seeks reliability, it becomes very important to bring in explainability. So we, through this research, have used Explainable AI(XAI) entitled LIME for creating trust-based models for the early detection of esophageal malignancy. We have used a simple CNN model and several transfer learning-based models, for this study. We have taken the actual endoscopic images from the Kvasir-v2 dataset resulting in an accuracy of 88.75%. with the DenseNet-201 model followed by the usage of an Explainable AI model, Lime, for giving an explanation for the images classified. The deep learning model, combined with explainable AI, helps in getting a clear picture of the regions contributing toward the malignancy prediction and promotes confidence in the model, without the intervention of a domain expert.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130683395","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998147
Xin Xu, Xuebo Deng, Bingyi Li, Li Zhao, Xian Qin, Yi Zeng
Traditional ad-hoc is infrastructure-less. UEs (User Equipment) can realize rapid networking, but cannot guarantee the reliability of D2D (Device to Device) connection. 5G provides a network infrastructure of reliable connection, based on this, D2D provides visualized connection i.e. an autonomously controllable "virtualization ad-hoc". In order to integration of 5G D2D (ie. DCE) with DTE (Data terminal equipment) in power grids’ automation control and protection in the field area, dual-plane redundancy in substation and heterogeneous hand in hand connection in distribution power lines are proposed. Cross-layer connection failure detection and autonomous maintenance are further discussed. The applicable test shows the method can significantly improve the reliability of the power grids’ D2D network.
传统的ad-hoc没有基础设施。ue (User Equipment)可以实现快速组网，但不能保证D2D (Device to Device)连接的可靠性。5G提供可靠连接的网络基础设施，在此基础上，D2D提供可视化连接，即自主可控的“虚拟化ad-hoc”。为了整合5G D2D(即。提出了DCE与DTE(数据终端设备)在现场电网自动化控制与保护、变电站双平面冗余和配电线路异构手把手连接中的应用。进一步讨论了跨层连接故障检测和自主维护。应用试验表明，该方法能显著提高电网D2D网络的可靠性。
{"title":"An Analysis of 5G D2D Network in Power Grids’ Automation","authors":"Xin Xu, Xuebo Deng, Bingyi Li, Li Zhao, Xian Qin, Yi Zeng","doi":"10.1109/ICCIS56375.2022.9998147","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998147","url":null,"abstract":"Traditional ad-hoc is infrastructure-less. UEs (User Equipment) can realize rapid networking, but cannot guarantee the reliability of D2D (Device to Device) connection. 5G provides a network infrastructure of reliable connection, based on this, D2D provides visualized connection i.e. an autonomously controllable \"virtualization ad-hoc\". In order to integration of 5G D2D (ie. DCE) with DTE (Data terminal equipment) in power grids’ automation control and protection in the field area, dual-plane redundancy in substation and heterogeneous hand in hand connection in distribution power lines are proposed. Cross-layer connection failure detection and autonomous maintenance are further discussed. The applicable test shows the method can significantly improve the reliability of the power grids’ D2D network.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130544318","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998131
Xingfei Feng, Chaobing Huang
Since December 2019, COVID-19 has ravaged the world, severely affecting the quality of life and physical health of human society. Computed tomography (CT) imaging is an effective way to detect solid lung lesions as well as pulmonary ground-glass nodules and is an effective way to diagnose COVID-19. The automatic and accurate segmentation of COVID-19 lesion areas from CT images can determine the severity of the disease, which is essential for the diagnosis and treatment of COVID-19. A new model CAE-UNet(Combine-ASPP-ECA-UNet) is proposed in this paper for COVID-19 CT image segmentation based on UNet. The coding structure of UNet is replaced with the improved ResNet50 and incorporated with ECA attention module and atrous spatial pyramid pooling(ASPP). Fusing different sensory fields, global, local and spatial features to enhance the detail segmentation effect of the network. The experimental results on the CC-CCII show that the mIoU of the proposed CAE-UNet reaches 79.53%, which is better than some other mainstream methods. The proposed method achieves automatic and efficient segmentation of COVID-19 CT images.
