Sep 2026· 2026 14th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)· pp. 1-6· 0 citations· 18 references
TL;DR
This study describes a submission to the AI4Pain 2026 Grand Challenge, which addresses three-class pain detection and localization using multimodal biological signals using multimodal biological signals, and suggests the potential usefulness of nonlinear physiological feature sequences for automated pain detection and localization.
Abstract
Automated pain assessment from biological signals presents significant challenges due to inter-subject variability, signal noise, and the complex relationship between autonomic responses and perceived pain. This study describes a submission to the AI4Pain 2026 Grand Challenge, which addresses three-class pain detection and localization using multimodal biological signals. The proposed approach extracts nonlinear descriptors from electrodermal activity, blood volume pulse, respiration, and oxygen saturation signals using overlapping temporal windows. Sample entropy, permutation entropy, detrended fluctuation analysis, Higuchi fractal dimension, and Poincare-based descriptors are organized as temporal feature sequences and classified using a compact bidirectional long short-term memory (BiLSTM) network. Two models were evaluated on the hidden test set, each achieving an accuracy of 59.03%, corresponding to 255 correctly classified samples out of 432. Although both models achieved identical accuracy, the second model obtained a Macro F1 score 4% higher than the first, indicating a more balanced performance across the three pain-related classes. These findings suggest the potential usefulness of nonlinear physiological feature sequences for automated pain detection and localization.
Automated pain recognition is a fundamental challenge for the advancement of clinical care and empathetic human-computer interaction, due to the subjective and dynamic nature of pain. In this study, we propose a deep learning framework for objective pain assessment based on multimodal physiological signals from the AI4...
Valentina Becchetti, Muhammad Umar Khan, Stefanos Gkikas et al.· 0 citations
This is the first study to perform subject independent multiclass classification of natural pain phenotypes with explicit handling of class imbalance by early fusion of MindWave EEG with Empatica E4 signals, representing a step toward generalizable and clinically useful digital biomarkers of pain.
Cuneyt Ozdemir· Journal of universal compute...· 0 citations
Abstract Cognitive load assessment using functional nearinfrared spectroscopy (fNIRS) has gained increasing attention due to its non-invasive and high spatial resolution nature. However, reliable classification remains challenging due to non-stationary and nonlinear nature of haemodynamic signals. Conventional time-fre...
B. Parthiban, Podakanti Satyajith Chary, N. Ganapathy· Current Directions in Biomed...· 0 citations
This review summarizes recent advances in EEG-based pain decoding, focusing on neural oscillatory mechanisms, signal processing strategies, and machine learning (ML) and deep learning (DL) approaches.
Guang-Hao Sun, Gui-Xing Lin, Yang Liao et al.· CAAI Artificial Intelligence...· 0 citations
Accurate classification of sleep stages is critical for diagnosing sleep disorders and monitoring neurological health. Traditional computerized sleep staging relies on spectral transformations, such as the Fast Fourier Transform (FFT) and Continuous Wavelet Transform (CWT), which frequently fail to capture the non-stat...
Rehanur Rahman Pranta, Khaled Akram Sany, Vabna Akter et al.· Journal of Artificial Intell...· 0 citations
Voice is a compelling, non-invasive biomarker for fatigue, yet much of the field's reported success rests on evaluation protocols that quietly permit information leakage and collapse once that leakage is removed. This paper reframes the question, asking not how high accuracy can be pushed but how much fatigue signal th...
Aya Alzatma, Zafer Cömert· 2026 11th International Conf...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.