2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)最新文献_第2页

Improving EEG-Based Motor Imagery Classification Using Hybrid Neural Network 利用混合神经网络改进基于脑电图的运动图像分类

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673861

Cong Li, Honghong Yang, Xia Wu, Yumei Zhang

{"title":"Improving EEG-Based Motor Imagery Classification Using Hybrid Neural Network","authors":"Cong Li, Honghong Yang, Xia Wu, Yumei Zhang","doi":"10.1109/icicn52636.2021.9673861","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673861","url":null,"abstract":"Motor imagery EEG (MI-EEG) is a subjective signal generated by testers, which is collected through brain-computer interface (BCI). With the characteristics of noninvasive, inexpensive, and easily applied to human beings, MI-EEG classification is a popular research area in recent years. Due to the low signal-to-noise ratio and incomplete EEG signals, high accuracy rate classification is still a challenging problem. Most existing works of deep learning only regard EEG signals as chain-like sequences data and use single neural network for classification. To solve the above issues, we propose an improved EEG signals classification method via a hybrid neural network (HNN). In our work, we first use the origin EEG signals without removing noise and any filtering process, to ensure real-time property. Then, the EEG signals are divided into some small segments, and we arrange the data by considering the spatial position of electrodes. Finally, we propose a hybrid neural network by combing CNN, DNN, LSTM network. Experimental results for two challenging EEG signal classification benchmark datasets show that the proposed method has a good classification performance compared with several state-of-the-art EEG signal classification algorithms. After multiple sample testing, the average experiment result is 75.52%, which is 7.32% higher than the latest method.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130606472","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}

引用次数: 1

Effect of Neural Network on Robot Position Control Using Force Information 基于力信息的神经网络在机器人位置控制中的作用

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673826

Yifei Zhang, Pingguo Huang, Y. Ishibashi, T. Okuda, K. Psannis

引用次数: 1

RAN Enhancement to Support Propagation Delay Compensation of TSN 支持TSN传播延迟补偿的RAN增强

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9674019

Hua Xu, Jincan Xin, Sen Xu, Hua Zhang

引用次数: 1

On the Design of Embedded Smart Home System Based on Internet of Things 基于物联网的嵌入式智能家居系统设计

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673964

Wei Yang, Qiaojie Jiang, Dongliang Xie, Xiaojun Jing

引用次数: 0

Object Detection and Image Segmentation for Autonomous Vehicles 自动驾驶汽车目标检测与图像分割

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673812

Lian-ri Cong, Chengbin Huang, Chaochen Zhang, Jia Li, B. Liu, P. Yang

{"title":"Object Detection and Image Segmentation for Autonomous Vehicles","authors":"Lian-ri Cong, Chengbin Huang, Chaochen Zhang, Jia Li, B. Liu, P. Yang","doi":"10.1109/icicn52636.2021.9673812","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673812","url":null,"abstract":"With the rapid development of edge computing and the demand for green, safe and efficient transportation system, edge intelligence has been widely used in various traffic scenarios. By collecting images and videos, vehicles can obtain basic data and traffic flow information, which can be used to predict future movement trends. In addition, different traffic participants and their surroundings can be distinguished by image segmentation technology. In this paper, considering the resource limitation and latency constraint on edge vehicles, we proposed an improved vehicle detection algorithm based on tailored YOLOv4(You Only Look Once). To further increase the detection accuracy and speed, we introduce the Efficient Channel Attention (ECA) mechanism and High-Resolution Network (HRNet) into improved YOLOv4. After that, based on collected and detected objects, we proposed an image segmentation algorithm based on the DeepLabv3+ network, in which the MobileNetv2 is taken as the backbone network and the Softpool pooling algorithm is adopted as the pooling method. Experimental results show that compared with other classic methods, our proposed model has a higher mean Average Precision (mAP) for object detection and can improve the accuracy of original YOLOv4 from 83.34% to 87.64%. For image segmentation, our model also outperform other models with the Mean Intersection over Union (mIOU) improved from 72.18% to 74.99%.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132122953","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}

引用次数: 0

Proposed Distributed System Architecture and Preliminary Measurements for the Detection of Trapped Individuals Inside Motorway Tunnels 高速公路隧道内被困人员检测的分布式系统架构及初步测量

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673900

Sotirios Kontogiannis, Anestis Kastellos, G. Kokkonis, Theodosios Gkamas, C. Pikridas

