Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976861
Juan Liu, Jia-fu Tang
This paper analyzes the doing-business environment (DBE) at prefecture-level city in China. Based on the input-process-output (IPO) thought of system theory, this study uses Porter Diamond Model and International Institute for Management Development (IMD) regional competitiveness model to construct the China City Doing-business Environment Index (CCDBEI) from five aspects: Factor Supply Index (FSI), Environmental Attraction Index (EAI), Demand Pull Index (DPI), Industrial Security Index (ISI) and Output Influence Index (OII). The weight of single index was calculated by entropy method, and the DBE quality of 289 prefecture-level cities in China was evaluated by correlation coefficient method on the basis of considering the logical relationship of secondary indexes. The evaluation results show that the overall quality of DBE in China is gradually improving, but the regional differences are significant, and the best region was always East China, the worst were in the Northwest and Northeast. Location analysis shows that the quality of DBE is closely related to regional development strategy. Furthermore, the advantages of DBE in different regions are also different. In addition, it is found that DBE quality and balance do not develop synchronously. The study provides guidance for further optimization of DBE in cities.
{"title":"Doing-business Environment Assessment of Prefecture-level Cities in China based on Input-output: Logical Structure, Difference Comparison and Benchmark Analysis","authors":"Juan Liu, Jia-fu Tang","doi":"10.1109/IAI55780.2022.9976861","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976861","url":null,"abstract":"This paper analyzes the doing-business environment (DBE) at prefecture-level city in China. Based on the input-process-output (IPO) thought of system theory, this study uses Porter Diamond Model and International Institute for Management Development (IMD) regional competitiveness model to construct the China City Doing-business Environment Index (CCDBEI) from five aspects: Factor Supply Index (FSI), Environmental Attraction Index (EAI), Demand Pull Index (DPI), Industrial Security Index (ISI) and Output Influence Index (OII). The weight of single index was calculated by entropy method, and the DBE quality of 289 prefecture-level cities in China was evaluated by correlation coefficient method on the basis of considering the logical relationship of secondary indexes. The evaluation results show that the overall quality of DBE in China is gradually improving, but the regional differences are significant, and the best region was always East China, the worst were in the Northwest and Northeast. Location analysis shows that the quality of DBE is closely related to regional development strategy. Furthermore, the advantages of DBE in different regions are also different. In addition, it is found that DBE quality and balance do not develop synchronously. The study provides guidance for further optimization of DBE in cities.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127293733","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976714
Yahang Qin, Zhenni Li, Shengli Xie, Rong Yuan, Junming Xie
In urban environments, multipath can significantly deteriorate the positioning precision of the global navigation satellite system (GNSS). BeiDou navigation satellite system independently established by China plays an important role in the GNSS market. Eliminating the multipath is a crucial problem to contribute to the development of the BeiDou navigation satellite system (BDS). In this paper, we use the machine learning algorithm support vector machine (SVM) to classify the BeiDou satellite signals into line-of-sight (LOS), multipath, and non-line-of-sight signals (NLOS). Single and multiple feature classification of the signal was performed by using the carrier to noise ratio (C/N0), elevation angle (ELE), and pseudorange residuals (PR). We use SVM with radial basis function (RBF), which can effectively handle nonlinear and high-dimensional data, and this feature is just suitable for the effective classification of nonlinear and high-dimensional data in this paper. It is a challenging problem to select the appropriate features from receiver independent exchange (RINEX) format signals for the diverse forms of signals output from BeiDou signal receivers. In this paper, we analyze the selected features C/N0, ELE, and PR, and it is proved that they can be used for BeiDou satellite signal classification. In the experimental study, BeiDou satellite signals are collected with static receivers in an urban canyon. The experimental results show that the highest classification accuracy of 78.48% is achieved based on the PR using a single feature aspect. The SVM classification accuracy based on feature C/N0, ELE, and PR can reach 87.22%. The classification using multiple features is significantly higher than that of single feature.
