Saurabh Hinduja
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saurabh Hinduja has a total of 102 co-authors. Here are the top co-authors by number of shared publications:
- Jeffrey F. Cohn
Department of Psychology and Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, USA and Deliberate AI, New York, NY, USA
5 shared publications - Shaun Canavan
University of South Florida
5 shared publications - Maneesh Bilalpur
University of Pittsburgh, Pittsburgh, Pennsylvania, USA
3 shared publications - Eric A. Storch
Baylor College of Medicine
2 shared publications - Itir Onal Ertugrul
Department of Information and Computing Sciences, Utrecht University, Utrecht, Netherlands
2 shared publications - Liza Jivnani
University of South Florida
2 shared publications
Latest Publications
- Open Access
- 5 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 337-346
Multimodal Depression Detection Varies with Cross-Dataset Differences
- 5 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 337-346
Open AccessMultimodal Depression Detection Varies with Cross-Dataset Differences
- Open Access
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1366-1370
Protocol-Aware Gradient Boosting for Context-Aware Student Engagement Detection
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1366-1370
Open AccessProtocol-Aware Gradient Boosting for Context-Aware Student Engagement Detection
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 137-146
EnsembleIQ-Pain: Intelligent Cluster Calibration for Personalized Pain Detection
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 137-146
Open AccessEnsembleIQ-Pain: Intelligent Cluster Calibration for Personalized Pain Detection
- Open Access
- 25 June 2025
- Published by The Royal Society in Royal Society Open Science
- Vol. 12 (6)
Big team science reveals promises and limitations of machine learning efforts to model physiological markers of affective experience
Researchers are increasingly using machine learning to study physiological markers of emotion. We evaluated the promises and limitations of this approach via a big team science competition. Twelve teams competed to predict self-reported affective experiences using a multi-modal set of peripheral nervous system measures. Models were trained and tested in multiple ways: with data divided by participants, targeted emotion, inductions, and time. In 100% of tests, teams outperformed baseline models that made random predictions. In 46% of tests, teams also outperformed baseline models that relied on the simple average of ratings from training datasets. More notably, results uncovered a methodological challenge: multiplicative constraints on generalizability. Inferences about the accuracy and theoretical implications of machine learning efforts depended not only on their architecture, but also how they were trained, tested, and evaluated. For example, some teams performed better when tested on observations from the same (vs. different) subjects seen during training. Such results could be interpreted as evidence against claims of universality. However, such conclusions would be premature because other teams exhibited the opposite pattern. Taken together, results illustrate how big team science can be leveraged to understand the promises and limitations of machine learning methods in affective science and beyond.
- 25 June 2025
- Published by The Royal Society in Royal Society Open Science
- Vol. 12 (6)
Open AccessBig team science reveals promises and limitations of machine learning efforts to model physiological markers of affective experience
Researchers are increasingly using machine learning to study physiological markers of emotion. We evaluated the promises and limitations of this approach via a big team science competition. Twelve teams competed to predict self-reported affective experiences using a multi-modal set of peripheral nervous system measures. Models were trained and tested in multiple ways: with data divided by participants, targeted emotion, inductions, and time. In 100% of tests, teams outperformed baseline models that made random predictions. In 46% of tests, teams also outperformed baseline models that relied on the simple average of ratings from training datasets. More notably, results uncovered a methodological challenge: multiplicative constraints on generalizability. Inferences about the accuracy and theoretical implications of machine learning efforts depended not only on their architecture, but also how they were trained, tested, and evaluated. For example, some teams performed better when tested on observations from the same (vs. different) subjects seen during training. Such results could be interpreted as evidence against claims of universality. However, such conclusions would be premature because other teams exhibited the opposite pattern. Taken together, results illustrate how big team science can be leveraged to understand the promises and limitations of machine learning methods in affective science and beyond.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 15 (4) , 2025-2041
Multimodal Prediction of Obsessive-Compulsive Disorder and Comorbid Depression Severity and Energy Delivered by Deep Brain Electrodes
To develop reliable, valid, and efficient measures of obsessive-compulsive disorder (OCD) severity, comorbid depression severity, and total electrical energy delivered (TEED) by deep brain stimulation (DBS), we trained and compared random forests regression models in a clinical trial of participants receiving DBS for refractory OCD. Six participants were recorded during open-ended interviews at pre- and post-surgery baselines and then at 3-month intervals following DBS activation. Ground-truth severity was assessed by clinical interview and self-report. Visual and auditory modalities included facial action units, head and facial landmarks, speech behavior and content, and voice acoustics. Mixed-effects random forest regression with Shapley feature reduction strongly predicted severity of OCD, comorbid depression, and total electrical energy delivered by the DBS electrodes (intraclass correlation, ICC, = 0.83, 0.87, and 0.81, respectively. When random effects were omitted from the regression, predictive power decreased to moderate for severity of OCD and comorbid depression and remained comparable for total electrical energy delivered (ICC = 0.60, 0.68, and 0.83, respectively). Multimodal measures of behavior outperformed ones from single modalities. Feature selection achieved large decreases in features and corresponding increases in prediction. The approach could contribute to closed-loop DBS that would automatically titrate DBS based on affect measures.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 15 (4) , 2025-2041
