The aim of our study is to develop smart healthcare system utilizing Internet of Things (IoT) technology. The first IoT system we proposed is based on position-based mesh network (PBMN) and analysis of big data. The PBMN is combing wearable gadget with various kinds of contact sensors. The wearable gadget along with Bluetooth Low Energy (BLE) and Wi-Fi connections, gather physiological information from aging people and transmit it to the cloud. Care provider or the family members is able to conveniently access this data through web pages on the computers or apps on tablets and smartphones. It enables real-time monitoring of the aging individuals' positions and behavioral mode. Our system's capability to detect the health risks, especially for the elderly, is particularly valuable. The utilization of analysis of big data focuses on collecting and analyzing health information from the tagged individuals. With the system's ability to obtain physiological information through BLE devices and run analytics, it can estimate disease risks and develop customized treatment strategies based on this continuously monitored physiological information and long-term analyzed reports for each user. The results show that the participant spent much time (65.1%) sitting on a chair with a relatively low daily moving distance (61.34 m in 8 h). Stationary lifestyle is not good to the wellbeing. Three persons (15%) exhibited a restless behavior pattern. Timely referral to the doctor for suspected psychological disorder is indicated. Overall, our study holds great potential to significantly improve healthcare outcomes for aging individuals through the power of IoT and analysis of big data. In addition, we also propose a system for determination and confirmation of a fall event according to a wearable gadget on the chest and Google speaker.The accelerometer and gyroscope in IMU (Inertial Measurement Unit) sensor in the wearable gadget is for posture determination of elderly including sitting and standing. Meanwhile, we can also know the fall direction including falling backward, falling forward and falling sideward. Besides, the impact force in a fall event can be obtained by the calculation. Through Google speakers and IoT, the system can know if the fall is true or not. The integration of Google speakers and IoT technology adds an extra layer of verification, enabling the system to confirm whether a fall has actually occurred. This verification process enhances the reliability of fall detection, reducing the risk of false alarms and ensuring that caregivers are promptly alerted when a genuine fall event takes place. By using a smartphone or computer app, caregivers can easily access real-time information regarding the position and behavioral state of the elderly. This allows for immediate response and assistance in case of a fall or any other health-related concerns. Moreover, the collected data can be analyzed and evaluated by medical specialists, providing valuable insights into the elderly person's health status and fall risks. The proposed solution's sensitivity, specificity, and accuracy for fall recognition in two types including fall when sitting and fall when standing are with high performance. In category I, the fall algorithm achieved sensitivity, specificity, and accuracy of 0.97, 0.94, and 0.96, respectively. In category II, the values were 0.98, 0.97, and 0.97, respectively. The system offers an ideal method for fall recognition and confirmation. The above two smart healthcare systems based on the IoT technology we have launched have enhanced the value of care for the health of the elderly.

CONTENTS

CHINESE ABSTRACT i
ENGLISH ABSTRACT ii
ACKNOWLEDGEMENTS v
CONTENTS vi
TABLE CONTENTS viii
FIGURE CONTENTS ix
Chapter I Introduction 1
1.1 Backgrounds 1
1.2 Literature Review 6
1.3 Research Purposes 8
Chapter II Material and Methods 9
2.1 IoT system using analysis of big data and PBMN 9
2.1.1 Bluetooth position-based Mesh Network 10
2.1.2 Setting end 13
2.1.3 Cloud server and database 14
2.1.4 The system of Indoor Positioning 14
2.1.5 Wearable gadget 16
2.1.6 Fixed Sensors 17
2.1.7 Physical activity determination 17
2.1.8 Posture determination 19
2.2 Fall determination and fall confirmation 21
2.2.1 Design of Falling Recognition 21
2.2.2 Design of Falling Verification 23
2.2.3 Experimental steps 25
Chapter III Results 28
3.1 IoT system with PBMN 28
3.1.1 Experiment of the Indoor Positioning 28
3.1.2 Wearable gadget test 29
3.1.3 Monitoring Status of the web 30
3.1.4 The analysis of Database 31
3.2 Fall recognition and fall verification 33
3.2.1 Recognition of falls 33
3.2.2 Verification of a fall 34
Chapter IV Discussion 36
Chapter V Conclusion 41
Chapter VI Future Prospects 43
Chapter VII Reference 45




TABLE CONTENTS

Table 1. Name card test 29
Table 2. Statistical analysis data of the behaviors 32
Table 3. The result of fall detection experiment 35