2019年12月以来，新冠肺炎疫情肆虐全球，严重影响了人类社会的生活质量和身体健康。CT成像是发现肺实性病变和肺磨玻璃结节的有效方法，是诊断新型冠状病毒肺炎的有效方法。CT图像中对COVID-19病变区域的自动准确分割可以判断疾病的严重程度，这对于COVID-19的诊断和治疗至关重要。本文提出了一种基于UNet的新型冠状病毒CT图像分割模型CAE-UNet(combined - asp - eca -UNet)。将UNet的编码结构替换为改进的ResNet50，并加入ECA注意力模块和亚鲁斯空间金字塔池(ASPP)。融合不同的感官场、全局、局部和空间特征，增强网络的细节分割效果。在CC-CCII上的实验结果表明，所提出的CAE-UNet的mIoU达到79.53%，优于其他一些主流方法。该方法实现了COVID-19 CT图像的自动高效分割。
{"title":"CAE-UNet: An Effective Automatic Segmentation Model for CT Images of COVID-19","authors":"Xingfei Feng, Chaobing Huang","doi":"10.1109/ICCIS56375.2022.9998131","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998131","url":null,"abstract":"Since December 2019, COVID-19 has ravaged the world, severely affecting the quality of life and physical health of human society. Computed tomography (CT) imaging is an effective way to detect solid lung lesions as well as pulmonary ground-glass nodules and is an effective way to diagnose COVID-19. The automatic and accurate segmentation of COVID-19 lesion areas from CT images can determine the severity of the disease, which is essential for the diagnosis and treatment of COVID-19. A new model CAE-UNet(Combine-ASPP-ECA-UNet) is proposed in this paper for COVID-19 CT image segmentation based on UNet. The coding structure of UNet is replaced with the improved ResNet50 and incorporated with ECA attention module and atrous spatial pyramid pooling(ASPP). Fusing different sensory fields, global, local and spatial features to enhance the detail segmentation effect of the network. The experimental results on the CC-CCII show that the mIoU of the proposed CAE-UNet reaches 79.53%, which is better than some other mainstream methods. The proposed method achieves automatic and efficient segmentation of COVID-19 CT images.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114425511","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998156
Tong Ye, Jianxin Zhang, Caijin Zhao, Yuliang Tang, Chen Zhu
The satellite-ground integrated network will play an important role in the future sixth generation (6G) network. Software defined networking (SDN) and network functions virtualization (NFV) technologies can be utilized in the satellite-ground integrated networks to satisfy various requirements and provide agile service provisioning for users. Thus, we investigate the service function chain (SFC) orchestration problem in software defined satellite-ground integrated networks (SDSGIN) to minimize the overall resource costs, where fully consider the time evolution characteristics of dynamic network topology. Specifically, we consider the resource constraints, latency requirements as well as intermittent spatial link conditions to guarantee link reliability. Moreover, we propose a heuristic decoupled SFC orchestration algorithm (HDSFCO) with low complexity. Finally, the effectiveness and superiority of our proposed algorithm are proved through extensive simulations.
