現今全臺癱瘓人口約為三十六萬人，其主要的症狀為行動性、靈巧性以及自主控制功能之喪失。人機介面(Human-Computer Interface, HCI) 的原理為使用者及電腦間之溝通提供橋梁，使用者經視覺之刺激或回饋後得以利用不同控制媒介來操控電腦。
本研究以眼動電波(Electrooculogram, EOG) 當作控制訊號，配合有別於以往的兩種電極配置，開發一基於眼動電波特徵之辨識系統演算法，並結合圖形使用者介面來進行滑鼠控制之模擬。本研究共招募十二位常人受試者，其中六位受試者進行了眼動電波之量測，接著利用這些資料進行了演算法的開發，另外六位則進行了將演算法與使用者介面整合的滑鼠控制系統之測試，最後以精確率、準確率以及花費時間作為指標，評估演算法於兩種電極配置之系統效能。結果顯示，在測試Winking Detection與Peak Detection演算法於兩種電極配置部分，精確率在所有受試者上的表現都達到了100%，Classification演算法的準確率於兩種電極配置皆達到了83%以上，而每位受試者完成一項任務的花費時間也於15~35秒內不等。此外利用T檢驗(Student’s t test)比較兩種電極配置之效能，p-value於Classification演算法之準確率的部分為0.13，於花費時間的部分為0.23，可得知兩電極配置所做出之結果並無顯著差異。
結論，本研究成功發展一套基於眼動電波之人機介面滑鼠控制系統，能使常人受試者利用眼動電波控制圖形使用者介面，並且證實兩種電極配置之系統效能結果並無顯著差異。往後應實際邀請四肢癱瘓病人對系統進行測試，以提升系統可靠性。

The current population of paralyzed people in Taiwan is about 360,000. The main symptoms are loss of mobility, dexterity, and autonomous control. The principle of the human-computer interface (HCI) provides a bridge for communication between the user and the computer. After visual stimulation or feedback, the user can use different control methods to manipulate the computer.
This research used electrooculogram (EOG) as the control signal in two configurations which differed from common configuration to develop an EOG-based features recognition system software and combine with a graphical user interface (GUI) for simulation of mouse control system. Twelve people were recruited in this research. Six of them were acquired EOG signal to implement system development. The other six performed validation experiment which integrated the algorithm with the user interface. In the test of the mouse control system, the precision, accuracy and time cost were used as indicators to evaluate the system performance of algorithms in two configurations. The results showed that in the test, winking detection and peak detection algorithm had achieved 100% accuracy for all subjects in both configurations, and the accuracy of the classification algorithm had reached 83% above. The time cost of each task for all subjects were between 15~35 second. T-test (Student’s t-test) was performed to compare the performance of algorithms in different configurations. The p-value was 0.13 for the accuracy of the classification algorithm and 0.23 for the time cost. There was no significant difference between the results in different configurations.
In conclusion, this research successfully developed a mouse control system based on EOG for human-computer interface, which enabled normal subjects to use EOG to control the graphical user interface. And there was no significant difference between the results in two configurations. In the future, patients with quadriplegia should be invited to test the system to improve system reliability.

[1] Armour, B. S., Courtney-Long, E. A., Fox, M. H., Fredine, H., & Cahill, A. (2016). Prevalence and causes of paralysis - United States, 2013. American Journal of Public Health, 106(10), 1855–1857.
[2] Ward, A. L., Hammond, S., Holsten, S., Bravver, E., & Brooks, B. R. (2015). Power Wheelchair Use in Persons with Amyotrophic Lateral Sclerosis: Changes over Time. Assistive Technology, 27(4), 238–245.
[3] Blignaut, P. (2017). Development of a gaze-controlled support system for a person in an advanced stage of multiple sclerosis: a case study. Universal Access in the Information Society, 16(4), 1003–1016.
[4] Kumar, A., Pau1, P. K., & Ghosh, M. (2018). Human Computer Interaction and its Types: A Types.
