建置在智慧型裝置上的一個準確地運用群眾外包適應技術的跌倒偵測方法

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳萱蔓 Chen, Hsuan Man
論文名稱：	建置在智慧型裝置上的一個準確地運用群眾外包適應技術的跌倒偵測方法 An Accurate Crowdsourcing-based Adaptive Fall Detection Approach Using Smart Devices
指導教授：	蔡仁松 Tsay, Ren Song
口試委員:	李洪松馬席彬
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2015
畢業學年度：	104
語文別：	英文
論文頁數：	28
中文關鍵詞：	跌倒偵測、群眾外包、智慧型裝置、健康照護
外文關鍵詞：	Fall detection, crowdsourcing, smart device, health care
相關次數：	點閱：2 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

一個低花費並且高準確度的跌倒偵測系統，不僅能照護到年長者更能擴及各個年齡層來做使用。現今的跌到偵測系統除了高花費，其敏感度更會因為使用者的身體素質（如身高，年齡，體重等）影響偵測的準確度。此外，過去大部分跌倒偵測的研究，因為實際數據取得困難，而必須透過模擬跌倒動作收集數據來做為測試，無法完整考量到不同使用者實際情況。為了解決這些問題，我們提出了一個透過群聚外包收集數據，並視使用者情況調整來提升準去度的跌倒偵測系統，用現今流行並具有網路連線及偵測功能（三軸加速器等）的智慧型裝置作為工具。我們能夠透過群聚外包收集每個使用者的數據，依照使用者條件來進行分類並做跌倒偵測演算法的調整來提升準確度。本篇實驗結果顯示我們透過分類並作個類別調整，其跌倒偵測系統準確度從68%提昇至97%。

Being able to provide a low cost but highly accurate fall detection mechanism is decidedly beneficial not only to senior people but also to people of all ages. Most existing approaches are expensive and all subject to the shortfalls of being sensitive to user physique and personal factor. Additionally, most approaches are developed using limited, simulated fall data and often perform poorly in field tests. To resolve these issues, we propose, in this paper, an accurate, crowdsourcing-based, adaptive, fall detection approach using smart devices with built in wireless connection and sensors. We adaptively refine the fall detection algorithm and user grouping for improved accuracy based on the crowdsourced real data. The field tests show that the fall detection accuracy rate can be improved from 68% to 97% with our proposed approach.

Contents

1.    Introduction…………………………………………….7
2.    Related Work………………………………………….11
3.    Our Propos Approach…………………………………14
3.1    Crowdsourcing Real User Data……………………14
3.2    System Adaptation for Better Accuracy…………...15
3.2.1     Categorize Users for Accuracy…………….15
3.2.2     Group-Specific Algorithms………………...16
3.2.3     A Reliable Accuracy Measure……………..18
3.3    Wearable Devices and Smart Phones……………...19
3.3.1     Device Initialization………………………..19
3.3.2     Fall-Detection Process……………………..20
4.    Evaluation……………………………………………..22
4.1    Data collection……………………………………..22
4.2    Test Results………………………………………..22
5.    Conclusion…………………………………………….24
BIBLIOGRAPHY………………………………………..25
List of Tables

Table 1: A list of test results to show that fall detection algorithms are user sensitive.……………………………...9

List of Figures

Figure 1    The forward-fall and daily activity patterns for users of different age and physique. The number on the vertical axis represents the sum-of-acceleration value. Here (a) and (b) are forward-falls of two different persons, and (c) is for a daily activity of sitting down.……………………..…………………...8
Figure 2    An illustration of grouping tree.……………………..……………………16
Figure 3    The process of algorithm customization and adaptation……………………………………18
Figure 4    Differentiate genuine falls from false falls…………………………………………..21
Figure 5     Accuracy rate comparisons with and without system adaptation……………………………23

