XGBoost (Gupta)
16.69↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · Glucose MAE (mg/dL)
subject-disjointuses extra training data
Results explorer
One row per reported result from wearable PPG, ECG, motion and sleep papers. Filter by task, dataset, metric, sensor and year, or show only SOTA rows. Each value links to its source: a paper table or figure, or the leaderboard row it came from.
Last updated
433
reported results
224
with a table or figure reference
92
papers and models
134
task × dataset × metric pairs
38
benchmarks with a SOTA star
433 results
VGG16-1s
17↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · Glucose MAE (mg/dL)
subject-disjointuses extra training data
CNN-LSTM-Att-1s
17.1↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · Glucose MAE (mg/dL)
subject-disjointuses extra training data
1D-CNN (Alghlayini)
18.21↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · Glucose MAE (mg/dL)
subject-disjointuses extra training data
ResNet34-1s
19.7↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · Glucose RMSE (mg/dL)
subject-disjointuses extra training data
VGG16-1s
21↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · Glucose RMSE (mg/dL)
subject-disjointuses extra training data
CNN-LSTM-Att-1s
24.4↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · Glucose RMSE (mg/dL)
subject-disjointuses extra training data
PLS (Islam)
10.67↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
MFCC + XGBoost (Prabha)
11.69↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
ResNet34-1s
12.8↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
CNN-LSTM-Att-1s
13↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
Mean baseline
14.13↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
XGBoost (Gupta)
14.46↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
ResNet34 (Zeynali)
14.99↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
VGG16-1s
15↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
1D-CNN (Alghlayini)
16.56↓
Glucose estimation · PPG Signals for Blood Glucose Measurement (Kermani / Mendeley) · MARD (%)
subject-disjointuses extra training data
ResNet34 (Zeynali)
55.62↑
Glucose estimation · VitalDB · Clarke error grid zone A (%)
subject-disjoint
MFCC + XGBoost (Prabha)
55.1↑
Glucose estimation · VitalDB · Clarke error grid zone A (%)
subject-disjoint
1D-CNN (Alghlayini)
54.19↑
Glucose estimation · VitalDB · Clarke error grid zone A (%)
subject-disjoint
XGBoost (Gupta)
53.88↑
Glucose estimation · VitalDB · Clarke error grid zone A (%)
subject-disjoint
PLS (Islam)
53.19↑
Glucose estimation · VitalDB · Clarke error grid zone A (%)
subject-disjoint
Mean baseline
52.27↑
Glucose estimation · VitalDB · Clarke error grid zone A (%)
subject-disjoint
MFCC + XGBoost (Prabha)
25.42↓
Glucose estimation · VitalDB · Glucose MAE (mg/dL)
subject-disjoint
XGBoost (Gupta)
25.77↓
Glucose estimation · VitalDB · Glucose MAE (mg/dL)
subject-disjoint
ResNet34 (Zeynali)
25.93↓
Glucose estimation · VitalDB · Glucose MAE (mg/dL)
subject-disjoint
1D-CNN (Alghlayini)
26.05↓
Glucose estimation · VitalDB · Glucose MAE (mg/dL)
subject-disjoint
PLS (Islam)
26.14↓
Glucose estimation · VitalDB · Glucose MAE (mg/dL)
subject-disjoint
Mean baseline
26.39↓
Glucose estimation · VitalDB · Glucose MAE (mg/dL)
subject-disjoint
MFCC + XGBoost (Prabha)
21.56↓
Glucose estimation · VitalDB · MARD (%)
subject-disjoint
1D-CNN (Alghlayini)
21.8↓
Glucose estimation · VitalDB · MARD (%)
subject-disjoint
XGBoost (Gupta)
21.96↓
Glucose estimation · VitalDB · MARD (%)
subject-disjoint
PLS (Islam)
22.28↓
Glucose estimation · VitalDB · MARD (%)
subject-disjoint
Mean baseline
22.52↓
Glucose estimation · VitalDB · MARD (%)
subject-disjoint
ResNet34 (Zeynali)
22.55↓
Glucose estimation · VitalDB · MARD (%)
subject-disjoint
PPG SA-CLIP (subject-aware, ECG-guided)
In PPG Heart Age via ECG-Guided Cross-Modal Pretraining (arXiv:2608.01620)
5.895↓
Heart age · PWV cohort (external) · MAE (years)
trained on the internal VHS cohort, tested on an external cohortexternal cohortPPG-only model after ECG–PPG contrastive pretraining
