A daily activity feature extraction approach based on time series of sensor events

Yong Liu; Hong Yang; Shanshan Gong; Yaqing Liu; Xingzhong Xiong; Yong Liu; Hong Yang; Shanshan Gong; Yaqing Liu; Xingzhong Xiong

doi:10.3934/mbe.2020280

Mathematical Biosciences and Engineering

2020, Volume 17, Issue 5: 5173-5189. doi: 10.3934/mbe.2020280

Previous Article Next Article

Research article

A daily activity feature extraction approach based on time series of sensor events

1.
Artificial Intelligence Key Laboratory of Sichuan Province, Sichuan University of Science and Engineering, Zigong 643000, China
2.
School of Information Science & Technology, Dalian Maritime University, Dalian 116026, China
3.
Key Laboratory of Higher Education of Sichuan Province for Enterprise Informationalization and Internet of Things, Zigong 643000, China

Received: 18 May 2020 Accepted: 24 July 2020 Published: 31 July 2020

Activity recognition benefits the lives of residents in a smart home on a daily basis. One of the aims of this technology is to achieve good performance in activity recognition. The extraction and selection of the daily activity feature have a significant effect on this performance. However, commonly used extraction of daily activity features have limited the performance of daily activity recognition. Based on the nature of the time series of sensor events caused by daily activities, this paper presents a novel extraction approach for daily activity feature. First, time tuples are extracted from sensor events to form a time series. Subsequently, several common statistic formulas are proposed to form the space of daily activity features. Finally, a feature selection algorithm is employed to generate final daily activity features. To evaluate the proposed approach, two distinct datasets are adopted for activity recognition based on four different classifiers. The results of the experiment reveal that the proposed approach is an improvement over the commonly used approach.
- daily activity recognition,
- feature extraction,
- smart home,
- time series
Citation: Yong Liu, Hong Yang, Shanshan Gong, Yaqing Liu, Xingzhong Xiong. A daily activity feature extraction approach based on time series of sensor events[J]. Mathematical Biosciences and Engineering, 2020, 17(5): 5173-5189. doi: 10.3934/mbe.2020280

Related Papers:

Abstract

Activity recognition benefits the lives of residents in a smart home on a daily basis. One of the aims of this technology is to achieve good performance in activity recognition. The extraction and selection of the daily activity feature have a significant effect on this performance. However, commonly used extraction of daily activity features have limited the performance of daily activity recognition. Based on the nature of the time series of sensor events caused by daily activities, this paper presents a novel extraction approach for daily activity feature. First, time tuples are extracted from sensor events to form a time series. Subsequently, several common statistic formulas are proposed to form the space of daily activity features. Finally, a feature selection algorithm is employed to generate final daily activity features. To evaluate the proposed approach, two distinct datasets are adopted for activity recognition based on four different classifiers. The results of the experiment reveal that the proposed approach is an improvement over the commonly used approach.

