Papers

Field

Top tools here

Open problems in Electrocardiogram ecg

Subject-independent generalization in wearable ECG/IMU systems1 paper raises it · 1 addresses it
Real-world deployment requires consistent performance across unseen individuals, but current models often fail under leave-one-subject-out evaluation.
- Towards Field-Deployable Wearable IMU Systems for Occupational Activity Recognitionraises · addresses
Motion artifact robustness in wrist PPG heart rate estimation1 paper raises it · 1 addresses it
Wrist PPG signals are corrupted by motion, leading to unreliable heart rate estimates in real-world conditions.
- An Agent Architecture with Tools and Memory for Selective Correction of Wrist PPG Heart Rate Estimatesraises · addresses
Nonstationarity and cross-subject distribution shifts in EEG-based BCIs1 paper raises it · 1 addresses it
EEG signals vary over time and across subjects, degrading model performance in practical deployments.
- Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibrationraises · addresses
High-fidelity EEG-guided target speaker extraction in noisy environments1 paper raises it · 1 addresses it
Time-frequency masking approaches for EEG-guided TSE struggle with spectro-temporal overlaps and narrowband audio.
- NeuroCodec: EEG-Guided Latent-Domain Generative Model for High-Fidelity Target Speaker Extractionraises · addresses
Lack of paired radar heart sound and echocardiographic datasets1 paper raises it · 1 addresses it
Public datasets linking non-contact cardiac signals to structural heart disease phenotypes are scarce, limiting research.
- Clinical radar heart sounds with echocardiographic phenotypes of ventricular dysfunction and valvular diseaseraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

eeg foundation models · electroencephalography eeg · eeg foundation model124 papers15 this week
electrocardiogram ecg · electrocardiogram · ecgs126 papers12 this week
spiking neural networks · networks spiking neural · spiking neural network48 papers6 this week

Topics in this field

Active contributors · 90 days

Chenyu LiuDEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models5
Muhammad ShafiqueThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification5
Cuntai GuanDo Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling4
Constantino Álvarez CasadoLearning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition4
Le NguyenLearning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition4
Manuel Lage CañellasLearning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition4

