State-Specific Respiratory Signatures for Affective and Stress Recognition: Interpretable Respiratory Markers, Autocorrelation Lags, and Compact CNN Models

• URL: http://arxiv.org/abs/2606.26723v1
• Date: Thu, 25 Jun 2026 08:01:36 GMT
• Title: State-Specific Respiratory Signatures for Affective and Stress Recognition: Interpretable Respiratory Markers, Autocorrelation Lags, and Compact CNN Models
• Abstract summary: Respiratory activity is a direct and interpretable physiological channel for wearable stress and affective-state recognition.<n>This work reframes RESP-based recognition as a joint predictive and explanatory problem.<n>We analyze 60 s windows under leave-one-subject-out validation and combine two complementary branches: compact raw-signal 1D-CNNs and handcrafted respiratory signatures.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Respiratory activity is a direct and interpretable physiological channel for wearable stress and affective-state recognition, yet many studies emphasize classification accuracy without identifying which respiratory properties separate different states. This work reframes RESP-based recognition as a joint predictive and explanatory problem. Using the chest respiratory channel of the WESAD dataset, we analyze 60 s windows under leave-one-subject-out validation and combine two complementary branches: compact raw-signal one-dimensional convolutional neural networks (1D-CNNs) and physically grouped handcrafted respiratory signatures. The primary application task is binary stress versus non-stress detection, while baseline, stress, amusement, and meditation are additionally analyzed in a one-vs-rest setting to reveal state-specific respiratory markers. The feature space is organized into respiratory timing, breath-to-breath variability, waveform statistics, spectral/time-frequency descriptors, and autocorrelation/nonlinear predictability descriptors, with the raw 60 s signal treated as a sixth representation for the CNN branch. We introduce autocorrelation transition lags (Zpm/Zmp) as interpretable markers of respiratory correlation scale and separately evaluate exploratory FEG-Pro/Lyapunov-like descriptors. In the final CNN refit setting, the raw-signal model achieved the strongest stress-vs-rest performance, with accuracy 96.72 percent, macro-F1 95.30 percent, and MCC 90.61 percent. In contrast, compact feature models were stronger for baseline, with MCC 65.34 percent, amusement, with MCC 35.69 percent, and especially meditation, with MCC 88.65 percent. These results show that CNNs are most useful for the practical stress detector, whereas interpretable respiratory signatures provide stronger and more physiologically transparent state-specific markers for several non-stress conditions.

Related papers

• Spectral Features Dominate BCG Respiratory-Event Detection: A Large-Scale Patient-Independent Comparison of Feature Groups in Sleep Apnea Patients [33.60217549899358]
  Ballistocardiographic (BCG) sensing is a promising modality for long-term sleep-apnea monitoring.<n>It remains unclear which signal features are most discriminative for respiratory-event detection.<n>We present a literature-guided, patient-independent comparison of ten BCG feature groups.
  arXiv  Detail & Related papers  (2026-08-28T11:56:12Z)
• AeroSpectra Sentinel: An Auditable LLM Prompt-Chaining Decision-Support Workflow for Acute Asthma Risk Assessment from Respiratory Sounds and Clinical Signals [0.0]
  This paper presents AeroSpectra Sentinel, a client-side research prototype and decision-support workflow.<n>It combines short-time Fourier transform (STFT) respiratory sound analysis, lightweight machine-learning screening, clinical feature fusion, and a five-stage large language model (LLM) prompt-chaining process.<n>It is intended as a research prototype, not as a diagnostic medical device or clinically validated risk-assessment product.
  arXiv  Detail & Related papers  (2026-06-06T16:11:45Z)
• Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion Models [42.11515368961642]
  Diffusion-based generative models offer a promising strategy for data synthesis.<n>We propose a controllable latent diffusion model that synthesizes pulmonary nodules within full 3D CT volumes.<n>Our framework achieves strong visual realism, validated through both quantitative metrics and a visual Turing test.
  arXiv  Detail & Related papers  (2026-05-28T22:32:06Z)
• Time-Localized Parametric Decomposition of Respiratory Airflow for Sub-Breath Analysis [0.0]
  This study introduces a parametric framework for decomposing inspiratory airflow into time-localized components.<n> Evaluation across 8,276 breaths demonstrates high reconstruction accuracy.
  arXiv  Detail & Related papers  (2026-04-24T16:28:45Z)
• Atrial Fibrillation Detection Using Machine Learning [3.5522386235856582]
  Atrial fibrillation (AF) is a common cardiac arrhythmia and a major risk factor for ischemic stroke.<n>We present a 10-fold machine learning framework for AF detection from simultaneous photoplethysmogram (ECG) and ECG signals.
  arXiv  Detail & Related papers  (2026-02-20T07:30:08Z)
• Combining Facial Videos and Biosignals for Stress Estimation During Driving [4.551432404727517]
  Stress is commonly detected using physiological signals such as perinasal perspiration and heart rate.<n>We propose a multimodal stress estimation framework that combines facial videos and physiological signals.<n>Although evaluated on driving data, the proposed framework and protocol may generalize to other stress estimation settings.
  arXiv  Detail & Related papers  (2026-01-07T20:32:34Z)
• Self-similarity Prior Distillation for Unsupervised Remote Physiological Measurement [39.0083078989343]
  We propose a Self-Similarity Prior Distillation (SSPD) framework for unsupervised r estimation. SSPD capitalizes on the intrinsic self-similarity of cardiac activities. It achieves comparable or even superior performance compared to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2023-11-09T02:24:51Z)
• Deep-seeded Clustering for Emotion Recognition from Wearable Physiological Sensors [1.380698851850167]
  We propose and test a deep-seeded clustering algorithm that automatically extracts and classifies features from physiological signals with minimal supervision.<n>We show that the model obtains good performance results across three different datasets frequently used in affective computing studies.
  arXiv  Detail & Related papers  (2023-08-17T14:37:35Z)
• Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation [67.19443246236048]
  Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases. Some small-sized airway branches (e.g., bronchus and terminaloles) significantly aggravate the difficulty of automatic segmentation. This paper presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network and a comprehensive loss function.
  arXiv  Detail & Related papers  (2022-09-05T16:38:13Z)
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification [74.84221280249876]
  An efficient analysis of large amounts of chest radiographs can aid physicians and radiologists. We propose a novel Discrete Wavelet Transform (DWT)-based method for the efficient identification and encoding of visual information.
  arXiv  Detail & Related papers  (2022-05-08T15:29:54Z)
• Identification of deep breath while moving forward based on multiple body regions and graph signal analysis [45.62293065676075]
  This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera. In validation experiments, the proposed approach outperforms the comparative methods with the accuracy, precision, recall and F1 of 75.5%, 76.2%, 75.0% and 75.2%, respectively.
  arXiv  Detail & Related papers  (2020-10-20T08:26:50Z)
• Video-based Remote Physiological Measurement via Cross-verified Feature Disentangling [121.50704279659253]
  We propose a cross-verified feature disentangling strategy to disentangle the physiological features with non-physiological representations. We then use the distilled physiological features for robust multi-task physiological measurements. The disentangled features are finally used for the joint prediction of multiple physiological signals like average HR values and r signals.
  arXiv  Detail & Related papers  (2020-07-16T09:39:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.