根據研究指出，頭部長時間處於不當姿勢，將導致肩頸僵硬，而久坐對於腰椎、眼睛的不適，有很大的影響，另外，導致電腦視覺綜合症(Computer vision syndrome, CVS)，或數位眼疲勞(digital eye strain, DES)的原因，可能包含了光線不好、坐姿不良、觀看距離不當等因素，美國眼科學會建議讓眼睛定期休息、有意識的多眨眼、調整電腦位置等方式，來緩解眼睛疲勞。
因此，本研究蒐集了人體工學的建議坐姿，以及眼科醫師對於如何正確使用電腦的建議，整理出需求，以提醒使用者。本研究使用筆電鏡頭，採用深度學習的方法，偵測使用者的頭部姿勢、使用時間、距離以及眼睛注視的方向，以偵測使用者是否不當使用電腦，也偵測眨眼頻率，用以提醒使用者適時休息或眨眼來滋潤眼睛。

According to research findings, maintaining an improper posture of the head for prolonged periods can lead to stiffness in the neck and shoulders. Prolonged sitting also significantly affects the discomfort in the lumbar spine and eyes. Additionally, the causes of Computer Vision Syndrome (CVS) or Digital Eye Strain (DES) may encompass factors such as poor lighting, poor posture, and improper viewing distance. The American Academy of Ophthalmology recommends practices like regular eye breaks, conscious blinking, and adjusting computer positions to alleviate eye fatigue.
Therefore, this study collected ergonomic recommendations for proper sitting posture and advices from ophthalmologists on correct computer usage. These insights were organized to serve as reminders for users. The study employed a laptop camera and employed deep learning techniques to detect users' head posture, usage time, distance, and the direction of their gaze. This allowed for the identification of improper computer usage and the measurement of blink frequency to prompt users to take breaks or blink more frequently to refresh their eyes.

[1] M. Vergara and Á. Page, "Relationship between comfort and back posture and mobility in sitting-posture," Applied Ergonomics, vol. 33, no. 1, pp. 1-8, 2002.
[2] 行政院勞工委員會勞工安全衛生研究所, "電腦工作者上肢疼痛之危險因子與職場運動之效果," 行政院勞工委員會勞工安全衛生研究所, 2004.
[3] S. Wimalasundera, “Computer vision syndrome,” Galle Medical Journal, vol. 11, no. 1, pp. 25–29, 2006.
[4] N. A. Charpe and V. Kaushik, "Computer vision syndrome (CVS): recognition and control in software professionals," Journal of Human Ecology, vol. 28, no. 1, pp. 67-69, 2009.
[5] American Optometric Association, "Computer vision syndrome," [Online]. Available: https://www.aoa.org/patients-and-public/caring-for-your-vision/protecting-your-vision/computer-vision-syndrome?sso=y (last accessed July 20, 2023).
[6] American Academy of Ophthalmology, "Computers, Digital Devices and Eye Strain," [Online]. Available: https://www.aao.org/eye-health/tips-prevention/computer-usage (last accessed July 20, 2023).
[7] Health and Safety Executive, "Working safely with display screen equipment," [Online]. Available: https://www.hse.gov.uk/msd/dse/work-routine.htm (last accessed July 20, 2023).
[8] Upright, [Online]. Available: https://store.uprightpose.com/products/upright-go2 (last accessed July 20, 2023).
[9] Olesya Chernyavskaya, "Fix-posture," [Online]. Available: https://www.hse.gov.uk/msd/dse/work-routine.htm (last accessed July 20, 2023).
[10] SitApp, [online]. Available: https://sitapp.app/ (last accessed July 20, 2023)
[11] F. Zhang, X. Fan, G. Ai, J. Song, Y. Qin, and J. Wu, "Accurate face detection for high performance," arXiv preprint arXiv:1905.01585, 2019.
[12] J. Li, Y. Wang, C. Wang, Y. Tai, J. Qian, J. Yang, et al., "DSFD: dual shot face detector," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5060-5069.
[13] Y. He, D. Xu, L. Wu, M. Jian, S. Xiang, and C. Pan, "Lffd: A light and fast face detector for edge devices," arXiv preprint arXiv:1904.10633, 2019.
[14] Y. Wang, X. Ji, Z. Zhou, H. Wang, and Z. Li, "Detecting faces using region-based fully convolutional networks," arXiv preprint arXiv:1709.05256, 2017.
[15] E. Ohn-Bar and M. M. Trivedi, "To boost or not to boost? on the limits of boosted trees for object detection," in 2016 23rd International Conference on Pattern Recognition (ICPR), 2016, pp. 3350-3355.
[16] K. Zhang, Z. Zhang, Z. Li, and Y. Qiao, "Joint face detection and alignment using multitask cascaded convolutional networks," IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499-1503, 2016.
