Joseph Cohen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Joseph Cohen has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Xun Huan
University of Michigan
7 shared publications Jun Ni
Department of Mechanical Engineering, University of Michigan, Ann Arbor, USA
4 shared publications- Jun Ni
Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, 48109, USA
4 shared publications Raphael Zagury-Orly
Bezalel Academy of Arts and Design
3 shared publicationsXun Huan
Department of Mechanical Engineering University of Michigan Ann Arbor Michigan USA
3 shared publications- Baoyang Jiang
Technology Service Business Group, Foxconn Industrial Internet, Guangdong, Shenzhen, China
2 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 2 (2) , 025015
Uncertainty-aware virtual metrology for chemical concentration prediction in electroless plating
- 26 October 2026
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 2 (2) , 025015
Open AccessUncertainty-aware virtual metrology for chemical concentration prediction in electroless plating
- 17 October 2026
- Published by Springer Nature
- p. 1220-1236
Levinas, Emmanuel (1905/06–1995)
- Open Access
- 13 October 2026
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 2 (2) , 025014
SHAP to shop floor: towards trustworthy reduced-order anomaly detection for privacy-sensitive manufacturing environments
As artificial intelligence (AI) and machine learning (ML) techniques become increasingly ubiquitous for digital twins in manufacturing, it is essential to create reduced-order models that offer interpretable insights and are compatible with real-time production data. This paper introduces a novel framework for explainable AI integration in industrial anomaly detection scenarios, in which we create reduced-order models that simultaneously serve as auditors that effectively identify instances of shortcut learning in existing ML-based anomaly detection pipelines. We address two realistic constraints: privacy-encoded inputs and limited or unlabeled data. We validate our approach on two real-world case studies in manufacturing. The first examines anomaly detection for a high storage system, where we find that utilizing simple dimensionality reduction techniques offers resilience to randomized nonlinear transformations used for privacy encoding. The second case study focuses on deriving reduced-order explanations for multiple anomaly conditions in a high-dimensional pick-and-place process. We demonstrate the effectiveness of an approach that combines XGBoost for anomaly detection with TreeSHAP explanations, which enables the formation of interpretable anomaly clusters characterized by 1–2 term rules based on measurable input features. In a high-dimensional and privacy-encoded case study featuring over 130 time series and overlapping anomaly conditions, our methodology is able to describe 9 out of 14 discovered anomaly clusters with a precision of at least 0.80. Importantly, our findings align with real-world insights, showcasing the utility of the approach for auditing conventional ML models and knowledge discovery in manufacturing and anomaly detection systems.
- 13 October 2026
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 2 (2) , 025014
Open AccessSHAP to shop floor: towards trustworthy reduced-order anomaly detection for privacy-sensitive manufacturing environments
As artificial intelligence (AI) and machine learning (ML) techniques become increasingly ubiquitous for digital twins in manufacturing, it is essential to create reduced-order models that offer interpretable insights and are compatible with real-time production data. This paper introduces a novel framework for explainable AI integration in industrial anomaly detection scenarios, in which we create reduced-order models that simultaneously serve as auditors that effectively identify instances of shortcut learning in existing ML-based anomaly detection pipelines. We address two realistic constraints: privacy-encoded inputs and limited or unlabeled data. We validate our approach on two real-world case studies in manufacturing. The first examines anomaly detection for a high storage system, where we find that utilizing simple dimensionality reduction techniques offers resilience to randomized nonlinear transformations used for privacy encoding. The second case study focuses on deriving reduced-order explanations for multiple anomaly conditions in a high-dimensional pick-and-place process. We demonstrate the effectiveness of an approach that combines XGBoost for anomaly detection with TreeSHAP explanations, which enables the formation of interpretable anomaly clusters characterized by 1–2 term rules based on measurable input features. In a high-dimensional and privacy-encoded case study featuring over 130 time series and overlapping anomaly conditions, our methodology is able to describe 9 out of 14 discovered anomaly clusters with a precision of at least 0.80. Importantly, our findings align with real-world insights, showcasing the utility of the approach for auditing conventional ML models and knowledge discovery in manufacturing and anomaly detection systems.
