Weng-Keen Wong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Weng-Keen Wong has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Bechir Hamdaoui
Oregon State University
2 shared publications - Matthew Olson
Lawrence Livermore National Laboratory, 7000 East Ave, Livermore, California, 94550-5507, UNITED STATES
2 shared publications Abdulsalam M. Alhawsawi
1 shared publication- Abdurrahman Elmaghbub
Oregon State University, Corvallis, OR, USA
1 shared publication Akira Tokuhiro
1 shared publication- Alan Fern
School of Electrical Engineering & Computer Science Oregon State University 97331 Corvallis OR USA
1 shared publication
Latest Publications
- 25 January 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Space Physics
- Vol. 131 (1)
Ionospheric Anomaly Detection and Source Geolocation Over Open Ocean With GNSS Remote Sensing
Ionospheric disturbances caused by acoustic waves (AW) are observed by Global Navigation Satellite Systems (GNSS) measures of total electron content (TEC). AWs that propagate to the ionosphere can be caused by ground‐based explosions, including seismic events. These events often occur in remote regions like the open ocean. Identifying an AW and locating the source of the AW from GNSS TEC measurements is challenging due to several variables between events such as propagation metrics, line of sight geometry, and ionization levels. This becomes especially difficult with a sparse network and limited signal coverage, typical of remote regions. We propose here the use of a deep learning, ionospheric anomaly detection algorithm and a geolocation algorithm capable of identifying atypical ionospheric behavior after a seismic event and estimating the source location. We outline the development of this algorithm and test results over the months of May and June 2023 for five GNSS receivers in the South Pacific. Results show the successful detection of two open ocean M7.7 and M7.1 earthquakes. Three TEC measurements detected as anomalous from the M7.7 earthquake event were used to estimate the epicenter of the earthquake, resulting in a source geolocation of S, E, a discrepancy of in latitude and in longitude, . This research demonstrates the feasibility of AW detection and source geolocation from a sparse GNSS network over open ocean.
- 25 January 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Space Physics
- Vol. 131 (1)
Ionospheric Anomaly Detection and Source Geolocation Over Open Ocean With GNSS Remote Sensing
Ionospheric disturbances caused by acoustic waves (AW) are observed by Global Navigation Satellite Systems (GNSS) measures of total electron content (TEC). AWs that propagate to the ionosphere can be caused by ground‐based explosions, including seismic events. These events often occur in remote regions like the open ocean. Identifying an AW and locating the source of the AW from GNSS TEC measurements is challenging due to several variables between events such as propagation metrics, line of sight geometry, and ionization levels. This becomes especially difficult with a sparse network and limited signal coverage, typical of remote regions. We propose here the use of a deep learning, ionospheric anomaly detection algorithm and a geolocation algorithm capable of identifying atypical ionospheric behavior after a seismic event and estimating the source location. We outline the development of this algorithm and test results over the months of May and June 2023 for five GNSS receivers in the South Pacific. Results show the successful detection of two open ocean M7.7 and M7.1 earthquakes. Three TEC measurements detected as anomalous from the M7.7 earthquake event were used to estimate the epicenter of the earthquake, resulting in a source geolocation of S, E, a discrepancy of in latitude and in longitude, . This research demonstrates the feasibility of AW detection and source geolocation from a sparse GNSS network over open ocean.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Machine Learning in Communications and Networking
- Vol. 4, 1527-1549
Extracting Bluetooth Fingerprints From Hardware Impairments Through Unsupervised Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Machine Learning in Communications and Networking
- Vol. 4, 1527-1549
Open AccessExtracting Bluetooth Fingerprints From Hardware Impairments Through Unsupervised Learning
- Open Access
- 20 May 2024
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 5 (2) , 025054
Transformer-powered surrogates close the ICF simulation-experiment gap with extremely limited data
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize better to new data and problems. This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios, where sparse experimental data is supplemented with simulation data. The proposed approach integrates transformer-based architecture with a novel graph-based hyper-parameter optimization technique. The resulting system not only effectively reduces simulation bias, but also achieves superior prediction accuracy compared to the prior method. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available, as well as synthetic versions of these experiments.
- 20 May 2024
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 5 (2) , 025054
Open AccessTransformer-powered surrogates close the ICF simulation-experiment gap with extremely limited data
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize better to new data and problems. This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios, where sparse experimental data is supplemented with simulation data. The proposed approach integrates transformer-based architecture with a novel graph-based hyper-parameter optimization technique. The resulting system not only effectively reduces simulation bias, but also achieves superior prediction accuracy compared to the prior method. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available, as well as synthetic versions of these experiments.
