Abstract
Wandering is a significant indicator in the clinical diagnosis of dementia and other related diseases for elders. Reliable monitoring of long-term continuous movement in indoor setting for detection of wandering movement is challenging because most elders are prone to forget to carry or wear sensors that collect motion information daily due to their declining memory. Wi-Fi as an emerging sensing modality has been widely used to monitor human indoor movement in a non-invasive manner. In order to continuously monitor individuals’ indoor motion and reliably identify wandering movement in a non-invasive manner, in this work, we develop a LSTM-based deep classification method that is able to differentiate the wandering-caused Wi-Fi signal change from the others. Specifically, we first use the off-the-shelf Wi-Fi devices to capture a resident’s indoor motion information, enabling to collect a group of Wi-Fi signal streams, which will be split into variable-size segments. Second, the deep network LSTM is adopted to develop wandering detection method that is able to classify every variable-size segment of Wi-Fi signals into categories according to the well-known wandering spatiotemporal patterns. Last, experimental evaluation conducted on a group of real-world Wi-Fi signal streams shows that our proposed LSTM-based detection method is workable and effective to identify indoor wandering behavior, obtaining an average value of 0.9286, 0.9618, 0.9634 and 0.9619 for accuracy, precision, recall and F-1 score, respectively.
Similar content being viewed by others
References
Fjellman-Wiklund A, Nordin E, Skelton D A, Lun-din-Olsson L. Reach the person behind the dementia — physical therapists’ reflections and strategies when composing physical training. PLoS ONE, 2016, 11(12): e0166686
Teri L, Larson E B, Reifler B V. Behavioral disturbance in dementia of the Alzheimer’s type. Journal of the American Geriatrics Society, 1988, 36: 1–6
Siders C, Nelson A, Brown L M, Joseph I, Ver-bosky-Cadena S. Evidence for implementing non-pharmacological interventions for wandering. Rehabilitation Nursing, 2004, 29(6): 195–206
Vassallo M, Poynter L, Sharma J C, Kwan J, Allen S C. Fall risk-assessment tools compared with clinical judgment: an evaluation in a rehabilitation ward. Age and Ageing, 2008, 37(3): 277–281
Vuong N K, Chan S, Lau C T. Application of ma-chine learning to classify dementia wandering patterns. Gerontechnology, 2014, 13(2): 294
Taft L B, Delaney K, Seman D, Stansell J. Dementia care creating a therapeutic milieu. Journal of Gerontological Nursing, 1993, 19(10): 30–39
Coltharp W J, Richie M F, Kaas M J. Wandering. Journal of Gerontological Nursing, 1996, 22(11): 5–10
Cohen-Mansfield J, Werner P. The effects of an enhanced environment on nursing home residents who pace. Gerontologist, 1998, 38(2): 199–208
Lin Q, Zhang D Q, Chen L M, Ni H B, Zhou X S. Managing elders’ wandering behavior using sensors-based solutions: a survey. International Journal of Gerontology, 2014, 8(2): 49–55
Taub D M, Lupton E C, Hinman R T, Leeb S, Zeisel J, Blackler S. The escort system: a safety monitor for people living with Alzheimer’s disease. IEEE Pervasive Computing, 2011, 10(2): 68–77
Lin Q, Liu X S, Wang W L. GPS trajectories based personalized safe geofence for elders with dementia. In: Proceedings of IEEE IEEE Smart-World, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation. 2018, 505–514
Doughty K, Williams G, King P J, Woods R. DIANA—a telecare system for supporting dementia sufferers in the community. In: Proceedings of International Conference of the IEEE Engineering in Medicine & Biology Society. 2002, 1980–1983
Masuda Y, Yoshimura T, Nakajima K, Nambu M, Tamura T. Unconstrained monitoring of prevention of wandering the elderly. In: Proceedings of Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society. 2002, 1906–1907
Jit B, Zhang D Q, Qiao G P, Foo V, Qiu Q, Yap H. A system for activity monitoring and patient tracking in a smart hospital. In: Proceedings of International Conference on Smart Homes and Health Telematics. 2006, 196–203
Lin Q, Liu X S, Zhao W C, Wang W L. Active IR sensor based solution for discovering wandering-related rhythmical repetition of motion events. Sensor Letters, 2018, 16(7): 517–528
Ota K, Ota Y, Otsu M, Kajiwara A. Elderly-care motion sensor using UWB-IR. In: Proceedings of Sensors Applications Symposium. 2011, 159–162
Wu X G, Chu Z B, Yang P L, Xiang C C, Zheng X, Huang W C. TW-See: human activity recognition through the wall with commodity Wi-Fi devices. IEEE Transactions on Vehicular Technology, 2019, 68(1): 306–319
