Muutke küpsiste eelistusi

Activity Recognition in Pervasive Intelligent Environments 2011 [Kõva köide]

Edited by , Edited by , Edited by , Edited by
  • Formaat: Hardback, 329 pages, kõrgus x laius: 235x155 mm, kaal: 831 g, 40 Illustrations, color; 56 Illustrations, black and white; XV, 329 p. 96 illus., 40 illus. in color., 1 Hardback
  • Sari: Atlantis Ambient and Pervasive Intelligence 4
  • Ilmumisaeg: 12-May-2011
  • Kirjastus: Atlantis Press
  • ISBN-10: 9078677422
  • ISBN-13: 9789078677420
Teised raamatud teemal:
Activity Recognition in Pervasive Intelligent Environments 2011Suurem pilt
  • Formaat: Hardback, 329 pages, kõrgus x laius: 235x155 mm, kaal: 831 g, 40 Illustrations, color; 56 Illustrations, black and white; XV, 329 p. 96 illus., 40 illus. in color., 1 Hardback
  • Sari: Atlantis Ambient and Pervasive Intelligence 4
  • Ilmumisaeg: 12-May-2011
  • Kirjastus: Atlantis Press
  • ISBN-10: 9078677422
  • ISBN-13: 9789078677420
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9789078677420.html
Märksõnad:
Addressing numerous aspects of activity recognition, this book's three sections cover the mathematical and AI aspects of activity modeling, methods and algorithms for activity recognition, and scalable new architectures and frameworks for activity recognition.

This book consists of a number of chapters addressing different aspects of activity recognition, roughly in three main categories of topics. The first topic will be focused on activity modeling, representation and reasoning using mathematical models, knowledge representation formalisms and AI techniques. The second topic will concentrate on activity recognition methods and algorithms. Apart from traditional methods based on data mining and machine learning, we are particularly interested in novel approaches, such as the ontology-based approach, that facilitate data integration, sharing and automatic/automated processing. In the third topic we intend to cover novel architectures and frameworks for activity recognition, which are scalable and applicable to large scale distributed dynamic environments. In addition, this topic will also include the underpinning technological infrastructure, i.e. tools and APIs, that supports function/capability sharing and reuse, and rapid development and deployment of technological solutions. The fourth category of topic will be dedicated to representative applications of activity recognition in intelligent environments, which address the life cycle of activity recognition and their use for novel functions of the end-user systems with comprehensive implementation, prototyping and evaluation. This will include a wide range of application scenarios, such as smart homes, intelligent conference venues and cars.
Preface v
1 Activity Recognition: Approaches, Practices and Trends
1(32)
Liming Chen
Ismail Khalil
1.1 Introduction
1(2)
1.2 Activity recognition approaches and algorithms
3(7)
1.2.1 Activity recognition approaches
3(2)
1.2.2 Activity recognition algorithms
5(3)
1.2.3 Ontology-based activity recognition
8(2)
1.3 The practice and lifecycle of ontology-based activity recognition
10(8)
1.3.1 Domain knowledge acquisition
11(1)
