More Like this

1. Semi-Supervised Autoencoder With Joint Loss Learning for Bearing Fault Detection

   https://doi.org/10.1115/DETC2023-112654  

   Zhou, Kai; Zhang, Yang; Tang, Jiong (August 2023, American Society of Mechanical Engineers)

   Abstract Timely and accurate bearing fault detection plays an important role in various industries. Data-driven deep learning methods have recently become a prevailing approach for bearing fault detection. Despite the success of deep learning, fault diagnosis performance is hinged upon the size of labeled data, the acquisition of which oftentimes is expensive in actual practice. Unlabeled data, on the other hand, are inexpensive. To fully utilize a large amount of unlabeled data together with limited labeled data to enhance fault detection performance, in this research, we develop a semi-supervised learning method built upon the autoencoder. In this method, a joint loss is established to account for the effects of both the labeled and unlabeled data, which is subsequently used to direct the backpropagation training. Systematic case studies using the Case Western Reserve University (CWRU) rolling bearing dataset are carried out, in which the effectiveness of this new method is verified by comparing it with other benchmark models. 

   more » « less
2. Semi-Supervised Learning for Wearable-based Momentary Stress Detection in the Wild

   https://doi.org/10.1145/3596246  

   Yu, Han; Sano, Akane (June 2023, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies)

   Physiological and behavioral data collected from wearable or mobile sensors have been used to estimate self-reported stress levels. Since stress annotation usually relies on self-reports during the study, a limited amount of labeled data can be an obstacle to developing accurate and generalized stress-predicting models. On the other hand, the sensors can continuously capture signals without annotations. This work investigates leveraging unlabeled wearable sensor data for stress detection in the wild. We propose a two-stage semi-supervised learning framework that leverages wearable sensor data to help with stress detection. The proposed structure consists of an auto-encoder pre-training method for learning information from unlabeled data and the consistency regularization approach to enhance the robustness of the model. Besides, we propose a novel active sampling method for selecting unlabeled samples to avoid introducing redundant information to the model. We validate these methods using two datasets with physiological signals and stress labels collected in the wild, as well as four human activity recognition (HAR) datasets to evaluate the generality of the proposed method. Our approach demonstrated competitive results for stress detection, improving stress classification performance by approximately 7% to 10% on the stress detection datasets compared to the baseline supervised learning models. Furthermore, the ablation study we conducted for the HAR tasks supported the effectiveness of our methods. Our approach showed comparable performance to state-of-the-art semi-supervised learning methods for both stress detection and HAR tasks. 

   more » « less
3. A hierarchical deep learning framework for combined rolling bearing fault localization and identification with data fusion

   https://doi.org/10.1177/10775463221091601  

   Liang, Mingxuan; Zhou, Kai (April 2022, Journal of Vibration and Control)

   Fault diagnosis of rolling bearings becomes an important research subject, where the data-driven deep learning-based techniques have been extensively exploited. While the state-of-the-art research has shown the substantial progresses in bearing fault diagnosis, they mostly were implemented upon the hypothesis that the location of bearing prone to failure already is known. Nevertheless, in actual practice many rolling bearings are installed in a complex machinery system, any of which is likely subject to fault. As such, fault diagnosis essentially is a process to achieve both fault localization and identification, which results in many fault scenarios to be handled. This will significantly degrade the fault diagnosis performance using conventional deep learning analysis. In this research, we aim to develop a new deep learning framework to address abovementioned challenge. We particularly design a hierarchical deep learning framework consisting of multiple sequentially deployed deep learning models built upon the transfer learning. This can improve the learning adequacy for a high-dimensional problem with many fault scenarios involved even under limited dataset, thereby enhancing the fault diagnosis performance. Without the prior knowledge regarding the fault location, this methodology is greatly favored by the sensor/data fusion which takes full advantage of the enriched pivot fault-related features in the measurements acquired from different accelerometers. Systematic case studies using the publicly accessible experimental rolling bearing dataset are carried out to validate this new methodology. 

   more » « less
4. VideoSSL: Semi-Supervised Learning for Video Classification

   Jing, L; Parag, T; Wu, Z; Tian, Y; Wang, H. (January 2021, Winter Conference on Applications of Computer Vision (WACV), 2021.)

   null (Ed.)

   We propose a semi-supervised learning approach for video classification, VideoSSL, using convolutional neural networks (CNN). Like other computer vision tasks, existing supervised video classification methods demand a large amount of labeled data to attain good performance. However, annotation of a large dataset is expensive and time consuming. To minimize the dependence on a large annotated dataset, our proposed semi-supervised method trains from a small number of labeled examples and exploits two regulatory signals from unlabeled data. The first signal is the pseudo-labels of unlabeled examples computed from the confidences of the CNN being trained. The other is the normalized probabilities, as predicted by an image classifier CNN, that captures the information about appearances of the interesting objects in the video. We show that, under the supervision of these guiding signals from unlabeled examples, a video classification CNN can achieve impressive performances utilizing a small fraction of annotated examples on three publicly available datasets: UCF101, HMDB51, and Kinetics. 

   more » « less
5. A One-Class Support Vector Machine Calibration Method for Time Series Change Point Detection

   https://doi.org/10.1109/ICPHM.2019.8819385  

   Jin, Baihong; Chen, Yuxin; Li, Dan; Poolla, Kameshwar; Sangiovanni-Vincentelli, Alberto (June 2019, 2019 IEEE International Conference on Prognostics and Health Management (ICPHM))

   Early detection of incipient faults is of vital im- portance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is known that the performance of supervised learning approaches highly relies on the availability and quality of labeled training data. In Fault Detection and Diagnosis (FDD) applications, the lack of labeled incipient fault data has posed a major challenge to applying these supervised learning techniques to commercial buildings. To overcome this challenge, this paper proposes using Monte Carlo dropout (MC-dropout) to enhance the supervised learning pipeline, so that the resulting neural network is able to detect and diagnose unseen incipient fault examples. We also examine the proposed MC-dropout method on the RP-1043 dataset to demonstrate its effectiveness in indicating the most likely incipient fault types. 

   more » « less