Ahmet Demirkaya
demirkaya@ece.neu.edu
ahmet-demirkaya
0000-0002-5859-6375
ahmetdemirkayaee
https://www.linkedin.com/in/ahmet-demirkaya

College of Engineering
EXP 710
Boston
Huntington, Massachusetts

Ahmet Demirkaya is a Ph.D. candidate at Northeastern University’s Cognitive Systems Laboratory (CSL). He received his B.S. degree in Electrical and Electronics Engineering from Bilkent University in 2020 and his M.S. degree from the Electrical and Computer Engineering Department of Northeastern University in 2022. His research focuses on developing hybrid modeling frameworks that merge physics-based methods with neural networks to explore complex dynamic systems, particularly those with partially observed states. Additionally, he applies machine learning to time series data for forecasting applications, such as utilizing wearable biosensing technology to predict aggressive behavior in autistic youth.

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.
Learning Physics Informed Neural ODEs With Partial Measurements

Published AAAI

Paul Ghanem, Ahmet Demirkaya, Tales Imbiriba, and 3 more authors

The 39th Annual AAAI Conference on Artificial Intelligence, 2025

Abs HTML

Learning dynamics governing physical and spatiotemporal processes is a challenging problem, especially in scenarios where states are partially measured. In this work, we tackle the problem of learning dynamics governing these systems when parts of the system’s states are not measured, specifically when the dynamics generating the non-measured states are unknown. Inspired by state estimation theory and Physics Informed Neural ODEs, we present a sequential optimization framework in which dynamics governing unmeasured processes can be learned. We demonstrate the performance of the proposed approach leveraging numerical simulations and a real dataset extracted from an electro-mechanical positioning system. We show how the underlying equations fit into our formalism and demonstrate the improved performance of the proposed method when compared with baselines.

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.