Context-based Human Activity Recognition Using Multimodal Wearable Sensors
Explore this paper's citation graph
Summary
This dissertation designed a novel approach for in-home, fine-grained activity recognition using multimodal wearable sensors on multiple body positions, along with very small Bluetooth beacons deployed in the environment and introduced Watch-Dog – a self-harm activity recognition engine, which attempts to infer selfharming activities from sensing accelerometer data using wearable sensors worn on a subject's wrist.
- Published
- 2017-01-01
- Cited by
- 0
- References
- 95
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:67258883
References
- Learning with Many Irrelevant Features
- A Public Domain Dataset for Human Activity Recognition using Smartphones
- Classification and Regression by randomForest
- Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning
- The impact of multiple predictors on generalist physicians' care of underserved populations.
- Can supervised exercise prevent treatment toxicity in patients with prostate cancer initiating androgen‐deprivation therapy: a randomised controlled trial
- Detecting self-harming activities with wearable devices
- Least Squares Support Vector Machine Classifiers
- Procedure for effortless in-field calibration of three-axial rate gyro and accelerometers
- Suicide in the Medical Setting
- Improved Use of Continuous Attributes in C4.5
- Feature extraction from smartphone inertial signals for human activity segmentation
- Multimodal Wearable Sensing for Fine-Grained Activity Recognition in Healthcare
- A-Wristocracy: Deep learning on wrist-worn sensing for recognition of user complex activities
- Applications of mobile activity recognition
- Supporting patient monitoring using activity recognition with a smartphone
- Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement
- The Estimation of the Lorenz Curve and Gini Index
- Noncontact Wideband Sonar for Human Activity Detection and Classification
- COSAR: hybrid reasoning for context-aware activity recognition
Cited by
No citing papers recorded for this paper.
Related papers
No related papers recorded.