Ashutosh Singh
singh.ashu@northeastern.edu
ashutosh-singh-8b034070
https://ashutosh17dec.github.io

College of Engineering
EXP 760
Boston
Huntington, Massachusetts

I am a Ph.D. student in the Cognitive Systems Lab at Northeastern University, where I am advised by Prof. Deniz Erdogmus. My research lies at the intersection of signal processing, control, and machine learning. I am fascinated by the ease with which humans process information and make decisions, and I aim to replicate this efficiency in machine learning models.

My work focuses on developing algorithms to recognize patterns in time series data, particularly in bio-signals, to understand complex system behaviors. I have a keen interest in studying human behavior through these patterns. Currently, I am engaged in key projects that involve designing machine learning models to discover emerging patterns in bio-signals, aiding our understanding of human behavior.

I collaborate closely with Prof. Lisa Feldman Barrett to analyze fMRI datasets, uncovering patterns that explain human behavior and emotions. Additionally, I work with Prof. Mathew Goodwin on developing predictive models for psychological states based on bio-signals collected from wearable devices.

I hold a Master of Science (M.Sc.) in Electrical and Computer Engineering (ECE) from Northeastern University (2021) and a Bachelor in Technology (B.Tech.) in Mechatronics with a minor in Robotics from Manipal Institute of Technology (2019). Beyond my primary research, I am passionate about robotics and autonomous vehicles.

In my leisure time, I enjoy engaging in conversations about geopolitics, the stock market, and chess. I also love reading manga and watching anime.

Publications

2025

Temporal Point Process Modeling of Aggressive Behavior Onset in Psychiatric Inpatient Youths with Autism

Under review NPJ

Michael Potter, Michael Everett, Ashutosh Singh, and 6 more authors

Nature Scientifc Reports, 2025

Abs HTML

Aggressive behavior, including aggression towards others and self-injury, occurs in up to 80% of children and adolescents with autism, making it a leading cause of behavioral health referrals and a major driver of healthcare costs. Predicting when autistic youth will exhibit aggression is challenging due to their communication difficulties. Many are minimally verbal or have poor emotional insight. Recent advances in Machine Learning and wearable biosensing enable short-term aggression predictions within a limited future window (typically one to three minutes). However, existing models do not estimate aggression probability within longer future windows nor the expected number of aggression onsets over such a period. To address these limitations, we employ Temporal Point Processes (TPPs) to model the generative process of aggressive behavior onsets in inpatient youths with autism. We hypothesize that aggressive behavior onsets follow a self-exciting process driven by short-term history, making them well-suited for Hawkes Point Process modeling. We establish a benchmark and demonstrate through Goodness-of-Fit statistics and predictive metrics that TPPs perform well modeling aggressive behavior onsets in inpatient youths with autism. Additionally, we gain insights into the onset generative process, like the branching factor near criticality, and suggest TPPs may enhance future clinical decision-making and preemptive interventions.
Exploring Theory-Laden Observations in the Brain Basis of Emotional Experience

Under review TBD

Christiana Westlin^*, Ashutosh Singh^*, Deniz Erdogmus, and 2 more authors

TBD, 2025

Abs HTML

In the science of emotion, it is widely assumed that folk emotion categories form a biological and psychological typology, and studies are routinely designed and analyzed to identify emotion-specific patterns. This approach shapes the observations that studies report, ultimately reinforcing the assumption that guided the investigation. Here, we reanalyzed data from one such typologically-guided study that reported mappings between individual brain patterns and group-averaged ratings of 34 emotion categories. Our reanalysis was guided by an alternative view of emotion categories as populations of variable, situated instances, and which predicts a priori that there will be significant variation in brain patterns within a category across instances. Correspondingly, our analysis made minimal assumptions about the structure of the variance present in the data. As predicted, we did not observe the original mappings and instead observed significant variation across individuals. These findings demonstrate how starting assumptions can ultimately impact scientific conclusions and suggest that a hypothesis must be supported using multiple analytic methods before it is taken seriously.