References

[1]	R. Bai, H. Y. Fan, J. F. Zhang, The effect of physical activity on cognitive function in older adults, Adv. Psychol. Sci., 19 (2011), 1777-1787.
[2]	P. N. Dawadi, D. J. Cook, M. Schmitter-Edgecombe, Automated cognitive health assessment using smart home monitoring of complex tasks, IEEE T. Syst. Man Cy-S., 43 (2013), 1302-1313.
[3]	S. Houidi, F. Auger, H. B. A. Sethomb, D. Fourer, L. Miègevillea, Multivariate event detection methods for non-intrusive load monitoring in smart homes and residential buildings, Energ. Buildings, 208 (2020).
[4]	S. Tanga, V. Kalavallya, K. Y. Nga, J. Parkkinen, Development of a prototype smart home intelligent lighting control architecture using sensors onboard a mobile computing system, Energ. Buildings, 138 (2017), 368-376.
[5]	Jordan D. Clark, Brennan D. Lessb, Spencer M. Duttonb, Iain S. Walkerb, Max H. Sherman, Efficacy of occupancy-based smart ventilation control strategies in energy efficient homes in the United States, Build. Environ., 156 (2019), 253-267.
[6]	K. D. Feuz, D. J. Cook, Collegial Activity Learning between Heterogeneous Sensors, Knowl. Inf. Syst., 53 (2017), 337-364.
[7]	S. Aminikhanghahi, T. Wang, D. J. Cook, Real-Time Change Point Detection with Application to Smart Home Time Series Data, IEEE T. Knowl. Data En., 31 (2019), 1010-1022.
[8]	W. Deng, J. Xu, Y. Song, H. Zhao, An effective improved co-evolution ant colony optimization algorithm with multi-strategies and its application, Int. J. Bio-Inspir. Com., 15 (2020), 1-10.
[9]	R. Chen, S. K. Guo, X. Z. Wang, T. L. Zhang, Fusion of multi-RSMOTE with fuzzy integral to classify bug reports with an imbalanced severity distribution, IEEE T. Fuzzy Syst., 27 (2019), 2406-2420.
[10]	J. Wan, M. J. O'Grady, G. M. P. O'Hare, Dynamic sensor event segmentation for real-time activity recognition in a smart home context, Pers. Ubiquit. Comput., 19 (2015), 287-301.
[11]	J. Guo, Y. Mu, M. D. Xiong, Y. Q. Liu, J. X. Gu, Activity feature solving based on TF-IDF for activity recognition in smart homes, Complexity, (2019).
[12]	H. Yang, S. Gong, Y. Liu, Z. Lin, Y. Qu, A Multi-task Learning Model for Daily Activity Forecast in Smart Home, Sensors-Basel, 20 (2020).
[13]	H. M. Zhao, H. D. Liu, J. J. Xu, W. Deng, Performance prediction using high-order differential mathematical morphology gradient spectrum entropy and extreme learning machine, IEEE T. Instrum. Meas., 69 (2019), 4165-4172.
[14]	W. Deng, H. M. Zhao, L. Zou, G. Y. Li, X. H. Yang, D. Q. Wu, A novel collaborative optimization algorithm in solving complex optimization problems, Soft Comput., 21 (2017), 4387-4398.
[15]	N. Yala, B. Fergani, A. Fleury, Towards improving feature extraction and classification for activity recognition on streaming data, J. Amb. Intel. Hum. Comp., 8 (2017), 177-189.
[16]	Y. Q. Liu, Y. Mu, K. Y. Chen, Y. M. Li, J. H. Guo, Daily activity feature selection in smart homes based on pearson correlation coefficient, Neural Process. Lett., 51 (2020), 1771-1787.
[17]	W. Deng, H. M. Zhao, X. H. Yang, J. X. Xiong, M. Sun, B. Li, Study on an improved adaptive PSO algorithm for solving multi-objective gate assignment, Appl. Soft Comput., 59 (2017), 288-302.
[18]	H. Zhao, J. Zheng, W. Deng, Y. Song, Semi-supervised broad learning system based on manifold regularization and broad network, IEEE T. Circuits-I, 67 (2020), 983-994.
[19]	Y. Q. Liu, X. X. Wang, Z. G. Zhai, R. Chen, B. Zhang, Y. Jiang, Timely daily activity recognition from headmost sensor events, ISA T., 94 (2019), 379-390.
[20]	L. Chen, C. Nugent, M. Mulvenna, D. Finlay, X. Hong, M. Poland, A logical framework for behaviour reasoning and assistance in a smart home, Int. J. Assist. Robot. Mechat., 9 (2008), 20-33.
[21]	D. Riboni, C. Bettini, COSAR: hybrid reasoning for context-aware activity recognition, Pers. Ubiquit. Comput., 15 (2011), 271-289.
[22]	L. Chen, C. D. Nugent, H. Wang, A knowledge-driven approach to activity recognition in smart homes, IEEE T. Knowl. Data En., 24 (2011), 961-974.
[23]	N. D. Rodríguez, M. P. Cuéllar, J. Lilius, et al., A survey on ontologies for human behavior recognition, ACM Comput. Surv., 46 (2014).
[24]	M. H. M. Noor, Z. Salcic, K. I-K. Wang, Enhancing ontological reasoning with uncertainty handling for activity recognition, Knowl. Inf. Syst., 114 (2016), 47-60.
[25]	G. Meditskos, S. Dasiopoulou, I. Kompatsiaris, MetaQ: A knowledge-driven framework for context-aware activity recognition combining SPARQL and OWL 2 activity patterns, Pervasive Mob. Comput., 25 (2016), 104-124.
[26]	G. Okeyo, L. Chen, H. Wang, R. Sterritt, Dynamic sensor data segmentation for real-time knowledge-driven activity recognition, Pervasive Mob. Comput., 10 (2014), 155-172.
[27]	O. Brdiczka, P. Reignier, J. L. Crowley, Detecting individual activities from video in a smart home, International Conference on Knowledge-Based Intelligent Informational and Engineering Systems (KES 2007), 2007, 363-370. Available from: https://link.springer.com/chapter/10.1007%2F978-3-540-74819-9_45.
[28]	D. J. Cook, M. Schmitter-Edgecombe, Assessing the quality of activities in a smart environment, Method. Inform. Med., 48 (2009), 480-485.
