发布求助
文献互助 智能选刊 最新文献

2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)最新文献

筛选
英文 中文
Open the Black Box of Recurrent Neural Network by Decoding the Internal Dynamics 破解递归神经网络的内部动力学，打开递归神经网络的黑匣子
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004061
Jiacheng Tang, Hao Yin, Qi Kang
{"title":"Open the Black Box of Recurrent Neural Network by Decoding the Internal Dynamics","authors":"Jiacheng Tang, Hao Yin, Qi Kang","doi":"10.1109/ICNSC55942.2022.10004061","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004061","url":null,"abstract":"With the development of the neural network, the complexity of the model goes far beyond the imagination. The number of neurons in the network is growing, and the black box problem requires to be solved. Although technics can record the internal dynamics of hidden neurons, the high dimension and complexity of the data bring poor interpretability. This paper introduces Tensor Component Analysis (TCA) to obtain low-dimensional information from the internal dynamics of recurrent neural networks (RNN). The proposed method extracts three interrelated neural factors: neuron factors, temporal factors, and input factors, to decode the forward propagation. This paper designs a variety of experiments to analyze the activity of RNN, and low-dimensional factors are used to explain the model's decision. The experiment shows the broad applicability of the TCA, which can accurately find the functional clustering of neurons and predict most of the classification.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126264352","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 Multi-modal Virtual-Real Fusion System for Multi-task Human-Computer Interaction 面向多任务人机交互的多模态虚实融合系统
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004097
Xin-Li Zhang, Jiahui Yu, Yuxiang Sun, Min Li, Yang Song, Xianzhong Zhou
{"title":"A Multi-modal Virtual-Real Fusion System for Multi-task Human-Computer Interaction","authors":"Xin-Li Zhang, Jiahui Yu, Yuxiang Sun, Min Li, Yang Song, Xianzhong Zhou","doi":"10.1109/ICNSC55942.2022.10004097","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004097","url":null,"abstract":"Due to the complexity of the task and the diversification of the scene, the traditional interactive control method can no longer meet the requirements of users. To solve this problem, a multi-modal virtual-real fusion system for multi-task human-computer interaction is proposed in this paper, which integrates eye movement, gesture and voice. Frist, aiming at the phenomenon of multi-task and multi-modal, a task-modal matching model is established. Then, the task-modal matching model is abstracted into a multi-objective optimization problem, and a method for solving this problem is designed and a matching scheme is successfully obtained. Meanwhile, the construction of the system is completed for the virtual-real fusion environment, and the control of unmanned car and virtual car is realized. The system can carry out multi-modal interaction and complete multiple tasks in real scene, virtual scene, parallel system and virtual-real fusion scene. Finally, the experiment proves the stability and reliability of the system.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126446899","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
Multi-scale feature fusion filtering module in convolutional neural networks 卷积神经网络中的多尺度特征融合滤波模块
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004098
Shining Chen, Xianghua Ma
{"title":"Multi-scale feature fusion filtering module in convolutional neural networks","authors":"Shining Chen, Xianghua Ma","doi":"10.1109/ICNSC55942.2022.10004098","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004098","url":null,"abstract":"Recent research has demonstrated that the multiscale representation of CNNs is considerably improved by the attention mechanism. However, the majority of current multiscale feature representation techniques only employ a small number of attention blocks in the attention mechanism, ignoring multiscale-level contextual data. This research suggests a multiscale fused feature filtering module as a solution to this issue (MFFFM). It enables branch-specific feature-selective learning of multiscale contextual data. These branches employ various sizes of null convolutions, and they further employ spatial injection correlation and channel correlation to provide channel feature responses that are adaptive. Tiny ImageNet, CIFAR-100, and MS COCO dataset experimental findings demonstrate that MFFFM provides extremely competitive outcomes in comparison to earlier baseline models.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127861009","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
Highly-Accurate Robot Calibration Based on Plane Constraint via Integrating Square-Root Cubature Kalman filter and Levenberg-Marquardt Algorithm 基于平方根卡尔曼滤波和Levenberg-Marquardt算法的平面约束高精度机器人标定
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004082
Ting Chen, Shuai Li, Hao Wu