[5] Karat, J., & Vanderdonckt, J. (2009). Brain-Computer Interfaces and Human-Computer Interaction. Lirmm.Fr, (December 2009), 409.
[6] Volosyak, I., Cecotti, H., & Gräser, A. (2009). Impact of Frequency Selection on LCD Screens for SSVEP Based Brain-Computer Interfaces
Bio-Inspired Systems: Computational and Ambient Intelligence, 5517, 706–713.
[7] Jukiewicz, M., & Cysewska-Sobusiak, A. (2016). Stimuli design for SSVEP-based brain computer-interface. International Journal of Electronics and Telecommunications, 62(2), 109–113.
[8] Cao, L., Li, J., Ji, H., & Jiang, C. (2014). A hybrid brain computer interface system based on the neurophysiological protocol and brain-actuated switch for wheelchair control. Journal of Neuroscience Methods, 229, 33–43.
[9] Tariq, M., Uhlenberg, L., Trivailo, P., Munir, K. S., & Simic, M. (2017). Mu-beta rhythm ERD/ERS quantification for foot motor execution and imagery tasks in BCI applications. 8th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2017 - Proceedings, 2018-Janua(CogInfoCom), 91–96.
[10] Wanluk, N., Visitsattapongse, S., Juhong, A., & Pintavirooj, C. (2017). Smart wheelchair based on eye tracking. BMEiCON 2016 - 9th Biomedical Engineering International Conference, 31–34.

[12] Eid, M. A., Giakoumidis, N., & El Saddik, A. (2016). A Novel Eye-Gaze-Controlled Wheelchair System for Navigating Unknown Environments: Case Study with a Person with ALS. IEEE Access, 4, 558–573.
[13] Kane, S. K., & Morris, M. R. (2017). Let’s Talk about X: Combining image recognition and eye gaze to support conversation for people with ALS. DIS 2017 - Proceedings of the 2017 ACM Conference on Designing Interactive Systems, 129–134.
[14] Maehara, T., Uchibori, A., Mizukami, Y., Wakasa, Y., & Tanaka, K. (2003). A communication system for ALS patients using eye-direction. APBME 2003 - IEEE EMBS Asian-Pacific Conference on Biomedical Engineering 2003, 18, 274–275.
[15] Yan, B., Yu, S., Liu, M., & Liu, X. (2016). Gaze estimation method based on EOG signals. Proceedings - 2016 6th International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2016, 443–446.
[16] Steinhausen, N., Prance, R., & Prance, H. (2014). A three sensor eye tracking system based on electrooculography. Proceedings of IEEE Sensors, 2014-Decem(December), 1084–1087.
[17] López, A., Ferrero, F. J., Valledor, M., Campo, J. C., & Postolache, O. (2016). A study on electrode placement in EOG systems for medical applications. 2016 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2016 - Proceedings, 6–10.
[18] Chakraborty, S., Sengupta, A., Dasgupta, A., Srihas, R. S., & Routray, A. (2017). Modeling and Analysis of Electrodes for Electrooculography. 2017 14th IEEE India Council International Conference (INDICON), 1–4.
[20] Bukhari, W. M., Daud, W., Sudirman, R., & Omar, C. (2011). Identification of electrooculography signals frequency energy distribution using wavelet algorithm. Journal of Computer Science, 7(11), 1619–1625.
[21] Lv, Z., Wu, X., Li, M., & Zhang, C. (2008). Implementation of the EOG-based human computer interface system. 2nd International Conference on Bioinformatics and Biomedical Engineering, ICBBE 2008, 1(070412038), 2188–2191.
[22] Merino, M., Rivera, O., Gómez, I., Molina, A., & Dorronzoro, E. (n.d.). A Method of EOG Signal Processing to Detect the Direction of Eye Movements.
