進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0202201615023200
論文名稱(中文) 基於傳感壓縮之體感網路的動作監測系統
論文名稱(英文) A CS-based Body Sensor Network for Motion Monitoring
校院名稱 成功大學
系所名稱(中) 資訊工程學系
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 104
學期 1
出版年 105
研究生(中文) 歐宏毅
研究生(英文) Hung-Yi Ou
學號 P76021190
學位類別 碩士
語文別 英文
論文頁數 56頁
口試委員 指導教授-藍崑展
口試委員-蔣榮先
口試委員-張大緯
口試委員-梁勝富
口試委員-陳伶志
中文關鍵字 帕金森氏症  跌倒和日常生活動作偵測  體感網路  電力消耗  壓縮傳感  判斷精準度 
英文關鍵字 Parkinson’s Disease  Fall detection and daily activites monitoring system  Wireless Body Sensor Network  Power consumption  Compressive Sensing  Detected accuracy 
學科別分類
中文摘要 帕金森氏症是一種最常見的神經退化失調性的疾病,對於高齡的人口有更高的比例患有此症狀,更有報告指出,患有帕金森氏症的病人,很容易會有跌倒的情況發生,這是病人的照顧者需要監測的事情。
先前有很多研究提及,監測帕金森氏症患者的日常生活中的動作,有助於了解病人是否處於一個安全的狀態並且也能得知運動神經的情況,另外監測病人有無跌倒發生,若發生則能即時通知他們的照顧者,而這些進行跌倒偵測和日常生活動作的監測都是使用無線體感網路(Wireless Body Sensor Network, WBSN)來實現,所以基於這些理由,我們使用無線體感網路來偵測跌倒和監測日常生活的動作。
監測工作都需要進行很長的一段時間,而先前偵測跌倒和動作監測的應用中,都沒有考慮過sensor電力方面的問題,但sensor主要透過電池來供電,所以sensor的電池續航力是一個需要改善和討論的問題。
傳感壓縮 (Compressive Sensing , CS)是一個用來壓縮資料的方法,CS可以降低sensor的耗電,所以為了節省電力消耗,我們將CS加入到跌倒和動作偵測的演算法中並且實做出這個系統,這是我們和其他動作偵測的研究不同的地方。
由於將CS和跌倒偵測且動作判斷做結合,而若在CS的部份壓縮率越高,系統可以越省電,但是之後的動作判斷精準度會下降,所以我們需要考慮如何選擇壓縮的參數,而最後的跌倒偵測和動作判斷的精準度卻不能太差,因此我們藉由分析數學式,來規劃出要如何決定參數的方法,再依循分析的方式做實驗,找到符合這個系統的最佳參數。最後我們得到,在有加入CS使省電的情況下,也可以讓偵測跌倒和動作判斷有95%的判斷精準度,而系統可以節省約47.4%的電力消耗。
英文摘要 Recently, Parkinson’s Disease (PD) is the most common neurodegenerative disorder, there are high proportion with this disease in the elder population; moreover, some report indicates that the patient with PD disease is more easy to fall down when they do some daily activities, so their caregiver have to pay much attenttion on patient’s daily life.
In previous work mentioned that monitor daily physical activities of PD patients can provide objective and valuable information to realize the level of motor functioning; besides, as PD is also associated with increase of falling down, so we also need to monitor the patients whether they fall down or not, if yes, then we can immediately inform their cargivers, and these researches use Wireless Body Sensor Network (WBSN) to detect fall and daily activities; however, the monitoring time is very long, but the sensor is battery-based device, and previous fall detection and daily activities monitoring application didn’t consider the life time of sensor; therefore, the power consumption of sensor is an important issue for devices.
There is a method called Compressive Sensing (CS) which is invented to prolong the worked time of sensor, we will introduce CS method in the latter; eventually, we mix with CS algorithm and motion detection procedure, and successfully implement the CS-based body sensor network for fall detection and daily activites monitoring system.
Owing to we mix the two different method so that we need to additionally consider how to choose suitable CS recovery algorithm in this application, and how to decide some parameters including compressed ratio, the size of window to be compressed … etc, and also keep the motion detection accuracy; therefore, we use the mathematical analysis as the parameters selected conditions, and then do the experiments to find optimal parameters in this application; finally, our CS-based fall detection and daily activity monitoring can has 95% detected accuracy, and achieve almost 47.4% power saving.