TF-IG
Interaction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate Estimation
1.227↓
Heart rate estimation · BIDMC PPG and Respiration (Pimentel 2016 / PhysioNet) · Mean absolute HR error (BPM)
subject-disjoint
Leaderboard row
2026
Bilateral-PPG → single-wrist KD student
Learning from Bilateral PPG via Cross-Site Attention and Knowledge Distillation
2.79↓
Heart rate estimation · bilateral-sports-30 · Mean absolute HR error (BPM)
Protocol not structured
Leaderboard row
2026
7.86↓
Heart rate estimation · Brno University of Technology Smartphone PPG Database (BUT PPG) · Mean absolute HR error (BPM)
uses extra training data
Leaderboard row
2026
Heart rate estimation · EarSet · Mean absolute HR error (BPM)
uses extra training data
Leaderboard row
10.22↓
Heart rate estimation · Gyro-Acc-PPG (BAMI-I, Wonkwang) · Mean absolute HR error (BPM)
uses extra training data
Leaderboard row
2026
Heart rate estimation · IEEE Signal Processing Cup 2015 (TROIKA) · Mean absolute HR error (BPM)
subject-disjointuses extra training data
Leaderboard row
2025
2.09↓
Heart rate estimation · IEEE Signal Processing Cup 2015 (TROIKA) · Mean absolute HR error (BPM)
subject-disjointuses extra training data
Leaderboard row
2026
Heart rate estimation · PPG-BP Database (Guilin / Liang 2018) · Mean absolute HR error (BPM)
subject-disjointuses extra training data
Leaderboard row
Heart rate estimation · PPG-DaLiA · exact_match
subject-disjoint
Leaderboard row
Heart rate estimation · PPG-DaLiA · Mean absolute HR error (BPM)
uses extra training data
Leaderboard row
Heart rate estimation · PPG-DaLiA · Mean absolute HR error (BPM)
subject-disjoint
Leaderboard row
Structured Trajectory Supervision for Reliable P
Structured Trajectory Supervision for Reliable Physiological Time-Series Regression (PPI-Net)
4.04↓
Heart rate estimation · PPG-DaLiA · Mean absolute HR error (BPM)
subject-disjoint
Leaderboard row
2026
Heart rate estimation · PPG-DaLiA · Mean absolute HR error (BPM)
subject-disjointuses extra training data
Leaderboard row
2025
4.96↓
Heart rate estimation · PPG-DaLiA · Mean absolute HR error (BPM)
subject-disjointuses extra training data
Leaderboard row
2026
Heart rate estimation · PPG-DaLiA · Mean absolute HR error (BPM)
subject-disjointuses extra training data
Leaderboard row
2026
Showing 151–200 of 433 results
Recent changes
New entry: A cross-subject stress recognition method…, 0.9158
Stress detection (acute / prolonged / affect): WESAD: accuracy
New entry: PC-AVCT wearable-state model, 7.697
From the hub's dated sync history: new results as they are added, and SOTA stars as they are awarded or move.
How SOTA is decided
- marks the best value for one task, dataset and metric, using the metric's direction (higher or lower is better).
- Results are compared only under the same evaluation protocol: split type, within- or cross-dataset testing, filtering, inputs and label set. Different protocols stay separate and are never ranked together.
- Only results with a table, figure or section reference compete, and a star needs at least two competing methods. Ties go to the earlier publication.
- Stars are recomputed whenever the research hub syncs, and every change is logged.
Downloads of every result (JSON and CSV) are free for members. Sign in to download.
Results as reported by the authors; not independently reproduced. Leaderboard rows without a structured protocol are listed but don't receive stars. See also the leaderboards.
Cite or reuse this
CC BY 4.0ChatPPG compiled this data. You can copy, adapt and republish it, including in articles, slides, papers and AI tools, as long as you credit ChatPPG and link to this page. Please also cite the original studies for any number you use.
Attribution
Source: ChatPPG, Wearable AI results explorer, https://chatppg.com/research/results (CC BY 4.0)
HTML link
Source: <a href="https://chatppg.com/research/results">ChatPPG, Wearable AI results explorer</a> (<a href="https://creativecommons.org/licenses/by/4.0/" rel="license">CC BY 4.0</a>)