||Development of a Smart Home Care System Based on Wireless Communication Technology and Low Frequency Ultrasonic Sensor
||Department of BioMedical Engineering
Smart home care
Low frequency ultrasonic sensor
4G mobile communication technology
結果表明，為了減少兩組超音波感測器偵測之間的重疊區域，兩組傳感器必須分別向外旋轉一定角度來區別兩顆超音波探頭發射出的波束，但兩組傳感器之間會有一些無法檢測到的死角，所以要測試的區域需要距離設備20cm以避開死角。此研究中使用4公尺之步行速度偵測裝置之精準度，並且在一般步行速度（<2 m / s）下，測量精度可以達到幾乎100%。最後，意外事故監測系統的技術不僅可以使用在獨居老人之家庭安全。該設備還可用於病房內，或移動不便的人。
Due to the trend of declining birthrate, the increase of solitary elderly number has greatly increased the possibility of accidents when no one is taking care of them. According to Ministry of Health and Welfare reports, the number of elderly people living alone in Taiwan exceeded 40,000 in 2018, and there were more than 2,000 cases of accidental death. According to the statistics, there are high-risk groups of accidental deaths, mostly those with limited mobility or those without family members. Although it is now feasible to monitor the user's activity by installing a camera, the camera has doubts about privacy violations. Therefore, the development of a simple accident monitoring system, which is cheap and easy to install, has become an important project for the safety of solitary living.
Accidents often occur to solitary elderly falls at home and already die when they are discovered a few days later. It’s common that solitary elderly dies in his own home. Most of these people seldom contact their family or neighbors after dying for a while, it was discovered by neighbors because of the stench of rot. In order to monitor the accidents of solitary elderly, smart home care is a major issue nowadays. A common alarm device nowadays, such as an emergency button placed in a toilet, but if the user falls in the toilet or even falls into a coma, he cannot press the emergency call button for help. There is no early warning system in current field. Therefore, it is very important that the accident monitoring system can calculate the time spent indoors and issue a warning.
The study proposes an accident monitoring system that does not need to be worry about any privacy invading concern. The home is divided into a plurality of space areas, for example, divided into two rooms, a living room and a toilet, and it is determined whether there is an abnormality by detecting the area where the user is currently located. The system uses two pairs of ultrasonic sensors to detect if someone is entering or leaving the room or toilet, then connecting all devices by wireless communication technology and calculating the time the user spends indoors. In this system, Bluetooth is used to transmit the data of the monitoring equipment in each room to the receiving end. The receiving end of the system can set a time. If the time of entering the room exceeds the preset warning time, the guardian can receive the emergency notification, and the system can send an alarm message to the family through the SIM7600CE chip of the 4G wireless communication technology.
The results indicated that in order to reduce the overlap between the two sets of ultrasonic sensor, these two sensors must be rotated outward by a certain angle to distinguish the beams emitted by the two ultrasonic sensors. There are some undetectable blind angles between the two sets of sensors, so tested area requires at least 20 cm away from the device to avoid blind angles. In this study, 4 meters of walking speed detection was used. At a normal walking speed (<2 m/s), the measurement accuracy can achieve a high accuracy. Finally, the technology of the smart home care accident monitoring system may not only use in the home safety, but also for use in wards or people with limited mobility.
List of Figures VIII
List of Tables X
Chapter 1 Introduction 1
1.1 Statistics on Elderly People Living Alone 1
1.2 The Background of the Accident 3
1.2.1 Fall and Fainting 4
1.3 Accident Detection Equipment and Systems 5
1.3.1 Image Monitoring Device 5
1.3.2 Wearable Device 6
1.3.3 Environmental Sensor 8
1.4 Literature Review 11
1.4.1 Problems Under Realistic Conditions 11
1.4.2 Personal Privacy 12
1.4.3 Comparison of Environmental Sensors 13
1.5 Motivation and Aim 14
Chapter 2 Material and Methods 15
2.1 System Configuration 15
2.2 System Structure 16
2.2.1 Inward and Outward Movement Detecting Device 16
2.2.2 Wireless Communication Control Unit 22
2.3 Experimental Design 25
2.3.1 Detection Area 26
2.3.2 Detection Test 27
2.4 Algorithm 30
Chapter 3 Results and Discussion 32
3.1 Algorithm Testing 32
3.1.1 Raw Data 32
3.1.2 Data Analysis and Correction 33
3.2 Accuracy 38
3.3 Device Appearance and Verification 40
3.4 Transmit and Receive Message 42
3.5 System Automatic Calibration 46
Chapter 4 Conclusion 47
Appendix I 51
Appendix II 53
Appendix III 55
Appendix IV 56
 R. O. C. T. Ministry of Health and Welfare, "The Service Conditions for Elders Living Alone 2018," 2019.
 L. Z. Rubenstein and K. R. Josephson, "The epidemiology of falls and syncope," Clinics in geriatric medicine, vol. 18, no. 2, pp. 141-158, 2002.
 L. Z. Rubenstein, "Falls in older people: epidemiology, risk factors and strategies for prevention," Age and ageing, vol. 35, no. suppl_2, pp. ii37-ii41, 2006.
