Abstract
The main additional problem in activity recognition (AR) systems in contrast to traditional ones is the importance of duration: a predicted concept in AR is durative and can be correct in a period and incorrect in another one. Therefore, it is fundamental to extend the correctness vocabulary and to formalize a new evaluation system including these extensions. Even in similar areas, few empirical attempts are proposed which are confronted with the problems of correctness and completeness. In this paper, we propose the first formal multi-modal evaluation approach for durative concepts. This novel mathematical method evaluates the performance of an AR system from multiple perspectives, including detection, total duration, relative duration, boundary alignment, and uniformity. It extracts the properties considered in the state-of-the-art and redefines the well-known true-positive, false-positive and false-negative terms for durative events. Our proposed method is extensible, interpretable, customizable, open source and improves the expressiveness of the evaluation while its computation complexity remains linear. Comprehensive experimental evaluations are conducted to show the usefulness of our proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
\(\mathrm {overfill}_{\mathrm {start}}\!\mathrm {(r,ps)}\!=\!\mathrm {max}\mathrm {(0,start(r)}-\mathrm {start(ps))}\quad \mathrm {underfill}_{\mathrm {start}}\!(\mathrm {r}\!,\mathrm {ps})\!=\!\mathrm {max}\mathrm {(0},\!\mathrm {start(ps)}\!-\!\mathrm {start(r))}\)
\(\mathrm {overfill}_{\mathrm {end}}\mathrm {(r,ps)}=\mathrm {max}\mathrm {(0,end(ps)}-\mathrm {end(r))}\qquad \mathrm {underfill}_{\mathrm {end}}\mathrm {(r,ps)}\!=\!\mathrm {max}\mathrm {(0,end(r)}-\mathrm {end(ps))}\).
- 2.
We use feature extraction in [13] and three layers perceptron for classifier step.
- 3.
The internal steps are not important since the concentration is on the metrics.
- 4.
For saving the space, the analysis of other classes are existed in our repository.
- 5.
If the used segmentation algorithm generates more segments for longer events which is the case with the well-used sliding window method.
References
Alemdar, H., Tunca, C., Ersoy, C.: Daily life behaviour monitoring for health assessment using machine learning: bridging the gap between domains. Pers. Ubiquit. Comput. 19(2), 303–315 (2014). https://doi.org/10.1007/s00779-014-0823-y
Asghari, P., Soleimani, E., Nazerfard, E.: Online human activity recognition employing hierarchical hidden Markov models. J. Ambient. Intell. Humaniz. Comput. 11(3), 1141–1152 (2020). https://doi.org/10.1007/s12652-019-01380-5
Awad, G., et al.: TRECVID 2020: a comprehensive campaign for evaluating video retrieval tasks across multiple application domains. In: Proceedings of TRECVID, pp. 1–55. NIST, USA (2021)
Bilen, C., Ferroni, G., Tuveri, F., Azcarreta, J., Krstulovic, S.: A framework for the robust evaluation of sound event detection. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 61–65 (2020). https://doi.org/10.1109/ICASSP40776.2020.9052995
Cook, D.J., Narayanan, C.K.: Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data. Wiley Series on Parallel and Distributed Computing, 1st edn. Wiley (2015)
Dutta, J., Banerjee, B.: Online detection of abnormal events using incremental coding length. In: AAAI Conference on Artificial Intelligence (2015). https://ojs.aaai.org/index.php/AAAI/article/view/9799
Fu, T.C.: A review on time series data mining. Eng. Appl. Artif. Intell. 24(1), 164–181 (2011). https://doi.org/10.1016/j.engappai.2010.09.007
Gjoreski, H., et al.: Competitive live evaluations of activity-recognition systems. IEEE Pervasive Comput. 14(1), 70–77 (2015). https://doi.org/10.1109/MPRV.2015.3
Hein, A., Kirste, T.: Generic performance metrics for continuous activity recognition. In: Bach, J., Edelkamp, S. (eds.) KI 2011. LNCS (LNAI), vol. 7006, pp. 139–143. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-24455-1_13
Hwang, W.S., Yun, J.H., Kim, J., Kim, H.C.: Time-series aware precision and recall for anomaly detection. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 2241–2244. ACM, New York (2019). https://doi.org/10.1145/3357384.3358118