{"title":"Highly-Accurate Robot Calibration Based on Plane Constraint via Integrating Square-Root Cubature Kalman filter and Levenberg-Marquardt Algorithm","authors":"Ting Chen, Shuai Li, Hao Wu","doi":"10.1109/ICNSC55942.2022.10004082","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004082","url":null,"abstract":"In the field of modern industrial manufacturing, industrial robots are indispensable intelligent automatic mechanical equipment for advanced industrial production. However, due to long-term mechanical wear and structural deformation, the absolute positioning accuracy is low, which greatly hinders the development of the manufacturing industry. Calibrating the kinematic parameters of the robot is an effective way to address it. However, the main measuring equipment such as laser trackers and coordinate measuring machines are expensive and need special personnel to operate. Additionally, in the measurement process, due to the influence of extensive environmental factors, measurement noises are generated affecting the calibration accuracy of the robot. Based on these, we have done the following work: a) developing a robot calibration method based on plane constraint to simplify measurement steps; b) employing square-root culture Kalman filter (SCKF) algorithm for reducing the influence of measurement noises; c) proposing a novel algorithm for identifying kinematic parameters based on SCKF algorithm and Levenberg-Marquardt (LM) algorithm to achieve the high calibration accuracy; d) adopting the dial indicator as the measuring equipment for slashing costs. Enough experiments verify the effectiveness of the proposed calibration algorithm and experimental platform.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120997846","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
Homogeneous-Heterogeneous Interaction Graph for Deep Learning-based Recommendation Systems 基于深度学习的推荐系统的同质-异质交互图
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004090
Zhi Li, Zhibiao Ba, Shuaiyu Yao
{"title":"Homogeneous-Heterogeneous Interaction Graph for Deep Learning-based Recommendation Systems","authors":"Zhi Li, Zhibiao Ba, Shuaiyu Yao","doi":"10.1109/ICNSC55942.2022.10004090","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004090","url":null,"abstract":"Graph convolutional neural network is a deep learning model for graph-structured data. It has become a popular approach for recommendation system research due to its powerful feature extraction and characterization learning capabilities. As for rating prediction in recommendation systems, most existing models based on graph convolutional networks use heterogeneous interaction information between users and items but lack sufficient use of homogeneous interaction information in the user and item graphs, thus it leads to the degradation of recommendation accuracy performance. For this purpose, this paper proposes some methods for constructing homogeneous interaction graph models that can be combined with heterogeneous interaction graphs to fully aggregate the node similarity and edge link information in the graph so that node embedding representations based on graph data can be better learned through graph convolutional networks. Experimental results based on several recommendation datasets show that the proposed homogeneous interaction graph can help the recommendation model to better mine the potential feature information and reduce the prediction error of ratings.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124596680","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
Hierarchical Water Wave Optimization 分层水波优化
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004174
Shibo Dong, Haichuan Yang, Haotian Li, Baohang Zhang, Sichen Tao, Shangce Gao
{"title":"Hierarchical Water Wave Optimization","authors":"Shibo Dong, Haichuan Yang, Haotian Li, Baohang Zhang, Sichen Tao, Shangce Gao","doi":"10.1109/ICNSC55942.2022.10004174","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004174","url":null,"abstract":"Water wave optimization algorithm (WWO) draws inspiration from the natural summary of the shallow water wave theory. It benefits from a modest population size and straightforward parameter design. However, WWO still has some performance problems that need to be solved, e.g., the convergence speed is too slow, and it cannot find the optimal point efficiently and accurately. This paper proposes a strategy of multi-level population structure for it, namely DWWO. The multi-level population structure strategy further enhances the balance between exploitation performance and exploration performance of the WWO algorithm. It makes the algorithm performance more stable, which leads to the DWWO algorithm can be used in more practical problems. DWWO algorithm is compared with the classical WWO algorithm, cuckoo search algorithm, sparrow search algorithm, and sine cosine algorithm on the basis of IEEE CEC2017 problem set. Comprehensive experimental results show that DWWO algorithm has better optimization ability and relatively fast convergence speed in comparison with other algorithms.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130884233","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
