{"title":"Accessibility for VANET in an Urban Scene","authors":"Jiujun Cheng, Lu-Xing Yang, Guangtao Zhou, Hongjiang Zheng, Shuai Feng, Jie Cui, Zhenhua Huang","doi":"10.1109/ICNSC52481.2021.9702242","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702242","url":null,"abstract":"Maintaining Vehicular Ad-hoc NETwork (VANET) accessibility is a thorny challenge in an urban scene. Existing methods assume that VANET obeys the ideal distribution, and do not consider the difference of connectivity between vehicles and vehicle groups. This work models VANET accessibility globally or locally. First, it measures connectivity between two vehicles. Then, it defines four connected states of paths and removes redundant connections. Finally, it proposes a path connectivity delay calculation method and a transfer station selection algorithm. Simulation results show that our method can evaluate VANET accessibility effectively and has a shorter averaged delay and higher packet delivery rate than a greedy perimeter stateless routing algorithm.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"85 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115793212","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}
{"title":"Fuzzy C-Means Clustering With Neighbor Information Constraint Using Sparse Self-Representation","authors":"Cun Sun, Yan Song, Ming Li, Min Li","doi":"10.1109/ICNSC52481.2021.9702237","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702237","url":null,"abstract":"Fuzzy c-means (FCM) clustering is a significant yet efficient unsupervised learning methods in many fields such as image segmentation, pattern recognition, etc. However, the traditional FCM algorithm cannot perform well at segmentation on images with vague boundaries especially in the presence of noises. To address this problem, by means of the sparse self-representation technique and the incorporation of the neighbor information, a novel FCM clustering method is put forward, which is called fuzzy c-means clustering with neighbor information constraint using sparse self-representation (SSRFCM_N). The main idea of the proposed SSRFCM_N is two fold: 1) besides the traditional cluster center regarding the global information of similarity, another center with respect to the local information is introduced into the objective by using the sparse self-representation technique; and 2) to consider the data distribution adequately, the neighbor information constraint is also incorporated into the objective, contributing to a better accuracy as well as the good robustness to the noise. Finally, experiments on different images show that SSRFCM_N is effective and more competitive than state-of-the-art clustering methods.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131561704","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}
{"title":"ROS Based Obstacle Avoidance Motion Planning of UR5 Manipulator","authors":"Tianqi Huang, He-Gen Xu, Ding Liu","doi":"10.1109/ICNSC52481.2021.9702223","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702223","url":null,"abstract":"The main work of the paper focuses on kinematic analysis modeling and obstacle avoidance motion planning based on a UR5 manipulator. It uses the software package MoveIt to generate various configuration files and startup files required for motion planning on Robot Operating System (ROS) platform. Through plug-ins of Python and Rviz, it accesses MoveIt and generates an obstacle environment. Then, it calls the Open Motion Planning Library to plan the motion of the UR5 manipulator, which is frequently used in both academic and industrial fields. The paper analyzes the widely used Rapidly-exploring Random Trees (RRT) algorithm and the improved RRT-connect algorithm by conducting a couple of motion planning experiments in an obstacle environment. It illustrates the experimental results of two different algorithms and compares their respective performances. Therefore, it sorts out the experiment process and the experimental results to provide ideas for the further improvement of motion planning of UR5 or other manipulators.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"352 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131460197","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}
{"title":"[ICNSC 2021 Copyright Notice]","authors":"","doi":"10.1109/icnsc52481.2021.9702193","DOIUrl":"https://doi.org/10.1109/icnsc52481.2021.9702193","url":null,"abstract":"","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134360116","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}
{"title":"Dual Modal Meta Metric Learning for Attribute-Image Person Re-identification","authors":"Rongxian Xu, Fei Shen, Hanxiao Wu, Jianqing Zhu, Huanqiang Zeng","doi":"10.1109/ICNSC52481.2021.9702261","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702261","url":null,"abstract":"Attribute-image person re-identification (AIPR) aiming to retrieve persons from massive images via an attribute query is a meaningful but challenging cross-modal retrieval task. Because there is a huge modal difference between person images and attributes, e.g., on the image modal one subject usually contains of varying instances, but on the attribute modal, one subject only contains an explicit instance. Unlike most existing AIPR methods focusing on shrinking feature differences crossing modals, we propose a dual modal meta metric learning (DM3L) method for AIPR in this paper. Specifically, in each episode, we sample a subset as a new task and split the training data into a single-modal support set of person images and a dual modal query set consisting of both person images and attributes. Based on the single-modal support set and the dual modal query set, our DM3L learns not only attribute-image cross-modal metrics but also learns image-image intra-modal metrics. Therefore, our DM3L method encourages data on both attribute and image modalities are discriminate to improve AIPR. Experiments show that our DM3L outperforms state-of-the-art approaches on Market-1501 Attribute and PETA datasets.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133348509","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}