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.CVOct 20
Multiscale Temporal-Spectral-Spatial EEG Learning With Modality-Specific and Modality-Invariant Representations for Emotion Recognition
Jian Zhang, Manrong Liu, Yilei Huang, Wenhua Liu, Xiaohui Yang +1
Multimodal physiological signals provide complementary cues for emotion recognition. They also raise two related challenges. Emotion-related EEG patterns vary across time, frequency bands, electrodes, and brain regions. Different physiological modalities also contain both modality-specific and shared affective information. This paper presents GMSI-Net, an EEG-centered multimodal emotion recognition framework. It has three key components. The temporal-spatial-spectral-region (TSSR) encoder models multiscale temporal-channel patterns, differential entropy features, and local-to-global brain-region relations. The modality-specific representation (MSR) branch uses bidirectional cross-modal attention and learnable gates. It controls information transfer while retaining modality-specific cues. The modality-invariant representation (MIR) branch learns a shared affective representation. An adaptively weighted contrastive loss aligns this representation across modalities. Independent multiscale Conv-Transformer encoders process the peripheral physiological signals. GMSI-Net is evaluated on DEAP and MAHNOB-HCI using within-subject random ten-fold cross-validation. The model reaches 96.21…
PDF arXiv
arXiv cs.LGOct 19
SleepPairNet: Learning Multimodal Pediatric Sleep Representations with Random-Pair Cross-Attention
Saurav Raj Pandey, Harlin Lee
Analyzing physiological sleep signals is important for assessing sleep quality and detecting sleep-related disorders. Learning inter-modal relationships across physiological signals can provide richer representations for downstream sleep analysis. We introduce SleepPairNet, a multimodal self-supervised learning (SSL) framework that learns pairwise interactions between physiological signals through cross-attention. We propose a random modality-pair selection strategy that exposes the model to diverse signal pairs during pretraining, enabling flexibility across modality combinations at test time. Pretrained on the NCH dataset, SleepPairNet outperforms the evaluated SSL baselines on all respiratory tasks while remaining competitive on EEG-related tasks, and shows even stronger results when transferred to the external CHAT dataset.
PDF arXiv
arXiv cs.LGOct 19
Global Time-Aware Conditioning (GTC): A Mechanism for Time-Aware Pediatric Sleep Representation Learning
Saurav Raj Pandey, Harlin Lee
Sleep physiology evolves throughout the night, with changes in sleep cycles, respiratory stability, and cardiovascular dynamics. However, self-supervised learning (SSL) methods for sleep typically process short, fixed-duration windows without explicitly modeling where each window occurs within the full sleep session. We introduce Global Time-Aware Conditioning (GTC), a mechanism that complements local positional encodings by conditioning latent representations on the global time-of-sleep of each input window. We integrate GTC into three representative SSL frameworks and evaluate them on five clinically relevant tasks with extreme class imbalance across two independent pediatric cohorts. GTC generally improves F1 and AUPRC across architectures and tasks, with gains persisting under cross-cohort transfer, highlighting the value of global temporal context for sleep representation learning.
PDF arXiv
arXiv cs.AIOct 19
Physiology-Aware Graph Attention for Early Ventricular Reentry Prediction
Ma{ë}lis Morier, Jairo Rodr{í}guez Padilla, Patrick Gallinari, Maxime Sermesant
Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains difficult to predict from infarct imaging alone. While in silico induction studies can reveal these mechanisms, exploring many substrates and pacing locations remains computationally expensive. We propose a graph attention classifier for early prediction of sustained ventricular reentry from simulated cardiac electrophysiology. Each simulation is represented as a graph with early nodal voltage samples and edge attributes encoding geometry, stimulation frequency, tissue labels, amplitude, and diastolic interval. These descriptors are computed only from the first two paced activations, before sustained reentry is observed. On a balanced independent test set of 1000 simulations, the classifier achieves 94.6% accuracy, 95.4% sensitivity, 93.8% specificity, 94.6% F1-score, 0.987 ROC-AUC, and 0.985 PR-AUC. Ablation experiments show that diastolic interval is the most critical descriptor. Qualitative attention inspection suggests that different heads focus on border-zone, stimulation location, and early propagation path.…
PDF arXiv
arXiv cs.LGOct 19
Logit Averaging During Training Sets a New State of the Art for Non-Invasive Speech BCI
Miran Özdogan, Gereon Elvers, Michael Bronstein, Oiwi Parker Jones
Non-invasive brain-computer interfaces are in practice limited by signal-to-noise ratio, and recent state-of-the-art methods address this limitation by aggregating over repeated trials of the same stimulus. Yet multi-trial aggregation has been treated inconsistently across the literature: some work averages brain signals at the model's input, other work averages predictions at the model's output, and neither treats aggregation as an architectural choice in its own right. We provide the first systematic comparison of aggregation strategies for non-invasive neural decoding, evaluating six paradigms (including logit averaging during training and three attention-based variants we introduce) across three datasets, four tasks, and two group sizes. We find that aggregation choice matters substantially: training-time logit averaging, the simplest method we propose, outperforms all others in 6 of 7 settings. On the phoneme classification setting of the 2025 PNPL competition, it sets a new state of the art, significantly outperforming the competition winner by 17.4 absolute percentage points in balanced accuracy. We further draw a theoretical connection between logit averaging and joint…
PDF arXiv
arXiv cs.CVOct 19
Context-Aware Topological Distillation Graph Network for Asymmetric EEG-Eye Movement Emotion Recognition
Peijun Shi, Xiujin Zhu, Zhenguo Lao, Chee-Onn Chow, Wei Ru Wong +2
EEG-eye movement emotion recognition can support mental-health monitoring and adaptive interfaces, but most fusion models treat the two signals as parallel features, classify each window alone and degrade when eye data are lost. We propose the Context-Aware Topological Distillation Graph Network (CTD-GNet), in which EEG features form the nodes of an electrode graph, and eye movements and preceding windows modulate its edges, nodes and readout, the edges through electrode-specific prompts. Bidirectional distillation of the graph, node relations and predictions couples this multimodal teacher with a single-window EEG student, improving the teacher and aligning the two graphs 35-fold. In leave-one-subject-out tests on SEED and SEED-IV against 17 baselines, CTD-GNet has the highest mean accuracy, 84.91% and 76.17%, significantly above 9 and 6 of 13 eye-based baselines after Holm correction, the smallest cross-subject spread among multimodal models and the highest worst-subject accuracy. It is the most accurate model at every rate of missing eye data on SEED-IV, keeps 66.1% on SEED without eye data, more than any EEG-only model, and stays 9.3 and 11.9 points above all single-window…
PDF arXiv

Papers

Topics in this field

eeg foundation models · electroencephalography eeg · eeg foundation model124 papers15 this week
electrocardiogram ecg · electrocardiogram · ecgs126 papers12 this week
spiking neural networks · networks spiking neural · spiking neural network48 papers6 this week

