Abstract
There are numerous applications (e.g., video surveillance, fraud detection, cybersecurity) in which we wish to identify unexplained sets of events. Most related past work has been domain-dependent (e.g., video surveillance, cybersecurity) and has focused on the valuable class of statistical anomalies in which statistically unusual events are considered. In contrast, suppose there is a set A of known activity models (both harmless and harmful) and a log L of time-stamped observations. We define a part L'⊆ L of the log to represent an unexplained situation when none of the known activity models can explain L' with a score exceeding a user-specified threshold. We represent activities via probabilistic penalty graphs (PPGs) and show how a set of PPGs can be combined into one Super-PPG for which we define an index structure. Given a compute cluster of (K + 1) nodes (one of which is a master node), we show how to split a Super-PPG into K subgraphs, each of which can be independently processed by a compute node. We provide algorithms for the individual compute nodes to ensure seamless handoffs that maximally leverage parallelism. PADUA is domain-independent and can be applied to many domains (perhaps with some specialization). We conducted detailed experiments with PADUA on two real-world datasets—the ITEA CANDELA video surveillance dataset and a network traffic dataset appropriate for cybersecurity applications. PADUA scales extremely well with the number of processors and significantly outperforms past work both in accuracy and time. Thus, PADUA represents the first parallel architecture and algorithm for identifying unexplained situations in observation data, offering both scalability and accuracy.
- Amit Adam, Ehud Rivlin, Ilan Shimshoni, and David Reinitz. 2008. Robust real-time unusual event detection using multiple fixed-location monitors. IEEE Trans. Pattern Anal. Mach. Intell. 30, 3 (2008), 555--560. Google ScholarDigital Library
- Rakesh Agrawal and Ramakrishnan Srikant. 1994. Fast algorithms for mining association rules in large databases. In Proceedings of the (VLDB). 487--499. Google ScholarDigital Library
- Safaa O. Al-Mamory and Hongli Zhang. 2009. IDS alerts correlation using grammar-based approach. J. Comput. Virology 5, 4 (2009), 271--282.Google ScholarCross Ref
- Massimiliano Albanese, Sushil Jajodia, Andrea Pugliese, and V. S. Subrahmanian. 2011a. Scalable analysis of attack scenarios. In Proceedings of the 16th European Symposium on Research in Computer Security (ESORICS'11). Lecture Notes in Computer Science, Vijay Atluri and Claudia Díaz (Eds.), Vol. 6879, Springer, Berlin, 416--433. Google ScholarDigital Library
- Massimiliano Albanese, Cristian Molinaro, Fabio Persia, Antonio Picariello, and V. S. Subrahmanian. 2011b. Finding “unexplained” activities in video. In Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI'11). Toby Walsh (Ed.), IJCAI/AAAI, 1628--1634. Google ScholarDigital Library
- Massimiliano Albanese, Vincenzo Moscato, Antonio Picariello, V. S. Subrahmanian, and Octavian Udrea. 2007. Detecting stochastically scheduled activities in video. In Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI'07). Manuela M. Veloso (Ed.), 1802--1807. Google ScholarDigital Library
- Alexander Artikis and Georgios Paliouras. 2009. Behaviour recognition using the event calculus. In Artificial Intelligence Applications and Innovations III. Springer, 469--478.Google Scholar
- Carmen E. Au, Sandra Skaff, and James J. Clark. 2006. Anomaly detection for video surveillance applications. In Proceedings of the 18th International Conference on Pattern Recognition (ICPR'06)., Vol. 4, IEEE Computer Society, 888--891. Google ScholarDigital Library
- Leonard E. Baum and Ted Petrie. 1966. Statistical inference for probabilistic functions of finite state Markov chains. Ann. Math. Stat. 37, 6 (1966), 1554--1563.Google ScholarCross Ref
- Stefano Bordoni and Gisella Facchinetti. 2001. Insurance fraud evaluation - A fuzzy expert system. In Proceedings of the 10th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, 1491--1494.Google Scholar
- Matthew Brand, Nuria Oliver, and Alex Pentland. 1997. Coupled hidden Markov models for complex action recognition. In Proceedings of the (CVPR). IEEE Computer Society, 994--999. Google ScholarDigital Library
- Luc Brun, Alessia Saggese, and Mario Vento. 2012. A clustering algorithm of trajectories for behaviour understanding based on string kernels. In Proceedings of the 8th International Conference on Signal Image Technology and Internet Based Systems. IEEE, 267--274. Google ScholarDigital Library
