JCJoseph Cohen

Joseph Cohen

*This is an algorithmically generated author record based on publicly available information.

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:


Latest Publications

  • Open Access

    SHAP to shop floor: towards trustworthy reduced-order anomaly detection for privacy-sensitive manufacturing environments

    by Joseph Cohen, Xun Huan

    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

    2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing

    by Jay Lee, Hanqi Su, Marco Macchi, Adalberto Polenghi, Wei Wu, Zhiheng Zhao, George Q Huang, Kiva Allgood, Devendra Jain, Benedikt Gieger, et al.

    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

    Inverted Transformers for Effective Post‐Calibration in Multisite Wind Power Forecasting

    by Joseph Cohen, Tianyi Xu, Youngchan Jang, Pengwei Du, Eunshin Byon, Xun Huan

    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.


  • Open Access

    Uncertainty-aware explainable AI as a foundational paradigm for digital twins

    by Joseph Cohen, Xun Huan

    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.


  • Stochastic deep Koopman model for quality propagation analysis in multistage manufacturing systems

    by Zhiyi Chen, Harshal Maske, Huanyi Shui, Devesh Upadhyay, Michael Hopka, Joseph Cohen, Xingjian Lai, Xun Huan, Jun Ni


  • Open Access

    To Trust or Not: Towards Efficient Uncertainty Quantification for Stochastic Shapley Explanations

    by Joseph Cohen, Eunshin Byon, Xun Huan

    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

    by Joseph Cohen, Xun Huan, Jun Ni

    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.