[29]	W. Deng, H. Liu, J. Xu, H. Zhao, Y. Song, An improved quantum-inspired differential evolution algorithm for deep belief network, IEEE T. Instrum. Meas., (2020). Available from: https://ieeexplore.ieee.org/document/9046849
[30]	U. Maurer, A. Rowe, A. Smailagic, Location and Activity Recognition Using eWatch: A Wearable Sensor Platform, Workshop on Ambient Intelligence in Everyday Life, 2005. Available from: https://link.springer.com/chapter/10.1007%2F11825890_4.
[31]	T. Van. Kasteren, A. Noulas, G. Englebienne, B. Kröse, Accurate activity recognition in a home setting, Proceedings of the 10th international conference on Ubiquitous computing (UbiComp 2008), 2008, 1-9. Available from: https://dl.acm.org/doi/10.1145/1409635.1409637.
[32]	T. B. Moeslund, A. Hilton, V. Krüger, A survey of advances in vision-based human motion capture and analysis, Comput. Vis. Image Und., 104 (2006), 90-126.
[33]	N. Oliver, A. Garg, E. Horvitz, Layered representations for learning and inferring office activity from multiple sensory channels, Comput. Vis. Image Und., 96 (2004), 163-180.
[34]	O. Brdiczka, J. L. Crowley, P. Reignier, Learning situation models in a smart home, IEEE T. Syst. Man Cy. B, 39 (2009), 56-63.
[35]	Y. Tong, R. Chen, J. Gao, Hidden State Conditional Random Field for Abnormal Activity Recognition in Smart Homes, Entropy-Switz., 17 (2015), 1358-1378.
[36]	F. A., Machot, S. Ranasinghe, J. Plattner, N. Jnoub, Human activity recognition based on real life scenarios, 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops 2018), 2018, 3-8. Available from: https://ieeexplore.ieee.org/document/8480138.
[37]	J. Wan, M. Li, M. OGrady, X. Gu, M. A. Alawlaqi, G. OHare, Time-bounded activity recognition for ambient assisted living, IEEE T. Emerg. Top. Com., (2018), Available from: https://ieeexplore.ieee.org/document/8464268.
[38]	J. Medina-Quero, S. Zhang, C. Nugent, M. Espinilla, Ensemble classifier of long short-term memory with fuzzy temporal windows on binary sensors for activity recognition, Expert Syst. Appl., 114 (2018), 441-453.
[39]	Y. Q. Liu, D. T. Ouyang, Y. Liu, R. Chen, A novel approach based on time cluster for activity recognition of daily living in smart homes, Symmetry-Basel, 9 (2017).
[40]	T. Gu, Z. Wu, X. Tao, H. K. Pung, J. Lu, epSCIAR: An emerging patterns based approach to sequential, interleaved and concurrent activity recognition, 7th Annual IEEE International Conference on Pervasive Computing and Communications (PerCom 2009), 2009. Available from: https://ieeexplore.ieee.org/document/4912776
[41]	P. Rashidi, D. J. Cook, Keeping the resident in the loop: Adapting the smart home to the user, IEEE T. Syst. Man Cy. A, 39 (2009), 949-959.
[42]	T. Huỳnh, B. Schiele, Unsupervised discovery of structure in activity data using multiple eigenspaces, 2nd International Workshop on Location- and Context-Awareness (LoCA 2006), 2006. 151-167. Available from: https://link.springer.com/chapter/10.1007%2F11752967_11.
[43]	J. Wen, M. Zhong, Z. Wang, Activity recognition with weighted frequent patterns mining in smart environments, Expert Syst. Appl., 42 (2015), 6423-6432.
[44]	S. Nasreen, M. A. Azam, U. Naeem, M. A. Ghazanfar, A. Khalid, Recognition framework for inferring activities of daily living based on pattern mining, Arab. J. Sci. Eng., 41 (2016), 3113-3126.
[45]	N. Twomey, D. Diethe, I. Craddock, I. Craddock, P. Flach, Unsupervised learning of sensor topologies for improving activity recognition in smart environments, Neurocomputing, 234 (2017), 93-106.
[46]	H. Y. Yatbaz, S. Eraslan, Y. Yesilada, E. Ever, Activity Recognition Using Binary Sensors for Elderly People Living Alone: Scanpath Trend Analysis Approach, IEEE Sens. J., 19 (2019), 7575-7582.
[47]	H. T. Malazi, M. Davari, Combining emerging patterns with random forest for complex activity recognition in smart homes, Appl. Intell., 48 (2018), 315-330.
[48]	N. Yala, B. Fergani, A. Fleury, Towards improving feature extraction and classification for activity recognition on streaming data, J. Amb. Intel. Hum. Comp., 8 (2017), 177-189.
[49]	G. L. Chen, A. G. Wang, S. H. Zhao, L. Liu, C. Y. Chang, Latent feature learning for activity recognition using simple sensors in smart homes, Multimed. Tools Appl., 77 (2018), 15201-15219.
[50]	A. R. Sanabria, T. W. Kelsey, S. Dobson, J. Ye, Representation learning for minority and subtle activities in a smart home environment, J. Amb. Intel. Smart En., 11 (2019), 495-513.
[51]	H. Alhakbani, M. M. Al-Rifaie, Feature Selection Using Stochastic Diffusion Search, Proceedings of the 2017 Genetic and Evolutionary Computation Conference (GECCO 2017), 2017, 385-392. Available from: https://dl.acm.org/doi/10.1145/3071178.3079193.
[52]	D. Cook, A. S. Crandall, B. L. Thomas, N. C. Krishnan, CASAS: A smart home in a box, Comput., 46 (2013), 62-69.
[53]	N. C. Krishnan, D. J. Cook, Activity recognition on streaming sensor data, Pervas. Mob. Comput., 10 (2014), 138-154.

Reader Comments

Your name:*

Email:*
© 2020 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)