Human Activity Sensing Corpus and Applications /: Corpus and Applications. (2019)
- Record Type:
- Book
- Title:
- Human Activity Sensing Corpus and Applications /: Corpus and Applications. (2019)
- Main Title:
- Human Activity Sensing Corpus and Applications
- Further Information:
- Note: Nobuo Kawaguchi, Nobuhiko Nishio, Daniel Roggen, Sozo Onoue, Susanna Pirttikangas, Kristof Van Laerhoven, editors.
- Other Names:
- Kawaguchi, Nobuo
Nishio, Nobuhiko
Roggen, Daniel
Inoue, Sozo
Pirttikangas, Susanna
Laerhoven, Kristof van - Contents:
- Intro; Preface; Contents; Contributors; Part I Modalities and Applications; 1 Optimizing of the Number and Placements of Wearable IMUs for Automatic Rehabilitation Recording; 1.1 Introduction; 1.2 Related Work; 1.3 System Configuration for Experiment; 1.3.1 System Overview; 1.3.2 Wearable Sensor; 1.4 Experiment; 1.4.1 Data Collection in Experiment; 1.4.2 Feature Values; 1.4.3 The Number of Data Instances; 1.4.4 Classifier; 1.4.5 Evaluation Method; 1.5 Results and Discussion; 1.5.1 Classifier; 1.5.2 Number of Sensors; 1.5.3 Combination of Sensor Positions; 1.6 Conclusion; References 2 Identifying Sensors via Statistical Analysis of Body-Worn Inertial Sensor Data2.1 Introduction; 2.2 Related Work; 2.3 Datasets; 2.4 Pre-processing and Analysis of Sensor Data Properties; 2.4.1 Detecting the Gyroscope Data; 2.4.2 Detecting the Accelerometer Data; 2.4.3 Detecting the Magnetometer Data; 2.4.4 Distinguishing Acceleration Versus Magnetometer Data; 2.5 Identification Ruleset; 2.6 A Discussion of Results and Limitations of Our Approach; 2.7 Conclusions; References; 3 Compensation Scheme for PDR Using Component-Wise Error Models; 3.1 Introduction; 3.2 Related Work 3.3 Compensation Scheme Proposal3.3.1 Moving Distance Error Model; 3.3.2 Error Model of Orientation Changing; 3.3.3 Drift Angle Error Model; 3.4 Evaluation; 3.4.1 Post-compensation; 3.4.2 Real-Time Compensation; 3.4.3 Discussion About the Moving Distance Error Model; 3.4.4 Discussion About Error Model of Orientation; 3.5Intro; Preface; Contents; Contributors; Part I Modalities and Applications; 1 Optimizing of the Number and Placements of Wearable IMUs for Automatic Rehabilitation Recording; 1.1 Introduction; 1.2 Related Work; 1.3 System Configuration for Experiment; 1.3.1 System Overview; 1.3.2 Wearable Sensor; 1.4 Experiment; 1.4.1 Data Collection in Experiment; 1.4.2 Feature Values; 1.4.3 The Number of Data Instances; 1.4.4 Classifier; 1.4.5 Evaluation Method; 1.5 Results and Discussion; 1.5.1 Classifier; 1.5.2 Number of Sensors; 1.5.3 Combination of Sensor Positions; 1.6 Conclusion; References 2 Identifying Sensors via Statistical Analysis of Body-Worn Inertial Sensor Data2.1 Introduction; 2.2 Related Work; 2.3 Datasets; 2.4 Pre-processing and Analysis of Sensor Data Properties; 2.4.1 Detecting the Gyroscope Data; 2.4.2 Detecting the Accelerometer Data; 2.4.3 Detecting the Magnetometer Data; 2.4.4 Distinguishing Acceleration Versus Magnetometer Data; 2.5 Identification Ruleset; 2.6 A Discussion of Results and Limitations of Our Approach; 2.7 Conclusions; References; 3 Compensation Scheme for PDR Using Component-Wise Error Models; 3.1 Introduction; 3.2 Related Work 3.3 Compensation Scheme Proposal3.3.1 Moving Distance Error Model; 3.3.2 Error Model of Orientation Changing; 3.3.3 Drift Angle Error Model; 3.4 Evaluation; 3.4.1 Post-compensation; 3.4.2 Real-Time Compensation; 3.4.3 Discussion About the Moving Distance Error Model; 3.4.4 Discussion About Error Model of Orientation; 3.5 Conclusion; References; 4 Towards the Design and Evaluation of Robust Audio-Sensing Systems; 4.1 Introduction; 4.2 Methodology; 4.3 Results; 4.4 Discussion and Future Directions; 4.5 Conclusions; References 5 A Wi-Fi Positioning Method Considering Radio Attenuation of Human Body5.1 Introduction; 5.1.1 Background and Purpose; 5.1.2 Related Work; 5.1.3 Preliminary Experiment; 5.2 Approach and Evaluation; 5.2.1 Proposed Method; 5.2.2 Evaluation; 5.3 Conclusion; References; Part II Data Collection and Corpus Construction; 6 Drinking Gesture Recognition from Poorly Annotated Data: A Case Study; 6.1 Introduction; 6.2 Related Work; 6.3 Dataset; 6.4 User Annotation Analysis; 6.5 Gesture Classification; 6.5.1 Data Processing and Training Set Selection; 6.5.2 Template Matching Using WLCSS 6.5.3 WLCSS Optimization Using Evolutionary Algorithm6.5.4 Confidence Computation; 6.5.5 Evaluation; 6.6 Unsupervised Learning; 6.6.1 K-Means with WLCSS; 6.6.2 Evaluation; 6.7 Discussion; 6.8 Conclusion; References; 7 Understanding How Non-experts Collect and Annotate Activity Data; 7.1 Introduction; 7.2 Related Work; 7.2.1 Interactive Physical Devices; 7.2.2 Event Recognizers and Interaction; 7.2.3 Hidden Markov Models, ASR and Other Activity Models; 7.3 Building an Event Recognizer with VAT; 7.3.1 Define Event Pieces; 7.3.2 Attach Data Logger; 7.3.3 Record and Synchronize Video and Data … (more)
- Publisher Details:
- Cham : Springer
- Publication Date:
- 2019
- Extent:
- 1 online resource (251 p.)
- Subjects:
- 006.2/5
Sensor networks
Internet of things
Internet of things
Sensor networks
Electronic books
Electronic books - Languages:
- English
- ISBNs:
- 9783030130015
3030130010 - Related ISBNs:
- 9783030130008
- Notes:
- Note: Includes bibliographical references.
- Access Rights:
- Legal Deposit; Only available on premises controlled by the deposit library and to one user at any one time; The Legal Deposit Libraries (Non-Print Works) Regulations (UK).
- Access Usage:
- Restricted: Printing from this resource is governed by The Legal Deposit Libraries (Non-Print Works) Regulations (UK) and UK copyright law currently in force.
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library HMNTS - ELD.DS.455382
- Ingest File:
- 02_592.xml