Ionescu, R.T., Khan, F.S., Georgescu, M.I., Shao, L.: Object-centric auto-encoders and dummy anomalies for abnormal event detection in video. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2019-June, pp. 7834–7843. IEEE (2019). https://doi.org/10.1109/CVPR.2019.00803, https://ieeexplore.ieee.org/document/8954309/
Kasteren, T.V., Alemdar, H., Ersoy, C.: Effective performance metrics for evaluating activity recognition methods. In: ARCS (2011)
Krishnan, N.C., Cook, D.J.: Activity recognition on streaming sensor data. Pervasive Mobile Comput. 10(PART B), 138–154 (2014). https://doi.org/10.1016/j.pmcj.2012.07.003
Lavin, A., Ahmad, S.: Evaluating real-time anomaly detection algorithms - the Numenta Anomaly Benchmark. In: IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 38–44. IEEE (2015). https://doi.org/10.1109/ICMLA.2015.141, http://ieeexplore.ieee.org/document/7424283/
Lu, Y., Kumar, K.M., Nabavi, S.S., Wang, Y.: Future frame prediction using convolutional VRNN for anomaly detection. In: IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE (2019). https://doi.org/10.1109/AVSS.2019.8909850
Mesaros, A., Heittola, T., Virtanen, T.: Metrics for polyphonic sound event detection. Appl. Sci. (Switzerland) 6(6) (2016). https://doi.org/10.3390/app6060162
Minnen, D., Westeyn, T.L., Starner, T., Ward, J.A., Lukowicz, P.: Performance metrics and evaluation issues for continuous activity recognition. In: Performance Metrics for Intelligent Systems, pp. 141–148. NIST, Gaithersburg (2006)
Modaresi, S., Osmani, A., Razzazi, M., Chibani, A.: Multimodal evaluation method for sound event detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP). IEEE (2022)
Ni, Q., García Hernando, A., de la Cruz, I.: The elderly’s independent living in smart homes: a characterization of activities and sensing infrastructure survey to facilitate services development. Sensors 15(5), 11312–11362 (2015). https://doi.org/10.3390/s150511312
NIST: TRECVID 2004 Evaluation (2004). https://www-nlpir.nist.gov/projects/tv2004/index.html
Osmani, A.: STCSP: a representation model for sequential patterns. Foundations and Applications of Spatio-Temporal Reasoning (FASTR) (2003). https://www.aaai.org/Library/Symposia/Spring/2003/ss03-03-010.php
Perera, C., Zaslavsky, A., Christen, P., Georgakopoulos, D.: Context aware computing for the Internet of Things: a survey. IEEE Commun. Surv. Tutor. 16(1), 414–454 (2014). https://doi.org/10.1109/SURV.2013.042313.00197, http://ieeexplore.ieee.org/document/6512846/
Qian, H., Pan, S.J., Miao, C.: Latent independent excitation for generalizable sensor-based cross-person activity recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 13, pp. 11921–11929 (2021). https://ojs.aaai.org/index.php/AAAI/article/view/17416
Ross, R.J., Kelleher, J.: Accuracy and timeliness in ML based activity recognition. In: Proceedings of the 13th AAAI Conference on Plan, Activity, and Intent Recognition, AAAIWS’13-13, vol. WS-13-13, pp. 39–46. AAAI Press (2013). https://doi.org/10.5555/2908241.2908247
Stowell, D., Giannoulis, D., Benetos, E., Lagrange, M., Plumbley, M.D.: Detection and classification of acoustic scenes and events. IEEE Trans. Multimedia 17(10), 1733–1746 (2015). https://doi.org/10.1109/TMM.2015.2428998
Tatbul, N., Lee, T.J., Zdonik, S., Alam, M., Gottschlich, J.: Precision and recall for time series. In: Neural Information Processing Systems (NIPS) (2018). https://papers.nips.cc/paper/7462-precision-and-recall-for-time-series
Ward, J.A., Lukowicz, P., Gellersen, H.W.: Ward: performance metrics for activity recognition. ACM Trans. Intell. Syst. Technol. (2011). https://doi.org/10.1145/1889681.1889687
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Modaresi, S.M.R., Osmani, A., Razzazi, M., Chibani, A. (2022). Uniform Evaluation of Properties in Activity Recognition. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13281. Springer, Cham. https://doi.org/10.1007/978-3-031-05936-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-05936-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05935-3
Online ISBN: 978-3-031-05936-0
eBook Packages: Computer ScienceComputer Science (R0)