PyTorch implementation of a local-global feature fusion framework for subject-independent EEG emotion recognition under LOSO evaluation.
-
Updated
Aug 3, 2026 - Python
#
loso
Here are 9 public repositories matching this topic...
基于 PPG+EDA 多模态信号的轻量级可穿戴情感状态检测系统 | WESAD | 1D-CNN 三分类 | LOSO | React Dashboard
-
Updated
Aug 7, 2026 - TypeScript
End-to-end blood-glucose forecasting platform: 3-phase tiered ML (CGM / post-CGM / watch-only Virtual CGM) with rigorous offline evaluation (baselines, clinical metrics, conformal intervals, LOSO, drift), a FastAPI + CockroachDB backend, a React Native app, and a keyless local-LLM health assistant. Portfolio project, APK-only.
data-science machine-learning cross-validation personalization healthcare xgboost lightgbm diabetes cgm model-evaluation wearables catboost time-series-forecasting conformal-prediction mlops fastapi glucose-prediction llm loso virtual-cgm
-
Updated
Aug 1, 2026 - Python
Three-class football player fatigue prediction from PAMAP2 wearable IoT data. Karvonen heart rate labeling, SMOTE balancing, LOSO cross-validation, personalized Random Forest. 97.96% LOSO accuracy + coach substitution-alert dashboard.
iot data-science random-forest tensorflow scikit-learn lstm data-analytics football smote sports-analytics football-analytics wearable-sensors pamap2 injury-prevention loso coach-dashboard fatigue-prediction karvonen
-
Updated
Apr 21, 2026 - Jupyter Notebook
Classifies football players into Attacker, Midfielder, Defender roles from PAMAP2 IoT wearable data. LSTM, BiLSTM, and TCN-Transformer architectures. 99.24% accuracy, LOSO 98.89%±0.42%. SHAP sensor attribution per role.
iot activity-recognition pytorch transformer lstm data-analytics football tcn bilstm sports-analytics shap positional-analysis football-analytics wearable-sensors pamap2 loso player-role-classification
-
Updated
Apr 21, 2026 - Jupyter Notebook
Leave-one-service-out open-world recognition and uncertainty analysis for darknet traffic.
machine-learning random-forest cybersecurity xgboost uncertainty-estimation traffic-classification leave-one-out loso open-world-recognition anonymity-networks darknet-traffic
-
Updated
Aug 6, 2026 - Jupyter Notebook
Official code for "Revisiting Subject-Independent Evaluation for Smartphone-Based Fall and Activity Recognition". This repository quantifies the CV-to-LOSO generalization gap on the MobiAct dataset and introduces Feature-Invariance-Conditioned (FIC) pooling with SAM to improve cross-subject HAR performance.
human-activity-recognition attention-mechanism fic sharpness-aware-minimization loso cross-subject-generalization mobiact
-
Updated
Aug 26, 2026 - Python
Add this topic to your repo
To associate your repository with the loso topic, visit your repo's landing page and select "manage topics."