Recent papers

All papers in Research

arXiv cs.CVOct 20
Multiscale Temporal-Spectral-Spatial EEG Learning With Modality-Specific and Modality-Invariant Representations for Emotion Recognition
Jian Zhang, Manrong Liu, Yilei Huang, Wenhua Liu, Xiaohui Yang +1
Multimodal physiological signals provide complementary cues for emotion recognition. They also raise two related challenges. Emotion-related EEG patterns vary across time, frequency bands, electrodes, and brain regions. Different physiological modalities also contain both modality-specific and shared affective information. This paper presents GMSI-Net, an EEG-centered multimodal emotion recognition framework. It has three key components. The temporal-spatial-spectral-region (TSSR) encoder models multiscale temporal-channel patterns, differential entropy features, and local-to-global brain-region relations. The modality-specific representation (MSR) branch uses bidirectional cross-modal attention and learnable gates. It controls information transfer while retaining modality-specific cues. The modality-invariant representation (MIR) branch learns a shared affective representation. An adaptively weighted contrastive loss aligns this representation across modalities. Independent multiscale Conv-Transformer encoders process the peripheral physiological signals. GMSI-Net is evaluated on DEAP and MAHNOB-HCI using within-subject random ten-fold cross-validation. The model reaches 96.21…
PDF arXiv
arXiv cs.LGOct 19
SleepPairNet: Learning Multimodal Pediatric Sleep Representations with Random-Pair Cross-Attention
Saurav Raj Pandey, Harlin Lee
Analyzing physiological sleep signals is important for assessing sleep quality and detecting sleep-related disorders. Learning inter-modal relationships across physiological signals can provide richer representations for downstream sleep analysis. We introduce SleepPairNet, a multimodal self-supervised learning (SSL) framework that learns pairwise interactions between physiological signals through cross-attention. We propose a random modality-pair selection strategy that exposes the model to diverse signal pairs during pretraining, enabling flexibility across modality combinations at test time. Pretrained on the NCH dataset, SleepPairNet outperforms the evaluated SSL baselines on all respiratory tasks while remaining competitive on EEG-related tasks, and shows even stronger results when transferred to the external CHAT dataset.
PDF arXiv
arXiv cs.LGOct 19
Global Time-Aware Conditioning (GTC): A Mechanism for Time-Aware Pediatric Sleep Representation Learning
Saurav Raj Pandey, Harlin Lee
Sleep physiology evolves throughout the night, with changes in sleep cycles, respiratory stability, and cardiovascular dynamics. However, self-supervised learning (SSL) methods for sleep typically process short, fixed-duration windows without explicitly modeling where each window occurs within the full sleep session. We introduce Global Time-Aware Conditioning (GTC), a mechanism that complements local positional encodings by conditioning latent representations on the global time-of-sleep of each input window. We integrate GTC into three representative SSL frameworks and evaluate them on five clinically relevant tasks with extreme class imbalance across two independent pediatric cohorts. GTC generally improves F1 and AUPRC across architectures and tasks, with gains persisting under cross-cohort transfer, highlighting the value of global temporal context for sleep representation learning.
PDF arXiv
arXiv cs.AIOct 19
Physiology-Aware Graph Attention for Early Ventricular Reentry Prediction
Ma{ë}lis Morier, Jairo Rodr{í}guez Padilla, Patrick Gallinari, Maxime Sermesant
Sudden cardiac death mostly originates from post-infarct ventricular tachycardia. This reentry is sustained by propagation around scar tissue, but its risk remains difficult to predict from infarct imaging alone. While in silico induction studies can reveal these mechanisms, exploring many substrates and pacing locations remains computationally expensive. We propose a graph attention classifier for early prediction of sustained ventricular reentry from simulated cardiac electrophysiology. Each simulation is represented as a graph with early nodal voltage samples and edge attributes encoding geometry, stimulation frequency, tissue labels, amplitude, and diastolic interval. These descriptors are computed only from the first two paced activations, before sustained reentry is observed. On a balanced independent test set of 1000 simulations, the classifier achieves 94.6% accuracy, 95.4% sensitivity, 93.8% specificity, 94.6% F1-score, 0.987 ROC-AUC, and 0.985 PR-AUC. Ablation experiments show that diastolic interval is the most critical descriptor. Qualitative attention inspection suggests that different heads focus on border-zone, stimulation location, and early propagation path.…
PDF arXiv
arXiv cs.LGOct 19
Logit Averaging During Training Sets a New State of the Art for Non-Invasive Speech BCI
Miran Özdogan, Gereon Elvers, Michael Bronstein, Oiwi Parker Jones
Non-invasive brain-computer interfaces are in practice limited by signal-to-noise ratio, and recent state-of-the-art methods address this limitation by aggregating over repeated trials of the same stimulus. Yet multi-trial aggregation has been treated inconsistently across the literature: some work averages brain signals at the model's input, other work averages predictions at the model's output, and neither treats aggregation as an architectural choice in its own right. We provide the first systematic comparison of aggregation strategies for non-invasive neural decoding, evaluating six paradigms (including logit averaging during training and three attention-based variants we introduce) across three datasets, four tasks, and two group sizes. We find that aggregation choice matters substantially: training-time logit averaging, the simplest method we propose, outperforms all others in 6 of 7 settings. On the phoneme classification setting of the 2025 PNPL competition, it sets a new state of the art, significantly outperforming the competition winner by 17.4 absolute percentage points in balanced accuracy. We further draw a theoretical connection between logit averaging and joint…
PDF arXiv
arXiv cs.CVOct 19
Context-Aware Topological Distillation Graph Network for Asymmetric EEG-Eye Movement Emotion Recognition
Peijun Shi, Xiujin Zhu, Zhenguo Lao, Chee-Onn Chow, Wei Ru Wong +2
EEG-eye movement emotion recognition can support mental-health monitoring and adaptive interfaces, but most fusion models treat the two signals as parallel features, classify each window alone and degrade when eye data are lost. We propose the Context-Aware Topological Distillation Graph Network (CTD-GNet), in which EEG features form the nodes of an electrode graph, and eye movements and preceding windows modulate its edges, nodes and readout, the edges through electrode-specific prompts. Bidirectional distillation of the graph, node relations and predictions couples this multimodal teacher with a single-window EEG student, improving the teacher and aligning the two graphs 35-fold. In leave-one-subject-out tests on SEED and SEED-IV against 17 baselines, CTD-GNet has the highest mean accuracy, 84.91% and 76.17%, significantly above 9 and 6 of 13 eye-based baselines after Holm correction, the smallest cross-subject spread among multimodal models and the highest worst-subject accuracy. It is the most accurate model at every rate of missing eye data on SEED-IV, keeps 66.1% on SEED without eye data, more than any EEG-only model, and stays 9.3 and 11.9 points above all single-window…
PDF arXiv