- Naresh P. Cuntoor, B. Yegnanarayana, and Rama Chellappa. 2008. Activity modeling using event probability sequences. IEEE Trans. Image Process. 17, 4 (2008), 594--607. Google ScholarDigital Library
- Pedro García-Teodoro, Jesús E. Díaz-Verdejo, Gabriel Maciá-Fernández, and Enrique Vázquez. 2009. Anomaly-based network intrusion detection: Techniques, systems and challenges. Comput. Security 28, 1--2 (2009), 18--28. Google ScholarDigital Library
- Zoubin Ghahramani. 1998. Learning dynamic Bayesian networks. In Adaptive Processing of Sequences and Data Structures. Springer, Berlin, 168--197. Google ScholarDigital Library
- Malik Ghallab. 1996. On chronicles: Representation, on-line recognition and learning. In Proceedings of the 5th International Conference on Principles of Knowledge Representation and Reasoning (KR). 597--606.Google Scholar
- Raffay Hamid, Yan Huang, and Irfan Essa. 2003. Argmode-activity recognition using graphical models. In Proceedings of the Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'03). Vol. 4, IEEE, 38--38.Google ScholarCross Ref
- Somboon Hongeng, Ramakant Nevatia, and François Brémond. 2004. Video-based event recognition: Activity representation and probabilistic recognition methods. Comput. Vision Image Understand. 96, 2 (2004), 129--162. Google ScholarDigital Library
- Derek Hao Hu, Xian-Xing Zhang, Jie Yin, Vincent Wenchen Zheng, and Qiang Yang. 2009. Abnormal activity recognition based on HDP-HMM models. In Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI'09), Craig Boutilier (Ed.), 1715--1720. Google ScholarDigital Library
- Fan Jiang, Ying Wu, and Aggelos K. Katsaggelos. 2009. Detecting contextual anomalies of crowd motion in surveillance video. In Proceedings of the International Conference on Image Processing (ICIP'09). IEEE, 1117--1120. Google ScholarDigital Library
- Fan Jiang, Junsong Yuan, Sotirios A. Tsaftaris, and Aggelos K. Katsaggelos. 2010. Video anomaly detection in spatiotemporal context. In Proceedings of the International Conference on Image Processing (ICIP'10). IEEE, 705--708.Google Scholar
- Anita Jones and Song Li. 2001. Temporal signatures for intrusion detection. In Proceedings of the 17th Annual Computer Security Applications Conference (ACSAC'01). IEEE Computer Society, 252--261. Google ScholarDigital Library
- David R. Karger and Clifford Stein. 1996. A new approach to the minimum cut problem. J. ACM 43, 4 (1996), 601--640. Google ScholarDigital Library
- Jaechul Kim and Kristen Grauman. 2009. Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'09). IEEE, 2921--2928.Google ScholarCross Ref
- Peter Lancaster and Kestutis Salkauskas. 1986. Curve and Surface Fitting: An Introduction. Academic Press, London.Google Scholar
- Dhruv Mahajan, Nipun Kwatra, Sumit Jain, Prem Kalra, and Subhashis Banerjee. 2004. A framework for activity recognition and detection of unusual activities. In Proceedings of the 4th Indian Conference on Computer Vision, Graphics & Image Processing (ICVGIP'04). Bhabatosh Chanda, Sharat Chandran, and Larry S. Davis (Eds.), Allied Publishers Private Limited, 15--21.Google Scholar
- Alessandro Mecocci and Massimo Pannozzo. 2005. A completely autonomous system that learns anomalous movements in advanced videosurveillance applications. In Proceedings of the International Conference on Image Processing (ICIP'05). Vol. 2, IEEE, 586--589.Google ScholarCross Ref
- Christopher Mutschler and Michael Philippsen. 2012. Learning event detection rules with noise hidden Markov models. In Proceedings of the NASA/ESA Conference on Adaptive Hardware and Systems (AHS). 159--166.Google ScholarCross Ref
- Peng Ning, Yun Cui, and Douglas S. Reeves. 2002. Constructing attack scenarios through correlation of intrusion alerts. In Proceedings of the 9th ACM Conference on Computer and Communications Security (CCS'02). Vijayalakshmi Atluri (Ed.), ACM, 245--254. Google ScholarDigital Library
- Adam J. Oliner, Ashutosh V. Kulkarni, and Alex Aiken. 2010. Community epidemic detection using time-correlated anomalies. In Proceedings of the 13th International Symposium Recent Advances in Intrusion Detection (RAID'10). Somesh Jha, Robin Sommer, and Christian Kreibich (Eds.). Lecture Notes in Computer Science, vol. 6307, Springer, Berlin, 360--381. Google ScholarDigital Library
- Nuria Oliver, Eric Horvitz, and Ashutosh Garg. 2002. Layered representations for human activity recognition. In Proceedings of the 4th IEEE International Conference on Multimodal Interfaces (ICMI'02). IEEE Computer Society, 3--8. Google ScholarDigital Library
- Girish Keshav Palshikar and Manoj M. Apte. 2008. Collusion set detection using graph clustering. Data Min. Knowl. Discov. 16, 2 (2008), 135--164. Google ScholarDigital Library