 E. B. Hitcho et al., "Characteristics and circumstances of falls in a hospital setting," Journal of general internal medicine, vol. 19, no. 7, pp. 732-739, 2004.
 M. E. Tinetti, W.-L. Liu, and E. B. Claus, "Predictors and prognosis of inability to get up after falls among elderly persons," Jama, vol. 269, no. 1, pp. 65-70, 1993.
 R. Elanchezhian et al., "Low glucose under hypoxic conditions induces unfolded protein response and produces reactive oxygen species in lens epithelial cells," Cell death & disease, vol. 3, no. 4, p. e301, 2012.
 M. C. Nevitt, S. R. Cummings, and E. S. Hudes, "Risk factors for injurious falls: a prospective study," Journal of gerontology, vol. 46, no. 5, pp. M164-M170, 1991.
 C. Rougier, J. Meunier, A. St-Arnaud, and J. Rousseau, "Robust video surveillance for fall detection based on human shape deformation," IEEE Transactions on circuits and systems for video Technology, vol. 21, no. 5, pp. 611-622, 2011.
 Z. Fu, T. Delbruck, P. Lichtsteiner, and E. Culurciello, "An address-event fall detector for assisted living applications," IEEE Transactions on Biomedical Circuits and Systems, vol. 2, no. 2, pp. 88-96, 2008.
 G. Mastorakis and D. Makris, "Fall detection system using Kinect’s infrared sensor," Journal of Real-Time Image Processing, vol. 9, no. 4, pp. 635-646, 2014.
 R. Cucchiara, A. Prati, and R. Vezzani, "A multi‐camera vision system for fall detection and alarm generation," Expert Systems, vol. 24, no. 5, pp. 334-345, 2007.
 T. Lee and A. Mihailidis, "An intelligent emergency response system: preliminary development and testing of automated fall detection," Journal of telemedicine and telecare, vol. 11, no. 4, pp. 194-198, 2005.
 N. Thome, S. Miguet, and S. Ambellouis, "A real-time, multiview fall detection system: A LHMM-based approach," IEEE transactions on circuits and systems for video technology, vol. 18, no. 11, pp. 1522-1532, 2008.
 M.-C. Su, J.-W. Liao, P.-C. Wang, and C.-H. Wang, "A smart ward with a fall detection system," in Environment and Electrical Engineering and 2017 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), 2017 IEEE International Conference on, pp. 1-4, 2017.
 A. Edgcomb and F. Vahid, "Privacy perception and fall detection accuracy for in-home video assistive monitoring with privacy enhancements," ACM SIGHIT Record, vol. 2, no. 2, pp. 6-15, 2012.
 邓正隆, "惯性技术," 哈尔滨工业大学出版社, 2006.
 K. Culhane, M. O’connor, D. Lyons, and G. Lyons, "Accelerometers in rehabilitation medicine for older adults," Age and ageing, vol. 34, no. 6, pp. 556-560, 2005.
 A. Brajdic and R. Harle, "Walk detection and step counting on unconstrained smartphones," in Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing, pp. 225-234, 2013.
 N. Noury et al., "Fall detection-principles and methods," in Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE, pp. 1663-1666, 2007.
 F. Bagalà et al., "Evaluation of accelerometer-based fall detection algorithms on real-world falls," PloS one, vol. 7, no. 5, p. e37062, 2012.
 S. Tao, M. Kudo, and H. Nonaka, "Privacy-preserved behavior analysis and fall detection by an infrared ceiling sensor network," Sensors, vol. 12, no. 12, pp. 16920-16936, 2012.
 M. Pouliot, V. Joshi, J. Chauvin, R. Goubran, and F. Knoefel, "Differentiating assisted and unassisted bed exits using ultrasonic sensor," in Instrumentation and Measurement Technology Conference (I2MTC), 2012 IEEE International, pp. 1104-1108, 2012.
 R. Igual, C. Medrano, and I. Plaza, "Challenges, issues and trends in fall detection systems," Biomedical engineering online, vol. 12, no. 1, p. 66, 2013.
 R. Hegde, B. Sudarshan, S. Kumar, S. Hariprasad, and B. Satyanarayana, "Technical advances in fall detection system—a review," Int. J. Comput. Sci. Mob. Comput, vol. 2, pp. 152-160, 2013.
 M. Mubashir, L. Shao, and L. Seed, "A survey on fall detection: Principles and approaches," Neurocomputing, vol. 100, pp. 144-152, 2013
 S. Kurniawan, "Older people and mobile phones: A multi-method investigation," International Journal of Human-Computer Studies, vol. 66, no. 12, pp. 889-901, 2008.
 C. Drost, "Privacy in context-aware systems," University of Twente, Enschede, Netherlands, Department of Informatics, Federal University of Espirito Santo, Vitoria, Brazil. Retrieved November, vol. 5, p. 2011, 2004.
 A. Cavoukian, A. Mihailidis, and J. Boger, "Sensors and in-home collection of health data: A privacy by design approach," Information and Privacy Commissioner, Tech. Rep, 2010.