Gabriel Michau

Dr. Gabriel Michau

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 February 2022 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
PDF file
GMGabriel Michau
Gabriel Michau
GFGaetan Frusque
Gaetan Frusque
OFOlga Fink
Olga Fink
Significance: Monitoring of industrial assets often relies on high-frequency (HF) signal measurements. One difficulty of dealing with such measurements in the industrial context is the conciliation between the high-frequency sampling and low-dimensional decision states (e.g., healthy/unhealthy), in a context where, very often, labels are not available. Here, we propose a fully unsupervised deep-learning framework for high-frequency time series that is able to extract meaningful and sparse representation of raw signals and is able to handle different lengths of time series flexibly, overcoming thereby several of the limitations of existing deep-learning approaches. The decomposition framework will be very useful for handling in an automatic manner high-frequency signals and is an important basis for future applications with HF data.


21 February 2021 in Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability
Verified
Journal Article
Closed access
PDF file
GGGabriel Rodriguez Garcia
Gabriel Rodriguez Garcia
GMGabriel Michau
Gabriel Michau
MDMélanie Ducoffe
Mélanie Ducoffe
JGJayant Sen Gupta
Jayant Sen Gupta
OFOlga Fink
Olga Fink
The ability to detect anomalies in time series is considered highly valuable in numerous application domains. The sequential nature of time series objects is responsible for an additional feature complexity, ultimately requiring specialized approaches in order to solve the task. Essential characteristics of time series, situated outside the time domain, are often difficult to capture with state-of-the-art anomaly detection methods when no transformations have been applied to the time series. Inspired by the success of deep learning methods in computer vision, several studies have proposed transforming time series into image-like representations, used as inputs for deep learning models, and have led to very promising results in classification tasks. In this paper, we first review the signal to image encoding approaches found in the literature. Second, we propose modifications to some of their original formulations to make them more robust to the variability in large datasets. Third, we compare them on the basis of a common unsupervised task to demonstrate how the choice of the encoding can impact the results when used in the same deep learning architecture. We thus provide a comparison between six encoding algorithms with and without the proposed modifications. The selected encoding methods are Gramian Angular Field, Markov Transition Field, recurrence plot, grey scale encoding, spectrogram, and scalogram. We also compare the results achieved with the raw signal used as input for another deep learning model. We demonstrate that some encodings have a competitive advantage and might be worth considering within a deep learning framework. The comparison is performed on a dataset collected and released by Airbus SAS, containing highly complex vibration measurements from real helicopter flight tests. The different encodings provide competitive results for anomaly detection.

3 January 2020 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
QWQin Wang
Qin Wang
GMGabriel Michau
Gabriel Michau
OFOlga Fink
Olga Fink

16 January 2017 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
GMGabriel Michau
Gabriel Michau
ANAlfredo Nantes
Alfredo Nantes
Ashish BhaskarAshish Bhaskar
Ashish Bhaskar
ECEdward Chung
Edward Chung
PAPatrice Abry
Patrice Abry
PBPierre Borgnat
Pierre Borgnat
Bluetooth sensors have recently been developed throughout the world for traffic information gathering. Primarily designed for travel time analysis, this article presents a method for vehicular trajectories retrieval. After a short description of some of the challenges at hand in using Bluetooth data in an urban network, a procedure to extract trip information from such data is proposed. It is further analyzed and illustrated at work on a real dataset collected in Brisbane. Last, this article shows that using spatially constrained shortest path analysis, this trip information, once extracted, can be used for the reconstruction of the trajectories. The performance of the process is assessed using both a simulated dataset and one from the real-world acquired in Brisbane, showing encouraging results, with up to 84% of accurately recovered trajectories.

24 August 2019 in Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability
Verified
Journal Article
Closed access
PDF file
GMGabriel Michau
Gabriel Michau
YHYang Hu
Yang Hu
TPThomas Palmé
Thomas Palmé
OFOlga Fink
Olga Fink
Complex industrial systems are continuously monitored by a large number of heterogeneous sensors. The diversity of their operating conditions and the possible fault types make it impossible to collect enough data for learning all the possible fault patterns. This article proposes an integrated automatic unsupervised feature learning and one-class classification for fault detection that uses data on healthy conditions only for its training. The approach is based on stacked extreme learning machines (namely hierarchical extreme learning machines) and comprises an autoencoder, performing unsupervised feature learning, stacked with a one-class classifier monitoring the distance of the test data to the training healthy class, thereby assessing the health of the system. This study provides a comprehensive evaluation of hierarchical extreme learning machines fault detection capability compared to other machine learning approaches, such as stand-alone one-class classifiers (extreme learning machines and support vector machines); these same one-class classifiers combined with traditional dimensionality reduction methods (principal component analysis) and a deep belief network. The performance is first evaluated on a synthetic dataset that encompasses typical characteristics of condition monitoring data. Subsequently, the approach is evaluated on a real case study of a power plant fault. The proposed algorithm for fault detection, combining feature learning with the one-class classifier, demonstrates a better performance, particularly in cases where condition monitoring data contain several non-informative signals.