2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)最新文献_第7页

Segmentation of Metastasized Lesions in Bone Scintigrams Using U-Net++ with Attention Gate 带注意门的U-Net++分割骨闪烁图中转移病灶

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105681

An Xie, Yang He, Qiang Lin, Yongchun Cao, Zhengxing Man

{"title":"Segmentation of Metastasized Lesions in Bone Scintigrams Using U-Net++ with Attention Gate","authors":"An Xie, Yang He, Qiang Lin, Yongchun Cao, Zhengxing Man","doi":"10.1109/NNICE58320.2023.10105681","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105681","url":null,"abstract":"Nuclear medicine imaging can effectively detect metastatic cancer, and early detection of bone metastases enables effective treatment of patients. Automatic recognition of bone scans will effectively enhance the diagnostic efficiency of physicians. To reliably identify bone metastases in bone scans, in this work, we propose an automated segmentation model based on $text{U-Net}{++}$ model. Specifically, the proposed model filters the feature maps of skip connections propagation by integrating AG (Attention gate), which enables the model to improve the learning of features in important regions. The feature fusion method is also used to make the feature maps to send to AG that contains richer information and further enhance the learning ability of the model for bone metastases lesions. An experimental evaluation using clinical data of 306 SPECT images shows that the proposed model performs well on identifying and segmenting bone metastasis lesions in bone SPECT images, obtaining scores of 0.6221, 0.6612 and 0.5878 for DSC (Dice Similarity Coefficient), CPA (Class Pixel Accuracy) and Recall. Comparison analysis with existing classical segmentation models also demonstrates the superiority of the proposed model with various loss functions. By integrating AGs into deep segmentation network and using the feature fusion, the overall performance can be improved.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114767216","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

Research on Gait Feature Fusion Method of OpenPose and GEI Based on Convolutional Network 基于卷积网络的OpenPose与GEI步态特征融合方法研究

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105757

Jia Yuan

{"title":"Research on Gait Feature Fusion Method of OpenPose and GEI Based on Convolutional Network","authors":"Jia Yuan","doi":"10.1109/NNICE58320.2023.10105757","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105757","url":null,"abstract":"Gait recognition has the advantages of low resolution, easy acquisition but not easy to imitate, and difficult to camouflage, etc. It is one of the biometric recognition technologies with the most development potential at long distances. However, factors such as viewing angle, clothing, and walking with weights in gait data can make gait recognition performance poor. Convolutional neural network is one of the best deep learning techniques, which has the ability to fit features and extract typical features. Therefore, this paper proposes a gait recognition method based on a multi-layer convolutional neural network. This method is based on the OpenPose module to obtain the skeletal key point set of the human body in the gait cycle and the gait energy image (GEI) corresponding to the gait cycle, autonomously learn the characteristics of the target in a gait cycle, and use the triplet loss function to optimize the network. The recognition accuracy of the method above is 92.40% in a single view and 90.25% in a cross view after testing on typical gait dataset CASIA-B, which is robust to several uncertain factors.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123506689","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

A Crowd Counting Method Based on Multi-Scale Attention Network 基于多尺度注意力网络的人群计数方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105713

Yu Xu, Mu Liang, Ziting Gong

引用次数: 0

Self-attention Convolutional Neural Network-based SLA Decomposition for Network Slicing 基于自关注卷积神经网络的网络切片SLA分解

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105804

Haidong Ji, Yuanyuan Wang, Lin Tian, Qian Sun, Zongshuai Zhang

{"title":"Self-attention Convolutional Neural Network-based SLA Decomposition for Network Slicing","authors":"Haidong Ji, Yuanyuan Wang, Lin Tian, Qian Sun, Zongshuai Zhang","doi":"10.1109/NNICE58320.2023.10105804","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105804","url":null,"abstract":"In 5G networks, a network slice is an independent end-to-end logical network running on a shared physical infrastructure, capable of guaranteeing a negotiated service level agreement (SLA) to deliver customized service. An end-to-end network slice includes three logical networks in the subnets: an access network (AN) sub-slice, a transport network (TN) sub-slice and a core network (CN) sub-slice. The network slice SLA needs to be decomposed into the corresponding sub-slice SLAs. In this paper, the SLA decomposition for network slicing is modelled as a constrained optimization problem and solved in two steps: building the sub-slice SLA acceptance probability models and solving the constrained optimization problem. The sub-slice SLA acceptance probability models are built by a self-attention convolutional neural network, and the constrained optimization problem is solved by a differential evolution algorithm based on the optimal acceptance probability of the SLA decomposition for network slicing. The simulation results show that the proposed self-attention convolutional neural network-based sub-slice SLA acceptance probability models (SACNN-SSAPMs) fit better with the ground truths, and the errors between the optimal acceptance probabilities of the SLA decomposition for network slicing based on the SACNN-SSAPMs and those based on the ground truths are smaller.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133693104","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

