Guangfan Zhang

Bio: Guangfan Zhang is an academic researcher. The author has contributed to research in topics: Prognostics & Redundancy (engineering). The author has an hindex of 8, co-authored 19 publications receiving 844 citations.

Active health monitoring of an aircraft wing with embedded piezoelectric sensor/actuator network: I. Defect detection, localization and growth monitoring

Abstract: This work focuses on an ultrasonic guided wave structural health monitoring (SHM) system development for aircraft wing inspection. In part I of the study, a detailed description of a real aluminum wing specimen and some preliminary wave propagation tests on the wing panel are presented. Unfortunately, strong attenuation and scattering impede guided waves for large-area inspection. Nevertheless, small, low-cost and light-weight piezoelectric (PZT) discs were bonded to various parts of the aircraft wing, in a form of relatively sparse arrays, for simulated cracks and corrosion monitoring. The PZT discs take turns generating and receiving ultrasonic guided waves. Pair-wise through-transmission waveforms collected at normal conditions served as baselines, and subsequent signals collected at defected conditions such as rivet cracks or corrosion detected the presence of a defect and its location with a novel correlation analysis based technique called RAPID (reconstruction algorithm for probabilistic inspection of defects). The effectiveness of the algorithm was tested with several case studies in a laboratory environment. It showed good performance for defect detection, size estimation and localization in complex aircraft wing structures.

A Deep Transfer Learning Approach for Improved Post-Traumatic Stress Disorder Diagnosis

Abstract: Post-traumatic stress disorder (PTSD) is a traumatic-stressor related disorder developed by exposure to a traumatic or adverse environmental event that caused serious harm or injury. Structured interview is the only widely accepted clinical practice for PTSD diagnosis but suffers from several limitations including the stigma associated with the disease. Diagnosis of PTSD patients by analyzing speech signals has been investigated as an alternative since recent years, where speech signals are processed to extract frequency features and these features are then fed into a classification model for PTSD diagnosis. In this paper, we developed a deep belief network (DBN) model combined with a transfer learning (TL) strategy for PTSD diagnosis. We computed three categories of speech features and utilized the DBN model to fuse these features. The TL strategy was utilized to transfer knowledge learned from a large speech recognition database, TIMIT, for PTSD detection where PTSD patient data is difficult to collect. We evaluated the proposed methods on two PTSD speech databases, each of which consists of audio recordings from 26 patients. We compared the proposed methods with other popular methods and showed that the state-of-the-art support vector machine (SVM) classifier only achieved an accuracy of 57.68%, and TL strategy boosted the performance of the DBN from 61.53% to 74.99%. Altogether, our method provides a pragmatic and promising tool for PTSD diagnosis.

An Enhanced Prognostic Model for Intermittent Failures in Digital Electronics

Abstract: This paper presents an enhanced prognostic model to predict remaining useful life. The model utilizes environmental loads and in-situ performance measurements in conjunction with two baseline prediction algorithms: life consumption monitoring (LCM) and uncertainty adjusted prognostics (UAP). Fusion techniques are then utilized to integrate the two prognostic algorithms. A key and unique value of this combined prognostic model is its ability to assess intermittent as well as "hard" failures. In the paper we show how it has been validated for intermittent and "hard" solder joint interconnect failures under temperature cycling loads.

A deep transfer learning approach for improved post-traumatic stress disorder diagnosis

Abstract: Post-traumatic stress disorder (PTSD) is a traumatic-stressor-related disorder developed by exposure to a traumatic or adverse environmental event that caused serious harm or injury. Structured interview is the only widely accepted clinical practice for PTSD diagnosis but suffers from several limitations including the stigma associated with the disease. Diagnosis of PTSD patients by analyzing speech signals has been investigated as an alternative since recent years, where speech signals are processed to extract frequency features and these features are then fed into a classification model for PTSD diagnosis. In this paper, we developed a deep belief network (DBN) model combined with a transfer learning (TL) strategy for PTSD diagnosis. We computed three categories of speech features and utilized the DBN model to fuse these features. The TL strategy was utilized to transfer knowledge learned from a large speech recognition database, TIMIT, for PTSD detection where PTSD patient data are difficult to collect. We evaluated the proposed methods on two PTSD speech databases, each of which consists of audio recordings from 26 patients. We compared the proposed methods with other popular methods and showed that the state-of-the-art support vector machine (SVM) classifier only achieved an accuracy of 57.68%, and TL strategy boosted the performance of the DBN from 61.53 to 74.99%. Altogether, our method provides a pragmatic and promising tool for PTSD diagnosis. Preliminary results of this study were presented in Banerjee (in: 2017 IEEE international conference on data mining (ICDM), IEEE, 2017).

Deep learning for time series classification: a review

Abstract: Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.

Deep learning for electroencephalogram (EEG) classification tasks: a review.

Abstract: Objective Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks? Approach A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture. Main results For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review. Significance This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

Deep learning-based electroencephalography analysis: a systematic review.