{"title":"BDS Multipath Signal Classification Using Support Vector Machine","authors":"Yahang Qin, Zhenni Li, Shengli Xie, Rong Yuan, Junming Xie","doi":"10.1109/IAI55780.2022.9976714","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976714","url":null,"abstract":"In urban environments, multipath can significantly deteriorate the positioning precision of the global navigation satellite system (GNSS). BeiDou navigation satellite system independently established by China plays an important role in the GNSS market. Eliminating the multipath is a crucial problem to contribute to the development of the BeiDou navigation satellite system (BDS). In this paper, we use the machine learning algorithm support vector machine (SVM) to classify the BeiDou satellite signals into line-of-sight (LOS), multipath, and non-line-of-sight signals (NLOS). Single and multiple feature classification of the signal was performed by using the carrier to noise ratio (C/N0), elevation angle (ELE), and pseudorange residuals (PR). We use SVM with radial basis function (RBF), which can effectively handle nonlinear and high-dimensional data, and this feature is just suitable for the effective classification of nonlinear and high-dimensional data in this paper. It is a challenging problem to select the appropriate features from receiver independent exchange (RINEX) format signals for the diverse forms of signals output from BeiDou signal receivers. In this paper, we analyze the selected features C/N0, ELE, and PR, and it is proved that they can be used for BeiDou satellite signal classification. In the experimental study, BeiDou satellite signals are collected with static receivers in an urban canyon. The experimental results show that the highest classification accuracy of 78.48% is achieved based on the PR using a single feature aspect. The SVM classification accuracy based on feature C/N0, ELE, and PR can reach 87.22%. The classification using multiple features is significantly higher than that of single feature.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122700444","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976771
Longxin Yu, Haofei Meng, Wenwu Yu
Mobile crowdsensing (MCS) uses participants' computing resources to collect and analyze data and it has been applied in several areas to bring the convenience to people's lives. In MCS, the minimization of travel distance with location privacy is a common objective but should not be the only one practically. Different from the single objective of travel distance minimization, in this paper we formulate a multi-objective optimization model based on bit flipping mechanism, i.e., travel distance minimization and sensing quality score maximization, which is more suitable for a practical scenario. In order to solve the large-scale optimization problem, a Multi-Objective Simulated Annealing approach (MOSA) is utilized to derive a Pareto solution for decision makers. Extensive simulation results illustrate the feasibility and effectiveness of the proposed scheme.
{"title":"Privacy Preserving Task Allocation with Multi-objectives in Edge Computing Enhanced Mobile Crowdsensing","authors":"Longxin Yu, Haofei Meng, Wenwu Yu","doi":"10.1109/IAI55780.2022.9976771","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976771","url":null,"abstract":"Mobile crowdsensing (MCS) uses participants' computing resources to collect and analyze data and it has been applied in several areas to bring the convenience to people's lives. In MCS, the minimization of travel distance with location privacy is a common objective but should not be the only one practically. Different from the single objective of travel distance minimization, in this paper we formulate a multi-objective optimization model based on bit flipping mechanism, i.e., travel distance minimization and sensing quality score maximization, which is more suitable for a practical scenario. In order to solve the large-scale optimization problem, a Multi-Objective Simulated Annealing approach (MOSA) is utilized to derive a Pareto solution for decision makers. Extensive simulation results illustrate the feasibility and effectiveness of the proposed scheme.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127852929","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976823
Ibrahim Babiker, Jiacai Liao, W. Xie
This paper presents a novel method for detecting dandelion weed (Taraxacum officinale) plant centers in perennial ryegrass using partial information gathered only from plant leaves. A primitive region proposal method generates proposals from original birds-eye view images of whole dandelion weeds in grass. The proposals containing dandelion weed leaves are taken and plant centers are labeled with a point based on the novel concept of the most “prominent” leaf. The samples are divided into a grid of cells and the cell containing the labeled point is considered the truth cell. A radial map and its inverse are generated based on the spatial location of the cells w.r.t. the truth cell. A fully convolutional network is trained to detect the positive truth cell using novel loss functions based on these maps. Using a relatively small dataset, the loss functions with the terms that compute regression loss on the maps yield significantly better model performance than those without. In addition, some errors are simply the result of the center of an alternate “prominent” leaf being automatically detected. Further, the comparison results with segmentation models reveal some advantages in detecting only plant centers as opposed to training computationally costly inference models.
{"title":"Grid Cell Detection of Dandelion Weed Centers via Convolutional Neural Network","authors":"Ibrahim Babiker, Jiacai Liao, W. Xie","doi":"10.1109/IAI55780.2022.9976823","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976823","url":null,"abstract":"This paper presents a novel method for detecting dandelion weed (Taraxacum officinale) plant centers in perennial ryegrass using partial information gathered only from plant leaves. A primitive region proposal method generates proposals from original birds-eye view images of whole dandelion weeds in grass. The proposals containing dandelion weed leaves are taken and plant centers are labeled with a point based on the novel concept of the most “prominent” leaf. The samples are divided into a grid of cells and the cell containing the labeled point is considered the truth cell. A radial map and its inverse are generated based on the spatial location of the cells w.r.t. the truth cell. A fully convolutional network is trained to detect the positive truth cell using novel loss functions based on these maps. Using a relatively small dataset, the loss functions with the terms that compute regression loss on the maps yield significantly better model performance than those without. In addition, some errors are simply the result of the center of an alternate “prominent” leaf being automatically detected. Further, the comparison results with segmentation models reveal some advantages in detecting only plant centers as opposed to training computationally costly inference models.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130212746","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976862
Yijun Guo, Wu Zhou
For the tracking control of robotic manipulator with actuator dynamics, this paper proposed a chattering-free sliding mode control scheme based on linear extended state observer. To deal with the system uncertainties, a linear extended state observer is designed, which can achieve the estimations of the system states and the uncertainties. A fast sliding mode surface is constructed to ensure fast convergence of the tracking error. Then, a chattering-free sliding mode control scheme is designed to facilitate the practical application of the controller. Finally, comparative simulation results are given to verify the effectiveness of the proposed control scheme.