- Open Access
- 31 March 2026
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 2 (2) , 022001
2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing
2026 roadmap on artificial intelligence and machine learning for smart manufacturing, Lee, Jay, Su, Hanqi, Macchi, Marco, Polenghi, Adalberto, Wu, Wei, Zhao, Zhiheng, Huang, George Q, Allgood, Kiva, Jain, Devendra, Gieger, Benedikt, Pandhare, Vibhor, Bhattacharjee, Soumyabrata, Mohril, Ram, Kong, Lingbao, Wang, Qiyuan, Tang, Xinlan, Kim, Sungjong, Park, Chan Hee, Youn, Byeng D, Goh, Guo Dong, Huang, Xi, Yeong, Wai Yee, Shin, Yung C, Zhang, He, Wang, Zitong, Tao, Fei, Srai, Jagjit Singh, Gupta, Satyandra K, Joung, Byung Gun, John, Albin, Sutherland, John W, Lee, Sang Won, Fink, Olga, Sharma, Vinay, Ahmed, Faez, Chen, Wei ‘Wayne’, Fuge, Mark, Waaler, Arild, Skjæveland, Martin G, Kyritsis, Dimitris, Chen, Wei, Karkaria, Vispi Nevile, Chen, Yi-Ping, Tsai, Ying-Kuan, Cohen, Joseph, Huan, Xun, Lin, Jing (Janet), Zhang, Liangwei, Vogl, Gregory W, Cornelius, Aaron W, Jia, Xiaodong, Ji, Dai-Yan, Minami, Takanobu, Wang, Ruoxin 2026 roadmap on artificial intelligence and machine learning for smart manufacturing, Lee, Jay, Su, Hanqi, Macchi, Marco, Polenghi, Adalberto, Wu, Wei, Zhao, Zhiheng, Huang, George Q, Allgood, Kiva, Jain, Devendra, Gieger, Benedikt, Pandhare, Vibhor, Bhattacharjee, Soumyabrata, Mohril, Ram, Kong, Lingbao, Wang, Qiyuan, Tang, Xinlan, Kim, Sungjong, Park, Chan Hee, Youn, Byeng D, Goh, Guo Dong, Huang, Xi, Yeong, Wai Yee, Shin, Yung C, Zhang, He, Wang, Zitong, Tao, Fei, Srai, Jagjit Singh, Gupta, Satyandra K, Joung, Byung Gun, John, Albin, Sutherland, John W, Lee, Sang Won, Fink, Olga, Sharma, Vinay, Ahmed, Faez, Chen, Wei ‘Wayne’, Fuge, Mark, Waaler, Arild, Skjæveland, Martin G, Kyritsis, Dimitris, Chen, Wei, Karkaria, Vispi Nevile, Chen, Yi-Ping, Tsai, Ying-Kuan, Cohen, Joseph, Huan, Xun, Lin, Jing (Janet), Zhang, Liangwei, Vogl, Gregory W, Cornelius, Aaron W, Jia, Xiaodong, Ji, Dai-Yan, Minami, Takanobu, Wang, Ruoxin
- 31 March 2026
- Published by IOP Publishing in Machine Learning: Engineering
- Vol. 2 (2) , 022001
Open Access2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing
2026 roadmap on artificial intelligence and machine learning for smart manufacturing, Lee, Jay, Su, Hanqi, Macchi, Marco, Polenghi, Adalberto, Wu, Wei, Zhao, Zhiheng, Huang, George Q, Allgood, Kiva, Jain, Devendra, Gieger, Benedikt, Pandhare, Vibhor, Bhattacharjee, Soumyabrata, Mohril, Ram, Kong, Lingbao, Wang, Qiyuan, Tang, Xinlan, Kim, Sungjong, Park, Chan Hee, Youn, Byeng D, Goh, Guo Dong, Huang, Xi, Yeong, Wai Yee, Shin, Yung C, Zhang, He, Wang, Zitong, Tao, Fei, Srai, Jagjit Singh, Gupta, Satyandra K, Joung, Byung Gun, John, Albin, Sutherland, John W, Lee, Sang Won, Fink, Olga, Sharma, Vinay, Ahmed, Faez, Chen, Wei ‘Wayne’, Fuge, Mark, Waaler, Arild, Skjæveland, Martin G, Kyritsis, Dimitris, Chen, Wei, Karkaria, Vispi Nevile, Chen, Yi-Ping, Tsai, Ying-Kuan, Cohen, Joseph, Huan, Xun, Lin, Jing (Janet), Zhang, Liangwei, Vogl, Gregory W, Cornelius, Aaron W, Jia, Xiaodong, Ji, Dai-Yan, Minami, Takanobu, Wang, Ruoxin 2026 roadmap on artificial intelligence and machine learning for smart manufacturing, Lee, Jay, Su, Hanqi, Macchi, Marco, Polenghi, Adalberto, Wu, Wei, Zhao, Zhiheng, Huang, George Q, Allgood, Kiva, Jain, Devendra, Gieger, Benedikt, Pandhare, Vibhor, Bhattacharjee, Soumyabrata, Mohril, Ram, Kong, Lingbao, Wang, Qiyuan, Tang, Xinlan, Kim, Sungjong, Park, Chan Hee, Youn, Byeng D, Goh, Guo Dong, Huang, Xi, Yeong, Wai Yee, Shin, Yung C, Zhang, He, Wang, Zitong, Tao, Fei, Srai, Jagjit Singh, Gupta, Satyandra K, Joung, Byung Gun, John, Albin, Sutherland, John W, Lee, Sang Won, Fink, Olga, Sharma, Vinay, Ahmed, Faez, Chen, Wei ‘Wayne’, Fuge, Mark, Waaler, Arild, Skjæveland, Martin G, Kyritsis, Dimitris, Chen, Wei, Karkaria, Vispi Nevile, Chen, Yi-Ping, Tsai, Ying-Kuan, Cohen, Joseph, Huan, Xun, Lin, Jing (Janet), Zhang, Liangwei, Vogl, Gregory W, Cornelius, Aaron W, Jia, Xiaodong, Ji, Dai-Yan, Minami, Takanobu, Wang, Ruoxin