1.3.2 Formal ontology modelling
12(1)
1.3.3 Semantic sensor metadata creation
13(1)
1.3.4 Semantic sensor metadata storage and retrieval
14(1)
1.3.5 Activity recognition
15(1)
1.3.6 Activity model learning
16(1)
1.3.7 Activity assistance
17(1)
1.4 An exemplar case study
18(4)
1.5 Emerging research on activity recognition
22(4)
1.5.1 Complex activity recognition
22(2)
1.5.2 Domain knowledge exploitation
24(1)
1.5.3 Infrastructure mediated activity monitoring
25(1)
1.5.4 Abnormal activity recognition
26(1)
1.6 Conclusions
26(7)
References
27(6)
2 Possibilistic Activity Recognition
33(26)
P.C. Roy
S. Giroux
B. Bouchard
A. Bouzouane
C. Phua
A. Tolstikov
J. Biswas
2.1 Introduction
33(3)
2.2 Overall Picture of Alzheimer's disease
36(1)
2.3 Related Work
37(4)
2.4 Possibilistic Activity Recognition Model
41(7)
2.4.1 Environment Representation and Context
42(1)
2.4.2 Action Recognition
42(3)
2.4.3 Behavior Recognition
45(3)
2.4.4 Overview of the activity recognition process
48(1)
2.5 Smart Home Validation
48(8)
2.5.1 Results
50(2)
2.5.2 Discussion
52(3)
2.5.3 Summary of Our Contribution
55(1)
2.6 Conclusion
56(3)
References
56(3)
3 Multi-user Activity Recognition in a Smart Home
59(24)
Liang Wang
Tao Gu
Xianping Tao
Hanhua Chen
Jian Lu
3.1 Introduction
59(2)
3.2 Related Work
61(2)
3.3 Multi-modal Wearable Sensor Platform
63(1)
3.4 Multi-chained Temporal Probabilistic Models
64(7)
3.4.1 Problem Statement
64(1)
3.4.2 Feature Extraction
65(1)
3.4.3 Coupled Hidden Markov Model
66(2)
3.4.4 Factorial Conditional Random Field
68(2)
3.4.5 Activity Models in CHMM and FCRF
70(1)
3.5 Experimental Studies
71(6)
3.5.1 Trace Collection
71(2)
3.5.2 Evaluation Methodology
73(1)
3.5.3 Accuracy Performance
73(4)
3.6 Conclusions and Future Work
77(6)
References
79(4)
4 Smart Environments and Activity Recognition: a Logic-based Approach
83(28)
F. Mastrogiovanni
A. Scalmato
A. Sgorbissa
R. Zaccaria
4.1 Introduction
83(3)
4.2 Related Work
86(4)
4.3 Representation of Temporal Contexts
90(7)
4.4 Assessment of Temporal Contexts
97(1)
4.5 Experimental Results and Discussion
98(8)
4.5.1 An Example of System Usage
100(5)
4.5.2 A Discussion about context assessment complexity and system performance
105(1)
4.6 Conclusion
106(5)
References
108(3)
5 ElderCare: An Interactive TV-based Ambient Assisted Living Platform
111(16)
D. Lopez-de-Ipina
S. Blanco
X. Laiseca
I. Diaz-de-Sarralde
5.1 Introduction
111(1)
5.2 Related Work
112(2)
5.3 The ElderCare Platform
114(3)
5.3.1 Eldercare Platform Components
116(1)
5.4 Implementation Overview
117(7)
5.4.1 Eldercare's Local System
118(1)
5.4.2 ElderCare's Central Server
119(1)
5.4.3 ElderCare's Mobile Client
120(4)
5.5 Conclusion and Further Work
124(3)
References
124(3)
6 An Ontology-based Context-aware Approach for Behaviour Analysis
127(22)
Shumei Zhang
Paul McCullagh
Chris Nugent
Huiru Zheng
6.1 Introduction
127(2)
6.2 Related Work
129(2)
6.3 Data Collection and Ontological Context Extraction
131(4)
6.3.1 Activity Context Extraction
131(1)
6.3.2 Location Context Detection
132(2)
6.3.3 Schedule Design
134(1)
6.4 Ontological ADL Modelling and Knowledge Base (KB) Building
135(4)
6.4.1 Ontological Modelling
135(2)
6.4.2 Knowledge Base Building
137(2)