Multimodal Prediction of Obsessive-Compulsive Disorder and Comorbid Depression Severity and Energy Delivered by Deep Brain Electrodes
To develop reliable, valid, and efficient measures of obsessive-compulsive disorder (OCD) severity, comorbid depression severity, and total electrical energy delivered (TEED) by deep brain stimulation (DBS), we trained and compared random forests regression models in a clinical trial of participants receiving DBS for refractory OCD. Six participants were recorded during open-ended interviews at pre- and post-surgery baselines and then at 3-month intervals following DBS activation. Ground-truth severity was assessed by clinical interview and self-report. Visual and auditory modalities included facial action units, head and facial landmarks, speech behavior and content, and voice acoustics. Mixed-effects random forest regression with Shapley feature reduction strongly predicted severity of OCD, comorbid depression, and total electrical energy delivered by the DBS electrodes (intraclass correlation, ICC, = 0.83, 0.87, and 0.81, respectively. When random effects were omitted from the regression, predictive power decreased to moderate for severity of OCD and comorbid depression and remained comparable for total electrical energy delivered (ICC = 0.60, 0.68, and 0.83, respectively). Multimodal measures of behavior outperformed ones from single modalities. Feature selection achieved large decreases in features and corresponding increases in prediction. The approach could contribute to closed-loop DBS that would automatically titrate DBS based on affect measures.
- Open Access
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Multimodal prediction of obsessive-compulsive disorder, comorbid depression, and energy of deep brain stimulation
To develop reliable, valid, and efficient measures of obsessive-compulsive disorder (OCD) severity, comorbid depressionseverity, and total electrical energy delivered (TEED) by deep brain stimulation (DBS), we trained and compared random forestsregression models in a clinical trial of participants receiving DBS for refractory OCD. Six participants were recorded during open-endedinterviews at pre- and post-surgery baselines and then at 3-month intervals following DBS activation. Ground-truth severity wasassessed by clinical interview and self-report. Visual and auditory modalities included facial action units, head and facial landmarks,speech behavior and content, and voice acoustics. Mixed-effects random forest regression with Shapley feature reduction stronglypredicted severity of OCD, comorbid depression, and total electrical energy delivered by the DBS electrodes (intraclass correlation,ICC, = 0.83, 0.87, and 0.81, respectively. When random effects were omitted from the regression, predictive power decreased tomoderate for severity of OCD and comorbid depression and remained comparable for total electrical energy delivered (ICC = 0.60,0.68, and 0.83, respectively). Multimodal measures of behavior outperformed ones from single modalities. Feature selection achievedlarge decreases in features and corresponding increases in prediction. The approach could contribute to closed-loop DBS that wouldautomatically titrate DBS based on affect measures
- 29 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessMultimodal prediction of obsessive-compulsive disorder, comorbid depression, and energy of deep brain stimulation
To develop reliable, valid, and efficient measures of obsessive-compulsive disorder (OCD) severity, comorbid depressionseverity, and total electrical energy delivered (TEED) by deep brain stimulation (DBS), we trained and compared random forestsregression models in a clinical trial of participants receiving DBS for refractory OCD. Six participants were recorded during open-endedinterviews at pre- and post-surgery baselines and then at 3-month intervals following DBS activation. Ground-truth severity wasassessed by clinical interview and self-report. Visual and auditory modalities included facial action units, head and facial landmarks,speech behavior and content, and voice acoustics. Mixed-effects random forest regression with Shapley feature reduction stronglypredicted severity of OCD, comorbid depression, and total electrical energy delivered by the DBS electrodes (intraclass correlation,ICC, = 0.83, 0.87, and 0.81, respectively. When random effects were omitted from the regression, predictive power decreased tomoderate for severity of OCD and comorbid depression and remained comparable for total electrical energy delivered (ICC = 0.60,0.68, and 0.83, respectively). Multimodal measures of behavior outperformed ones from single modalities. Feature selection achievedlarge decreases in features and corresponding increases in prediction. The approach could contribute to closed-loop DBS that wouldautomatically titrate DBS based on affect measures
- Open Access
- 18 April 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 182, 111-117
Time to retire F1-binary score for action unit detection
- 18 April 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 182, 111-117
Open AccessTime to retire F1-binary score for action unit detection
- Open Access
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- Vol. 2023, 537-544
SHAP-based Prediction of Mother's History of Depression to Understand the Influence on Child Behavior
Depression strongly impacts parents’ behavior. Does parents’ depression strongly affect the behavior of their children as well? To investigate this question, we compared dyadic interactions between 73 depressed and 75 non-depressed mothers and their adolescent child. Families were of low income and 84% were white. Child behavior was measured from audio-video recordings using manual annotation of verbal and nonverbal behavior by expert coders and by multimodal computational measures of facial expression, face and head dynamics, prosody, speech behavior, and linguistics. For both sets of measures, we used Support Vector Machines. For computational measures, we investigated the relative contribution of single versus multiple modalities using a novel approach to SHapley Additive exPlanations (SHAP). Computational measures outperformed manual ratings by human experts. Among individual computational measures, prosody was the most informative. SHAP reduction resulted in a four-fold decrease in the number of features and highest performance (77% accuracy; positive and negative agreements at 75% and 76%, respectively). These findings suggest that maternal depression strongly impacts the behavior of adolescent children; differences are most revealed in prosody; multimodal features together with SHAP reduction are most powerful.
