To solve the problem of variations in radio frequency characteristics among different devices,transfer learning is applied to transform device diversity to domain adaptation in the indoor localization algorithm.A robu...To solve the problem of variations in radio frequency characteristics among different devices,transfer learning is applied to transform device diversity to domain adaptation in the indoor localization algorithm.A robust indoor localization algorithm based on the aligned fingerprints and ensemble learning called correlation alignment for localization(CALoc)is proposed with low computational complexity.The second-order statistical properties of fingerprints in the offline and online phase are needed to be aligned.The real-time online calibration method mitigates the impact of device heterogeneity largely.Without any time-consuming deep learning retraining process,CALoc online only needs 0.11 s.The effectiveness and efficiency of CALoc are verified by realistic experiments.The results show that compared to the traditional algorithms,a significant performance gain is achieved and that it achieves better positioning accuracy with a 19%improvement.展开更多
Intelligent diagnosis driven by big data for mechanical fault is an important means to ensure the safe operation ofequipment. In these methods, deep learning-based machinery fault diagnosis approaches have received in...Intelligent diagnosis driven by big data for mechanical fault is an important means to ensure the safe operation ofequipment. In these methods, deep learning-based machinery fault diagnosis approaches have received increasingattention and achieved some results. It might lead to insufficient performance for using transfer learning alone andcause misclassification of target samples for domain bias when building deep models to learn domain-invariantfeatures. To address the above problems, a deep discriminative adversarial domain adaptation neural networkfor the bearing fault diagnosis model is proposed (DDADAN). In this method, the raw vibration data are firstlyconverted into frequency domain data by Fast Fourier Transform, and an improved deep convolutional neuralnetwork with wide first-layer kernels is used as a feature extractor to extract deep fault features. Then, domaininvariant features are learned from the fault data with correlation alignment-based domain adversarial training.Furthermore, to enhance the discriminative property of features, discriminative feature learning is embeddedinto this network to make the features compact, as well as separable between classes within the class. Finally, theperformance and anti-noise capability of the proposedmethod are evaluated using two sets of bearing fault datasets.The results demonstrate that the proposed method is capable of handling domain offset caused by differentworkingconditions and maintaining more than 97.53% accuracy on various transfer tasks. Furthermore, the proposedmethod can achieve high diagnostic accuracy under varying noise levels.展开更多
Recently, data-driven methods, especially deep learning, outperform other methods for rolling elementbearing (REB) fault diagnosis. Nevertheless, most research work assumes that REB dataset is unbiased. Inthe real ind...Recently, data-driven methods, especially deep learning, outperform other methods for rolling elementbearing (REB) fault diagnosis. Nevertheless, most research work assumes that REB dataset is unbiased. Inthe real industry applications, the dataset bias exists with REB owing to varying REB working conditions andnoise interference. Recently proposed adversarial discriminative domain adaptation (ADDA) is an increasinglypopular incarnation to solve dataset bias problem. However, it mainly devotes to realizing domain alignments, andignores class-level alignments;it can cause degradation of classification performance. In this study, we proposea new REB fault diagnosis model based on improved ADDA to address dataset bias. The proposed diagnosismodel realizes domain- and class-level alignments in dataset bias scenario;it consists of two feature extractors,a domain discriminator, and two label classifiers. The feature extractors and domain discriminator are trainedin an adversarial manner to minimize the domain difference in feature extractors. The domain discrepancy inlabel classifier is reduced by minimizing correlation alignment (CORAL) loss. We evaluate the proposed model onthe Case Western Reserve University (CWRU) bearing dataset and Paderborn University bearing dataset. Theproposed method yields better results than other methods and has good prospects for industrial applications.展开更多
This paper examines the prediction of film ratings.Firstly,in the data feature engineering,feature construction is performed based on the original features of the film dataset.Secondly,the clustering algorithm is util...This paper examines the prediction of film ratings.Firstly,in the data feature engineering,feature construction is performed based on the original features of the film dataset.Secondly,the clustering algorithm is utilized to remove singular film samples,and feature selections are carried out.When solving the problem that film samples of the target domain are unlabelled,it is impossible to train a model and address the inconsistency in the feature dimension for film samples from the source domain.Therefore,the domain adaptive transfer learning model combined with dimensionality reduction algorithms is adopted in this paper.At the same time,in order to reduce the prediction error of models,the stacking ensemble learning model for regression is also used.Finally,through comparative experiments,the effectiveness of the proposed method is verified,which proves to be better predicting film ratings in the target domain.展开更多
基金The National Key Research and Development Program of China(No.2018YFB1802400)the National Natural Science Foundation of China(No.61571123)the Research Fund of National M obile Communications Research Laboratory,Southeast University(No.2020A03)
文摘To solve the problem of variations in radio frequency characteristics among different devices,transfer learning is applied to transform device diversity to domain adaptation in the indoor localization algorithm.A robust indoor localization algorithm based on the aligned fingerprints and ensemble learning called correlation alignment for localization(CALoc)is proposed with low computational complexity.The second-order statistical properties of fingerprints in the offline and online phase are needed to be aligned.The real-time online calibration method mitigates the impact of device heterogeneity largely.Without any time-consuming deep learning retraining process,CALoc online only needs 0.11 s.The effectiveness and efficiency of CALoc are verified by realistic experiments.The results show that compared to the traditional algorithms,a significant performance gain is achieved and that it achieves better positioning accuracy with a 19%improvement.