[17] G. Fanelli, M. Dantone, J. Gall, A. Fossati, and L. Van Gool, "Random forests for real time 3D face analysis," International Journal of Computer Vision, vol. 101, pp. 437-458, 2013.
[18] J. Yang, W. Liang, and Y. Jia, "Face pose estimation with combined 2d and 3d hog features," in Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), 2012, pp. 2492-2495.
[19] T. Baltrušaitis, P. Robinson, and L. P. Morency, "3D constrained local model for rigid and non-rigid facial tracking," in 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2610-2617.
[20] A. Saeed and A. Al-Hamadi, "Boosted human head pose estimation using Kinect camera," in 2015 IEEE International Conference on Image Processing (ICIP), 2015, pp. 1752-1756.
[21] M. Venturelli, G. Borghi, R. Vezzani, and R. Cucchiara, "From depth data to head pose estimation: a siamese approach," arXiv preprint arXiv:1703.03624, 2017.
[22] M. Venturelli, G. Borghi, R. Vezzani, and R. Cucchiara, "Deep head pose estimation from depth data for in-car automotive applications," in Understanding Human Activities Through 3D Sensors: Second International Workshop, UHA3DS 2016, Held in Conjunction with the 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun, Mexico, December 4, 2016, Revised Selected Paperss 2, 2018, pp. 74-85.
[23] T. Hempel, A. A. Abdelrahman, and A. Al-Hamadi, "6D rotation representation for unconstrained head pose estimation," in 2022 IEEE International Conference on Image Processing (ICIP), October 2022, pp. 2496-2500.
[24] E. Wood, T. Baltrušaitis, L. P. Morency, P. Robinson, and A. Bulling, "Learning an appearance-based gaze estimator from one million synthesised images," in Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications, 2016, pp. 131-138.
[25] X. Zhang, Y. Sugano, M. Fritz, and A. Bulling, "MPIIGaze: Real-world dataset and deep appearance-based gaze estimation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 1, pp. 162-175, 2017.
[26] X. Zhang, Y. Sugano, M. Fritz, and A. Bulling, "It's written all over your face: Full-face appearance-based gaze estimation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp. 51-60.
[27] T. Baltrusaitis, A. Zadeh, Y. C. Lim, and L. P. Morency, "OpenFace 2.0: Facial behavior analysis toolkit," in 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), 2018, pp. 59-66.
[28] M. M. Rahman, M. S. Islam, M. K. A. Jannat, M. H. Rahman, M. Arifuzzaman, R. Sassi, and M. Aktaruzzaman, "EyeNet: An improved eye states classification system using convolutional neural network," in 2020 22nd International Conference on Advanced Communication Technology (ICACT), 2020, pp. 84-90.
[29] S. Mohanty, S. V. Hegde, S. Prasad, and J. Manikandan, "Design of real-time drowsiness detection system using dlib," in 2019 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE), 2019, pp. 1-4.
[30] J. C. Izquierdo et al., "Factors leading to the Computer Vision Syndrome: an issue at the contemporary workplace," Boletin de la Asociacion Medica de Puerto Rico, vol. 96, no. 2, pp. 103-110, 2004.
[31] Office for National Statistics, "Internet users in the UK 2020," [Online]. Available: https://www.ons.gov.uk/businessindustryandtrade/itandinternetindustry/bulletins/internetusers/2020 (last accessed: June 4, 2022.)
[32] Ofcom, "UK’s internet use surges to record level," 2020. [Online]. Available: https://www.ofcom.org.uk/about-ofcom/latest/media/media-releases/2020/uk-internet-use-surges (last accessed: June 4, 2022.)
[33] C. Blehm et al., "Computer vision syndrome: a review," Survey of ophthalmology, vol. 50, no. 3, pp. 253-262, 2005.
[34] S. Gowrisankaran and J. E. Sheedy, "Computer vision syndrome: A review," Work, vol. 52, no. 2, pp. 303-314, 2015.
[35] K. M. Daum et al., "Productivity associated with visual status of computer users," Optometry-Journal of the American Optometric Association, vol. 75, no. 1, pp. 33-47, 2004.
[36] J. E. Sheedy, J. Hayes, and J. Engle, "Is all asthenopia the same?," Optometry and vision science, vol. 80, no. 11, pp. 732-739, 2003.
[37] Y. Yaginuma et al., "Study of the relationship between lacrimation and blink in VDT work," Ergonomics, vol. 33, no. 6, pp. 799-808, 1990.
[38] K. Tsubota, "Tear dynamics and dry eye," Progress in retinal and eye research, vol. 17, no. 4, pp. 565-596, 1998.
[39] G. V. Hultgren and B. Knave, "Discomfort glare and disturbances from light reflections in an office landscape with CRT display terminals," Applied Ergonomics, vol. 5, no. 1, pp. 2-8, 1974.
[40] A. J. Wilkins, C. D. Binnie, and C. E. Darby, "Visually-induced seizures," Progress in Neurobiology, vol. 15, no. 2, pp. 85-117, 1980.