- Open Access
- 3 September 2025
- Published by Wiley in Wind Energy
- Vol. 28 (10)
Inverted Transformers for Effective Post‐Calibration in Multisite Wind Power Forecasting
Accurate wind power forecasts are essential for energy management and resource allocation. However, because of complex weather dynamics and other nonlinearities, it is exceedingly difficult to forecast wind power on the multisite level for dozens of wind farms at once. This paper proposes a hybridized approach that leverages deep learning to predict future forecast errors from physics‐based numerical weather prediction (NWP) model estimates. Utilizing errors from NWP forecasts allows integration of critical atmospheric and meteorological dynamics into the forecasting model, and we demonstrate the importance of post‐calibration based on the physics versus pure data‐driven wind power prediction. This post‐calibration approach is enabled by the inverted transformer architecture, which efficiently and effectively learns meaningful wind farm variate representations, resulting in accurate spatiotemporal corrections to the forecasts. We also investigate modifying the iTransformer with a new embedding approach, named SpaceEmbed, that explicitly encodes spatial distance information into the network. The proposed approach is validated with a case study using real‐world data and forecasts from the Electric Reliability Council of Texas (ERCOT) in 2015 for 74 wind farms in Texas at different time scales. Using the high sustained limit as the metric for power generation, the iTransformer outperforms other state‐of‐the‐art deep learning forecasting methods, succeeding at the post‐calibration task by reducing NWP forecast error by up to 33% on average.
- 3 September 2025
- Published by Wiley in Wind Energy
- Vol. 28 (10)
Open AccessInverted Transformers for Effective Post‐Calibration in Multisite Wind Power Forecasting
Accurate wind power forecasts are essential for energy management and resource allocation. However, because of complex weather dynamics and other nonlinearities, it is exceedingly difficult to forecast wind power on the multisite level for dozens of wind farms at once. This paper proposes a hybridized approach that leverages deep learning to predict future forecast errors from physics‐based numerical weather prediction (NWP) model estimates. Utilizing errors from NWP forecasts allows integration of critical atmospheric and meteorological dynamics into the forecasting model, and we demonstrate the importance of post‐calibration based on the physics versus pure data‐driven wind power prediction. This post‐calibration approach is enabled by the inverted transformer architecture, which efficiently and effectively learns meaningful wind farm variate representations, resulting in accurate spatiotemporal corrections to the forecasts. We also investigate modifying the iTransformer with a new embedding approach, named SpaceEmbed, that explicitly encodes spatial distance information into the network. The proposed approach is validated with a case study using real‐world data and forecasts from the Electric Reliability Council of Texas (ERCOT) in 2015 for 74 wind farms in Texas at different time scales. Using the high sustained limit as the metric for power generation, the iTransformer outperforms other state‐of‐the‐art deep learning forecasting methods, succeeding at the post‐calibration task by reducing NWP forecast error by up to 33% on average.