{"title":"Service Function Chain Orchestration in 6G Software Defined Satellite-Ground Integrated Networks","authors":"Tong Ye, Jianxin Zhang, Caijin Zhao, Yuliang Tang, Chen Zhu","doi":"10.1109/ICCIS56375.2022.9998156","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998156","url":null,"abstract":"The satellite-ground integrated network will play an important role in the future sixth generation (6G) network. Software defined networking (SDN) and network functions virtualization (NFV) technologies can be utilized in the satellite-ground integrated networks to satisfy various requirements and provide agile service provisioning for users. Thus, we investigate the service function chain (SFC) orchestration problem in software defined satellite-ground integrated networks (SDSGIN) to minimize the overall resource costs, where fully consider the time evolution characteristics of dynamic network topology. Specifically, we consider the resource constraints, latency requirements as well as intermittent spatial link conditions to guarantee link reliability. Moreover, we propose a heuristic decoupled SFC orchestration algorithm (HDSFCO) with low complexity. Finally, the effectiveness and superiority of our proposed algorithm are proved through extensive simulations.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131737896","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998145
Siji Chen, Bo Jiang, Hong-xun Xu, Yan Ding, Xin Wang
Subject to high mobility, dynamic topology, and limited energy of unmanned aerial vehicles (UAVs), maintaining stable communication performance is a challenging task in UAV ad-hoc networks (UANETs). As a potential solution, clustering routing algorithm divides the entire network into multiple clusters and various optimal strategies can be adopted to achieve strong network performance. In this paper, we propose a firefly swarm intelligence based automatic clustering and tracking algorithm (FSIACT) for UANETs, which is inspired by the collective behavior of fireflies. Firstly, we propose the fitness function consisting of link survival possibility, average distance and residual energy, and utilize it as the light intensity of the firefly. Secondly, firefly algorithm (FA) is put forward for cluster head (CH) selection and cluster management. Based on the characteristics of the FA, the whole swarm can be automatically divided into several clusters and cluster members (CMs) are willing to track the CH in the cluster. It is verified in simulations that the proposed algorithm achieves the lower handover rate of CHs, longer link expiration time (LET) and longer node lifetime.
{"title":"Firefly Swarm Intelligence Based Automatic Clustering and Tracking for UANETs","authors":"Siji Chen, Bo Jiang, Hong-xun Xu, Yan Ding, Xin Wang","doi":"10.1109/ICCIS56375.2022.9998145","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998145","url":null,"abstract":"Subject to high mobility, dynamic topology, and limited energy of unmanned aerial vehicles (UAVs), maintaining stable communication performance is a challenging task in UAV ad-hoc networks (UANETs). As a potential solution, clustering routing algorithm divides the entire network into multiple clusters and various optimal strategies can be adopted to achieve strong network performance. In this paper, we propose a firefly swarm intelligence based automatic clustering and tracking algorithm (FSIACT) for UANETs, which is inspired by the collective behavior of fireflies. Firstly, we propose the fitness function consisting of link survival possibility, average distance and residual energy, and utilize it as the light intensity of the firefly. Secondly, firefly algorithm (FA) is put forward for cluster head (CH) selection and cluster management. Based on the characteristics of the FA, the whole swarm can be automatically divided into several clusters and cluster members (CMs) are willing to track the CH in the cluster. It is verified in simulations that the proposed algorithm achieves the lower handover rate of CHs, longer link expiration time (LET) and longer node lifetime.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123403513","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 : 2022-10-14DOI: 10.1109/ICCIS56375.2022.9998159
Rui Xue, Zhengwei Du, Jialu Duan
At present, the fault identification method of glass insulators has the problems of difficult feature extraction and poor generalization ability of the model, which leads to the low accuracy of fault identification of glass insulators. Based on the Yolov5 network, this paper introduces a lightweight general sampling operator CARAFE to solve the problem of difficult feature extraction. At the same time, the attention mechanism module SENet is added to give different channels different weights to improve recognition accuracy. In addition, this paper makes further improvements in the network structure to make the network fit the above improvements. The experimental results show that the fault recognition rate of glass insulators is significantly improved compared with the unimproved network.
{"title":"Glass Insulator Fault Identification Method Based on Improved YOLOv5","authors":"Rui Xue, Zhengwei Du, Jialu Duan","doi":"10.1109/ICCIS56375.2022.9998159","DOIUrl":"https://doi.org/10.1109/ICCIS56375.2022.9998159","url":null,"abstract":"At present, the fault identification method of glass insulators has the problems of difficult feature extraction and poor generalization ability of the model, which leads to the low accuracy of fault identification of glass insulators. Based on the Yolov5 network, this paper introduces a lightweight general sampling operator CARAFE to solve the problem of difficult feature extraction. At the same time, the attention mechanism module SENet is added to give different channels different weights to improve recognition accuracy. In addition, this paper makes further improvements in the network structure to make the network fit the above improvements. The experimental results show that the fault recognition rate of glass insulators is significantly improved compared with the unimproved network.","PeriodicalId":398546,"journal":{"name":"2022 6th International Conference on Communication and Information Systems (ICCIS)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124079159","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：