Abstract: Context Electroencephalography (EEG) is a complex signal and can require several years of training, as well as advanced signal processing and feature extraction methodologies to be correctly interpreted. Recently, deep learning (DL) has shown great promise in helping make sense of EEG signals due to its capacity to learn good feature representations from raw data. Whether DL truly presents advantages as compared to more traditional EEG processing approaches, however, remains an open question. Objective In this work, we review 154 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain-computer interfacing, and cognitive and affective monitoring. We extract trends and highlight interesting approaches from this large body of literature in order to inform future research and formulate recommendations. Methods Major databases spanning the fields of science and engineering were queried to identify relevant studies published in scientific journals, conferences, and electronic preprint repositories. Various data items were extracted for each study pertaining to (1) the data, (2) the preprocessing methodology, (3) the DL design choices, (4) the results, and (5) the reproducibility of the experiments. These items were then analyzed one by one to uncover trends. Results Our analysis reveals that the amount of EEG data used across studies varies from less than ten minutes to thousands of hours, while the number of samples seen during training by a network varies from a few dozens to several millions, depending on how epochs are extracted. Interestingly, we saw that more than half the studies used publicly available data and that there has also been a clear shift from intra-subject to inter-subject approaches over the last few years. About [Formula: see text] of the studies used convolutional neural networks (CNNs), while [Formula: see text] used recurrent neural networks (RNNs), most often with a total of 3-10 layers. Moreover, almost one-half of the studies trained their models on raw or preprocessed EEG time series. Finally, the median gain in accuracy of DL approaches over traditional baselines was [Formula: see text] across all relevant studies. More importantly, however, we noticed studies often suffer from poor reproducibility: a majority of papers would be hard or impossible to reproduce given the unavailability of their data and code. Significance To help the community progress and share work more effectively, we provide a list of recommendations for future studies and emphasize the need for more reproducible research. We also make our summary table of DL and EEG papers available and invite authors of published work to contribute to it directly. A planned follow-up to this work will be an online public benchmarking portal listing reproducible results.

Prognostics and Health Management of Electronics

Abstract: Reliability is the ability of a product or system to perform as intended (i.e., without failure and within specified performance limits) for a specified time, in its life-cycle environment. Commonly used electronics reliability prediction methods (e.g., Mil-HDBK-217, 217-PLUS, PRISM, Telcordia, FIDES) based on handbook methods have been shown to be misleading and provide erroneous life predictions. The use of stress and damage models permits a far superior accounting of the reliability and the physics of failure (PoF); however, sufficient knowledge of the actual operating and environmental application conditions of the product is still required. This article presents a PoF-based prognostics and health management approach for effective reliability prediction. PoF is an approach that utilizes knowledge of a product's life-cycle loading and failure mechanisms to perform reliability modeling, design, and assessment. This method permits the assessment of the reliability of a system under its actual application conditions. It integrates sensor data with models that enable in situ assessment of the deviation or degradation of a product from an expected normal operating condition and the prediction of the future state of reliability. This article presents a formal implementation procedure, which includes failure modes, mechanisms, and effects analysis, data reduction and feature extraction from the life-cycle loads, damage accumulation, and assessment of uncertainty. Applications of PoF-based prognostics and health management are also discussed. Keywords: reliability; prognostics; physics of failure; design-for-reliability; reliability prediction

The Harmony of Illusions: Inventing Post-Traumatic Stress Disorder.@@@Rewriting the Soul: Multiple Personality and the Sciences of Memory.

Abstract: As far back as we know, there have been individuals inca-pacitated by memories that have filled them with sadness and remorse, fright and horror, or a sense of irreparable loss. Only recently, however, have people tormented with such recollections been diagnosed as suffering from "post-traumatic stress disorder". Here Allan Young traces this malady, particularly as it is suffered by Vietnam veterans, to its beginnings in the emergence of ideas about the unconscious mind and to earlier manifestations of traumatic memory like shell shock or traumatic hysteria. In Young's view PTSD is not a timeless or universal phenomemon newly discovered. Rather, it is a "harmony of illusions, a cultural product gradually put together by the practices, technologies, and narratives with which it is diagnosed, studied, and treated and by the various interests, institutions, and moral arguments mobilising these efforts. This book is part history and part ethnography, and it includes a detailed account of everyday life in a psychiatric unit specialising in the treatment of Vietnam veterans with PTSD. To illustrate his points, Young presents a number of fascinating transcripts of the group therapy and diagnostic sessions that he observed firsthand over a period of two years. Through his comments and the tran-scripts themselves, the reader becomes familiar with the individual hospital personnel and clients and their struggle to make sense of life after a tragic war. One observes that everyone on the unit is heavily invested in the PTSD diagnosis: boundaries between therapist and patient are as unclear as were the distinctions between victim and victimizer in the jungles of Southeast Asia.