- 29 July 2024
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (8) , 4071-4086
Shapley-based explainable AI for clustering applications in fault diagnosis and prognosis
- 29 July 2024
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (8) , 4071-4086
Shapley-based explainable AI for clustering applications in fault diagnosis and prognosis
- Open Access
- 5 January 2024
- Published by Frontiers Media SA in Frontiers in Mechanical Engineering
- Vol. 9, 1329146
Uncertainty-aware explainable AI as a foundational paradigm for digital twins
In the era of advanced manufacturing, digital twins have emerged as a foundational technology, offering the promise of improved efficiency, precision, and predictive capabilities. However, the increasing presence of AI tools for digital twin models and their integration into industrial processes has brought forth a pressing need for trustworthy and reliable systems. Uncertainty-Aware eXplainable Artificial Intelligence (UAXAI) is proposed as a critical paradigm to address these challenges, as it allows for the quantification and communication of uncertainties associated with predictive models and their corresponding explanations. As a platform and guiding philosophy to promote human-centered trust, UAXAI is based on five fundamental pillars: accessibility, reliability, explainability, robustness, and computational efficiency. The development of UAXAI caters to a diverse set of stakeholders, including end users, developers, regulatory bodies, the scientific community, and industrial players, each with their unique perspectives on trust and transparency in digital twins.
- 5 January 2024
- Published by Frontiers Media SA in Frontiers in Mechanical Engineering
- Vol. 9, 1329146
Open AccessUncertainty-aware explainable AI as a foundational paradigm for digital twins
In the era of advanced manufacturing, digital twins have emerged as a foundational technology, offering the promise of improved efficiency, precision, and predictive capabilities. However, the increasing presence of AI tools for digital twin models and their integration into industrial processes has brought forth a pressing need for trustworthy and reliable systems. Uncertainty-Aware eXplainable Artificial Intelligence (UAXAI) is proposed as a critical paradigm to address these challenges, as it allows for the quantification and communication of uncertainties associated with predictive models and their corresponding explanations. As a platform and guiding philosophy to promote human-centered trust, UAXAI is based on five fundamental pillars: accessibility, reliability, explainability, robustness, and computational efficiency. The development of UAXAI caters to a diverse set of stakeholders, including end users, developers, regulatory bodies, the scientific community, and industrial players, each with their unique perspectives on trust and transparency in digital twins.
- 28 October 2023
- Published by Elsevier in Journal of Manufacturing Systems
- Vol. 71, 609-619
Stochastic deep Koopman model for quality propagation analysis in multistage manufacturing systems
- 28 October 2023
- Published by Elsevier in Journal of Manufacturing Systems
- Vol. 71, 609-619
Stochastic deep Koopman model for quality propagation analysis in multistage manufacturing systems
- Open Access
- 4 September 2023
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 4 (1)
To Trust or Not: Towards Efficient Uncertainty Quantification for Stochastic Shapley Explanations
Recently, explainable AI (XAI) techniques have gained traction in the field of prognostics and health management (PHM) to enhance the credibility and trustworthiness of data-driven nonlinear models. Post-hoc model explanations have been popularized via algorithms such as SHapley Additive exPlanations (SHAP), but remain impractical for real-time prognostics applications due to the curse of dimensionality. As an alternative to deterministic approaches, stochastically sampled Shapley-based approximations have computational benefits for explaining model predictions. This paper will introduce and examine a new concept of explanation uncertainty through the lens of uncertainty quantification of stochastic Shapley attribution estimates. The proposed algorithm for estimating Shapley explanation uncertainty is efficiently applied for the 2021 PHM Data Challenge problem. The uncertainty in the derived explanation for a single prediction is also illustrated through personalized prediction recipe plots, improving post-hoc model visualization. Finally, important practical considerations for the implementation of Shapley-based XAI for industrial prognostics are provided.