[41] Video Electronic Standards Association, “White paper| VESA DISPLAYPORT ADAPTIVE-SYNC,” 2014. [Online]. Available: https://www.vesa.org/wp-content/uploads/2014/07/VESA-Adaptive-Sync-Whitepaperstudy-140620.pdf (last accessed: June 4, 2022.)
[42] K. L. Turville et al., "The effects of video display terminal height on the operator: a comparison of the 15 and 40 recommendations," Applied Ergonomics, vol. 29, no. 4, pp. 239-246, 1998.
[43] D. Rempel et al., "The effects of visual display distance on eye accommodation, head posture, and vision and neck symptoms," Human factors, vol. 49, no. 5, pp. 830-838, 2007.
[44] M. Vergara and Á. Page, "Relationship between comfort and back posture and mobility in sitting-posture," Applied ergonomics, vol. 33, no. 1, pp. 1-8, 2002.
[45] L. Punnett and U. Bergqvist, "Visual display unit work and upper extremity musculoskeletal disorders," Stockholm: National Institute for Working Life 997, 1997.
[46] S. M. Moore, J. Torma-Krajewski, and L. J. Steiner, "Practical demonstrations of ergonomic principles," 2011.
[47] S. L. Sauter, L. M. Schleifer, and S. J. Knutson, "Work posture, workstation design, and musculoskeletal discomfort in a VDT data entry task," Human factors, vol. 33, no. 2, pp. 151-167, 1991.
[48] Intel, “What is AI?”. [online]. Available: https://www.intel.com/content/dam/develop/public/us/en/documents/ai-infographic.pdf. (last accessed: July 20, 2023).
[49] R. Yamashita et al., "Convolutional neural networks: an overview and application in radiology," Insights into imaging, vol. 9, no. 4, pp. 611-629, 2018.
[50] S. Albawi, T. A. Mohammed, and S. Al-Zawi, "Understanding of a convolutional neural network," 2017 international conference on engineering and technology (ICET), IEEE, 2017.
[51] Y. LeCun et al., "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[52] B. Sapp and B. Taskar, "Modec: Multimodal decomposable models for human pose estimation," Proceedings of the IEEE conference on computer vision and pattern recognition, 2013.
[53] M. Andriluka et al., "2d human pose estimation: New benchmark and state of the art analysis," Proceedings of the IEEE Conference on computer Vision and Pattern Recognition, 2014.
[54] T.-Y. Lin et al., "Microsoft coco: Common objects in context," European conference on computer vision, Springer, Cham, 2014.
[55] V. Bazarevsky et al., "Blazepose: On-device real-time body pose tracking," arXiv preprint arXiv:2006.10204, 2020.
[56] A. Toshev and C. Szegedy, "Deeppose: Human pose estimation via deep neural networks," Proceedings of the IEEE conference on computer vision and pattern recognition, 2014.
[57] J. J. Tompson et al., "Joint training of a convolutional network and a graphical model for human pose estimation," Advances in neural information processing systems 27, 2014.
[58] Z. Cao et al., "Realtime multi-person 2d pose estimation using part affinity fields," Proceedings of the IEEE conference on computer vision and pattern recognition, 2017.
[59] G. Fanelli et al., "Random forests for real time 3d face analysis," International journal of computer vision, vol. 101, no. 3, pp. 437-458, 2013.
[60] D. F. DeMenthon and L. S. Davis, "Model-based object pose in 25 lines of code," International journal of computer vision, vol. 15, no. 1, pp. 123-141, 1995.
[61] J. Canny, "A computational approach to edge detection," IEEE Transactions on pattern analysis and machine intelligence, vol. 6, pp. 679-698, 1986.
[62] R. O. Duda and P. E. Hart, "Use of the Hough transformation to detect lines and curves in pictures," Communications of the ACM, vol. 15, no. 1, pp. 11-15, 1972.
[63] OpenVINO. “face-detection-adas-001”. [online]. Available: https://docs.openvino.ai/2023.0/omz_models_model_face_detection_adas_0001.html. (last accessed:: July 22, 2023.)
[64] OpenVINO. “head-pose-estimation-001”. [online]. Available: https://docs.openvino.ai/2023.0/omz_models_model_head_pose_estimation_adas_0001.html. (last accessed: July 22, 2023.)
[65] OpenVINO. “open-closed-eye-0001”. [Online]. Available: https://docs.openvino.ai/2023.0/omz_models_model_open_closed_eye_0001.html. (last accessed: July 22, 2023.)
[66] OpenVINO. “gaze-estimation-adas-0002”. [Online]. Available: https://docs.openvino.ai/2023.0/omz_models_model_gaze_estimation_adas_0002.html. (last accessed: July 22, 2023.)
[67] W. H. DeLone and E. R. McLean, "Information systems success revisited," Proceedings of the 35th annual Hawaii international conference on system sciences, pp. 2966-2976, January 2002.