Fire Flame Detection in Tunnel Based on Halcon and ResNet50 基于Halcon和ResNet50的隧道火灾火焰探测

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105717

F. Jia

引用次数: 1

Study on The Robustness of Cascade Failure and Recovery of Dependent Networks Under Load 负载下依赖网络级联故障与恢复的鲁棒性研究

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105798

Jie Meng, Yaolin Zhu, Lei Wang

{"title":"Study on The Robustness of Cascade Failure and Recovery of Dependent Networks Under Load","authors":"Jie Meng, Yaolin Zhu, Lei Wang","doi":"10.1109/NNICE58320.2023.10105798","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105798","url":null,"abstract":"In view of the vulnerability of dependent networks and in order to avoid the huge impact of cascading failures on life, this paper adopts four dependent network recovery algorithms: random recovery (RR), preferential recovery based on local centrality (PRL), preferential recovery based on degree centrality (PRD), and preferential recovery based on connectivity link (PRCL). Using scale-free network (SF) and random network (ER) as sub-network models, a one-to-one dependent network is built with random coupling of SF-SF and ER-ER, and the cascade failure process includes dependent failure, overload failure and non-maximum connected network failure, and experiments were conducted to examine the recovery effects of these four recovery models on different recovery ratios and different dependent network models under the action of load [1]. In this paper, the curve of the robustness of dependent networks with load tolerance after cascading failure and recovery is drawn, and finally it is proved that the robustness of the dependent network after recovery is significantly improved compared with that before recovery, which proves that all four recovery methods are effective, and the relationship between robustness of dependent network after recovery and load tolerance, recovery ratio and edge parameters is obtained.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116454266","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

STANet: a Spatial-Temporal Aggregation Network for Video Deraining STANet:一个用于视频训练的时空聚合网络

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105752

Bin Li, Tao Yan, Weijiang He, Xiangjie Zhu

引用次数: 0

Fractional Fourier Transform Based Channel Estimation in XL-MIMO systems 基于分数阶傅立叶变换的xml - mimo系统信道估计

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105704

Jingyi Peng, Yuhong Wang

{"title":"Fractional Fourier Transform Based Channel Estimation in XL-MIMO systems","authors":"Jingyi Peng, Yuhong Wang","doi":"10.1109/NNICE58320.2023.10105704","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105704","url":null,"abstract":"Massive multiple-input multiple-output (MIMO) is a promising technology for current 5G communications, which can improve the spectral efficiency through beamforming or multiplexing. For future 6G communications, XL-MIMO has been proposed, which has much more antenna numbers than massive MIMO. With the increasement of antenna numbers, the spatial non-stationary effect becomes more obvious, which means different parts of the antenna see totally different scatterers. Traditional channel estimation schemes imply the spatial stationary assumption. Therefore, if traditional channel estimation schemes are utilized, the accuracy of channel estimation will decrease a lot. In this paper, we propose a fractional fourier transform (FrFT) based channel estimation scheme. This scheme can accurately estimate the spatial non-stationary channel. Specifically, the channel estimation scheme is divided into two steps. In the first step, the whole antenna is divided into several sub-arrays. In the second step, the channel corresponding to each sub-array is estimated based on the FrFT. Simulation results reveal that the proposed FrFT based channel estimation schemes has a better NMSE performance than the existing schemes.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128224305","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

A new appearance-based gaze estimation via multi-modal fusion 基于多模态融合的基于外观的凝视估计

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105698

Huijie Yang, Zuoyun Yang, Jiahui Liu, Jiannan Chi

{"title":"A new appearance-based gaze estimation via multi-modal fusion","authors":"Huijie Yang, Zuoyun Yang, Jiahui Liu, Jiannan Chi","doi":"10.1109/NNICE58320.2023.10105698","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105698","url":null,"abstract":"Appearance-based gaze estimation has gained more and more attention because of its generality, robustness, and subject independence. Deep learning, which has made a great deal of success in computer vision, has also greatly improved the accuracy of appearance-based gaze estimation. To further reduce the error in gaze estimation, we focus on extracting better feature information from eye and face images. In this paper, we propose a novel multimodal fusion gaze estimation model based on ConvNext and dilated convolution. In this model, the eye image and face image are used as input, and the ConvNext network is used to extract the features of the face image and the eye features are extracted by a dilated convolution-based network, and the feature map of the two images are fused using the fully connected layer to perform gaze estimation. In the experimental part, the designed model is verified on the public dataset MPIIGaze, and compared the proposed model with other gaze estimation models. The experimental results show that our proposed method has greatly improved the accuracy of gaze estimation on the MPIIGaze dataset compared to other related works. Our proposed multimodal fusion gaze estimation model achieves state-of-the-art result on the MPIIGaze dataset.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128318085","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

Prediction Model of Ship Arrival Time using Neural Network and Kalman Filter 基于神经网络和卡尔曼滤波的船舶到达时间预测模型

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105708

Xinyan Zhang, Xining Zhang, Pu Li

引用次数: 0