- Open Access
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 86801-86823
Deep Learning Model Portability for Domain-Agnostic Device Fingerprinting
RF (Radio Frequency) device fingerprinting approaches using deep learning have recently emerged as potential methods of identifying devices solely based on their RF transmissions. However, these recently proposed approaches suffer from the domain portability problem, in that when the deep learning models used for fingerprinting are trained on data collected on one (source) domain but tested on data collected on a different (target) domain, the models will not perform well. For example of a change in the receiver used for data collection, in the day on which data was captured, or in the configuration settings of transmitters amounts to a change in the domain. This work proposes a technique that uses metric learning and model calibration to enable a model trained with data from one source domain to perform well on data collected on another target domain. This is accomplished with only a small amount of training data from the target domain and without changing the weights of the model, which makes the technique computationally quick. The effectiveness of the proposed technique is assessed using RF data captured using a testbed of real devices and under various different setup scenarios. Our results show that the proposed technique is viable and useful for networks with limited computational resources and applications with time-critical missions.
- 14 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 86801-86823
Open AccessDeep Learning Model Portability for Domain-Agnostic Device Fingerprinting
RF (Radio Frequency) device fingerprinting approaches using deep learning have recently emerged as potential methods of identifying devices solely based on their RF transmissions. However, these recently proposed approaches suffer from the domain portability problem, in that when the deep learning models used for fingerprinting are trained on data collected on one (source) domain but tested on data collected on a different (target) domain, the models will not perform well. For example of a change in the receiver used for data collection, in the day on which data was captured, or in the configuration settings of transmitters amounts to a change in the domain. This work proposes a technique that uses metric learning and model calibration to enable a model trained with data from one source domain to perform well on data collected on another target domain. This is accomplished with only a small amount of training data from the target domain and without changing the weights of the model, which makes the technique computationally quick. The effectiveness of the proposed technique is assessed using RF data captured using a testbed of real devices and under various different setup scenarios. Our results show that the proposed technique is viable and useful for networks with limited computational resources and applications with time-critical missions.
- 1 June 2021
- Published by Elsevier in Artificial Intelligence
- Vol. 295
Counterfactual state explanations for reinforcement learning agents via generative deep learning
- 1 June 2021
- Published by Elsevier in Artificial Intelligence
- Vol. 295
Counterfactual state explanations for reinforcement learning agents via generative deep learning
- Open Access
- 1 February 2021
- Published by Elsevier in Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
- Vol. 988
Isotope identification using deep learning: An explanation
- 1 February 2021
- Published by Elsevier in Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
- Vol. 988
Open AccessIsotope identification using deep learning: An explanation
- Open Access
- 22 June 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 14 (4) , 1-32
Discovering Anomalies by Incorporating Feedback from an Expert
Unsupervised anomaly detection algorithms search for outliers and then predict that these outliers are the anomalies. When deployed, however, these algorithms are often criticized for high false-positive and high false-negative rates. One main cause of poor performance is that not all outliers are anomalies and not all anomalies are outliers. In this article, we describe the Active Anomaly Discovery (AAD) algorithm, which incorporates feedback from an expert user that labels a queried data instance as an anomaly or nominal point. This feedback is intended to adjust the anomaly detector so that the outliers it discovers are more in tune with the expert user’s semantic understanding of the anomalies. The AAD algorithm is based on a weighted ensemble of anomaly detectors. When it receives a label from the user, it adjusts the weights on each individual ensemble member such that the anomalies rank higher in terms of their anomaly score than the outliers. The AAD approach is designed to operate in an interactive data exploration loop. In each iteration of this loop, our algorithm first selects a data instance to present to the expert as a potential anomaly and then the expert labels the instance as an anomaly or as a nominal data point. When it receives the instance label, the algorithm updates its internal model and the loop continues until a budget of B queries is spent. The goal of our approach is to maximize the total number of true anomalies in the B instances presented to the expert. We show that the AAD method performs well and in some cases doubles the number of true anomalies found compared to previous methods. In addition we present approximations that make the AAD algorithm much more computationally efficient while maintaining a desirable level of performance.