基金the Natural Science Foundation of Henan Province(232300420094)the Science and TechnologyResearch Project of Henan Province(222102220092).
文摘Intelligent diagnosis driven by big data for mechanical fault is an important means to ensure the safe operation ofequipment. In these methods, deep learning-based machinery fault diagnosis approaches have received increasingattention and achieved some results. It might lead to insufficient performance for using transfer learning alone andcause misclassification of target samples for domain bias when building deep models to learn domain-invariantfeatures. To address the above problems, a deep discriminative adversarial domain adaptation neural networkfor the bearing fault diagnosis model is proposed (DDADAN). In this method, the raw vibration data are firstlyconverted into frequency domain data by Fast Fourier Transform, and an improved deep convolutional neuralnetwork with wide first-layer kernels is used as a feature extractor to extract deep fault features. Then, domaininvariant features are learned from the fault data with correlation alignment-based domain adversarial training.Furthermore, to enhance the discriminative property of features, discriminative feature learning is embeddedinto this network to make the features compact, as well as separable between classes within the class. Finally, theperformance and anti-noise capability of the proposedmethod are evaluated using two sets of bearing fault datasets.The results demonstrate that the proposed method is capable of handling domain offset caused by differentworkingconditions and maintaining more than 97.53% accuracy on various transfer tasks. Furthermore, the proposedmethod can achieve high diagnostic accuracy under varying noise levels.
基金Foundation item:the Research on Intelligent Ship Testing and Verification(No.[2018]473)。
文摘Recently, data-driven methods, especially deep learning, outperform other methods for rolling elementbearing (REB) fault diagnosis. Nevertheless, most research work assumes that REB dataset is unbiased. Inthe real industry applications, the dataset bias exists with REB owing to varying REB working conditions andnoise interference. Recently proposed adversarial discriminative domain adaptation (ADDA) is an increasinglypopular incarnation to solve dataset bias problem. However, it mainly devotes to realizing domain alignments, andignores class-level alignments;it can cause degradation of classification performance. In this study, we proposea new REB fault diagnosis model based on improved ADDA to address dataset bias. The proposed diagnosismodel realizes domain- and class-level alignments in dataset bias scenario;it consists of two feature extractors,a domain discriminator, and two label classifiers. The feature extractors and domain discriminator are trainedin an adversarial manner to minimize the domain difference in feature extractors. The domain discrepancy inlabel classifier is reduced by minimizing correlation alignment (CORAL) loss. We evaluate the proposed model onthe Case Western Reserve University (CWRU) bearing dataset and Paderborn University bearing dataset. Theproposed method yields better results than other methods and has good prospects for industrial applications.
基金Supported by the Scientific Research Foundation of Liaoning Provincial Department of Education(No.LJKZ0139).
文摘This paper examines the prediction of film ratings.Firstly,in the data feature engineering,feature construction is performed based on the original features of the film dataset.Secondly,the clustering algorithm is utilized to remove singular film samples,and feature selections are carried out.When solving the problem that film samples of the target domain are unlabelled,it is impossible to train a model and address the inconsistency in the feature dimension for film samples from the source domain.Therefore,the domain adaptive transfer learning model combined with dimensionality reduction algorithms is adopted in this paper.At the same time,in order to reduce the prediction error of models,the stacking ensemble learning model for regression is also used.Finally,through comparative experiments,the effectiveness of the proposed method is verified,which proves to be better predicting film ratings in the target domain.