Sampled-data control of fuzzy systems 模糊系统的采样数据控制
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004133
Jinnan Luo, Jianming Xiong
{"title":"Sampled-data control of fuzzy systems","authors":"Jinnan Luo, Jianming Xiong","doi":"10.1109/ICNSC55942.2022.10004133","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004133","url":null,"abstract":"This paper studies the stability and stabilization of fuzzy systems based on sampled-data control. By making fully use of sampling information, a Lyapunov-Krasovskii functional (LKF) is given. Combing with tighter inequalities and several processing techniques, some results are built to guarantee the fuzzy systems to be stable. Finally, the sampled-data controller is designed.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125399801","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
Optimization of train safety distance based on CBTC 基于CBTC的列车安全距离优化
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004173
Y. Sun, Linjie Ren, Hongjian Huang
{"title":"Optimization of train safety distance based on CBTC","authors":"Y. Sun, Linjie Ren, Hongjian Huang","doi":"10.1109/ICNSC55942.2022.10004173","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004173","url":null,"abstract":"In the existing safety brake model, the stopping point of the following train is set at the tail envelope of the preceding train. At this stopping point, the target speed of the rear vehicle is 0, regardless of the traveling distance and the operating speed of the preceding train. Although this method ensures safety, it reduces the efficiency of train operation. In the calculation of the safety point of the rear train, the real-time speed of the preceding train can be considered to narrow the tracking distance. And a more accurate speed detecting scheme is fundamental to narrowing the tracking distance. Based on the existing ATP braking curve, this paper proposed a new scheme to optimize train safety tracking distance by considering the real-time speed of the preceding train in order to shorten the tracking distance","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122120173","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
Inventory Space Minimization in Smart Factory by a Designed Grey Wolf Optimizer 基于灰狼优化器的智能工厂库存空间最小化
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004058
Liang-Tu Chen, SiWei Zhang, N. Wu, Yan Qiao, Zhichao Zhong
{"title":"Inventory Space Minimization in Smart Factory by a Designed Grey Wolf Optimizer","authors":"Liang-Tu Chen, SiWei Zhang, N. Wu, Yan Qiao, Zhichao Zhong","doi":"10.1109/ICNSC55942.2022.10004058","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004058","url":null,"abstract":"With severe global competitions, how to control inventory so as to reduce the material storage space plays a pivotal role in reducing the daily cost resulting from the land rental. The goal of this paper is to develop a periodic material delivering schedule to minimize the space required for inventory. We take a leading home appliance manufacturing system in China as a case problem to study the material delivery scheduling optimization problem so as to ensure the synchronization between production and material delivering. The problem can be divided into a number of subproblems with each of them served by a turnover vehicle (TV) and this paper investigates one of its subproblems. With the combinatorial nature, we design a grey wolf optimizer algorithm. Experiments and comparisons are made with existing metaheuristics to validate the proposed algorithm. Results demonstrate the efficiency and effectiveness of the proposed method.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122172919","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 stream processing engine and benchmarking framework 流处理引擎和基准框架的研究
2022 IEEE International Conference on Networking, Sensing and Control (ICNSC) Pub Date : 2022-12-15 DOI: 10.1109/ICNSC55942.2022.10004188
Qionghua Le, Mingang Chen, Wenjie Chen
{"title":"Research on stream processing engine and benchmarking framework","authors":"Qionghua Le, Mingang Chen, Wenjie Chen","doi":"10.1109/ICNSC55942.2022.10004188","DOIUrl":"https://doi.org/10.1109/ICNSC55942.2022.10004188","url":null,"abstract":"Stream computing engine is an important part of big data system, and benchmarking is one of the main means to measure the engine's performance. In this paper, we compare the differences between two engines, Spark Streaming and Flink, in stream processing technologies. Then the open source benchmarking frameworks supporting stream processing and their respective characteristics are studied, and the HiBench testing framework is selected to test the two stream processing engines. The test results show that Flink is better than Spark Streaming in terms of performance in shuffle, stateful computation and windowed computation.","PeriodicalId":230499,"journal":{"name":"2022 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117194175","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信