{"title":"Chattering-free sliding mode tracking control for robotic manipulator with actuator dynamics","authors":"Yijun Guo, Wu Zhou","doi":"10.1109/IAI55780.2022.9976862","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976862","url":null,"abstract":"For the tracking control of robotic manipulator with actuator dynamics, this paper proposed a chattering-free sliding mode control scheme based on linear extended state observer. To deal with the system uncertainties, a linear extended state observer is designed, which can achieve the estimations of the system states and the uncertainties. A fast sliding mode surface is constructed to ensure fast convergence of the tracking error. Then, a chattering-free sliding mode control scheme is designed to facilitate the practical application of the controller. Finally, comparative simulation results are given to verify the effectiveness of the proposed control scheme.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"413 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116699108","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976840
Xue Yu, Gang Wang, Jinhai Liu, Zhen Wang
Event-triggered tracking control for multi-agent systems with time-varying delays is proposed in this paper. Time-varying delays and the event-triggered mechanism are considered at the same time. The event-triggered tracking consensus is proved through the Lyapunov-Krasovskii functional, and the Zeno behavior is excluded. Finally, a simulation result is given to verify the effectiveness of the proposed method.
{"title":"Event-triggered tracking consensus for multi-agent systems with time-varying delays","authors":"Xue Yu, Gang Wang, Jinhai Liu, Zhen Wang","doi":"10.1109/IAI55780.2022.9976840","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976840","url":null,"abstract":"Event-triggered tracking control for multi-agent systems with time-varying delays is proposed in this paper. Time-varying delays and the event-triggered mechanism are considered at the same time. The event-triggered tracking consensus is proved through the Lyapunov-Krasovskii functional, and the Zeno behavior is excluded. Finally, a simulation result is given to verify the effectiveness of the proposed method.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127426683","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976570
Jin-Zi Yang, Jin‐Xi Zhang
The output feedback tracking control problem for a class of a one-link manipulator with full state constraints is investigated. Firstly, a fuzzy state observer is constructed for estimating the unmeasurable states. Then, by fusion of the new state transformation function and the dynamic surface control method, an observer-based adaptive fuzzy control strategy is established. Moreover, it is proved that the signals in the control systems are bound and the states of systems are never transcended the constraints by using the Lyapunov stability theory. Finally, numerical simulations are performed to validate the feasibility of the proposed methodology.
{"title":"Observer-based Adaptive Tracking Control for One-Link Manipulator with Full State Constraints","authors":"Jin-Zi Yang, Jin‐Xi Zhang","doi":"10.1109/IAI55780.2022.9976570","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976570","url":null,"abstract":"The output feedback tracking control problem for a class of a one-link manipulator with full state constraints is investigated. Firstly, a fuzzy state observer is constructed for estimating the unmeasurable states. Then, by fusion of the new state transformation function and the dynamic surface control method, an observer-based adaptive fuzzy control strategy is established. Moreover, it is proved that the signals in the control systems are bound and the states of systems are never transcended the constraints by using the Lyapunov stability theory. Finally, numerical simulations are performed to validate the feasibility of the proposed methodology.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122183654","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}
Root cause diagnosis (RCD) is an important technique for maintaining the safe operation of industrial processes. Traditional RCD methods usually require stationarity assumptions. However, the process inevitably shows nonstationarity due to factors such as switching of operating conditions. Although there have been some previous studies trying to overcome the challenge of nonstationarity, these methods fail to guarantee the significance of the extracted causalities and lead to redundant relationships. To address the above issues, a sparse causal analysis model with time-varying parameters is extracted in this study. First, we propose an end-to-end information fusion and prediction task to characterize predictive relationships between variables and avoid repeated modeling. Second, we design time-varying parameters for the information fusion mechanism to cope with nonstationarity and automatically identify significant causality through sparse parameter updates. We design an update strategy that constrains the gradient information to guarantee sparsity. Finally, a causal metric is constructed for the time-varying predictive relationship to comprehensively obtain the overall causal relationship, which further guarantees causal significance. The validity of the proposed method is illustrated through a real industrial example collected from a thermal power plant.
