1.Assisted Living
1. 1. Introduction
1.2. Surveys on Assisted Living
1.3. Assisted Living Projects
1.4. Target Users
1.4.1. Indoor Observations
1.4.2. Outdoor Observations
1.5. Privacy and Data Protection
1.6. Conclusion
References
2. Sensors and Features for Assisted Living Technologies
2.1. Sensors in User care
2.1.1. Wearable Sensors
2.1.2. Smart Daily Objects
2.1.3. Environmental Sensors
2.1.2. Wearables with Ambient Sensors
2.1.3. Ambient Sensors in Robotic Assisted Living
2.2. Feature Extraction
2.2.1. Feature Extraction Using PCA
2.2.2. Kernel Principal Component Analysis (KPCA)
2.2.3. Feature Extraction Using ICA
2.2.4. Linear Discriminant Analysis (LDA)
2.2.5. Generalized Discriminant Analysis (GDA)
2.3. Discussion
2.4. Conclusion
References
3. Machine Learning
3.1 Shallow Machine Learning
3.1.1. Support Vector Machines
vii
3.1.2. Random Forests
3.1.3. AdaBoost and Gradient Boosting
3.1.4. Nearest Neighbors
3.1.5. Examples
3.2. Deep Machine Learning
3.2.1. Deep Belief Networks (DBN)
3.2.2. Convolutional Neural Network
3.2.3. Recurrent Neural Networks
3.2.4. Neural Structured Learning
3.2.4. Pre-trained deep learning models
3.3. Explainable AI (XAI)
3.3.1. Local Explanations
3.3.2. Rule-based Explanations
3.3.3. Visual Explanations
3.3.4. Feature Relevance Explanations
3.4. Discussion
3.5. Conclusion
References
4. Applications
4.1. Wearable Sensor-based Behavior Recognition
4.1.1. MHEALTH Dataset
4.1.2. Experimental Results on MHEALTH Dataset
4.1.3. PUC-Rio Dataset
4.1.4. Experimental Results on PUC-Rio Dataset
4.1.5. ARem Dataset
4.1.6. Experimental Results on AReM Dataset
4.3. Video Camera-based Behavior Recognition
4.3.1. Binary Silhouettes and Features
4.3.2. Depth Silhouettes and Features
4.3.3. 3-D Model-based HAR
4.4. Other Ambient Sensor-based Behavior Recognition
4.4.1. CASAS Dataset
viii
4.4.2. Experimental Results
4.5. Conclusion
References.