2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)最新文献_第8页

Analysis of Radar Survival Probability against Front Door Coupling Attack based on Beam Pattern 基于波束方向图的雷达抵抗前门耦合攻击的生存概率分析

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105731

Xin Hu, Jiangping Yang, Cangzhen Meng, Yi-Ze Xu, Yuxi Xie

引用次数: 0

Unsupervised Abnormality Detection with Normalizing Flow and Neural Network 基于归一化流和神经网络的无监督异常检测

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105724

Wenxuan Fang, XianE Tang, Kai Zhang

引用次数: 0

Medium and Long Term Scenario Generation Method Based on Autoencoder and Generation Adversarial Network 基于自编码器和生成对抗网络的中长期场景生成方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105806

Boya Peng, Zhiyuan Sun, Mosi Liu

引用次数: 0

A fusion method based on 1D vibration signals and 2D images for detection of railway surface defects 基于一维振动信号与二维图像融合的铁路表面缺陷检测方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105728

Tiantian Yang, Tianhua Xu, Yu Cheng, Zelong Tang, S. Su, Yuan Cao

{"title":"A fusion method based on 1D vibration signals and 2D images for detection of railway surface defects","authors":"Tiantian Yang, Tianhua Xu, Yu Cheng, Zelong Tang, S. Su, Yuan Cao","doi":"10.1109/NNICE58320.2023.10105728","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105728","url":null,"abstract":"Rail surface defects detection is a significant and challenging task to ensure the safety and efficiency of railway transportation. Due to the variety of shapes and sizes of rail surface defects, the existing methods based on a single-source data have low detection accuracy, high false alarm and high miss rate. In this paper, a fusion detection method is proposed based on one-dimensional (lD) vibration signals and two-dimensional (2D) images. Firstly, an Improved Sparse Auto Encoder (ISAE) is used to extract the features of vibration signals. Then Linear Discriminant Analysis-Support Vector Classifier (LDA-SVC) is utilized to diagnose rail surface defects by feature dimension reduction. At the same time, combined with YOLOv5, defects are located and detected based on 2D images. Finally, the results of the two models are fused at the decision-level. The experimental results show that the integration of multi-source information effectively improves the detection accuracy and provides maintenance guidance for the railway department.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"98 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":"129459306","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

License Plate Recognition in Wild with Super-Resolution 车牌识别在野外与超分辨率

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105735

Yu Lu, Yu Gu, Bi Wang

引用次数: 0

Transformer fault identification method based on improved oversampling and MSFO-SVM 基于改进过采样和MSFO-SVM的变压器故障识别方法

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105767

G. Xie, Shilin Li

{"title":"Transformer fault identification method based on improved oversampling and MSFO-SVM","authors":"G. Xie, Shilin Li","doi":"10.1109/NNICE58320.2023.10105767","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105767","url":null,"abstract":"Aiming at the problem of low fault identification rate caused by transformer fault sample imbalance, a transformer fault diagnosis method for improved oversampling and improved sailfish algorithm (MSFO) optimization support vector machine (SVM) is proposed. Firstly, TLR, K-means++ and the introduction of anticosine function improved oversampling (SMOTE) are used to process the fault data. Then, the Tent chaotic mapping, the new sailfish exploration mechanism and the elite inverse learning strategy of the optimal individual are used to improve the swordfish algorithm (SFO), and the superiority of the improved SFO(MSFO) algorithm is proved by comparing it with the original SFO, PSO, and GWO optimization tests. Then, an MSFO optimized SVM model is constructed. Finally, it was compared with PSO-SVM, GWO-SVM and SFO-SVM. It can be seen that when the balanced training set is used, the diagnostic accuracy of each model is improved by 6.48%, 5.56%, 5.56% and 8.34% compared with the original training set, respectively, which verifies the effectiveness of the data balancing method in this paper. In the case of the same balanced training set, the fault diagnosis rate of MSFO-SVM was the highest, indicating that MSFO-SVM had stronger fault identification ability.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"20 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":"121057638","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 hybrid multiple hypothesis prediction reconstruction algorithm based on measured value reorganization 基于实测值重组的混合多假设预测重构算法研究

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105784

An Lu, Ling Yu, Qinghui Yang, Fan Yang, Yong Huang, Lihua Tan, Deyi Xiong

引用次数: 0

A Flexible and Low-Resource CNN Accelerator on FPGA for Edge Computing 面向边缘计算的FPGA柔性低资源CNN加速器

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105734

Haoli Bai

{"title":"A Flexible and Low-Resource CNN Accelerator on FPGA for Edge Computing","authors":"Haoli Bai","doi":"10.1109/NNICE58320.2023.10105734","DOIUrl":"https://doi.org/10.1109/NNICE58320.2023.10105734","url":null,"abstract":"With the development of deep learning, convolutional neural networks are widely used in the areas of edge computing, such as gait recognition, video surveillance, human-computer interaction, entertainment, and gaming. However, as the number of network layers deepens, CNNs are inappropriate to be deployed in the time-sensitive edge system. Most existing CNN accelerators require significant data movement and frequent off-chip memory (DRAM) access, which will decreases the inference speed and power efficiency. Field Programmable Gate Arrays (FPGA) is considered as a promising platforms for accelerating CNN s, due to its reconfigurable property. To address this issue, This paper designs an FPGA based CNN accelerator for edge computing, which can significantly reduce the dependence on logical resources and storage resources. An improved 4-bit PoT quantization (CPoT) was proposed to compress the model. Our design is assessed by deploying models on Intel Arria 10 GXl150 FPGA platform. As revealed from the experimental results, compared with other accelerator designs, our design can significantly reduce the utilization of Logic Elements (LE). The performance(throughput) of our accelerator achieves 8.92ms per image with a size of, 1.58 times faster than the GPU accelerator on an high-end NVIDIA GPU.","PeriodicalId":263114,"journal":{"name":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","volume":"37 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":"116024233","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

Rail track curve recognition model based on PSO-LSTM algorithm 基于PSO-LSTM算法的轨道曲线识别模型

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105699

Youyu Wu, Qinsong Wang

引用次数: 0

Monotonic Optimization-based Resource Allocation for D2D-enabled MC-NOMA Networks 基于单调优化的d2d MC-NOMA网络资源分配

2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE) Pub Date : 2023-02-24 DOI: 10.1109/NNICE58320.2023.10105677

Caihong Kai, Huihao Ge, Jianyue Zhu, W. Huang

引用次数: 0