[1] Vincent, Mathis L., and Theo M. Moreau. Accidental falls: causes, prevention and intervention. Nova Science, 2008.
[2] Cao, Yabo, Yujiu Yang, and WenHuang Liu. “E-FallD: A fall detection system using android-based smartphone.” Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th International Conference on. IEEE, 2012.
[3] Ekachai, Thammasat, and JarreeChaicharn. “A Simply Fall-Detection Algorithm Using Accelerometers on a Smartphone.” Biomedical Engineering International Conference (BMEiCON), 2012.
[4] Majumder, Akm Jahangir Alam, Farzana Rahman, Ishmat Zerin, William Ebel, Jr., and Sheikh Iqbal Ahamed. “iPrevention: Towards a novel real-time smartphone-based fall prevention system.” 28th Symposium On Applied Computing, 2013.
[5] Oscal T.-C. Chen, and Chih-Jung Kuo. “Self-Adaptive Fall-Detection Apparatus Embedded in Glasses.” Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference on. IEEE, 2014.
[6] Bagalà, Fabio, et al. "Evaluation of accelerometer-based fall detection algorithms on real-world falls." PloS one 7.5 (2012): e37062.
[7] Bergström, Ulrica, et al. "Fracture mechanisms and fracture pattern in men and women aged 50 years and older: a study of a 12-year population-based injury register, Umeå, Sweden." Osteoporosis international 19.9 (2008): 1267-1273.
[8] Klenk, J., et al. "Comparison of acceleration signals of simulated and real-world backward falls." Medical engineering & physics 33.3 (2011): 368-373.
[9] Kangas, Maarit, et al. "Comparison of real-life accidental falls in older people with experimental falls in middle-aged test subjects." Gait & posture 35.3 (2012): 500-505.
[10] Koshmak, Gregory, Maria Linden, and Ahmed Loutfi. "Evaluation of the android-based fall detection system with physiological data monitoring." Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE. IEEE, 2013.
[11] Vavoulas, George, et al. "The mobifall dataset: An initial evaluation of fall detection algorithms using smartphones." Bioinformatics and Bioengineering (BIBE), 2013 IEEE 13th International Conference on. IEEE, 2013.
[12] Jantaraprim, P., et al. "Improving the accuracy of a fall detection algorithm using free fall characteristics." Electrical Engineering/Electronics Computer Telecommunications and Information Technology (ECTI-CON), 2010 International Conference on. IEEE, 2010.
[13] Dai, Jiangpeng, et al. "Mobile phone-based pervasive fall detection." Personal and ubiquitous computing 14.7 (2010): 633-643.
[14] Bourke, A. K., et al. "Evaluation of waist-mounted tri-axial accelerometer based fall-detection algorithms during scripted and continuous unscripted activities." Journal of biomechanics 43.15 (2010): 3051-3057.
[15] He, Yi, Ye Li, and Chuan Yin. "Falling-incident detection and alarm by smartphone with Multimedia Messaging Service (MMS)." (2012).
[16] Sposaro, Frank, and Gary Tyson. "iFall: an Android application for fall monitoring and response." Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE. IEEE, 2009.
[17] Rahul, Tiwari, Singh, A.K., and Khan,S.N. “Using Android Platform to detect Free Fall.” Information Systems and Computer Networks (ISCON), 2013 International Conference on. IEEE, 2013.
[18] Khan, Adil Mehmood, et al. "Accelerometer’s position independent physical activity recognition system for long-term activity monitoring in the elderly." Medical & biological engineering & computing 48.12 (2010): 1271-1279.
[19] Fang, Shih-Hau, Yi-Chung Liang, and Kuan-Ming Chiu. "Developing a mobile phone-based fall detection system on Android platform." Computing, Communications and Applications Conference (ComComAp), 2012. IEEE, 2012.
[20] Philips, “Lifeline,” http://www.lifelinesys.com/content/
[21] Guidercare, “AngelCare” http://www.guidercare.com/en/
[22] Wu, Ge. "Distinguishing fall activities from normal activities by velocity characteristics." Journal of biomechanics 33.11 (2000): 1497-1500.

全文公開日期本全文未授權公開 (校內網路)
全文公開日期本全文未授權公開 (校外網路)
全文公開日期本全文未授權公開 (國家圖書館：臺灣博碩士論文系統)

簡易檢索 / 詳目顯示

相關論文