臺灣博碩士論文加值系統

人口老化是世界各國都須面對的人口變遷問題，根據聯合國人口與發展委員會的推估，隨著多年來平均預期壽命的增加和人口成長率趨緩，全球人口正在逐漸高齡化。因此，老年護理市場正在增長，並顯示出巨大的開發潛力。為了應對這些挑戰，人們越來越關注醫療輔助技術，以支持老年人在他們的家庭環境中盡可能長時間保持健康和自主。機器人系統是那些提供與支持自主生活，監測和維持安全或通過提供陪伴來增強老年人的健康和心理健康相關的功能的舉措。因此，為了改善老年人獨立生活和生活質量，而開發的照護機器人系統為重要議題。
本研究基於運用生醫訊號特性的情緒辨識居家照護機器人系統，該機器人包含了情緒辨識模組和機器人控制模組。在情緒辨識模組中配置了呼吸和心率感測器，用以感測使用對象的生醫訊號數據，並為其提供生醫訊號處理和情緒辨識功能，在情緒辨識後藉由音樂來安撫受照護者之情緒。在機器人控制模組中，配置了馬達、超音波感測器和紅外線感測器，馬達用於機器人移動功能，超音波用於機器人移動時的避障功能，而紅外線感測器運用其訊號強度來達到定位和跟隨的效果，讓機器人能夠更貼近受照護者的生活。
本研究目的為運用生醫訊號特性的情緒辨識居家照護機器人系統來達到陪伴的效果並探討其實用性及未來趨勢，有助於應對人口老化所帶來的議題。

The ageing of the population is a problem of population change that all countries in the world have to face. According to the report of the United Nations Commission on Population and Development, the global population is slowly aging as the average life increases and the population growth rate slows down over the years. As a result, the aged care market is growing and shows great potential for development. In response to these challenges, there is a growing interest in medical assistive technologies to support elderly to stay healthy and autonomous in their home as long as possible. Robotic system is a particular initiative that provides and supports independent living, monitors and maintains safety by providing companionship to improve the health of elderly. Therefore, the development of the care robot system is an important issue to improve the independent living and quality of life of the elderly.
This study is based on the emotional recognition of the home care robot system using the feature of physiological signals. The robot includes an emotion recognition module and the robot control module. The breathing and blood pressure sensor are arranged in the emotion recognition module to sense the physiological signal data of the elderly to be used, and to provide physiological signal processing and emotion recognition functions. Then emotional recognition system will play music to appease the feeling of elderly. In the robot control module, a motor, an ultrasonic sensor and an infrared sensor are deployed. The motor is used for the robot movement function, the ultrasonic wave is used for the obstacle avoidance function. When the robot starts, Infrared sensors use their signal strength to positioning and following, allowing the robot to be closer to the elderly.
The purpose of this study is to apply the emotional recognition of the home care robot system to achieve the companion effect and explore its realism and future trends, which will help solve the issues of population aging.

中文摘要 ...i
英文摘要 ...iii
誌謝 ...v
目錄 ...vi
表目錄 ...viii
圖目錄 ...ix
第一章 緒論 ...1
1.1 研究背景 ...2
1.2 研究目的 ...5
1.3 論文架構 ...6
第二章 文獻回顧 ...9
2.1 居家照護機器人 ...9
2.2 生醫訊號之情緒辨識研究 ...11
2.3 適用於情緒辨識的機器學習演算法 ...15
2.4 音樂對心理的影響 ...18
第三章 居家照護機器人系統設計 ...21
3.1 系統規劃 ...21
3.2 情緒辨識模組 ...23
3.3 機器人控制模組 ...35
第四章 實驗結果分析與探討 ...41
4.1 情緒辨識實驗 ...41
4.2 機器人控制實驗 ...51
第五章 結論與未來展望 ...58
5.1 結論 ...58
5.2 未來展望 ...60
參考文獻 ...61
Extended Abstract ...63

[1]Gu Xinwen, Take the mirror of Japan - wisdom technology into the home care, https://www.chinatimes.com/newspapers/2016012600033
6-260207?chdtv.
[2]National Development Council Population Projections for the R.O.C (Taiwan), Demographic Indicators, https://pop-roj.ndc.gov.tw/main_e
n/dataSearch.aspx?uid=78&pid=78.
[3]Marek KD, Rantz MJ, “Ageing in place: a new model for long-term care,” Nurs Admin Quart, Vol. 24, No. 3, pp.1-11, February 2000.
[4]Robinson, H., MacDonald, B. & Broadbent, “The Role of Healthcare Robots for Older People at Home: A Review,” Int J of Soc Robotics, pp. 575–591, November 2014.
[5]Broekens J, HeerinkM,RosendalH, “Assistive social robots in elderly care: a review,” Gerontechnology, Vol. 8, No. 2, pp. 94–103, 2009.
[6]N. Roy, G. Baltus, D. Fox, F. Gemperle, J. Goetz, T. Hirsch, D. Margaritis, M. Montemerlo, J. Pineau, J. Schulte and S. Thrun, “Towards Personal Service Robots for the Elderly, ” In Workshop on Interactive Robots and Entertainment, October 2000.
[7]K. Wada, T. Shibata, T. Saito and K. Tanie, “Effects of Robot-Assisted Activity for Elderly People and Nurses at a Day Service Center, ” In Proceedings of the IEEE, Vol. 99, No. 11, November 2004.
[8]Broadbent E, Stafford R, MacDonald B, “Acceptance of healthcare robots for the older population: reviewand future directions, ” International Journal of Social Robotics, pp. 319–330, October 2009.
[9]David Portugal, Luís Santos, Paulo Alvito, Jorge Dias, George Samaras, Eleni Christodoulou, “SocialRobot: An interactive mobile robot for elderly home care, ” IEEE/SICE International Symposium on System Integration, December 2015.
[10]R. w. Picard, E. Vyzas, and J. Healey, "Toward Machine Emotional Intelligence: Analysis of Affective Physiological State," IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 23, no. 10, pp. 1175-1191, October 2001.
[11]Qing Li, Zongkai Yang, Sanya Liu, Zhicheng Dai, Yang Liu, "The study of emotion recognition from physiological signals," Seventh International Conference on Advanced Computational Intelligence (ICACI), March 2015.
[12]Kitimapond Rattanadoung, Paskorn Champrasert and Somrawee Aramku, "The emotional state classification using physiological signal interpretation framework," International Conference on Signals and Systems, pp. 79-85, May 2018.
[13]Michael Negnevitsky著，2007，人工智慧:智慧型系統導論，顧立栩，沈晉惠譯，全華圖書。
[14]Mitul Kumar Ahirwal, Mangesh Ramaji Kose, “Emotion Recognition System based on EEG signal: A Comparative Study of Different Features and Classifiers,” Second International Conference on Computing Methodologies and Communication, February 2018.
[15]陳信源，葉鎮源，林昕潔，黃明居，柯皓仁，楊維邦，2009，” 結合支援向量機與詮釋資料之圖書自動分類方法”，資訊科技國際期刊，3卷，1期，頁6~7，6月。
[16]Jonghwa Kim, Elisabeth André, “Emotion Recognition Based on Physiological Changes in Music Listening,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30, No. 12, pp. 2067-2083, January 2009.
[17]林楊菁，“音樂對於老年人情緒影響相關因素之調查研究” ，國立臺灣師範大學音樂學系碩士論文，2007。
[18]循環系統, http://spaces.isu.edu.tw/upload/19526/updown4.pdf.