Comparison of LSTM and Transformer Models for Activities of Daily Living Recognition using In-Home Ambient Sensors
Abdalnabi, N.; Addepalli, V. r.; Sarker, S.; Kiselica, A.; Kummerfeld, E.; Rao, P.; Lee, K.
Show abstract
This study evaluated Long Short-Term Memory (LSTM) and Transformer artificial intelligence (AI) models for recognizing Activities of Daily Living (ADLs) using data collected from a low-cost, non-invasive ambient in-home sensor system. Motion, temperature, luminance, and door-contact sensors were deployed in a two-participant home for 22 days, with ground truth established through volunteer logs and expert validation. Missing data were handled using Akima and linear interpolation. Models were trained using a 16/3-day train-validation split with the last three days reserved for testing to avoid temporal leakage. Performance assessments included participant-specific modeling, sequence-length variation, and hyperparameter tuning, using micro-accuracy and AUC-ROC as evaluation metrics. The Transformer consistently outperformed the LSTM, particularly for Participant 2 (AUC 0.91 vs. 0.87), and demonstrated superior adaptability to irregular time-series data. Findings underscore the feasibility of combining ambient sensing with AI for accurate ADL recognition and its potential to enable early detection of cognitive decline, reduce hospitalization risk, and alleviate caregiver burden.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Statistical and machine learning models for classification of human wear and delivery days in accelerometry data 92%
- Measuring Repositioning in Home Care for Pressure Injury Prevention and Management 92%
- Advancing Mobile Neuroscience: A Novel Wearable Backpack for Multi-Sensor Research in Urban Environments 91%
Similar papers in this journal
- An infection prediction model developed from inpatient data can predict out-of-hospital COVID-19 infections from wearable data when controlled for dataset shift 95%
- An Unsupervised XAI Framework for Dementia Detection with Context Enrichment 93%
- Visualization of Incrementally Learned Projection Trajectories for Longitudinal Data 91%
Similar papers in this journal
- Listening to mental health crisis needs at scale: using Natural Language Processing to understand and evaluate a mental health crisis text messaging service 90%
- Development and Validation of a Machine Learning Model Integrated with the Clinical Workflow for Inpatient Discharge Date Prediction 89%
- Using wearable and nearable devices in telerehabilitation for COPD: A review of digital endpoints in home-based programs 89%
Similar papers in this journal
- Longitudinally Tracking Personal Physiomes for Precision Management of Childhood Epilepsy 91%
- Evaluating and mitigating unfairness in multimodal remote mental health assessments 91%
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 91%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.