- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Minimum material quality threshold for intermediate band solar cells using a multi-band device simulator with fully coupled optics
摘要： One of the common ways to perform data-driven fault diagnosis is to employ statistical models, which can classify the data into nominal (healthy) and a fault class or distinguish among different fault classes. The former is termed fault (anomaly) detection, and the latter is termed fault isolation (classi?cation, diagnosis). Traditionally, statistical classi?ers are trained using data from faulty and nominal behaviors in a batch mode. However, it is dif?cult to anticipate, a priori, all the possible ways in which failures can occur, especially when a new vehicle model is introduced. Therefore, it is imperative that diagnostic algorithms adapt to new cases on an ongoing basis. In this paper, a uni?ed methodology to incrementally learn new information from evolving databases is presented. The performance of adaptive (or incremental learning) classi?cation techniques is discussed when: 1) the new data has the same fault classes and same features and 2) the new data has new fault classes, but with the same set of observed features. The proposed methodology is demonstrated on data sets derived from an automotive electronic throttle control subsystem.
关键词： fault diagnosis,automotive systems,incremental classi?ers,Adaptive learning,ensemble systems
更新于2025-09-23 15:19:57
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Defect Analysis in CSS and Sputtered CdSe <sub/>x</sub> Te <sub/>1-x</sub> Thin Films
摘要： This paper addresses a new person reidenti?cation problem without label information of persons under nonoverlapping target cameras. Given the matched (positive) and unmatched (negative) image pairs from source domain cameras, as well as unmatched (negative) and unlabeled image pairs from target domain cameras, we propose an adaptive ranking support vector machines (AdaRSVMs) method for reidenti?cation under target domain cameras without person labels. To overcome the problems introduced due to the absence of matched (positive) image pairs in the target domain, we relax the discriminative constraint to a necessary condition only relying on the positive mean in the target domain. To estimate the target positive mean, we make use of all the available data from source and target domains as well as constraints in person reidenti?cation. Inspired by adaptive learning methods, a new discriminative model with high con?dence in target positive mean and low con?dence in target negative image pairs is developed by re?ning the distance model learnt from the source domain. Experimental results show that the proposed AdaRSVM outperforms existing supervised or unsupervised, learning or non-learning reidenti?cation methods without using label information in target cameras. Moreover, our method achieves better reidenti?cation performance than existing domain adaptation methods derived under equal conditional probability assumption.
关键词： Person re-identi?cation,ranking SVMs,target positive mean,adaptive learning,domain adaptation
更新于2025-09-23 15:19:57
-
[IEEE 2019 IEEE Power & Energy Society General Meeting (PESGM) - Atlanta, GA, USA (2019.8.4-2019.8.8)] 2019 IEEE Power & Energy Society General Meeting (PESGM) - Fault Location in Ungrounded Photovoltaic System Using Wavelets and ANN
摘要： This paper addresses a new person reidenti?cation problem without label information of persons under nonoverlapping target cameras. Given the matched (positive) and unmatched (negative) image pairs from source domain cameras, as well as unmatched (negative) and unlabeled image pairs from target domain cameras, we propose an adaptive ranking support vector machines (AdaRSVMs) method for reidenti?cation under target domain cameras without person labels. To overcome the problems introduced due to the absence of matched (positive) image pairs in the target domain, we relax the discriminative constraint to a necessary condition only relying on the positive mean in the target domain. To estimate the target positive mean, we make use of all the available data from source and target domains as well as constraints in person reidenti?cation. Inspired by adaptive learning methods, a new discriminative model with high con?dence in target positive mean and low con?dence in target negative image pairs is developed by re?ning the distance model learnt from the source domain. Experimental results show that the proposed AdaRSVM outperforms existing supervised or unsupervised, learning or non-learning reidenti?cation methods without using label information in target cameras. Moreover, our method achieves better reidenti?cation performance than existing domain adaptation methods derived under equal conditional probability assumption.
关键词： adaptive learning,target positive mean,ranking SVMs,domain adaptation,Person re-identi?cation
更新于2025-09-23 15:19:57
-
[IEEE 2019 11th Electrical Engineering Faculty Conference (BulEF) - Varna, Bulgaria (2019.9.11-2019.9.14)] 2019 11th Electrical Engineering Faculty Conference (BulEF) - Operating regimes of a rooftop photovoltaic installation
摘要： This paper addresses a new person reidenti?cation problem without label information of persons under nonoverlapping target cameras. Given the matched (positive) and unmatched (negative) image pairs from source domain cameras, as well as unmatched (negative) and unlabeled image pairs from target domain cameras, we propose an adaptive ranking support vector machines (AdaRSVMs) method for reidenti?cation under target domain cameras without person labels. To overcome the problems introduced due to the absence of matched (positive) image pairs in the target domain, we relax the discriminative constraint to a necessary condition only relying on the positive mean in the target domain. To estimate the target positive mean, we make use of all the available data from source and target domains as well as constraints in person reidenti?cation. Inspired by adaptive learning methods, a new discriminative model with high con?dence in target positive mean and low con?dence in target negative image pairs is developed by re?ning the distance model learnt from the source domain. Experimental results show that the proposed AdaRSVM outperforms existing supervised or unsupervised, learning or non-learning reidenti?cation methods without using label information in target cameras. Moreover, our method achieves better reidenti?cation performance than existing domain adaptation methods derived under equal conditional probability assumption.
关键词： ranking SVMs,target positive mean,domain adaptation,Person re-identi?cation,adaptive learning
更新于2025-09-19 17:13:59