FIGURE CONTENTS

Figure 1. IoT based healthcare system 10
Figure 2. Information transmission in PBMN 12
Figure 3. Diagram of bwRouter architecture 13
Figure 4. The information of packets while the user touch a fixed sesnor 16
Figure 5. Inside the wearable gadget on the chest 22
Figure 6. Monitoring data of wearable gadget 23
Figure 7. Behavior state switching via FSM 26
Figure 8. The criteria of various behaviors 27



1. World population ageing, Highlights, Department of Economic and Social Affairs, United Nations, 2015.
2. R. Margaret, “Internet of things (IoT),” IOT Agenda, vol.14, 2019, pp.28–42.
3. H. Drew, “The Trouble with the Internet of Things,” G. L. A. vol.10, 2015, pp.1–12.
4. B. Eric, “21 Open Source Projects for IoT,” Linux com, vol.23, 2016, pp. 21–30.
5. Internet of Things Global Standards Initiative, ITU, 2015.
6. Y. Wu, A. Beiser and M. Breteler, “The changing prevalence and incidence of dementia over time—current evidence,” Nat. Rev. Neurol, vol.13, 2017, pp. 327–342.
7. M. Prince, R. Bryce, E. Albanese, A. Wimo, W. Ribeiro and C. Ferri, “The global prevalence of dementia: a systematic review and metaanalysis,” Alzheimers Dement, vol.9, 2013, pp. 63–75.
8. WHO. World Health Organization, Step safely: strategies for preventing and managing falls across the life-course, Geneva, 2021.
9. Y. Sahlin, “Occurrence of fractures in a defined population: a 1-year study, “ Injury,. vol.21, no.3, 1990, pp.158–160.
10. J. C. Davis, M. C. Robertson, M. C. Ashe, T. Liu-Ambrose, K. M. Khan and C. A.
Marra, "International comparison of cost of falls in older adults living in the community: A systematic review," Osteoporosis Int, vol. 21, no. 8, 2010, pp. 1295–1306.
11 F. Dalgaard, J.L. Pallisgaard, A.K. Numé, T.B. Lindhardt, G.H. Gislason, and C. Torp-Pedersen, “Rate or Rhythm Control in Older Atrial Fibrillation Patients: Risk of Fall-Related Injuries and Syncope,” J Am Geriatr Soc, vol.67, no.10, 2019, pp.2023–2030.
12. J. Bhangu, B.I. King-Kallimanis, Q.A. Donoghue, L. Carroll and R.A. Kenny, “Falls, non-accidental falls and syncope in community-dwelling adults aged 50 years and older: Implications for cardiovascular assessment,” PLoS One, vol.12, no.7, 2017, pp.1–12.
13. S. Jansen, J. Bhangu, S. de Rooij, J. Daams, R.A. Kenny and N. van der Velde, “The Association of Cardiovascular Disorders and Falls: A Systematic Review,” J Am Med Dir Assoc, vol.17, no.3, 2016, pp.193–199.
14. S.S. Paul, A. Thackeray, R.P. Duncan, J.T. Cavanaugh, T.D. Ellis and G.M. Earhart, “Two-year trajectory of fall risk in people with Parkinson disease: a latent class analysis,” Arch Phys Med Rehabil, vol.97, no.3, 2016, pp.372–379.
15. M. Suzuki, S. Kurata, E. Yamamoto, K. Makino, M. Kanamori, “Impact of fall-related behaviors as risk factors for falls among the elderly patients with dementia in a geriatric facility in Japan,” Am J Alzheimers Dis Other Demen, vol.27, no.6, 2012, pp.439–446.
16. Y. Hiorth, J.P. Laresn, K. Lode, O.B. Tysnes , A. Godfrey and S. Lord, “Impact of falls on physical activity in people with Parkinson’s Disease,” J Parkinsons Dis, vol.6, no.1, 2016, pp.175–182
17. M.E. Taylor, K. Delbaere, S.R. Lord, A.S. Mikolaizak and J.C. Close, ” Physical impairments in cognitively impaired older people: implications for risk of falls,” Int Psychogeriatr, vol.25, 2013, pp.148–156.
18. N.E. Allen, A.K. Schwarzel and C.G. Canning, “Recurrent falls in Parkinson’s disease: a systematic review,” Parkinsons Dis, 2013, 906274.
19. L. Hanssens and J.Y. Reginster, “Relevance of bone mineral density, bone quality and falls in reduction of vertebral and non-vertebral fractures," J Musculoskelet Neuronal Interact, vol.3, no.3, 2003, pp.189–193.
20. E. Schacht, F. Richy and J. Reginster, “The therapeutic effects of alfacalcidol on bone strength, muscle metabolism and prevention of falls and fractures,” J Musculoskelet Neuronal Interact, vol.5, no.3, 2005, pp.273–284.