Arshad S, Feng C H, Liu Y H, Hu Y P, Liu H. Wi-chase: a WiFi based human activity recognition system for sensor-less environments. In: Proceedings of International Symposium on World of Wireless, Mobile and Multimedia Networks. 2017, 1–6
Guo L L, Wang L, Liu J L, Zhou W. HuAc: human activity recognition using crowdsourced WiFi signals and skeleton data. Wireless Communications and Mobile Computing, 2018, 2018: 1–15
Li H, He X, Chen X K, Fang Y, Fang Q. Wi-Motion: a robust human activity recognition using WiFi signals. IEEE Access, 2019, 7: 153287–153299
Zhang L, Wang C, Ma M D, Zhang D Q. WiDIGR: direction-independent gait recognition system using commercial Wi-Fi devices. IEEE Internet of Things Journal, 2020, 7(2): 1178–1191
Zhang D Q, Wang H, Wu D. Toward centimeter-scale human activity sensing with Wi-Fi signals. IEEE Computer, 2017, 50(1): 48–57
Hoang M T, Yuen B, Dong X D, Lu T, Westendorp R, Reddy K. Recurrent neural networks for accurate RSSI indoor localization. IEEE Internet of Things Journal, 2019, 6(6): 10639–10651
Hsieh H Y, Prakosa S W, Leu J S. Towards the implementation of recurrent neural network schemes for Wi-Fi fingerprint-based indoor positioning. In: Proceedings of IEEE Vehicular Technology Conference. 2018, 1–5
Kianoush S, Savazzi S, Nicoli M. Device-free crowd sensing in dense WiFi MIMO networks: channel features and machine learning tools. In: Proceedings of the 15th Workshop on Positing, Navigation and Communications. 2018, 1–6
Zou H, Zhou Y X, Yang J F, Jiang H. DeepSense: device-free human activity recognition via autoen-coder long-term recurrent convolutional network. In: Proceedings of IEEE International Conference on Communications. 2018, 1–6
Martino-Saltzman D, Blasch B B, Morris R D, McNeal L W. Travel behavior of nursing home residents perceived as wanderers and nonwanderers. Gerontologist, 1991, 31: 666–672
Zhou Z M, Yang Z, Wu C S, Shangguan L F, Liu Y H. Omnidirectional coverage for device-free passive human detection. IEEE Transactions on Parallel and Distributed Systems, 2014, 25(7): 1819–1829
Algase D, Moore D H, Vandeweerd C, Ga-vin-Dreschnack D J. Mapping the maze of terms and definitions in dementia-related wandering. Aging and Mental Health, 2007, 11: 686–698
Algase D. Wandering: a dementia-compromised behavior. Journal of Gerontological Nursing, 1999, 25: 10–16
Qian K, Wu C S, Zhang Y, Zhang G D, Liu Y H. Widar2.0: passive human tracking with a single Wi-Fi link. In: Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services. 2018, 350–361
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735–1780
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014, arXiv preprint arXiv:1409.1556
Acknowledgements
This work was funded by the Fundamental Research Funds for the Central Universities (31920210013), the National Natural Science Foundation of China (Grant No. 61562075), the Natural Science Foundation of Gansu Province (20JR5RA511, 1506RJZA269), the Gansu Provincial First-class Discipline Program of Northwest Minzu University (11080305), and the Program for Innovative Research Team of SEAC ([2018] 98).
Author information
Authors and Affiliations
Corresponding author
Additional information
Qiang Lin received the PhD degree in computer science and technology from Northwestern Polytechnical University, China in 2014. He is currently an associate professor at School of Mathematics and Computer Science, Northwest Minzu University, China. His research interest includes medical image computing, pervasive computing, intelligent information processing and human behavior sensing.
Yusheng Hao received the MS degree in computer system architecture from Lanshou Jiaotong University, China in 2014. He is currently an senior lecturer at School of Mathematics and Computer Science, Northwest Minzu University, China. His research interest includes human behavior sensing, pervasive computing, intelligent information processing and human behavior sensing.
Caihong Liu received the MS degree in computer application technique from Lanzhou University of Technology, China in 2006. She is currently associate professor at School of Mathematics and Computer Science, Northwest Minzu University, China. Her research interest includes human behavior sensing, wireless senosr networks, and data mining.
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Lin, Q., Hao, Y. & Liu, C. Wi-Fi based non-invasive detection of indoor wandering using LSTM model. Front. Comput. Sci. 15, 156505 (2021). https://doi.org/10.1007/s11704-020-0270-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11704-020-0270-z