{"title":"Multi-pass Object Detection Method for Flaw Inspection of Ammeters","authors":"Guang Shen, Zhiqiang Jiao, Huajiang Yan, Qiang Wang, Chuanzi Xu, An Wen","doi":"10.1109/ICSAI48974.2019.9010170","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010170","url":null,"abstract":"In object detection tasks, the detection accuracy and recall rate of small size are not satisfied. This paper proposes a multi-pass object detection algorithm, applied in flaw inspection of electric metering devices. The images in the training set are categorized by clustering the labeled positions. In the first detection pass, the input image is inspected by the YOLO method, and then the parts of the image are cropped according to the type of the image and detected by a second pass. Experiments show that multi-pass detection is superior to a single pass of detection, and achieves 4% higher average recall rate than single-pass detection.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115688176","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}
Weixin Zhang, Hong Lu, M. Ma, Cong Kong, He Huang, Shaojun Wang
{"title":"The Manipulator Path Planning of Bolt Disassembly Based on Improved Genetic Algorithm and A* Algorithm","authors":"Weixin Zhang, Hong Lu, M. Ma, Cong Kong, He Huang, Shaojun Wang","doi":"10.1109/ICSAI48974.2019.9010205","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010205","url":null,"abstract":"The manipulator is widely applied in bolt disassembly in the field of remanufacturing. The intelligent manipulator with the ability of generating suitable operating path is increasingly required. To improve the path planning ability of manipulator in bolt disassembly, a strategy of dual path planning using a hybrid algorithm which combines an improved genetic algorithm (GA) and A* algorithm is proposed in this paper. The model of bolt disassembly sequence and algorithm are first established to find out the shortest disassembly path. The improvement of selecting and crossing operators are designed to enhance the stability and efficiency of basic GA. Both basic GA and improved GA are used and compared in the simulation of path planning with MATLAB. Then, the A* algorithm is adopted to accomplish the obstacle avoidance based on the path obtained with improved GA. Last, the experiment focusing on the bolt disassembly of a specific reduction gearbox is performed, and the correctness and feasibility of the hybrid algorithm are verified in the simulation and experiment.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"67 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116656542","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":"Solving for Inverse-Like Dynamic Matrices of Variables and Derivatives Using Zhang Neural Dynamics (ZND) Equivalency","authors":"Jianrong Chen, Mingzhi Mao, Yunong Zhang","doi":"10.1109/ICSAI48974.2019.9010194","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010194","url":null,"abstract":"Solving for inverse-like dynamic matrices of variables and derivatives is exciting and challenging. Although it may be encountered in the fields of industrial control or scientific research, it has not been widely studied because of its complexity and difficulty. In this work, to solve this problem, the Zhang neural dynamics (ZND, or called, zeroing neural dynamics) method is employed to the equivalent transformation of the original problem, and a model termed ZND equivalency (ZE) model is proposed and investigated. Meanwhile, a derivative dynamics (DD) model is proposed for comparison purposes. In order to facilitate the implementation of digital hardware, a five- instant Zhang et al discretization (ZeaD) formula is presented. Thus, two discrete models termed discrete-time ZE model and discrete-time DD model (in short DZE model and DDD model, respectively) are proposed by using the presented ZeaD formula. Theoretical analysis and numerical experimental results indicate the good performance, accuracy and superiority of the DZE model.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116763311","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}
A. Hemanth, Manoj Kumar Reddy, Jhansi Lakshmi, B. H. Kumar, Lavanya Bandi, G. Sheu, Yu-Lin Song, Po-An Chen, Luh-Maan Chang
{"title":"Investigations of Low Dynamic Ron on GaN/AlGaN/GaN HEMT by Field Plate Using Physical Device Simulations","authors":"A. Hemanth, Manoj Kumar Reddy, Jhansi Lakshmi, B. H. Kumar, Lavanya Bandi, G. Sheu, Yu-Lin Song, Po-An Chen, Luh-Maan Chang","doi":"10.1109/ICSAI48974.2019.9010088","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010088","url":null,"abstract":"This study examines the effects of field plate structure with gallium nitrite cap contact scheme and inter layer dielectric (ILD) as nitride on the performance of GaN/AlGaN/GaN High electron mobility transistor (HEMT). We have exhibited the prominent results at the peak of electric field happened on the hot spot region. This indicates that the field plate can help to suppress the peak of electric field at the verge of the gate towards drain. The key advantage is rise of the breakdown voltage with low electric peak field. These Synopsys Technology Computer Aided Design (TCAD) simulated results clearly show that besides field plate design dielectric material thickness also plays a vital role to obtain low dynamic Ron ratio.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"2005 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116898834","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":"The dendritic neuron model is a universal approximator","authors":"Jingyao Wu, Jiaxin He, Yuki Todo","doi":"10.1109/ICSAI48974.2019.9010178","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010178","url":null,"abstract":"According to the biological composition of neurons, the DNM was invented based on the dendrites of neurons, which can break through the functions that traditional simple neuron model (McCulloch and Pitts, 1943) cannot achieve. While by using traditional single-layer model, the approximation to any continuous function cannot be achieved by a single neuron. In this paper, an accurate mathematical method is used to demonstrate that the DNM can approximate any continuous function which could be achieved with only one neuron.