6.5 Experiments
139(6)
6.5.1 iMessenger Ontologies
139(1)
6.5.2 Rules Definition
140(1)
6.5.3 Case Study: Querying the Ontology Using SQWRL
141(4)
6.6 Discussion and future work
145(4)
References
146(3)
7 User's Behavior Classification Model for Smart Houses Occupant Prediction
149(16)
R. Kadouche
H. Pigot
B. Abdulrazak
S. Giroux
7.1 Introduction
149(1)
7.2 Background and Related Work
150(1)
7.3 Our Approach
151(2)
7.3.1 Support Vector Machines (SVM)
152(1)
7.4 Experimentation
153(8)
7.4.1 DOMUS
153(4)
7.4.2 CASAS Smart Home Project
157(4)
7.5 Result and Discussion
161(2)
7.5.1 SVM Vs others classifiers
161(1)
7.5.2 BCM Accuracy Results'
162(1)
7.6 Conclusion
163(2)
References
163(2)
8 Activity Recognition Benchmark
165(22)
T.L.M. van Kasteren
G. Englebienne
B.J.A. Krose
8.1 Introduction
165(1)
8.2 Models
166(6)
8.2.1 Notation
166(1)
8.2.2 Naive Bayes
167(1)
8.2.3 Hidden Markov model
168(1)
8.2.4 Hidden semi-Markov model
168(1)
8.2.5 Conditional random fields
169(1)
8.2.6 Inference
170(1)
8.2.7 Learning
171(1)
8.3 Datasets
172(4)
8.3.1 Sensors Used
172(1)
8.3.2 Annotation
173(2)
8.3.3 Houses
175(1)
8.4 Experiments
176(4)
8.4.1 Experimental Setup
176(1)
8.4.2 Feature Representation
177(1)
8.4.3 Experiment 1: Timeslice Length
177(3)
8.4.4 Experiment 2: Feature Representations and Models
180(1)
8.5 Discussion
180(3)
8.6 Related and Future work
183(1)
8.7 Conclusion
184(3)
References
184(3)
9 Smart Sweet Home
187(22)
N. Noury
J. Poujaud
A. Fleury
R. Nocua
T. Haddidi
9.1 Introduction
188(1)
9.2 Daily Activities at Home
188(2)
9.2.1 State of the art in health smart homes
189(1)
9.3 Detection of activities with basic PIR sensors
190(3)
9.3.1 PIR sensors
190(2)
9.3.2 The HIS of Grenoble
192(1)
9.4 Ambulatograms
193(1)
9.5 Circadian activity rhythms?
194(2)
9.6 Night and day alternation
196(1)
9.7 Inactivity of Daily Living?
197(3)
9.8 Activities of daily living
200(1)
9.9 On the automatic detection of the ADL
201(2)
9.10 Discussion
203(2)
9.11 Conclusion
205(4)
References
205(4)
10 Synthesising Generative Probabilistic Models for High-Level Activity Recognition
209(28)
C. Burghardt
M. Wurdel
S. Bader
G. Ruscher
T. Kirste
10.1 Introduction & Motivation
209(2)
10.2 Related Work
211(1)
10.3 Preliminaries
212(6)
10.3.1 Hidden Markov Models
212(1)
10.3.2 Planning Problem
213(2)
10.3.3 Task Models
215(2)
10.3.4 Probabilistic Context-Free Grammars
217(1)
10.4 Synthesising Probabilistic Models
218(12)
10.4.1 From Task Models to Hidden Markov Models
218(2)
10.4.2 From Planning Problems to Hidden Markov Models
220(2)
10.4.3 From Probabilistic Context-Free Grammars to Hidden Markov Models
222(5)
10.4.4 Joint HMMs
227(3)
10.5 Discussion
230(3)
10.5.1 Planning operators
230(1)
10.5.2 Task models
231(1)
10.5.3 Probabilistic Context-Free Grammars
232(1)
10.5.4 Joint Hidden Markov Models
232(1)
10.6 Summary and Outlook
233(4)
References
233(4)
11 Ontology-based Learning Framework for Activity Assistance in an Adaptive Smart Home
237(28)
G. Okeyo
L. Chen
H. Wang
R. Sterritt
11.1 Introduction
237(2)
11.2 Related Work
239(2)
11.3 Activity and Behaviour Learning and Model Evolution Framework
241(4)
11.3.1 Rationale
241(2)
11.3.2 The Architecture
243(1)
11.3.3 The Process