2024

Advancing post-traumatic seizure classification and biomarker identification: Information decomposition based multimodal fusion and explainable machine learning with missing neuroimaging data

Published CMIG

Md Navid Akbar, Sebastian F Ruf, Ashutosh Singh, and 8 more authors

Computerized Medical Imaging and Graphics, 2024

Abs HTML

A late post-traumatic seizure (LPTS), a consequence of traumatic brain injury (TBI), can potentially evolve into a lifelong condition known as post-traumatic epilepsy (PTE). Presently, the mechanism that triggers epileptogenesis in TBI patients remains elusive, inspiring the epilepsy community to devise ways to predict which TBI patients will develop PTE and to identify potential biomarkers. In response to this need, our study collected comprehensive, longitudinal multimodal data from 48 TBI patients across multiple participating institutions. A supervised binary classification task was created, contrasting data from LPTS patients with those without LPTS. To accommodate missing modalities in some subjects, we took a two-pronged approach. Firstly, we extended a graphical model-based Bayesian estimator to directly classify subjects with incomplete modality. Secondly, we explored conventional imputation techniques. The imputed multimodal information was then combined, following several fusion and dimensionality reduction techniques found in the literature, and subsequently fitted to a kernel- or a tree-based classifier. For this fusion, we proposed two new algorithms: recursive elimination of correlated components (RECC) that filters information based on the correlation between the already selected features, and information decomposition and selective fusion (IDSF), which effectively recombines information from decomposed multimodal features. Our cross-validation findings showed that the proposed IDSF algorithm delivers superior performance based on the area under the curve (AUC) score. Ultimately, after rigorous statistical comparisons and interpretable machine learning examination using Shapley values of the most frequently selected features, we recommend the two following magnetic resonance imaging (MRI) abnormalities as potential biomarkers: the left anterior limb of internal capsule in diffusion MRI (dMRI), and the right middle temporal gyrus in functional MRI (fMRI).
Learning Semilinear Neural Operators: A Unified Recursive Framework For Prediction And Data Assimilation

Published ICLR

Ashutosh Singh, Ricardo Augusto Borsoi, Deniz Erdogmus, and 1 more author

International Conference on Learning Representations, 2024

Abs PDF

Recent advances in the theory of Neural Operators (NOs) have enabled fast and accurate computation of the solutions to complex systems described by partial differential equations (PDEs). Despite their great success, current NO-based solutions face important challenges when dealing with spatio-temporal PDEs over long time scales. Specifically, the current theory of NOs does not present a systematic framework to perform data assimilation and efficiently correct the evolution of PDE solutions over time based on sparsely sampled noisy measurements. In this paper, we propose a learning-based state-space approach to compute the solution operators to infinite-dimensional semilinear PDEs. Exploiting the structure of semilinear PDEs and the theory of nonlinear observers in function spaces, we develop a flexible recursive method that allows for both prediction and data assimilation by combining prediction and correction operations. The proposed framework is capable of producing fast and accurate predictions over long time horizons, dealing with irregularly sampled noisy measurements to correct the solution, and benefits from the decoupling between the spatial and temporal dynamics of this class of PDEs. We show through experiments on the KuramotoSivashinsky, Navier-Stokes and Korteweg-de Vries equations that the proposed model is robust to noise and can leverage arbitrary amounts of measurements to correct its prediction over a long time horizon with little computational overhead.
A Variational Autoencoder-Based Method to Investigate Degeneracy in the Neural Correlates of Psychological Concepts

Published SANS

Kieran McVeigh, Ashutosh Singh, Deniz Erdogmus, and 2 more authors

Social & Affective Neuroscience Society, 2024

PDF

2023

Wearable biosensing to predict imminent aggressive behavior in psychiatric inpatient youths with autism