- 4 September 2023
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 4 (1)
Open AccessTo Trust or Not: Towards Efficient Uncertainty Quantification for Stochastic Shapley Explanations
Recently, explainable AI (XAI) techniques have gained traction in the field of prognostics and health management (PHM) to enhance the credibility and trustworthiness of data-driven nonlinear models. Post-hoc model explanations have been popularized via algorithms such as SHapley Additive exPlanations (SHAP), but remain impractical for real-time prognostics applications due to the curse of dimensionality. As an alternative to deterministic approaches, stochastically sampled Shapley-based approximations have computational benefits for explaining model predictions. This paper will introduce and examine a new concept of explanation uncertainty through the lens of uncertainty quantification of stochastic Shapley attribution estimates. The proposed algorithm for estimating Shapley explanation uncertainty is efficiently applied for the 2021 PHM Data Challenge problem. The uncertainty in the derived explanation for a single prediction is also illustrated through personalized prediction recipe plots, improving post-hoc model visualization. Finally, important practical considerations for the implementation of Shapley-based XAI for industrial prognostics are provided.
- Open Access
Shapley-based Explainable AI for Clustering Applications in Fault Diagnosis and Prognosis
Data-driven artificial intelligence models require explainability in intelligent manufacturing to streamline adoption and trust in modern industry. However, recently developed explainable artificial intelligence (XAI) techniques that estimate feature contributions on a model-agnostic level such as SHapley Additive exPlanations (SHAP) have not yet been evaluated for semi-supervised fault diagnosis and prognosis problems characterized by class imbalance and weakly labeled datasets. This paper explores the potential of utilizing Shapley values for a new clustering framework compatible with semi-supervised learning problems, loosening the strict supervision requirement of current XAI techniques. This broad methodology is validated on two case studies: a heatmap image dataset obtained from a semiconductor manufacturing process featuring class imbalance, and a benchmark dataset utilized in the 2021 Prognostics and Health Management (PHM) Data Challenge. Semi-supervised clustering based on Shapley values significantly improves upon clustering quality compared to the fully unsupervised case, deriving information-dense and meaningful clusters that relate to underlying fault diagnosis model predictions. These clusters can also be characterized by high-precision decision rules in terms of original feature values, as demonstrated in the second case study. The rules, limited to 1-2 terms utilizing original feature scales, describe 12 out of the 16 derived equipment failure clusters with precision exceeding 0.85, showcasing the promising utility of the explainable clustering framework for intelligent manufacturing applications.
Open AccessShapley-based Explainable AI for Clustering Applications in Fault Diagnosis and Prognosis
Data-driven artificial intelligence models require explainability in intelligent manufacturing to streamline adoption and trust in modern industry. However, recently developed explainable artificial intelligence (XAI) techniques that estimate feature contributions on a model-agnostic level such as SHapley Additive exPlanations (SHAP) have not yet been evaluated for semi-supervised fault diagnosis and prognosis problems characterized by class imbalance and weakly labeled datasets. This paper explores the potential of utilizing Shapley values for a new clustering framework compatible with semi-supervised learning problems, loosening the strict supervision requirement of current XAI techniques. This broad methodology is validated on two case studies: a heatmap image dataset obtained from a semiconductor manufacturing process featuring class imbalance, and a benchmark dataset utilized in the 2021 Prognostics and Health Management (PHM) Data Challenge. Semi-supervised clustering based on Shapley values significantly improves upon clustering quality compared to the fully unsupervised case, deriving information-dense and meaningful clusters that relate to underlying fault diagnosis model predictions. These clusters can also be characterized by high-precision decision rules in terms of original feature values, as demonstrated in the second case study. The rules, limited to 1-2 terms utilizing original feature scales, describe 12 out of the 16 derived equipment failure clusters with precision exceeding 0.85, showcasing the promising utility of the explainable clustering framework for intelligent manufacturing applications.