21. Y. Dionyssiotis, I.A. Dontas, D. Economopoulos and G.P. Lyritis, “Rehabilitation after falls and fractures,” J Musculoskelet Neuronal Interact, vol.8, no.3, 2008, pp.244–250.
22. F. Farshad, A.M. Rahmanibc, K. Mankodiyad, M. Badaroglue, G.V. Merrett, P. Wong and B. Farahani, “Internet-of-Things and Big Data for smarter healthcare: from device to architecture, applications and analytics,” Future Gen Comput Syst, vol.78, 2018, pp.583–586.
23. D. Yacchirema, D. Sarabia-JáCome, C. Palau and M. Esteve, “A smart system for sleep monitoring by integrating IoT with Big Data Analytics,” IEEE Access, vol.6, 2018, pp.35988–36001.
24. S.P. Kumar, V.R.R. Samson, U.B. Sai, P.L.S.D.M. Rao, and K.K. Eswar, “Smart health monitoring system of patient through IoT.” In: 2017 International conference on I-SMAC (IoT in social, mobile, analytics and cloud) (I-SMAC). IEEE, 2017, pp. 551–556.
25. L. Minh, M. Kuynbok, H. Dongi and J. Md, “A Survey on Internet of Things and Cloud computing for healthcare,” Electronics, vol.8, no.7, 2019, 768.
26. M.R. Desai and S. Toravi, “A smart sensor interface for smart homes and heartbeat monitoring using WSN in IoT environment,” In: 2017 International conference on current trends in computer, electrical, electronics and communication (CTCEEC). IEEE, 2017, pp. 74–77.
27. L. Greco, G. Percannella, P. Ritrovato, F. Torterella and M. Mento, “Trends in IoT based solutions for healthcare: Moving AI to the edge,” Pattern Recognit Lett. vol.135, 2020, pp. 346–353.
28. M. Saleh, and R.L. Jeannés, “Elderly fall detection using wearable sensors: a low cost highly accurate algorithm, IEEE Sens. J , vol.19, 2019, pp.3156–3164.
29. I. Putra, J. Brusey, E. Gaura and R. Vesilo, “An event-triggered machine learning approach for accelerometer-based fall detection,” Sensors, vol.18, 2017, 20.
30. Z. Zitouni, Q. Pan, D. Brulin and E. Campo, “Design of a smart sole with advanced fall detection algorithm,” J. Sensor Technol, vol.9, 2019, pp.71-90.
31. S. Scheurer, J. Koch, M. Kucera, H. Bryn, M. Bärtschi and T. Meerstetter, “Optimization and technical validation of the AIDE-MOI fall detection algorithm in a real-life setting with older adults,” Sensors, vol.19, 2019, 1357.
32. E. Auvinet, F. Multon, A. Saint-Arnaud, J. Rousseau and J. Meunier, “Fall detection with multiple cameras: An occlusion-resistant method based on 3-D silhouette vertical distribution,” IEEE Trans. Inf. Technol. Biomed, vol.15, 2011, pp.290–300.
33. P. Feng, M. Yu, S. M. Naqvi and J. A. Chambers, “Deep learning for posture analysis in fall detection,” In Proceedings of the 2014 19th International Conference on Digital Signal Processing, Hong Kong, China, 20–23 August 2014, pp. 12–17.
34. S. Yoo, and D. Oh, “An artificial neural network–based fall detection,” Int. J. Eng. Bus. Manag, vol.10, 2018.
35. C. Hsieh, C. Huang, K. Liu, W. Chu and C. Chan, “A machine learning approach to fall detection algorithm using wearable sensor,” In Proceedings of the 2016 International Conference on Advanced Materials for Science and Engineering (ICAMSE), Chiang Mai, Thailand, 12–13 November 2016, pp. 707–710.
36. S. Khojasteh, J. Villar, C. Chira, V. González and E. de la Cal, “Improving fall detection using an on-wrist wearable accelerometer,” Sensors, vol.18, 2018, 1350.
37. T. Wu, Y. Gu, Y. Chen, Y. Xiao, and J. Wang, “A mobile cloud collaboration fall detection system based on ensemble learning,” Proceedings of the 22nd International ACM SIGACCESS Conference on Computers and Accessibility, 2019
38. O. Aziz, J. Klenk, L. Schwickert, L. Chiari, C. Becker and E.J. Park, “Validation of accuracy of SVM-based fall detection system using real-world fall and non-fall datasets,” PLoS One, vol. 12, no.17, 2017, e0180318.