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117262990","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":"On Pricing Problem of Two-Channel Reverse Supply Chain Considering Consumer Psychology under “Internet +” Environment","authors":"Yi Chen, Bin Sun, Meiling Feng, Junqing Sun","doi":"10.1109/ICSAI48974.2019.9010348","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010348","url":null,"abstract":"In recent years, “Internet +” and e-commerce technology have had a profound impact on the recycling industry. Consumer psychology, as the most important factor in the positive sales chain, has received little attention in the recycling field. Based on the consumer's acceptance of online recycling channels and sensitivity to recycling prices, this paper investigates a two-channel reverse supply chain system consisting of the brand owner and a dismantling center. Firstly, the pricing strategy model, which takes consumer psychology into account, is established based on the Stackelberg game. It is found that the consumer's acceptance of the online recycling channel will reduce the profit of the dismantling center, but has no effect on the profit of the brand owner. Consumers' sensitivity to price will increase the profits of both the brand owner and the dismantling center, and will also make the optimal pricing of both parties tend to be fixed. Finally, the simulation experiment is carried out to verify the influence of psychological indicators on the pricing strategy and profit of the brand owner and dismantling center, and the optimal pricing strategy of both models is obtained after the online acceptance index and price sensitivity index are determined.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127182007","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":"Design of Intelligent Measurement System of Vehicle Dimensions Based on Structured Light Imaging and Machine Vision","authors":"Hui Yu, Wen Yan, Jinglai Sun, Huiquan Wang, Lixin Zhang","doi":"10.1109/ICSAI48974.2019.9010242","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010242","url":null,"abstract":"At present, manual measurement is the main method of vehicle dimensions detection, which has some defects such as low efficiency, high cost, low accuracy, and non-standard manual operation. In order to solve these problems, this study proposed an intelligent measurement system of vehicle dimensions based on depth of field reconstruction and machine vision. The design of the depth of field sensor was based on the principle of structured light imaging. The structured light was decoded by two-dimensional cross-correlation technology to acquire the depth information of the vehicle surface. Then, hybrid Gaussian background modeling algorithm was used to extract the foreground signal of the vehicle, and machine vision was used to realize the coarse registration of point cloud information. Finally, vehicle accessories were extracted and removed according to the national standard requirements. Meanwhile, a prototype system was built to measure 964 vehicles with various types, and experimental results showed that the proportion of vehicle dimension error within 10cm is more than 90%, and the error of repeated measurement for the same vehicle is less than 0.5%. In this paper, the intelligent measurement method of vehicle dimensions meets the requirements of GB 21861–2014, and ensures the accuracy and objectivity of the detection process, as well as the fairness and openness of the results.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124834255","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 Fuzzy Multi-class Twin Support Vector Machine","authors":"H. Ju, Ling Jing","doi":"10.1109/ICSAI48974.2019.9010402","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010402","url":null,"abstract":"Multi-class twin support vector machine (MTSVM) is a multi-class classification algorithm. It has extensive application in the multi-class classification problems. In order to improve the classification performance of MTSVM, an improved fuzzy multiclass twin support vector machine (IF-MTSVM) is proposed. Then the solution to IF-MTSVM is derived. Experiments on ordinary UCI datasets and datasets with 5% noises added show that this new method has certain advantages over other fuzzy multi-class twin support vector machines.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125098042","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":"Storage Allocation Algorithm with Multi-Objective Optimization in High-Density Tridimensional Warehouse","authors":"Qiubo Huang, Shuda Xie, Guohua Liu","doi":"10.1109/ICSAI48974.2019.9010580","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010580","url":null,"abstract":"Storage allocation in a high-density tridimensional warehouse has more constraints and optimization objectives than that in a single or dual rack warehouse. As a result, algorithms for storage allocation in this kind of warehouse must be different. This paper mapped the storage allocation problem to the knapsack problem (KP) and introduced a dynamic programming (DP) algorithm to solve the problem. A penalty score strategy was defined for the DP algorithm, and the optimization objective is to minimize the penalty score while satisfying the constraints. A multi-index strategy was used for preprocess according to the constraints, and this strategy also helped to reduce the scale of DP algorithm. Finally, the simulation showed that the time complexity of DP algorithm was greatly reduced compared with depth-first-search based recursive algorithm. While compared with particle swarm optimization (PSO), DP algorithm can run faster in actual projects problem scale, and more importantly, DP can get the optimal solution, not a suboptimal one.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123329673","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":"Design and Development of Feedback System in Martial Arts Skill Teaching","authors":"Xiaoyu Wang, Zhiyong Chen, Yao Zhang","doi":"10.1109/ICSAI48974.2019.9010581","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010581","url":null,"abstract":"Starting from the practice of martial arts skill teaching and the need to master the skills of sports, this paper designed and empoldered a feedback system for martial arts skill teaching, by combining independent research and development with software and hardware information resources. The system can realize instant feedback of martial arts skill teaching, comparative analysis of basic technique, network sharing, teacher-student interaction etc. At the same time, it has the characteristics of interface simple, convenient operation and good fault-tolerant technology. It will play an important role in martial arts learning, training and evaluation of learning effect.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115512797","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}