- Xinzhou Qin. 2005. A Probabilistic-based framework for INFOSEC alert correlation. Ph.D. Dissertation. Georgia Institute of Technology. Google ScholarDigital Library
- Xinzhou Qin and Wenke Lee. 2003. Statistical causality analysis of INFOSEC alert data. In Proceedings of the 6th International Symposium on Recent Advances in Intrusion Detection. Lecture Notes in computer Science, Giovanni Vigna, Erland Jonsson, and Christopher Krügel (Eds.), vol. 2820., Springer, 73--93.Google Scholar
- Michael O. Rabin. 1963. Probabilistic automata. Inform. Control 6, 3 (1963), 230--245.Google ScholarCross Ref
- Ivandro Sanches. 2000. Noise-compressed hidden Markov models. IEEE Trans. Speech Audio Process. 8, 5 (2000), 533--540.Google ScholarCross Ref
- Namrata Vaswani, Amit K. Roy Chowdhury, and Rama Chellappa. 2005. “Shape activity”: A continuous-state HMM for moving/deforming shapes with application to abnormal activity detection. IEEE Trans. Image Process. 14, 10 (2005), 1603--1616. Google ScholarDigital Library
- Ricardo Vilalta and Sheng Ma. 2002. Predicting rare events in temporal domains. In Proceedings of the ICDM. 474--481. Google ScholarDigital Library
- Junbo Wang, Zixue Cheng, Mengqiao Zhang, Yinghui Zhou, and Lei Jing. 2012. Design of a situation-aware system for abnormal activity detection of elderly people. In Proceedings of the 8th International Conference on Active Media Technology. Runhe Huang, Ali A. Ghorbani, Gabriella Pasi, Takahira Yamaguchi, Neil Y. Yen, and Beijing Jin (Eds.), vol. 7669, Springer, Berlin, 561--571. Google ScholarDigital Library
- Lingyu Wang, Anyi Liu, and Sushil Jajodia. 2006. Using attack graphs for correlating, hypothesizing, and predicting intrusion alerts. Comput. Commun. 29, 15 (2006), 2917--2933. Google ScholarDigital Library
- Gary M. Weiss and Haym Hirsh. 1998. Learning to predict rare events in event sequences. In KDD. 359--363.Google Scholar
- Tao Xiang and Shaogang Gong. 2008. Video behavior profiling for anomaly detection. IEEE Trans. Pattern Anal. Mach. Intell. 30, 5 (2008), 893--908. Google ScholarDigital Library
- Rui Xu and Donald C. Wunsch. 2005. Survey of clustering algorithms. IEEE Trans. Neural Netw. 16, 3 (2005), 645--678. Google ScholarDigital Library
- Jie Yin, Qiang Yang, and Jeffrey Junfeng Pan. 2008. Sensor-based abnormal human-activity detection. IEEE Trans. Knowl. Data Eng. 20, 8 (2008), 1082--1090. Google ScholarDigital Library
- Dong Zhang, Daniel Gatica-Perez, Samy Bengio, and Iain McCowan. 2005. Semi-supervised adapted HMMs for unusual event detection. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). Vol. 1, IEEE Computer Society, 611--618. Google ScholarDigital Library
- Xian-Xing Zhang, Hua Liu, Yang Gao, and Derek Hao Hu. 2009. Detecting abnormal events via hierarchical dirichlet processes. In Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining (PAKDD'O9). Thanaruk Theeramunkong, Boonserm Kijsirikul, Nick Cercone, and Tu Bao Ho (Eds.), Lecture Notes in computer science, vol. 5476, Springer, Berlin, 278--289. Google ScholarDigital Library
- Hua Zhong, Jianbo Shi, and Mirkó Visontai. 2004. Detecting unusual activity in video. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04). Vol. 4, 819--826. Google ScholarDigital Library
- Yue Zhou, Shuicheng Yan, and Thomas S. Huang. 2007. Detecting anomaly in videos from trajectory similarity analysis. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME'07). IEEE, 1087--1090.Google Scholar
Index Terms
- PADUA: Parallel Architecture to Detect Unexplained Activities
Recommendations
Towards unobtrusive detection and realistic attribute analysis of daily activity sequences using a finger-worn device
Detection and analysis of activities of daily living (ADLs) are important in activity tracking, security monitoring, and life support in elderly healthcare. Recently, many research projects have employed wearable devices to detect and analyze ADLs. ...
Augmenting motion sensing to improve detection of periods of unusual inactivity
HealthNet '08: Proceedings of the 2nd International Workshop on Systems and Networking Support for Health Care and Assisted Living EnvironmentsTwo sensing options are examined for their potential to improve the sensitivity of a system that detects periods of inactivity in the homes of elderly persons. A previous prototype used passive infrared motion sensors and door sensors combined with a ...
Activity Detection in Smart Home Environment
Detection of human activities is a set of techniques that can be used in wide range of applications, including smart homes and healthcare. In this paper we focus on activity detection in a smart home environment, more specifically on detecting entrances ...
Comments