Published JAMA

Tales Imbiriba, Ahmet Demirkaya, Ashutosh Singh, and 2 more authors

JAMA network open, 2023

Abs HTML

IMPORTANCE Aggressive behavior is a prevalent and challenging issue in individuals with autism. OBJECTIVE To investigate whether changes in peripheral physiology recorded by a wearable biosensor and machine learning can be used to predict imminent aggressive behavior before it occurs in inpatient youths with autism. DESIGN, SETTING, AND PARTICIPANTS This noninterventional prognostic study used data collected from March 2019 to March 2020 from 4 primary care psychiatric inpatient hospitals. Enrolled participants were 86 psychiatric inpatients with confirmed diagnoses of autism exhibiting operationally defined self-injurious behavior, emotion dysregulation, or aggression toward others; 16 individuals were not included (18.6%) because they would not wear the biosensor (8 individuals) or were discharged before an observation could be made (8 individuals). Data were analyzed from March 2020 through October 2023. MAIN OUTCOMES AND MEASURES Research staff performed live behavioral coding of aggressive behavior while inpatient study participants wore a commercially available biosensor that recorded peripheral physiological signals (cardiovascular activity, electrodermal activity, and motion). Logistic regression, support vector machines, neural networks, and domain adaptation were used to analyze time-series features extracted from biosensor data. Area under the receiver operating characteristic curve (AUROC) values were used to evaluate the performance of population- and persondependent models.
Inv-senet: Invariant self expression network for clustering under biased data

Published ICASSP

Ashutosh Singh, Ashish Singh, Aria Masoomi, and 3 more authors

In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Abs HTML

Subspace clustering algorithms are used for understanding the cluster structure that explains the patterns prevalent in the dataset well. These methods are extensively used for data-exploration tasks in various areas of Natural Sciences. However, most of these methods fail to handle confounding attributes in the dataset. For datasets where a data sample represent multiple attributes, naively applying any clustering approach can result in undesired output. To this end, we propose a novel framework for jointly removing confounding attributes while learning to cluster data points in individual subspaces. Assuming we have label information about these confounding attributes, we regularize the clustering method by adversarially learning to minimize the mutual information between the data representation and the confounding attribute labels. Our experimental result on synthetic and real-world datasets demonstrate the effectiveness of our approach.

2022

Variation in brain correlates of emotional experience

Published SAS

Christiana Westlin^*, Ashutosh Singh^*, Dana H Brooks, and 2 more authors

In Society for Affective Science Annual Conference, 2022

Abs PDF

For the last several decades, emotion research has attempted to identify a "biomarker" or consistent pattern of brain activity to characterize a single category of emotion (e.g., fear) that will remain consistent across all instances of that category, regardless of individual and context. In this study, we investigated variation rather than consistency during emotional experiences while people watched video clips chosen to evoke instances of specific emotion categories. Specifically, we developed a sequential probabilistic approach to model the temporal dynamics in a participant’s brain activity during video viewing. We characterized brain states during these clips as distinct state occupancy periods between state transitions in blood oxygen level dependent (BOLD) signal patterns. We found substantial variation in the state occupancy probability distributions across individuals watching the same video, supporting the hypothesis that when it comes to the brain correlates of emotional experience, variation may indeed be the norm.

2021

Variation is the norm: Brain state dynamics evoked by emotional video clips

Published EMBC

Ashutosh Singh, Christiana Westlin, Hedwig Eisenbarth, and 7 more authors

In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021

Abs

For the last several decades, emotion research has attempted to identify a “biomarker” or consistent pattern of brain activity to characterize a single category of emotion (e.g., fear) that will remain consistent across all instances of that category, regardless of individual and context. In this study, we investigated variation rather than consistency during emotional experiences while people watched video clips chosen to evoke instances of specific emotion categories. Specifically, we developed a sequential probabilistic approach to model the temporal dynamics in a participant’s brain activity during video viewing. We characterized brain states during these clips as distinct state occupancy periods between state transitions in blood oxygen level dependent (BOLD) signal patterns. We found substantial variation in the state occupancy probability distributions across individuals watching the same video, supporting the hypothesis that when it comes to the brain correlates of emotional experience, variation may indeed be the norm.