- 22 June 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 14 (4) , 1-32
Open AccessDiscovering Anomalies by Incorporating Feedback from an Expert
Unsupervised anomaly detection algorithms search for outliers and then predict that these outliers are the anomalies. When deployed, however, these algorithms are often criticized for high false-positive and high false-negative rates. One main cause of poor performance is that not all outliers are anomalies and not all anomalies are outliers. In this article, we describe the Active Anomaly Discovery (AAD) algorithm, which incorporates feedback from an expert user that labels a queried data instance as an anomaly or nominal point. This feedback is intended to adjust the anomaly detector so that the outliers it discovers are more in tune with the expert user’s semantic understanding of the anomalies. The AAD algorithm is based on a weighted ensemble of anomaly detectors. When it receives a label from the user, it adjusts the weights on each individual ensemble member such that the anomalies rank higher in terms of their anomaly score than the outliers. The AAD approach is designed to operate in an interactive data exploration loop. In each iteration of this loop, our algorithm first selects a data instance to present to the expert as a potential anomaly and then the expert labels the instance as an anomaly or as a nominal data point. When it receives the instance label, the algorithm updates its internal model and the loop continues until a budget of B queries is spent. The goal of our approach is to maximize the total number of true anomalies in the B instances presented to the expert. We show that the AAD method performs well and in some cases doubles the number of true anomalies found compared to previous methods. In addition we present approximations that make the AAD algorithm much more computationally efficient while maintaining a desirable level of performance.
- Open Access
Sequential Feature Explanations for Anomaly Detection
In many applications, an anomaly detection system presents the most anomalous data instance to a human analyst, who then must determine whether the instance is truly of interest (e.g. a threat in a security setting). Unfortunately, most anomaly detectors provide no explanation about why an instance was considered anomalous, leaving the analyst with no guidance about where to begin the investigation. To address this issue, we study the problems of computing and evaluating sequential feature explanations (SFEs) for anomaly detectors. An SFE of an anomaly is a sequence of features, which are presented to the analyst one at a time (in order) until the information contained in the highlighted features is enough for the analyst to make a confident judgement about the anomaly. Since analyst effort is related to the amount of information that they consider in an investigation, an explanation's quality is related to the number of features that must be revealed to attain confidence. One of our main contributions is to present a novel framework for large scale quantitative evaluations of SFEs, where the quality measure is based on analyst effort. To do this we construct anomaly detection benchmarks from real data sets along with artificial experts that can be simulated for evaluation. Our second contribution is to evaluate several novel explanation approaches within the framework and on traditional anomaly detection benchmarks, offering several insights into the approaches.
Open AccessSequential Feature Explanations for Anomaly Detection
In many applications, an anomaly detection system presents the most anomalous data instance to a human analyst, who then must determine whether the instance is truly of interest (e.g. a threat in a security setting). Unfortunately, most anomaly detectors provide no explanation about why an instance was considered anomalous, leaving the analyst with no guidance about where to begin the investigation. To address this issue, we study the problems of computing and evaluating sequential feature explanations (SFEs) for anomaly detectors. An SFE of an anomaly is a sequence of features, which are presented to the analyst one at a time (in order) until the information contained in the highlighted features is enough for the analyst to make a confident judgement about the anomaly. Since analyst effort is related to the amount of information that they consider in an investigation, an explanation's quality is related to the number of features that must be revealed to attain confidence. One of our main contributions is to present a novel framework for large scale quantitative evaluations of SFEs, where the quality measure is based on analyst effort. To do this we construct anomaly detection benchmarks from real data sets along with artificial experts that can be simulated for evaluation. Our second contribution is to evaluate several novel explanation approaches within the framework and on traditional anomaly detection benchmarks, offering several insights into the approaches.
- 23 April 2010
- Published by Springer Nature in Machine Learning
- Vol. 79 (3) , 257-259
Machine learning algorithms for event detection
- 23 April 2010
- Published by Springer Nature in Machine Learning
- Vol. 79 (3) , 257-259
Machine learning algorithms for event detection
- Open Access
- 24 February 2009
- Published by Springer Nature in BMC Bioinformatics
- Vol. 10 (1) , 69
QSRA – a quality-value guided de novo short read assembler
New rapid high-throughput sequencing technologies have sparked the creation of a new class of assembler. Since all high-throughput sequencing platforms incorporate errors in their output, short-read assemblers must be designed to account for this error while utilizing all available data.
- 24 February 2009
- Published by Springer Nature in BMC Bioinformatics
- Vol. 10 (1) , 69
Open AccessQSRA – a quality-value guided de novo short read assembler
New rapid high-throughput sequencing technologies have sparked the creation of a new class of assembler. Since all high-throughput sequencing platforms incorporate errors in their output, short-read assemblers must be designed to account for this error while utilizing all available data.