Full text of article: Russian language.

 PDF

Abstract:
This paper considers a problem of improving the accuracy of identifying human activity in buildings based on an ecological feature space. To solve this problem a model of logistic regression was implemented on the assumption of the unstable estimation of logistic regression parameters for near linearly separable classes. To reach a compromise between the presence of outliers and the accuracy of recognition an algorithm of anomaly detection was proposed. Computational experiments confirmed the effectiveness of the algorithm and its theoretical consistency.

Keywords:
anomaly detection, logistic regression, machine learning, Cox-Box transformation, detection system, ecological feature.

Citation:
Kulikovskikh IM. Anomaly detection in an ecological feature space to improve the accuracy of human activity identification in buildings. Computer Optics 2017; 41(1): 126-133. – DOI: 10.18287/2412-6179-2017-41-1-126-133.

References:

1. Dubski R, Kastek M, Trzaskawka P, Piatkowski T, Szustakowski M, Zyczkowski M. Concept of data processing in multi-sensor systems for perimeter protection. Proc SPIE 2011; 8019: 8019X. DOI: 10.1117/12.883965.
2. Epifantsev BN, Pyatkov AA, Kopeykin SA. Multi-sensor systems for monitoring access to restricted areas: capabilities of the intrusion detection video analytical channel. Computer Optics 2016; 40(1): 121-129. DOI: 10.18287/2412-6179-2016-40-1-121-129.
3. Soucek B, Carlson A.D. Computers in Neurobiology and Behaviour. New York: John Wiley & Sons; 1976. ISBN: 978-0471813897.
4. Soucek B, Prokhorov S. Event-train correlation and real-time microcomputer systems. Microprocessing and Microprogramming 1983; 11(1): 23-29. DOI: 10.1016/0165-6074(83)90161-8.
5. Candanedo LM, Feldheim V. Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models. Energy and Buildings 2016; 112: 28-39. DOI: 10.1016/j.enbuild.2015.11.071.
6. Chen Z, Masood MK, Soh YC. A fusion framework for occupancy estimation in office buildings based on environmental sensor data. Energy and Buildings 2016; 133: 790-798. DOI: 10.1016/j.enbuild.2016.10.030.
7. Erickson VL, Carreira-Perpi><n MA, Cerpa AE. OBSERVE: Occupancy-based system for efficient reduction of HVAC energy. Proc 10th IEEE International Conference on Information Processing in Sensor Networks (IPSN). Stockholm, Sweden 2011: 258-269.
8. Erickson VL, Carreira-Perpi><n MA, Cerpa AE. Occupancy modeling and prediction for building energy management. ACM Transactions on Sensor Networks (TOSN) 2014; 10(3): 42. DOI: 10.1145/2594771.
9. Dong B, Andrews B. Sensor-based occupancy behavioral pattern recognition for energy and comfort management in intelligent buildings. Source: <www.ibpsa.org/proceedings/BS2009/BS09_1444_1451.pdf >.
10. Lam KP, Höynck M, Dong B, Andrews B, Chiou YS, Zhang R, Benitez D, Choi J. Occupancy detection through an extensive environmental sensor network in an open-plan office building. IBPSA Building Simulation 2009: 1452-1459.
11. Hailemariam E, Goldstein R, Attar R, Khan A. Real-time occupancy detection using decision trees with multiple sensor types. SimAUD’11 2011: 141-148.
12. Yang Z, Li N, Becerik-Gerber B, Orosz M. A multi-sensor based occupancy estimation model for supporting demand driven HVAC operations. SimAUD’12 2012: 49-56.
13. Vorontsov KV. Mathematical methods for supervised learning (machine learning theory) [In Russian]. Source: <http://www.machinelearning.ru/wiki/images/6/6d/Voron-ML-1.pdf>
14. Brax A, Niklasson L, Laxhammar R. An ensemble approach for increased anomaly detection performance in video surveillance data. FUSION ’09 2009: 694-701.
15. Saini DK, Ahir D, Ganatra A. Techniques and challenges in building intelligent systems: anomaly detection in camera surveillance. 1st International Conference on Information and Communication Technology for Intelligent Systems: Volume 2, Smart Innovation, Systems and Technologies 51 2016; 1: 11-21. DOI: 10.1007/978-3-319-30927-9_2.
16. Gashnikov MV, Glumov NI, Kuznetsov AV, Mitekin VA, Myasnikov VV, Sergeev VV. Hyperspectral remote sensing data compression and protection. Computer Optics 2016; 40(5): 689-712. DOI: 10.18287/2412-6179-2016-40-5-689-712.
17. Xu Y, Wu Z, Li J, Plaza A, Wei Z. Anomaly detection in hyperspectral images based on low-rank and sparse representation. IEEE Trans on Geoscience and Remote Sensing 2016; 54(4): 1990-2000. – DOI: 10.1109/TGRS.2015. 2493201.
18. Zhao R, Du B, Zhang L, Zhang L. Beyond background feature extraction: An anomaly detection algorithm inspired by slowly varying signal analysis. IEEE Trans on Geoscience and Remote Sensing 2016; 54(3): 1757-1774. DOI: 10.1109/TGRS.2015.2488285.
19. G?rnitz N, Kloft M, Rieck K, Brefeld U. Toward supervised anomaly detection. Journal of Artificial Intelligence Research 2013; 46: 235-262. DOI: 10.1613/jair.3623.
20. Goldstein M, Uchida S. A Comparative evaluation of unsupervised anomaly detection algorithms for multivariate data. PLoS One 2016; 11(4): e0152173. DOI: 10.1371/journal.pone.0152173.
21. Petrenko SA. Methods of intrusion detection and anomaly detection for cybersystems. Proceedings of ISA RAS 2009; 41: 194-202.
22. Kiryati N, Raviv TR, Ivanchenko Y, Rochel S. Real time abnormal motion detection in surveillance video. ICPR 2008. DOI: 10.1109/ICPR.2008.4761138.
23. Buch N, Velastin S. Local feature saliency classifier for real-time intrusion moitoring. Optical Engineering 2014; 53(7): 073108. DOI: 10.1117/1/OE.53.7.073108.
24. Nedelko VM. Regression models in classification problems. Siberian Journal of Industrial Mathematics 2014; 17(1): 86-98.
25. Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: Data mining, inference, and prediction: 2nd ed. New York, NY, USA: Springer Science+Business Media; 2013. ISBN: 978-0387848570.
26. UCI Machine Learning Repository. Occupancy Detection Data Set. Source: <https://archive.ics.uci.edu/ml/datasets/Oc­cupancy+Detection+>.
27. Kulikovskikh IM. Feature extraction to detect occupancy in buildings using ecological factors. Proceedings of SSC RAS 2016; 18(4): 754-759.
28. Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters 2006; 27(8): 861-874. DOI: 10.1016/j.patrec.2005.10.010.
29. Van Rijsbergen CJ. Information Retrieval: 2nd ed. London: Butterworths-Heinemann; 1979. ISBN: 978-0408709294.
30. Box GEP, Cox DR. An analysis of transformations. Journal of the Royal Statistical Society. Series B (Methodological) 1964; 26(2): 211-252.

---

© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: journal@computeroptics.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-20