{"title":"Fault identification of DES using Petri net","authors":"Wenyan Hou, Jianhong Ye, Jiayao Wang","doi":"10.1109/ICNSC52481.2021.9702163","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702163","url":null,"abstract":"This paper deals with the problem of fault identification in discrete event systems. A designed system will produce deviation log, which often implies that there are faults in the actual operation of the system. However, these failures appear in the log in the form of invisible transitions. Therefore, how to quickly find these faults is a worth issue. In this paper two cases are studied within the framework of Petri net. Firstly, the prerequisite is that each transition in the system model is clearly identified, and we focus on how to find these faults from the deviation log. The status marking and the difference of the transition relationship are combined to identify these faults. Secondly, we extend it to label Petri net, i.e., some transitions in the system have the same name. The position of each label transition in the network system is clarified firstly, and then an improved algorithm is used to solve this kind of problem. Experiments are presented to demonstrate the effectiveness of proposed approaches.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133809143","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}
{"title":"A Method to Quickly Determine Some Non-Reachable Markings in Cyclic Petri Nets Based on State Equation","authors":"Yueh-chih Su, Liang Qi, Xiwang Guo, Kun Wang","doi":"10.1109/ICNSC52481.2021.9702245","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702245","url":null,"abstract":"Reachability is the basis of studying the dynamic characteristics of a system, and is also one of the important properties of Petri nets (PNs). For acyclic PNs, the existence of non-negative integer solutions of the state equation is a sufficient and necessary condition of a reachable marking. For cyclic PNs, it has been proved to be only a sufficient condition. This paper presents a reachability analysis method for cyclic ordinary PNs. It determines markings that are not reachable from some initial markings. Firstly, according to the structural relationship between the incidence matrix and the PN, a subnet is generated by a transformation method. Then, the marking reachability is determined by judging the structural characteristics of the subnet. Finally, we give an algorithm to identify the non-reachable markings. This work is an important complement to PNs’ reachability analysis methods.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132581073","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}
{"title":"A Dynamic VRP with Varying Transportation Costs and Its Solution Strategy","authors":"Xianghu Meng, Zi-qiang Li, Jing Tang","doi":"10.1109/ICNSC52481.2021.9702224","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702224","url":null,"abstract":"A vehicle routing problem (VRP) is a well-known routing optimization problem. This work presents a capacitated VRP where transportation costs among the customers change over time, and constructs its non-linear integer program. It applies to vehicle distribution optimization problems under a dynamic traffic network. Then, a dynamic optimization strategy with an enhanced Variable Neighborhood Search (VNS) is proposed for addressing this problem. It contains two steps, i.e., initial scheduling and rescheduling. The former provides an initial solution for vehicles and the latter generates a new solution if the traffic information changes. Furthermore, to simulate the transportation costs in the dynamic traffic network, a dynamic simulator with adjustable frequency and amplitude is designed. Finally, experiments are conducted and the results show that the solution quality is improved by 2% ~ 6% over that static scheduling strategy.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114950397","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}
{"title":"An Improved Siamese Network Model for Handwritten Signature Verification","authors":"Wang Xiao, Di Wu","doi":"10.1109/ICNSC52481.2021.9702190","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702190","url":null,"abstract":"Handwritten signature verification is one of the most prominent and prevalent biometric methods in many real applications. A siamese neural network, which can extract stylistic features of handwriting writers, proves to be efficient in verifying handwritten signature. However, a traditional siamese neural network fails to fully represent an author’s writing style and suffers from low performance when the distribution of positive and negative handwritten samples is extremely unbalanced. To address this issue, this paper proposes an improved siamese network model with two main ideas: a) adopting a two-stage convolutional neural network to verify original and enhanced handwriting images simultaneously, and b) utilizing the Focal loss to handle the extreme imbalance between positive and negative handwritten samples. Experimental results on three challenging signature datasets of different languages demonstrate that compared with state-of-the-art models, the proposed model achieves a higher prediction accuracy.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115004526","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}
{"title":"Multi-Objective Multi-Verse Optimizer for Multi-Product Partial U-Shaped Disassembly Line Balancing Problem","authors":"Shancheng Zhang, Laide Guo, Xiwang Guo, Shixin Liu, Liang Qi, Shujin Qin, Ying Tang, Ziyan Zhao","doi":"10.1109/ICNSC52481.2021.9702256","DOIUrl":"https://doi.org/10.1109/ICNSC52481.2021.9702256","url":null,"abstract":"The development of industry and technology promotes the acceleration of product replacement, and generate a large number of end-of-life products. Meanwhile, robots also play a significant role in disassembly. This paper proposes a scheme to solve a U-shaped disassembly line balancing problem with robots. A mathematical model for maximizing profits and minimizing carbon emissions is established. Then, the paper proposes an improved Multi-Objective Multi-Verse Optimizer (MOMVO) to solve the problem. Taking the disassembly of ballpoint pen and hammer drill as examples, our method is compared with Non-dominated Sorting Genetic Algorithm II (NSGA-II), Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), and Multi-Objective Cellular Genetic Algorithm (MOCGA). Comparison indexes include Inverted Generational Distance+ (IGD+) and hypervolume epsilon metric. The experimental results show that the MOMVO algorithm performs better than others on the U-shaped and robotic disassembly line.","PeriodicalId":129062,"journal":{"name":"2021 IEEE International Conference on Networking, Sensing and Control (ICNSC)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116170356","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}