{"title":"Sparse Causality Analysis Approach with Time-varying Parameters for Root Cause Localization of Nonstationary Process","authors":"Pengyu Song, Chunhui Zhao, Biao Huang, Jinliang Ding","doi":"10.1109/IAI55780.2022.9976691","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976691","url":null,"abstract":"Root cause diagnosis (RCD) is an important technique for maintaining the safe operation of industrial processes. Traditional RCD methods usually require stationarity assumptions. However, the process inevitably shows nonstationarity due to factors such as switching of operating conditions. Although there have been some previous studies trying to overcome the challenge of nonstationarity, these methods fail to guarantee the significance of the extracted causalities and lead to redundant relationships. To address the above issues, a sparse causal analysis model with time-varying parameters is extracted in this study. First, we propose an end-to-end information fusion and prediction task to characterize predictive relationships between variables and avoid repeated modeling. Second, we design time-varying parameters for the information fusion mechanism to cope with nonstationarity and automatically identify significant causality through sparse parameter updates. We design an update strategy that constrains the gradient information to guarantee sparsity. Finally, a causal metric is constructed for the time-varying predictive relationship to comprehensively obtain the overall causal relationship, which further guarantees causal significance. The validity of the proposed method is illustrated through a real industrial example collected from a thermal power plant.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123271580","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976561
Zihang Zhou, Ding Wang, Xin Xu
In this paper, we develop an event-driven robust guaranteed cost control strategy of continuous-time (CT) systems via improved adaptive critic learning (ACL). First, we choose a suitable cost function which reflects uncertainties, control, and regulation, in order to transform the robust control problem into the optimal control problem. Then, we obtain the time-driven optimal control law and the Hamilton-Jacobi-Bellman equation. Next, through theoretical analysis, we derive the event-driven optimal control law of the nominal system based on the ACL method, and prove the robust stabilization of the CT nonlinear system. Additionally, we construct a novel critic neural network learning algorithm to accelerate the convergence of weights. We also obtain the neural-network-based event-driven condition and prove the closed-loop system stability. Finally, the simulation result shows the effectiveness of the event-driven guaranteed cost control design.
{"title":"Event-Driven Robust Guaranteed Cost Control via an Improved Adaptive Critic Learning Strategy","authors":"Zihang Zhou, Ding Wang, Xin Xu","doi":"10.1109/IAI55780.2022.9976561","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976561","url":null,"abstract":"In this paper, we develop an event-driven robust guaranteed cost control strategy of continuous-time (CT) systems via improved adaptive critic learning (ACL). First, we choose a suitable cost function which reflects uncertainties, control, and regulation, in order to transform the robust control problem into the optimal control problem. Then, we obtain the time-driven optimal control law and the Hamilton-Jacobi-Bellman equation. Next, through theoretical analysis, we derive the event-driven optimal control law of the nominal system based on the ACL method, and prove the robust stabilization of the CT nonlinear system. Additionally, we construct a novel critic neural network learning algorithm to accelerate the convergence of weights. We also obtain the neural-network-based event-driven condition and prove the closed-loop system stability. Finally, the simulation result shows the effectiveness of the event-driven guaranteed cost control design.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131511246","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}
Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976593
Yee Tat Ng, Xiang Li, Ji-Yan Wu, Van Tung Tran, Wenju Lu
In this paper, a hybrid classification method for image based anomaly detection is proposed to improve the detection rate from industrial high-dimensional process data. The method involves feature selection with clustering based classification to discover failure patterns for marginal datasets to improve detection accuracy. The proposed hybrid classification method is tested with a real industry data sets. Results show that the proposed hybrid classification method is superior to the conventional classification methods such as multilayer perceptron (MLP) and decision tree in term of anomaly detection accuracy.
{"title":"Hybrid Classification Method for Image-based Anomaly Detection in Manufacturing Processes","authors":"Yee Tat Ng, Xiang Li, Ji-Yan Wu, Van Tung Tran, Wenju Lu","doi":"10.1109/IAI55780.2022.9976593","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976593","url":null,"abstract":"In this paper, a hybrid classification method for image based anomaly detection is proposed to improve the detection rate from industrial high-dimensional process data. The method involves feature selection with clustering based classification to discover failure patterns for marginal datasets to improve detection accuracy. The proposed hybrid classification method is tested with a real industry data sets. Results show that the proposed hybrid classification method is superior to the conventional classification methods such as multilayer perceptron (MLP) and decision tree in term of anomaly detection accuracy.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131385612","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：