Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 30000010303858 | QA76.9.A25 M335 2012 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
The Intelligent Systems Series comprises titles that present state of the art knowledge and the latest advances in intelligent systems. Its scope includes theoretical studies, design methods, and real-world implementations and applications.
Traditionally, Intelligence and Security Informatics (ISI) research and applications have focused on information sharing and data mining, social network analysis, infrastructure protection and emergency responses for security informatics. With the continuous advance of IT technologies and the increasing sophistication of national and international security, in recent years, new directions in ISI research and applications have emerged to address complicated problems with advanced technologies. This book provides a comprehensive and interdisciplinary account of the new advances in ISI area along three fundamental dimensions: methodological issues in security informatics; new technological developments to support security-related modeling, detection, analysis and prediction; and applications and integration in interdisciplinary socio-cultural fields.
Author Notes
Wenji Mao, Associate Professor, State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences. Prof. Mao has published widely in ACM-, JEEE- and AAAI-sponsored journals arid conference proceedings, and serves as co-chairs and on the organizing and program committees of various international conferences and workshops on security informatics, social computing and intelligent agents. She is a member of ACM, AAAI, INFORMS and serves on the Technical Committee on Homeland Security of the IEEE Systems, Man, Cybernetics Society.
Fei-Yue Wang, Professor, NUDT, Chinese Academy of Sciences. Currently, Prof. Wang is the Editor-in-Chief of the IEEE Intelligent Systems and IEEE Transactions on Intelligent Transportation Systems. He is a Fellow of IEEE, INCOSE, IFAC, ASME, and AAAS. In 2007, he received the 2nd Class National Prize in Natural Sciences of China and was awarded ACM Distinguished Scientist for his work in intelligent systems and social computing. In 2011, he received IEEE ITSS Outstanding ITS Research Award.
Table of Contents
Preface | p. ix |
Acknowledgements | p. xi |
Chapter 1 Intelligence and Security Informatics: Research Frameworks | p. 1 |
1.1 Research Methodology and Frameworks for ISI | p. 1 |
1.2 The ACP Approach | p. 2 |
1.2.1 Modeling with Artificial Societies | p. 2 |
1.2.2 Analysis with Computational Experiments | p. 3 |
1.2.3 Control Through Parallel Execution | p. 3 |
1.2.4 Foundations in Philosophy and Physics | p. 4 |
1.3 Outline of Chapters | p. 5 |
Chapter 2 Agent Modeling of Terrorist Organization Behavior | p. 9 |
2.1 Modeling Organizational Behavior | p. 9 |
2.2 Action Extraction from the Web | p. 10 |
2.2.1 Action Data Collection | p. 10 |
2.2.2 Raw Action Extraction | p. 10 |
2.2.3 Action Elimination | p. 11 |
2.2.4 Action Refinement | p. 11 |
2.3 Extracting Causal Knowledge from the Web | p. 11 |
2.4 Construction of Action Hierarchy | p. 13 |
2.5 Designing, Causal Scenarios | p. 15 |
2.6 Case Study on Terrorist Organization | p. 16 |
2.7 Conclusion | p. 18 |
Chapter 3 Security Story Generation for Computational Experiments | p. 21 |
3.1 Story Generation Systems | p. 21 |
3.2 System Workflow and Narrative Structure | p. 23 |
3.3 Story Extraction Approach | p. 25 |
3.3.1 Text Processing with Domain Knowledge | p. 25 |
3.3.2 Event Detection and Event Element Extraction | p. 26 |
3.3.3 Design and Organization of Patterns | p. 27 |
3.3.4 Event Element Standardization | p. 28 |