Active contributors · 90 days

Chenyu LiuDEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models5
Muhammad ShafiqueThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification5
Cuntai GuanDo Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling4
Constantino Álvarez CasadoLearning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition4
Le NguyenLearning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition4
Manuel Lage CañellasLearning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition4

Activity · 12 weeks

Fields · AI · updated 1h ago

Electrocardiogram ecg

Found by the topic model: electrocardiogram ecg, eeg foundation models, spiking neural networks.

33papers this week−21.4% vs last week

All papers · 298 With code · 0

Newest Most relevant

235 papers this month

Open problems in Electrocardiogram ecg

Subject-independent generalization in wearable ECG/IMU systems1 paper raises it · 1 addresses it
Real-world deployment requires consistent performance across unseen individuals, but current models often fail under leave-one-subject-out evaluation.
- Towards Field-Deployable Wearable IMU Systems for Occupational Activity Recognitionraises · addresses
Motion artifact robustness in wrist PPG heart rate estimation1 paper raises it · 1 addresses it
Wrist PPG signals are corrupted by motion, leading to unreliable heart rate estimates in real-world conditions.
- An Agent Architecture with Tools and Memory for Selective Correction of Wrist PPG Heart Rate Estimatesraises · addresses
Nonstationarity and cross-subject distribution shifts in EEG-based BCIs1 paper raises it · 1 addresses it
EEG signals vary over time and across subjects, degrading model performance in practical deployments.
- Memory-Augmented Online Test-Time Adaptation for EEG Motor Imagery via Perturbation Consistency and Confidence Calibrationraises · addresses
High-fidelity EEG-guided target speaker extraction in noisy environments1 paper raises it · 1 addresses it
Time-frequency masking approaches for EEG-guided TSE struggle with spectro-temporal overlaps and narrowband audio.
- NeuroCodec: EEG-Guided Latent-Domain Generative Model for High-Fidelity Target Speaker Extractionraises · addresses
Lack of paired radar heart sound and echocardiographic datasets1 paper raises it · 1 addresses it
Public datasets linking non-contact cardiac signals to structural heart disease phenotypes are scarce, limiting research.
- Clinical radar heart sounds with echocardiographic phenotypes of ventricular dysfunction and valvular diseaseraises · addresses

Named by an AI from these papers' abstracts.