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- Vol. 2023, 537-544
Open AccessSHAP-based Prediction of Mother's History of Depression to Understand the Influence on Child Behavior
Depression strongly impacts parents’ behavior. Does parents’ depression strongly affect the behavior of their children as well? To investigate this question, we compared dyadic interactions between 73 depressed and 75 non-depressed mothers and their adolescent child. Families were of low income and 84% were white. Child behavior was measured from audio-video recordings using manual annotation of verbal and nonverbal behavior by expert coders and by multimodal computational measures of facial expression, face and head dynamics, prosody, speech behavior, and linguistics. For both sets of measures, we used Support Vector Machines. For computational measures, we investigated the relative contribution of single versus multiple modalities using a novel approach to SHapley Additive exPlanations (SHAP). Computational measures outperformed manual ratings by human experts. Among individual computational measures, prosody was the most informative. SHAP reduction resulted in a four-fold decrease in the number of features and highest performance (77% accuracy; positive and negative agreements at 75% and 76%, respectively). These findings suggest that maternal depression strongly impacts the behavior of adolescent children; differences are most revealed in prosody; multimodal features together with SHAP reduction are most powerful.
- Open Access
- 8 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Multimodal Temporal Modeling of Emotion using Physiological Signals
Modeling of human emotion is a challenging problem that can require multiple signals types, as well as contextual information that has been obtained over time. Considering this, in this paper we present our approach, based on physiological signals, to the Emotion Physiology and Experience Collaboration (EPIC) challenge at Affective Computing & Intelligent Interaction (ACII), 2023. In total there are four scenarios that we model: 1) across time; 2) across subjects; 3) across elicitor; and 4) across version. To tackle this challenge, we propose to use a physiological fusion-based approach to solve each scenario. Along with this, we give a detailed analysis of the evaluated physiological signals and personalized predictions for each subject are shown. Our proposed approach shows encouraging results with the lowest root mean square error achieved for scenario 4 (across version) for both valence and arousal on the challenge test set.
- 8 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessMultimodal Temporal Modeling of Emotion using Physiological Signals
Modeling of human emotion is a challenging problem that can require multiple signals types, as well as contextual information that has been obtained over time. Considering this, in this paper we present our approach, based on physiological signals, to the Emotion Physiology and Experience Collaboration (EPIC) challenge at Affective Computing & Intelligent Interaction (ACII), 2023. In total there are four scenarios that we model: 1) across time; 2) across subjects; 3) across elicitor; and 4) across version. To tackle this challenge, we propose to use a physiological fusion-based approach to solve each scenario. Along with this, we give a detailed analysis of the evaluated physiological signals and personalized predictions for each subject are shown. Our proposed approach shows encouraging results with the lowest root mean square error achieved for scenario 4 (across version) for both valence and arousal on the challenge test set.
- Open Access
- 15 February 2023
- Published by Elsevier in Brain Stimulation
- Vol. 16 (1) , 174
Identification of candidate neural biomarkers of obsessive-compulsive symptom intensity and response to deep brain stimulation
- 15 February 2023
- Published by Elsevier in Brain Stimulation
- Vol. 16 (1) , 174
Open AccessIdentification of candidate neural biomarkers of obsessive-compulsive symptom intensity and response to deep brain stimulation