引用次数: 1

An Efficient Spectrum Mobility and Handover Method for Cognitive Satellite Network 一种有效的认知卫星网络频谱迁移与切换方法

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673953

Chunfeng Wang, Naijin Liu

引用次数: 0

Transacting Multiple Mother Wavelets in Continuous Wavelet Transform for Epilepsy EEG Classification via CNN 连续小波变换中多母小波处理用于CNN癫痫脑电分类

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673990

Xiaojun Yu, Zeming Fan, M. Jamil, Muhammad Zulkifal Aziz, Yiyan Hou, Haopeng Li, Jialin Lv

{"title":"Transacting Multiple Mother Wavelets in Continuous Wavelet Transform for Epilepsy EEG Classification via CNN","authors":"Xiaojun Yu, Zeming Fan, M. Jamil, Muhammad Zulkifal Aziz, Yiyan Hou, Haopeng Li, Jialin Lv","doi":"10.1109/icicn52636.2021.9673990","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673990","url":null,"abstract":"Epileptic electroencephalogram (EEG) is one of the most adopted schemes to localize epileptiform discharge via brain signal recordings during seizure, and neurologists typically derive conjectures via ocular assessment. However, such a scheme is time-consuming with immense dependency on scrutinizer’s expertise, and thus, automated models are deemed to be the most feasible solutions to this predicament. This paper studies, for the first time, on the impact of transacting multiple mother wavelets (TMMW) on a benchmark signal decomposition algorithm known as Continuous Wavelet Transform (CWT). 1D signals are transformed into 2D scalograms discretely for three mother wavelets, namely ‘amor’, ‘bump’, and ‘mores’ first, and then, the such images are categorized with a pre-trained alexnet for classifications. The configured approach finally capitalizes on the repercussions of directing variables, which are adam, rmsprop, sgdm, and four learning rates, i.e., $10^{-3}, 10^{-4}, 10^{-5}$, and $10^{-6}$. Simulations are trialed on the renowned Bern-Barcelona dataset for verification. Results imply that deep learning classifier yields better results on morse based images, while the highest segregation is achieved when alexnet is operated on adam at $10^{-5}$, where classification mark up secures 90.4% with parametric values of 87.6%, 84.3%, and 85.5% for sensitivity, specificity, and specificity f1-score, respectively. This study offers an expanded understanding of the feasibility of mother wavelets on the skeleton of CWT for the classification of epileptic seizures via Convolutional Neural Network (CNN) classifier.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132201274","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}

引用次数: 1

Performance Analysis of CPM in Multi-Cell Massive MIMO System 多小区大规模MIMO系统中CPM的性能分析

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673933

Lei Guowei, Liao Wenliang

引用次数: 0

Group Public Key Encryption With Equality Test for Dynamic Membership 基于动态成员等式检验的组公钥加密

2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN) Pub Date : 2021-11-25 DOI: 10.1109/icicn52636.2021.9673959

Ru Xiang, Sha Ma, Xinjie Liu

{"title":"Group Public Key Encryption With Equality Test for Dynamic Membership","authors":"Ru Xiang, Sha Ma, Xinjie Liu","doi":"10.1109/icicn52636.2021.9673959","DOIUrl":"https://doi.org/10.1109/icicn52636.2021.9673959","url":null,"abstract":"Group public key encryption with equality test supports group granularity authorization, which allows a tester to perform equality test only on ciphertexts of group users. If two ciphertexts are encrypted by users from two different groups, they cannot be performed the equality test. Indeed, most of the existing works either only support users to join the group but do not support group members to leave the group, or are inefficient for all the ciphertexts need to be re-encrypted after each revocation operation. In this paper, we propose a group public key encryption with equality test for dynamic membership. Compared with the existing works, (1) our scheme supports efficient member revocation function. Once a group member has malicious behavior, it can be withdrawn from the group, which improves the security of the scheme, (2) our scheme supports the verification of ciphertext encryptors, that is, it verifies whether the ciphertext encryptors have been revoked and come from the same group before an equality test, which improves the efficiency of our scheme. Besides, we prove our scheme can achieve OW-CCA security against the Type-I adversary and IND-CCA security against the Type-II adversary in the random oracle model.","PeriodicalId":231379,"journal":{"name":"2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124151969","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}

引用次数: 0