應用於自動化居家照顧之多功能腦機介面系統

隨著現代醫療技術不斷的進步，以及生育率逐漸下降的現象，造成世界人口有逐漸老化的趨勢，因此需要大量的人力在於醫療看護上。而現今台灣的醫療護理現況卻面臨護理人力不足，需要一套有效的系統來輔助護理人員減輕負擔，也使得病患能夠獲得好的醫療品質。本論文利用腦機介面(Brain-Computer Interface, BCI)系統，讓病患可以透過自身的能力與外界溝通，除了老年人口的看護問題，對於喪失運動機能的患者，例如: 脊隨損傷、中風或肌萎縮性脊髓側索硬化症(俗稱漸凍人症)等等，也可以在不需他人的協助下，傳達出自身的想法或需求。本論文的腦機介面系統是運用兩種視覺誘發電位腦波訊號所開發的醫療看護系統，其中視覺誘發電位為P300事件相關電位(Event-related potential)與穩態視覺誘發電位(Steady state visually evoked potential, SSVEP)。過去P300事件相關電位的主要研究為P300拼字器，為一種由英文及數字的拼字面板，是利用新異刺激法的方式，隨機閃爍行列來誘發P300波形，再藉由腦波訊號的判斷來達到拼字的功能。但是若要拼出一句話需花上一段時間，因此在本文中將英文及數字改成客製化的醫療看護圖案，利用圖案來表達完整的語句，藉此來縮短拼字的時間。本文使用了K-NN與SVM分類演算法判別P300訊號，可以達到88%與95%的分類率。但是P300的缺點在於，必須透過事件的刺激才會誘發波形，意味著需要有人在旁協助才能讓系統開始執行，為了克服上述的問題，本文利用SSVEP作為系統的開關。當人受到週期性的刺激時大腦會產生相同週期的響應，因此系統可以利用LED燈泡進行閃爍刺激，病患若要啟動系統時只需透過注視LED燈泡來SSVEP即可。在本中使用相對變化率與典型相關分析作為辨識SSVEP的方法，分別可以達到100%與80%的偵測率以及0%與20%的偽正率。本文使用了以上兩種方式開發一套即時的醫療看護系統，讓病患自主性的利用腦波來選擇看護功能，並透過網路的方式傳遞訊息給護理人員，藉此減輕護理人員的負擔，也可以讓病患表達自己的真正想法與需求。

關鍵字

即時腦機介面； P300事件相關電位；穩態視覺誘發電位

並列摘要

With the progress of modern medical technology and the decline of fertility rate, giving rise to large aging population around the world, causing strong demand in human resource on caregiving. Yet caregiving in Taiwan is facing the lack of human resources, and is in strong need of an efficient system to support and reduce the work load of the caregivers, providing better care quality. This thesis aims to allow patients to communicate with the outside world on their own through Brain-Computer Interface (BCI), in addition to caregiving for the elderlies, other patients suffering from motor disabilities due to reasons such as spinal cord injury, stroke or amyotrophic lateral sclerosis (ALS), etc., can also express themselves and their needs without the assistance of others. The proposed medical caregiving system was developed based on two different visual evoked potential EEGs, the P300 event-related potential and the steady-state visual evoked potential. Major studies of P300 event-related potentials in the past were P300 speller which consists of characters and numbers. Using oddball paradigm method the P300 speller’s rows and columns flash in a random manner to induce P300 waveform, and achieve spelling function via recognition of EEG signals. Due to time consumption issue, we reduced the time needed for spelling by replacing characters and numbers with custom designed caregiving graphics, expressing a complete sentence with graphics. This thesis uses K-NN and SVM classification algorithm to recognize P300 signals, achieving 88% and 95% accuracy rate. A disadvantage of P300 is that waveform can only be evoked by stimulation, meaning assistance from others is needed to start the system, to overcome this problem; we use SSVEP as the trigger for our system. When people receive cyclical visual stimulation, the brain will produce a response with the same frequency as the stimulation, as a result we use flashing LED light as our switch. Patients can start the system by inducing SSVEP while watching the LED light. In this thesis, we use the relative variation and canonical correlation analysis to detect SSVEP, each achieves 100% and 80% true positive rate, 0% and 20% false positive rate. This thesis uses two kinks of EEG signal to develop an online caregiving system. Patients can choose the care functions by using brain activities at their own pace, send out messages to the caregiver through the Internet. With the proposed system not only the burden on caregivers can be reduced, the patients are able to express their true needs and thoughts.

並列關鍵字

BCI ； P300 Event-Related Potential ； SSVEP

參考文獻

[28] 高永樺, “情緒腦波分析及腦機介面之開發,” 中原大學機械工程學系碩士論文, 2013.

[1] Rakotomamonjy, and V. Guigue, “ BCI competition III: Dataset II-ensemble of SVMs for BCI P300 speller,” IEEE Trans. Biomed. Eng., vol. 55, no. 3, pp. 1147-1154, Mar. 2008.

[2] M. Kaper, P. Meinicke, U. Grossekathoefer, T. Lingner, and H. Ritter, “ BCI competition 2004 － Dataset IIb: support bector machines for the P300 Speller paradigm,” IEEE Trans. Biomed. Eng., vol.51, no. 6, pp. 1073-1076, Jun. 2004.

[3] J.R. Wolpaw, N. Birbaumer, W.J. Heetderks, D.J. Mcfarland, P.H. Peckham, G. Schalk, E.Donchin, L.A. Quatrano, C.J. Robinson, and T.M. Vaughan, “ Brain－computer interface technology: a review of the first international meeting,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 8, no. 2, pp. 164-173, Jun. 2000.

[4] T.M. Vaughan, “ Guest editorial brain-computer interface technology: a review of the second international meeting,” IEEE Trans. Neural Syst. Rehabil. Eng.,vol. 11,no. 2, pp.94-109, Jun. 2003.

國際替代計量

應用於自動化居家照顧之多功能腦機介面系統

未授權

主題瀏覽