論文目次 Chapter 1: Introduction(page 1)
Chapter 2: Related works(page 3)
2.1: Survey of Fall detection procedure (page 3)
2.2: The method of saving sensor power (page 4)
2.3: Sparsity (page 5)
2.4: Compressive Sensing (page 6)
2.5: Block Sparse Bayesian Learning (BSBL) (page 7)
2.6: Temporally correlated Sparse Bayesian Learning (T-MSBL) (page 10)
Chapter 3: Methodology (page 12)
3.1: SpatioTemporal Sparse Bayesian Learning (STSBL) (page 13)
3.2: Motion detection procedure (page 19)
3.3: Mathematical Analysis for Selecting Paramters (page 26)
3.4: Parameters Selected Results (page 32)
Chapter 4 System Evaluation (page 37)
4.1: Hardware Specification (page 37)
4.2: Power Consumption Model (page 39)
4.3: Detected Accuracy and Power Saving Percetage (page 43)
Chapter 5: Discussion (page 45)
Chapter 6: Conclusion (page 51)
Reference: (page 52)
參考文獻 [1] Cancela, Jorge, et al (2014). "Wearability assessment of a wearable system for Parkinson’s disease remote monitoring based on a body area network of sensors." Sensors 14.9: 17235-17255.
[2] Ashburn, Ann, et al (2001). "A community‐dwelling sample of people with Parkinson's disease: characteristics of fallers and non‐fallers." Age and ageing 30.1: 47-52.
[3] Salarian, Arash, et al (2007). "Ambulatory monitoring of physical activities in patients with Parkinson's disease." Biomedical Engineering, IEEE Transactions on 54.12: 2296-2299.
[4] POLLACK, Martha E (2005). Intelligent technology for an aging population: The use of AI to assist elders with cognitive impairment. AI magazine, 26.2: 9.
[5] HIJAZ, Farrukh, et al (2010). Survey of fall detection and daily activity monitoring techniques. In: Information and Emerging Technologies (ICIET), International Conference on. IEEE. p. 1-6.
[6] Li, Qiang, et al (2009). "Accurate, fast fall detection using gyroscopes and accelerometer-derived posture information." Wearable and Implantable Body Sensor Networks. Sixth International Workshop on. IEEE.
[7] Zhang, Tong, et al (2006):. "Fall detection by embedding an accelerometer in cellphone and using KFD algorithm." International Journal of Computer Science and Network Security 6.10 : 277-284.
[8] Cheng, Juan, Xiang Chen, and Minfen Shen (2013). "A framework for daily activity monitoring and fall detection based on surface electromyography and accelerometer signals." Biomedical and Health Informatics, IEEE Journal of17.1: 38-45.
[9] CANDÈ, Emmanuel J.; WAKIN, Michael B (2008). An introduction to compressive sampling. Signal Processing Magazine, IEEE, 25.2: 21-30.
[10] BARANIUK, Richard G (2007). Compressive sensing. IEEE signal processing magazine, 24.4.
[11] AVIYENTE, Selin (2007). Compressed sensing framework for EEG compression. In:Statistical Signal Processing. SSP'07. IEEE/SP 14th Workshop on. IEEE. p. 181-184.
[12] DIXON, Anna MR, et al (2012). Compressed sensing system considerations for ECG and EMG wireless biosensors. Biomedical Circuits and Systems, IEEE Transactions on, 6.2: 156-166.
[13] ZHANG, Zhilin, et al (2013). Compressed sensing for energy-efficient wireless telemonitoring of noninvasive fetal ECG via block sparse Bayesian learning.Biomedical Engineering, IEEE Transactions on, 60.2: 300-309.
[14] LIU, Benyuan, et al (2014). Energy efficient telemonitoring of physiological signals via compressed sensing: A fast algorithm and power consumption evaluation.Biomedical Signal Processing and Control, 11: 80-88.
[15] Aguiar, Braulio, et al (2014). "Accelerometer-based fall detection for smartphones." Medical Measurements and Applications (MeMeA), 2014 IEEE International Symposium on.
[16] Zhang, Tong, et al (2006). "Fall detection by embedding an accelerometer in cellphone and using KFD algorithm." International Journal of Computer Science and Network Security 6.10: 277-284.