3.3.5 Evaluation of Event Relations | p. 29 |
3.4 Experiment | p. 29 |
3.5 Conclusion | p. 30 |
Chapter 4 Forecasting Croup Behavior via Probabilistic Plan Inference | p. 33 |
4.1 Review of Plan-Based Inference | p. 34 |
4.2 Probabilistic Plan Representation | p. 35 |
4.3 Probabilistic Reasoning Approach | p. 36 |
4.3.1 Notation | p. 36 |
4.3.2 Computation | p. 36 |
4.4 Case Study in Security Informatics | p. 39 |
4.4.1 Construction of Plan Library | p. 39 |
4.4.2 The Test Set | p. 40 |
4.4.3 Experimental Results | p. 42 |
4.5 Conclusion | p. 43 |
Chapter 5 Forecasting Complex Croup Behavior via Multiple Plan Recognition | p. 45 |
5.1 Multiple Plan Recognition for Behavior Prediction | p. 46 |
5.2 The MPR Problem Definition | p. 47 |
5.3 The Proposed MPR Approach | p. 49 |
5.3.1 Constructing the Explanation Graph | p. 49 |
5.3.2 Computing Probability of an Explanation | p. 51 |
5.3.3 Finding the Best Explanation | p. 53 |
5.3.4 Algorithm and Complexity Analysis | p. 53 |
5.3.5 Discussion | p. 55 |
5.4 Case Study in Security Informatics | p. 55 |
5.4.1 Experimental Design | p. 56 |
5.4.2 Results | p. 57 |
5.5 Conclusion | p. 58 |
Chapter 6 Social Computing in ISI: A Synthetic View | p. 61 |
6.1 Social Computing | p. 61 |
6.1.1 Theoretical and Infrastructure Underpinnings | p. 62 |
6.1.2 Major Application Areas | p. 64 |
6.2 A Social Computing-Based ISI Research Framework | p. 64 |
6.2.1 Modeling with Artificial Societies | p. 65 |
6.2.2 Analysis with Computational Experiments | p. 66 |
6.2.3 Control and Management Through Parallel Execution | p. 66 |
6.3 Main Issues in the ACP-Based ISI Research Framework | p. 66 |
6.3.1 Modeling Cyber-Physical Societies | p. 66 |
6.3.2 Scenario-Based Computational Experiment and Evaluation | p. 67 |
6.3.3 Interactive Co-Evolution of Artificial and Actual Systems | p. 68 |
6.3.4 Social Media Information Processing and Standardization | p. 69 |
6.3.5 ISI Research Platform | p. 69 |
6.4 Summary | p. 70 |
Chapter 7 Cyber-Enabled Social Movement Organizations | p. 73 |
7.1 Studies on Social Movement Organizations: A Review | p. 74 |
7.2 A New Research Framework for CeSMOs | p. 76 |
7.2.1 CeSMO Research Questions | p. 76 |
7.2.2 A Social Computing-Based CeSMO Research Framework | p. 76 |
7.3 Case Study: Wenchuan Earthquake | p. 77 |
7.4 Discussions on CeSMO Research Issues | p. 85 |
7.4.1 CeSMO Behavior Modeling | p. 86 |
7.4.2 CeSMO Network Analysis | p. 86 |
7.4.3 CeSMO Social and Cultural Information Modeling and Analysis | p. 86 |
7.4.4 CeSMO Behavior Prediction | p. 87 |
7.5 Conclusion | p. 87 |
Chapter 8 Cultural Modeling for Behavior Analysis and Prediction | p. 91 |
8.1 Modeling Cultural Data in Security Informatics | p. 92 |
8.2 Major Machine Learning Methods | p. 93 |
8.2.1 Naive Bayesian (NB) | p. 93 |
8.2.2 Support Vector Machines (SVMs) | p. 93 |
8.2.3 Artificial Neural Networks | p. 93 |
8.2.4 k-Nearest Neighbor (kNN) | p. 93 |
8.2.5 Decision Trees | p. 94 |
8.2.6 Random Forest (RF) | p. 94 |
8.2.7 Associative Classification (AC) | p. 94 |
8.3 Experiment and Analysis | p. 94 |
8.3.1 Datasets | p. 94 |
8.3.2 Evaluation Measures | p. 95 |
8.3.3 Experimental Results | p. 96 |
8.3.4 Observations and Analysis | p. 96 |
8.4 Discussions on Cultural Modeling Research Issues | p. 98 |
8.4.1 Cultural Datasets Construction | p. 98 |
8.4.2 Attribute Selection | p. 98 |
8.4.3 Best Performance of Classifiers | p. 99 |
8.4.4 Handling the Class Imbalance Problem | p. 99 |
8.4.5 Model Interpretability | p. 99 |
8.4.6 Incorporation of Domain Knowledge | p. 100 |
8.4.7 Cultural and Social Dynamics of Behavioral Patterns | p. 100 |
8.5 Conclusion | p. 100 |
Index | p. 103 |