[23] Muthmainnah, N., Noor, M., & Ahmad, S. (2013). Analysis of Different Level of EOG Signal from Eye Movement for Wheelchair Control. Int. J. of Biomedical Engineering and Technology, 11(2), 175–196.
[24] Bhuyain, M. F., Kabir Shawon, M. A. U., Sakib, N., Faruk, T., Islam, M. K., & Salim, K. M. (2019). Design and development of an EOG-based system to control electric wheelchair for people suffering from Quadriplegia or Quadriparesis. 1st International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2019, 460–465.
[25] Ding, X. J., & Lv, Z. (2020). Design and development of an EOG-based simplified Chinese eye-writing system. Biomedical Signal Processing and Control, 57, 101767.
[26] López, A., Fernández, M., Rodríguez, H., Ferrero, F., & Postolache, O. (2018). Development of an EOG-based system to control a serious game. Measurement: Journal of the International Measurement Confederation, 127(April), 481–488.
[27] Zhang, P., Ito, M., Ito, S. I., & Fukumi, M. (2013). Implementation of EOG mouse using learning vector quantization and EOG-feature based methods. Proceedings - 2013 IEEE Conference on Systems, Process and Control, ICSPC 2013, (December), 88–92.
[28] Soltani, S., & Mahnam, A. (2016). A practical efficient human computer interface based on saccadic eye movements for people with disabilities. Computers in Biology and Medicine, 70, 163–173.
[29] Zhang, R., He, S., Yang, X., Wang, X., Li, K., Huang, Q., … Li, Y. (2019). An EOG-Based Human-Machine Interface to Control a Smart Home Environment for Patients with Severe Spinal Cord Injuries. IEEE Transactions on Biomedical Engineering, 66(1), 89–100.
[30] Navarro, K. F. (2004). Wearable, wireless brain computer interfaces in augmented reality environments. International Conference on Information Technology: Coding Computing, ITCC, 2(1), 643–647.
[31] Texas Instruments, WANDA PDA, http://focus.ti.com/pdfs/vf/wireless/wanda_031403.pdf
[32] Dünser, A., Grasset, R., Seichter, H., & Billinghurst, M. (2007). Applying HCI Principles to AR Systems Design. Proceedings of 2nd International Workshop on Mixed Reality User Interfaces: Specification, Authoring, Adaptation (MRUI ’07), (March 11), 37–42.
[33] Recoupling, O., Zao, J. K., Jung, T., Chang, H., Gan, T., Wang, Y., … Chien, Y. (2016). Augmenting VR / AR Applications with EEG / EOG Monitoring, 4(July 2018), 121–131.
[34] Putze, F., Weib, D., Vortmann, L. M., & Schultz, T. (2019). Augmented reality interface for smart home control using SSVEP-BCI and eye gaze. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, 2019-Octob, 2812–2817.
[35] Bona, S., Donvito, G., Cozza, F., Malberti, I., Vaccari, P., Lizio, A., … Lunetta, C. (2019). The development of an augmented reality device for the autonomous management of the electric bed and the electric wheelchair for patients with amyotrophic lateral sclerosis: a pilot study. Disability and Rehabilitation: Assistive Technology, 0(0), 1–7.
[36] Wei-An, H. (2020). Developing A Portable Smart Label Recognition System of Environmental Control for Amyotrophic Lateral Sclerosis Patients.
[37] Wiener, A. L. and M. (2001). Classification and Regression by RandomForest.
[38] Díaz-Uriarte, R., & Alvarez de Andrés, S. (2006). Gene selection and classification of microarray data using random forest. BMC Bioinformatics, 7, 1–13.
[39] Zhang, W., & Yu, L. (2018). ECG Signal Classification with Deep Learning for Heart Disease Identification.
[40] Li, D., Zhang, J., Zhang, Q., & Wei, X. (2017). Classification of ECG Signals Based on 1D Convolution Neural Network, 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom) Classification, 17–22.
[41] He, S., & Li, Y. (2017). A single-channel EOG-based speller. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(11), 1978–1987.