Activity Learning : Discovering, Recognizing, and Predicting Human Behavior from Sensor Data.

Cover -- Contents -- Preface -- List of Figures -- Chapter 1 Introduction -- Chapter 2 Activities -- 2.1 Definitions -- 2.2 Classes of Activities -- 2.3 Additional Reading -- Chapter 3 Sensing -- 3.1 Sensors Used for Activity Learning -- 3.1.1 Sensors in the Environment -- 3.1.2 Sensors on the Body -- 3.2 Sample Sensor Datasets -- 3.3 Features -- 3.3.1 Sequence Features -- 3.3.2 Discrete Event Features -- 3.3.3 Statistical Features -- 3.3.4 Spectral Features -- 3.3.5 Activity Context Features -- 3.4 Multisensor Fusion -- 3.5 Additional Reading -- Chapter 4 Machine Learning -- 4.1 Supervised Learning Framework -- 4.2 Naïve Bayes Classifier -- 4.3 Gaussian Mixture Model -- 4.4 Hidden Markov Model -- 4.5 Decision Tree -- 4.6 Support Vector Machine -- 4.7 Conditional Random Field -- 4.8 Combining Classifier Models -- 4.8.1 Boosting -- 4.8.2 Bagging -- 4.9 Dimensionality Reduction -- 4.10 Additional Reading -- Chapter 5 Activity Recognition -- 5.1 Activity Segmentation -- 5.2 Sliding Windows -- 5.2.1 Time Based Windowing -- 5.2.2 Size Based Windowing -- 5.2.3 Weighting Events Within a Window -- 5.2.4 Dynamic Window Sizes -- 5.3 Unsupervised Segmentation -- 5.4 Measuring Performance -- 5.4.1 Classifier-Based Activity Recognition Performance Metrics -- 5.4.2 Event-Based Activity Recognition Performance Metrics -- 5.4.3 Experimental Frameworks for Evaluating Activity Recognition -- 5.5 Additional Reading -- Chapter 6 Activity Discovery -- 6.1 Zero-Shot Learning -- 6.2 Sequence Mining -- 6.2.1 Frequency-Based Sequence Mining -- 6.2.2 Compression-Based Sequence Mining -- 6.3 Clustering -- 6.4 Topic Models -- 6.5 Measuring Performance -- 6.5.1 Expert Evaluation -- 6.6 Additional Reading -- Chapter 7 Activity Prediction -- 7.1 Activity Sequence Prediction -- 7.2 Activity Forecasting -- 7.3 Probabilistic Graph-Based Activity Prediction.

7.4 Rule-Based Activity Timing Prediction -- 7.5 Measuring Performance -- 7.6 Additional Reading -- Chapter 8 Activity Learning in the Wild -- 8.1 Collecting Annotated Sensor Data -- 8.2 Transfer Learning -- 8.2.1 Instance and Label Transfer -- 8.2.2 Feature Transfer with No Co-occurrence Data -- 8.2.3 Informed Feature Transfer with Co-occurrence Data -- 8.2.4 Uninformed Feature Transfer with Co-occurrence Data Using a Teacher-Learner Model -- 8.2.5 Uninformed Feature Transfer with Co-occurrence Data Using Feature Space Alignment -- 8.3 Multi-Label Learning -- 8.3.1 Problem Transformation -- 8.3.2 Label Dependency Exploitation -- 8.3.3 Evaluating the Performance of Multi-Label Learning Algorithms -- 8.4 Activity Learning for Multiple Individuals -- 8.4.1 Learning Group Activities -- 8.4.2 Train on One/Test on Multiple -- 8.4.3 Separating Event Streams -- 8.4.4 Tracking Multiple Users -- 8.5 Additional Reading -- Chapter 9 Applications of Activity Learning -- 9.1 Health -- 9.2 Activity-Aware Services -- 9.3 Security and Emergency Management -- 9.4 Activity Reconstruction, Expression and Visualization -- 9.5 Analyzing Human Dynamics -- 9.6 Additional Reading -- Chapter 10 The Future of Activity Learning -- Appendix: Sample Activity Data -- Bibliography -- Index -- EULA.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.