본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
회원가입 로그인
HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색

결과 내 검색

동의어 포함

고급검색

인명/단체명

저자정보 상세정보
인명/단체명을 입력하세요.

키워드

  • 대표어

  • 외국어

-

목차보기

Title Page 2

Abstract 7

Acronyms & Abbreviations 8

Contents 11

Chapter 01. Introduction 13

1.1. Background & Motivation 13

1.2. Problem Statement 14

1.3. Main Contributions 15

1.4. Thesis Structure 16

Chapter 02. Photoplethysmography (PPG) and its Role in Predicting Blood Pressure: A Literature Review 17

2.1. Introduction to PPG 17

2.2. Types of PPG sensor 18

2.2.1. Transmissive Type PPG 18

2.2.2. Reflective Type PPG 18

2.3. Effect of LED color on PPG signal 19

2.4. Literature Review 19

Chapter 03. Proposed Hardware Architecture 23

3.1. Introduction 23

3.1.1. Microcontroller Unit (nRF52832, Nordic Semiconductor) 23

3.1.2. PPG Sensor (SFH7050, OSRAM) 24

3.1.3. Analog Front-End (AFE4403, Texas Instruments) 25

3.2. Proposed Hardware Architecture 27

3.3. Power Consumption 29

Chapter 04. Proposed Methodology along with Real-Time Signal Acquisition and PWV calculation 30

4.1. Introduction 30

4.2. Signal Acquisition 31

4.3. Peak detection 31

4.4. Calculation of Pulse Wave Velocity 33

4.5. Heart Rate 35

Chapter 05. Dataset collection and Machine Learning Implementation 36

5.1. Introduction 36

5.2. Dataset collection 36

5.3. PWV-BP Correlation 37

5.4. Machine Learning Implementation 39

5.4.1. Support Vector Regressor 39

5.4.2. Performance assessment 43

5.4.3. Training of Support Vector Regression Model 44

5.5. Comparison of SVR with Different ML Models 45

5.6. Model Deployment 48

Chapter 06. Experiment and Results 49

6.1. Introduction 49

6.2. Real-Time Evaluation 49

6.3. Results 51

6.3.1. Heart Rate 51

6.3.2. Blood Pressure 52

6.4. Discussion 52

Chapter 07. Healthcare IoT (HIoT) Platform 56

7.1. Introduction 56

7.2. Wireless connection between wearable devices and Gateway 56

7.3. Gateway to Server Data Transmission 57

7.4. IoT Cloud Server 59

7.5. Security and Data Privacy 60

Chapter 08. Conclusion and Future Directions 64

Publications 65

International Journals (SCIE) 65

References 66

List of Tables 10

Table 1. Power Consumption of central PCB 29

Table 2. Summary of PWV-BP dataset, SD stands for standard deviation 39

Table 3. R² Score Based Comparative Analysis 48

Table 4. Comparison of proposed device with different BP estimation methods 54

Table 5. Comparison of Proposed result with BHS standards 55

Table 6. Recent advancements in wearable sensor systems for HIoT... 63

List of Figures 9

Figure 1. PPG light absorption diagram 20

Figure 2. Types of PPG (a) Transmissive (b) Reflective 20

Figure 3. Effect of wavelengths on PPG signal 20

Figure 4. (a) Nordic semiconductor nRF52832 CIAA (b) SFH 7050 PPG Sensor... 26

Figure 5. Functional block diagram of AFE4403 26

Figure 6. Compact Size PCBs 27

Figure 7. Functional Block Diagram of Proposed hardware 28

Figure 8. Proposed methodology for wearable IoT-connected BP estimation... 30

Figure 9. Signal acquisition from PPG 32

Figure 10. Real-time peak detection 32

Figure 11. Pulse transit time calculation in real-time 33

Figure 12. Statistical Analysis of (a) average SBP and DBP, (b) average PWV 38

Figure 13. PWV-BP correlation matrix 38

Figure 14. General structure of support vector regressor 40

Figure 15. SVR model implementation flowchart 47

Figure 16. R² score of training and testing for different regressors (a) systolic... 47

Figure 17. Flowchart of data processing and wireless connection 50

Figure 18. Experimental setup for real-time BP prediction 50

Figure 19. Real-time comparison between predicted and estimated heart rate 53

Figure 20. Real-time Predicted BP verses reference BP 53

Figure 21. Basic architecture of MQTT 59

Figure 22. Data transmission from wearable device to Server 59

초록보기

 The Internet of Things has evolved into a modern communication framework facilitating efficient connectivity among diverse entities across various domains through the internet. Recent strides in biosensing devices and their integration with Internet of Things (IoT) have significantly enhanced the monitoring and sensing capabilities of human biological vital signs. Notably, blood pressure (BP) sensing has emerged as a promising application within the realm of healthcare IoT (HIoT). This study introduces a novel wearable device, comprising a 3D printed wristband and finger cover, which enables remote blood pressure and heart rate monitoring through real-time signal acquisition and processing. Utilizing Bluetooth low energy (BLE) 5.1.1, the proposed device transmits measurements from photoplethysmography (PPG) sensors to a smartphone acting as a gateway. Facilitating seamless data transmission between the wearable device and the server, this gateway acts as a middleman. In the investigation, pulse wave velocity (PWV) derived from 30 participants serves as input for 14 different machine learning (ML) models aimed at estimating systolic and diastolic blood pressures. Among these ML models, the Support Vector Regressor (SVR) demonstrates the highest R-square (R²) scores, exceeding 0.92 for systolic blood pressure and 0.7896 for diastolic blood pressure. The lightweight SVR model in this study shows encouraging results, achieving a mean absolute error of 2.68 mmHg in estimating systolic blood pressure (SBP) and 2.94 mmHg for diastolic blood pressure (DBP). Integrated seamlessly into wearable devices, this SVR model holds significant potential for real-world applications within Healthcare Internet of Things scenarios, offering a critical component for remote monitoring and management of cardiovascular health.

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차

권호

기사명 원문보기 기사목차
닫기