Atjaunināt sīkdatņu piekrišanu

Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data [Hardback]

(University of Texas, USA),
  • Formāts: Hardback, 288 pages, height x width x depth: 244x163x24 mm, weight: 590 g
  • Sērija : Wiley Series on Parallel and Distributed Computing
  • Izdošanas datums: 21-Apr-2015
  • Izdevniecība: John Wiley & Sons Inc
  • ISBN-10: 111889376X
  • ISBN-13: 9781118893760
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 131,38 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
  • Bibliotēkām
Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor DataPalielināt
  • Formāts: Hardback, 288 pages, height x width x depth: 244x163x24 mm, weight: 590 g
  • Sērija : Wiley Series on Parallel and Distributed Computing
  • Izdošanas datums: 21-Apr-2015
  • Izdevniecība: John Wiley & Sons Inc
  • ISBN-10: 111889376X
  • ISBN-13: 9781118893760
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9781118893760.html
Keywords:
Defines the notion of an activity model learned from sensor data and presents key algorithms that form the core of the field

Activity Learning: Discovering, Recognizing and Predicting Human Behavior from Sensor Data provides an in-depth look at computational approaches to activity learning from sensor data. Each chapter is constructed to provide practical, step-by-step information on how to analyze and process sensor data. The book discusses techniques for activity learning that include the following:





Discovering activity patterns that emerge from behavior-based sensor data Recognizing occurrences of predefined or discovered activities in real time Predicting the occurrences of activities

The techniques covered can be applied to numerous fields, including security, telecommunications, healthcare, smart grids, and home automation. An online companion site enables readers to experiment with the techniques described in the book, and to adapt or enhance the techniques for their own use.

With an emphasis on computational approaches, Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data provides graduate students and researchers with an algorithmic perspective to activity learning.
Preface ix
List of Figures
xi
1 Introduction
1(4)
2 Activities
5(6)
2.1 Definitions
5(2)
2.2 Classes of Activities
7(1)
2.3 Additional Reading
8(3)
3 Sensing
11(30)
3.1 Sensors Used for Activity Learning
11(6)
3.1.1 Sensors in the Environment
12(3)
3.1.2 Sensors on the Body
15(2)
3.2 Sample Sensor Datasets
17(1)
3.3 Features
17(17)
3.3.1 Sequence Features
21(2)
3.3.2 Discrete Event Features
23(2)
3.3.3 Statistical Features
25(6)
3.3.4 Spectral Features
31(3)
3.3.5 Activity Context Features
34(1)
3.4 Multisensor Fusion
34(4)
3.5 Additional Reading
38(3)
4 Machine Learning
41(34)
4.1 Supervised Learning Framework
41(3)
4.2 Naive Bayes Classifier
44(4)
4.3 Gaussian Mixture Model
48(2)
4.4 Hidden Markov Model
50(4)
4.5 Decision Tree
54(2)
4.6 Support Vector Machine
56(6)
4.7 Conditional Random Field
62(1)
4.8 Combining Classifier Models
63(3)
4.8.1 Boosting
64(1)
4.8.2 Bagging
65(1)
4.9 Dimensionality Reduction
66(6)
4.10 Additional Reading
72(3)
5 Activity Recognition
75(32)
5.1 Activity Segmentation
76(5)
5.2 Sliding Windows
81(7)
5.2.1 Time Based Windowing
81(1)
5.2.2 Size Based Windowing
82(1)
5.2.3 Weighting Events Within a Window
83(4)
5.2.4 Dynamic Window Sizes
87(1)
5.3 Unsupervised Segmentation
88(4)
5.4 Measuring Performance
92(11)
5.4.1 Classifier-Based Activity Recognition Performance Metrics
95(4)
5.4.2 Event-Based Activity Recognition Performance Metrics
99(3)
5.4.3 Experimental Frameworks for Evaluating Activity Recognition
102(1)
5.5 Additional Reading
103(4)
6 Activity Discovery
107(20)
6.1 Zero-Shot Learning
108(2)
6.2 Sequence Mining
110(7)
6.2.1 Frequency-Based Sequence Mining
111(1)
6.2.2 Compression-Based Sequence Mining
112(5)
6.3 Clustering
117(2)
6.4 Topic Models
119(2)
6.5 Measuring Performance
121(3)
6.5.1 Expert Evaluation
121(3)
6.6 Additional Reading
124(3)
7 Activity Prediction
127(22)
7.1 Activity Sequence Prediction
128(5)
7.2 Activity Forecasting
133(4)
7.3 Probabilistic Graph-Based Activity Prediction
137(2)
7.4 Rule-Based Activity Timing Prediction
139(3)
7.5 Measuring Performance
142(4)
7.6 Additional Reading
146(3)
8 Activity Learning in the Wild
149(46)
8.1 Collecting Annotated Sensor Data
149(9)
8.2 Transfer Learning
158(12)
8.2.1 Instance and Label Transfer
162(4)
8.2.2 Feature Transfer with No Co-occurrence Data
166(1)
8.2.3 Informed Feature Transfer with Co-occurrence Data
167(1)
8.2.4 Uninformed Feature Transfer with Co-occurrence Data Using a Teacher--Learner Model
168(2)
8.2.5 Uninformed Feature Transfer with Co-occurrence Data Using Feature Space Alignment
170(1)
8.3 Multi-Label Learning
170(10)
8.3.1 Problem Transformation
173(1)
8.3.2 Label Dependency Exploitation
174(5)
8.3.3 Evaluating the Performance of Multi-Label Learning Algorithms
179(1)
8.4 Activity Learning for Multiple Individuals
180(10)
8.4.1 Learning Group Activities
180(3)
8.4.2 Train on One/Test on Multiple
183(2)
8.4.3 Separating Event Streams
185(3)
8.4.4 Tracking Multiple Users
188(2)
8.5 Additional Reading
190(5)
9 Applications of Activity Learning
195(18)
9.1 Health
195(3)
9.2 Activity-Aware Services
198(1)
9.3 Security and Emergency Management
199(2)
9.4 Activity Reconstruction, Expression and Visualization
201(6)
9.5 Analyzing Human Dynamics
207(3)
9.6 Additional Reading
210(3)
10 The Future of Activity Learning
213(4)
Appendix: Sample Activity Data 217(20)
Bibliography 237(16)
Index 253
DIANE J. COOK, PhD, is a professor in the School of Electrical Engineering and Computer Science at Washington State University, USA. Her research relating to artificial intelligence and data mining have been supported by grants from the National Science Foundation, the National Institutes of Health, NASA, DARPA, USAF, NRL, and DHS. She is the co-author of Mining Graph Data and Smart Environments, both published by Wiley. Dr. Cook is an IEEE fellow and a member of AAAI.

NARAYANAN C. KRISHNAN, PhD, is a faculty member of the Department of Computer Science and Engineering at the Indian Institute of Technology Ropar, India. His research focuses on activity recognition, pervasive computing, and applied machine learning. Dr. Krishnan received the gold medal for academic excellence in Masters of Technology in Computer Science in 2004 and was nominated for the Best PhD Thesis Award at Arizona State University in 2010.