244(1)
11.4 Activity Learning and Model Evolution Methods
245(6)
11.4.1 Preliminaries
246(1)
11.4.2 Learning Algorithm for Unlabelled Traces
247(2)
11.4.3 Learning Algorithm for Labelled Traces
249(2)
11.5 Behaviour Learning and Evolution Method
251(3)
11.5.1 Algorithm for Behaviour Learning
253(1)
11.6 Illustration
254(7)
11.6.1 Ontological modelling and representation
254(3)
11.6.2 Inferring and Logging ADL Activities
257(1)
11.6.3 Use scenario for ADL Learning and Evolution
257(2)
11.6.4 Use scenario for Behaviour Learning and Evolution
259(2)
11.7 Conclusion
261(4)
References
261(4)
12 Benefits of Dynamically Reconfigurable Activity Recognition in Distributed Sensing Environments
265(26)
C. Lombriser
O. Amft
P. Zappi
L. Benini
G. Troster
12.1 Introduction
265(2)
12.2 Related Work
267(2)
12.3 Distributed activity recognition
269(3)
12.3.1 Distributed activity recognition architecture
270(2)
12.4 Dynamic reconfiguration of activity models
272(2)
12.4.1 Reconfiguration concept
272(1)
12.4.2 Reconfiguration granularities
273(1)
12.5 Implementation of the activity recognition chain
274(4)
12.5.1 Event recognition at distributed sensor nodes
274(2)
12.5.2 Network fusion of distributed detector events
276(1)
12.5.3 Architecture and reconfiguration complexity metrics
276(1)
12.5.4 Performance evaluation
277(1)
12.6 Evaluation dataset
278(2)
12.6.1 Experimental procedure
279(1)
12.6.2 Sensor node complexity
280(1)
12.7 Results
280(5)
12.7.1 Baseline results
281(1)
12.7.2 Setting-specific results
281(1)
12.7.3 Composite-specific results
282(1)
12.7.4 Object-specific results
282(1)
12.7.5 Costs of reconfiguration
283(2)
12.8 Discussion
285(3)
12.9 Conclusion
288(3)
References
288(3)
13 Embedded Activity Monitoring Methods
291(22)
N. Shah
M. Kapuria
K. Newman
13.1 Introduction
291(1)
13.2 Related Work
292(7)
13.2.1 Machine Vision
292(1)
13.2.2 RFID-Object Tracking
293(2)
13.2.3 RFID and Machine Vision
295(1)
13.2.4 Motion Sensors
295(1)
13.2.5 Pressure Sensors
296(1)
13.2.6 Accelerometers
297(1)
13.2.7 Accelerometers and Gyroscopes
298(1)
13.3 Ultrasonic Activity Recognition Method
299(10)
13.3.1 Ultrasonic Sensor Selection
300(2)
13.3.2 Construction of the System
302(1)
13.3.3 System Operation
303(2)
13.3.4 Activity and Pose Recognition
305(2)
13.3.5 Open Issues and Drawbacks
307(2)
13.4 Conclusion
309(4)
References
310(3)
14 Activity Recognition and Healthier Food Preparation
313
T. Plotz
P. Moynihan
C. Pham
P. Olivier
14.1 Introduction
313(2)
14.2 The Role of Technology for Healthier Eating
315(2)
14.2.1 Current dietary guidelines
315(1)
14.2.2 Barriers to healthier eating with focus on preparation
316(1)
14.2.3 Why technology-based approach to healthier cooking?
316(1)
14.2.4 Evaluation and assessment of cooking skills
317(1)
14.3 Activity Recognition in the Kitchen - The State-of-the-Art
317(3)
14.3.1 Sensor-based Activity Recognition
317(1)
14.3.2 Instrumented Kitchens
318(2)
14.4 Automatic Analysis of Food Preparation Processes
320(6)
14.4.1 Activity Recognition in the Ambient Kitchen
320(2)
14.4.2 System Description
322(2)
14.4.3 Experimental Evaluation
324(2)
14.5 Activity recognition and the promotion of health and wellbeing
326
References
327