[17] Bourke, Alan K., et al (2007). "The design and development of a long-term fall detection system incorporated into a custom vest for the elderly." Conference proceedings:... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.
[18] Bourke, Alan K., et al (2008). "Testing of a long-term fall detection system incorporated into a custom vest for the elderly." Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE.
[19] JURDAK, Raja; RUZZELLI, Antonio G.; O'HARE, Gregory MP (2010). Radio sleep mode optimization in wireless sensor networks. Mobile Computing, IEEE Transactions on, 9.7: 955-968.
[20] Arvinti, Beatrice, Alexandru Isar, and Marius Costache (2011). "An adaptive compression algorithm for ECG signals." Computational Intelligence and Informatics (CINTI), 2011 IEEE 12th International Symposium on. IEEE.
[21] JALALEDDINE, Sateh, et al (1990). ECG data compression techniques-a unified approach. Biomedical Engineering, IEEE Transactions on, 37.4: 329-343.
[22] Ciancio, Alexandre, et al (2006). "Energy-efficient data representation and routing for wireless sensor networks based on a distributed wavelet compression algorithm." Proceedings of the 5th international conference on Information processing in sensor networks. ACM.
[23] MAMAGHANIAN, Hossein, et al (2011). Compressed sensing for real-time energy-efficient ECG compression on wireless body sensor nodes. Biomedical Engineering, IEEE Transactions on, 58.9: 2456-2466.
[24] Kanoun, Karim, et al (2011). "A real-time compressed sensing-based personal electrocardiogram monitoring system." Design, Automation & Test in Europe Conference & Exhibition (DATE), 2011.
[25] Davenport, Mark A (2010). Random observations on random observations: Sparse signal acquisition and processing. Diss. Texas A&M University.
[26] CHEN, Weijie; WASSELL, Ian (2015). Optimized Node Selection for Compressive Sleeping Wireless Sensor Networks.
[27] Cotter, Shane F., et al (2005). "Sparse solutions to linear inverse problems with multiple measurement vectors." Signal Processing, IEEE Transactions on 53.7 : 2477-2488.
[28] Eldar, Yonina C., and Helmut Bölcskei (2009). "Block-sparsity: Coherence and efficient recovery." Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on. IEEE.
[29] ZHANG, Zhenhao; RAO, Bhaskar (2009-2015). Extension of SBL algorithms for the recovery of block sparse signals with intra-block correlation. Signal Processing, IEEE Transactions on, 2013, 61.8.
[30] TIPPING, Michael E (2001). Sparse Bayesian learning and the relevance vector machine. The journal of machine learning research, 1: 211-244.
[31] ZHANG, Zhilin; RAO, Bhaskar D (2011). Sparse signal recovery with temporally correlated source vectors using sparse Bayesian learning. Selected Topics in Signal Processing, IEEE Journal of, 5.5: 912-926.
[32] ZHANG, Zhilin, et al (2014). Spatiotemporal sparse Bayesian learning with applications to compressed sensing of multichannel physiological signals. Neural Systems and Rehabilitation Engineering, IEEE Transactions on, 22.6: 1186-1197.
[33] ZHONG, Shi; GHOSH, Joydeep (2002). HMMs and coupled HMMs for multi-channel EEG classification. Proceedings of the IEEE International Joint Conference on Neural Networks. p. 1254-1159.
[34] MANABE, H.; ZHANG, Z (2004). Multi-stream HMM for EMG-based speech recognition. Engineering in Medicine and Biology Society. IEMBS'04. 26th Annual International Conference of the IEEE. IEEE, 2004. p. 4389-4392.
[35]RABINER, Lawrence R (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77.2: 257-286.
[36] ZHANG, Xu, et al (2011). A framework for hand gesture recognition based on accelerometer and EMG sensors. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 41.6: 1064-1076.
[37] BOYLE, Justin; KARUNANITHI, Mohan (2008). Simulated fall detection via accelerometers. In: Engineering in Medicine and Biology Society. EMBS 2008. 30th Annual International Conference of the IEEE. p. 1274-1277.
[38] Bourke, A. K., J. V. O’brien, and G. M. Lyons (2007). "Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm." Gait & posture 26.2: 194-199.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2021-02-05起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw