2021 IEEE 19th International Conference on Industrial Informatics (INDIN)最新文献_第6页

Novelty Detection for Iterative Learning of MIMO Fuzzy Systems MIMO模糊系统迭代学习的新颖性检测

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557354

J. S. Junior, Jérôme Mendes, R. Araújo, J. Paulo, C. Premebida

{"title":"Novelty Detection for Iterative Learning of MIMO Fuzzy Systems","authors":"J. S. Junior, Jérôme Mendes, R. Araújo, J. Paulo, C. Premebida","doi":"10.1109/INDIN45523.2021.9557354","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557354","url":null,"abstract":"This paper proposes a methodology for iterative learning of multi-input multi-output (MIMO) fuzzy models focusing on dynamic system identification. The first step of the proposed method is the learning of the antecedent part of the fuzzy system, which is learned iteratively, where fuzzy rules can be added or merged based on the presented novelty detection and similarity criteria defined by a recursive extension of the Gath-Geva clustering algorithm. Then, the consequent part consists in the direct implementation of a non-recursive fuzzy approach that uses global least squares, Observer Kalman Filter Identification (OKID) and the Eigensystem Realization Algorithm (ERA). The proposed method is validated using experimental data from a real quadrotor aerial robot, a nonlinear dynamic system. Using quantitative performance metrics, the proposed method is compared with Hammerstein-Wiener models (H.-W.), nonlinear autoregressive models with exogenous input (NARX), and state-space models using subspace method with time-domain data (N4SID), other MIMO system identification techniques. The proposed method achieved better results compared to other techniques, showing the importance and versatility of learning based on novelty detection for MIMO problems.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127297061","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

The Role of Service Contracts in Interoperability Mismatch Identification 服务契约在互操作性不匹配识别中的作用

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557376

Cristina Paniagua

{"title":"The Role of Service Contracts in Interoperability Mismatch Identification","authors":"Cristina Paniagua","doi":"10.1109/INDIN45523.2021.9557376","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557376","url":null,"abstract":"The introduction of new technologies opens a wide range of new possibilities; however, it also leads to new challenges that need to be addressed to fully exploit the potential of such technologies. The identification of the barriers and challenges that preclude the adoption of Industry 4.0 helps identify solutions in the early stages and promote its establishment. One of the major problems facing the new technological paradigm is the lack of interoperability between heterogeneous systems.An initial step to solving this problem is the accurate identification of the interoperability mismatches between systems that preclude the consumption of services. This paper proposes the service contract as the main element in the definition and identification of interoperability problems that can occur in SOA-based heterogeneous environments. The presented approach modifies the traditional service contract viewpoint and introduces a new reformulation of the concept to adapt it to current technological requirements. The new service contract concept can be used as a core factor in the identification of interoperability mismatches at the service interface level. Problems related to the current definition of a service contract and potential solutions are introduced and discussed.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127433808","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

Business Analytical Framework for the Manufacturing Industry 制造业的商业分析框架

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557370

Emanuel Lima, Roy Bayot, Paulo Brito, N. Rodrigues, Bruno T. Ribeiro, Nuno Lopes

引用次数: 1

Reinforcement Learning based Condition-oriented Maintenance Scheduling for Flow Line Systems 基于强化学习的管道系统状态维护调度

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557373

Raphael Lamprecht, Ferdinand Wurst, Marco F. Huber

引用次数: 3

Robotic Grasp Detection by Rotation Region CNN 基于旋转区域CNN的机器人抓取检测

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557573

Hsien-I Lin, Hong-Qi Chu

引用次数: 4

Stock-bond Yield Correlation Analysis based on Natural Language Processing 基于自然语言处理的股票-债券收益率相关性分析

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557369

Yueyue Xu, Ying Kong, Jianwu Lin

{"title":"Stock-bond Yield Correlation Analysis based on Natural Language Processing","authors":"Yueyue Xu, Ying Kong, Jianwu Lin","doi":"10.1109/INDIN45523.2021.9557369","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557369","url":null,"abstract":"U.S. Treasury yield rates are the most important reference for global asset pricing and usually affect the stock market. Therefore, research on the correlation between China's core asset valuation and Treasury yield rates is becoming more and more important. The current statistical measurement methods have shortcomings such as the short period of market variables, low frequency, and inability to observe indicators of different countries in real-time. News, as information that reflects the public's attention and cognition, directly affects investors' stock trading behavior in the short term and has timeliness. We construct Correlation Strength by News (CSN) index for the first time to measure the correlation strength between treasury yield rates and the stock market from the perspective of media attention. The proposed method effectively solves the problem of the traditional method, such as the lack of data update timeliness and forecasting effectiveness. The capability of the index as an alternative variable of the correlation degree between the treasury yield rates and the stock market is verified.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126188505","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

Data Acquisition, Filtering and Buffering Protocol Design for Edge Computing Nodes 边缘计算节点的数据采集、过滤和缓冲协议设计

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557533

Xinyi Xu, W. Dai

引用次数: 1

The digital twin as an enabler of digital transformation: a sociotechnical perspective 数字孪生作为数字化转型的推动者:一个社会技术视角

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557455

E. Rebentisch, D. Rhodes, A. Soares, Ricardo Zimmerman, Sérgio Tavares

引用次数: 4

Automated Deviation Detection for Partially-Observable Human-Intensive Assembly Processes 部分可观察的人工密集装配过程的自动偏差检测

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557502

Ouijdane Guiza, Christoph Mayr-Dorn, G. Weichhart, M. Mayrhofer, Bahman Bahman Zangi, Alexander Egyed, Björn Fanta, Martin Gieler

引用次数: 2

Open Set Recognition for Machinery Fault Diagnosis 机械故障诊断中的开集识别

2021 IEEE 19th International Conference on Industrial Informatics (INDIN) Pub Date : 2021-07-21 DOI: 10.1109/INDIN45523.2021.9557572

Jiawen Xu, Matthias Kovatsch, S. Lucia

{"title":"Open Set Recognition for Machinery Fault Diagnosis","authors":"Jiawen Xu, Matthias Kovatsch, S. Lucia","doi":"10.1109/INDIN45523.2021.9557572","DOIUrl":"https://doi.org/10.1109/INDIN45523.2021.9557572","url":null,"abstract":"AI tasks based on deep neural networks have been widely applied in industrial applications, such as process control, quality inspection or predictive maintenance. Deep neural network classifiers are particularly successful, as they provide powerful and reliable algorithms for many applications such as object recognition and fault diagnosis. However, most deep classifier applications are not able to recognize class samples that are beyond the scope of their training data. Samples of unknown classes (denoted as open set data) lead to significant drops in performance, as the output of deep classifiers is limited to the known classes of the training data (denoted as closed set data). This paper presents a method to recognize open set samples without changing the neural network architecture, the training process, nor the trained models. In our method, we firstly train a neural network for normal closed set fault diagnosis. Then we compare the feature maps of testing samples and known class samples during inference using local outlier factor to recognize open set samples. We evaluate our method with two public datasets and show that our method can increase the overall accuracy by 40% when classifying open set data. Besides, we also compared our method to the state-of-the-art open set recognition approach for fault diagnosis applications and the results show that our method leads to better F1-scores.","PeriodicalId":370921,"journal":{"name":"2021 IEEE 19th International Conference on Industrial Informatics (INDIN)","volume":"128 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133971135","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: 5