Intention-use gaps and displacement of valued activities predict social media regret more strongly than duration, with pre-session context generalizing across users and physiological signals adding person-specific predictive power.
hub
Introducing wesad, a multimodal dataset for wearable stress and affect detection
12 Pith papers cite this work, alongside 1,170 external citations. Polarity classification is still indexing.
12
Pith papers citing it
1,170
external citations · external index
hub tools
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 2polarities
background 2representative citing papers
MuteBench evaluates multimodal fusion robustness to modality missing and within-modality missing on 125000 samples from 9 clinical datasets, finding architecture family predicts tolerance better than parameter count.
This survey provides the first comprehensive overview of deep multimodal learning methods designed to remain robust when some input modalities are absent.
Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.
A unified inference-time augmentation framework with 13 methods and Bayesian-optimized parameters improves AUROC up to 8.5% and reduces false positives in PPG-based AF detection across five datasets.
DEM distills XGBoost into a residual decision tree with a new fidelity metric for interpretable anomaly detection in WBAN data, reporting AUC 0.9964 and 0.9047 with 0.17ms inference.
Wearable accelerometry, EDA, and temperature data from 9 students with profound autism, processed with fine-tuned foundation models, enables prediction of challenging behavior episodes up to 10 minutes in advance at AUC-ROC 0.78 in actual classroom sessions.
DSTAN-Med uses separate sensor-wise and time-wise attention plus a zero-parameter physiological filter to detect falsified vital signs, reporting 7.4-8.3 percentage point sensitivity gains over Transformer baselines on three public datasets.
Dywave uses wavelet hierarchical decomposition to create event-aligned compact token sequences for heterogeneous IoT signals, yielding up to 12% accuracy gains and 75% shorter inputs on mainstream sequence models across five datasets.
WARM-VR provides a new public dataset of wristband and ECG signals from 31 people in VR stress-relaxation experiences with olfactory cues, plus baseline ML classification results for valence and arousal.
On WESAD respiratory data under leave-one-subject-out validation, raw 1D-CNNs reach 96.72% accuracy for stress-vs-rest while grouped respiratory signatures yield higher MCC for baseline (65.34%), amusement (35.69%), and meditation (88.65%).
A review synthesizes evidence from EEG, EMG, ECG, PPG and ocular signals to argue that waveform morphology, rather than modality or model class, primarily determines TSC performance and interpretability.
citing papers explorer
-
Before You Scroll Again: Predicting Regretful Social Media Sessions from In-the-Wild Contextual and Wearable Sensing
Intention-use gaps and displacement of valued activities predict social media regret more strongly than duration, with pre-session context generalizing across users and physiological signals adding person-specific predictive power.
-
MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion
MuteBench evaluates multimodal fusion robustness to modality missing and within-modality missing on 125000 samples from 9 clinical datasets, finding architecture family predicts tolerance better than parameter count.
-
Deep Multimodal Learning with Missing Modality: A Survey
This survey provides the first comprehensive overview of deep multimodal learning methods designed to remain robust when some input modalities are absent.
-
Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection
Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.
-
A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection
A unified inference-time augmentation framework with 13 methods and Bayesian-optimized parameters improves AUROC up to 8.5% and reduces false positives in PPG-based AF detection across five datasets.
-
DEM: A Distilled Explanation Model for Interpretable Anomaly Detection in Physiological Sensor Networks
DEM distills XGBoost into a residual decision tree with a new fidelity metric for interpretable anomaly detection in WBAN data, reporting AUC 0.9964 and 0.9047 with 0.17ms inference.
-
Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensors
Wearable accelerometry, EDA, and temperature data from 9 students with profound autism, processed with fine-tuned foundation models, enables prediction of challenging behavior episodes up to 10 minutes in advance at AUC-ROC 0.78 in actual classroom sessions.
-
DSTAN-Med: Dual-Channel Spatiotemporal Attention with Physiological Plausibility Filtering for False Data Injection Attack Detection in IoT-Based Medical Devices
DSTAN-Med uses separate sensor-wise and time-wise attention plus a zero-parameter physiological filter to detect falsified vital signs, reporting 7.4-8.3 percentage point sensitivity gains over Transformer baselines on three public datasets.
-
Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals
Dywave uses wavelet hierarchical decomposition to create event-aligned compact token sequences for heterogeneous IoT signals, yielding up to 12% accuracy gains and 75% shorter inputs on mainstream sequence models across five datasets.
-
Introducing WARM-VR: Benchmark Dataset for Multimodal Wearable Affect Recognition in Virtual Reality
WARM-VR provides a new public dataset of wristband and ECG signals from 31 people in VR stress-relaxation experiences with olfactory cues, plus baseline ML classification results for valence and arousal.
-
State-Specific Respiratory Signatures for Affective and Stress Recognition: Interpretable Respiratory Markers, Autocorrelation Lags, and Compact CNN Models
On WESAD respiratory data under leave-one-subject-out validation, raw 1D-CNNs reach 96.72% accuracy for stress-vs-rest while grouped respiratory signatures yield higher MCC for baseline (65.34%), amusement (35.69%), and meditation (88.65%).
-
Modality vs. Morphology: A Framework for Time Series Classification for Biological Signals
A review synthesizes evidence from EEG, EMG, ECG, PPG and ocular signals to argue that waveform morphology, rather than modality or model class, primarily determines TSC performance and interpretability.