在現代社會中，大部分人的生活型態，不論是工作或者休息，往往有很長的時間維
持坐姿。近年來有越來越多的疾病被證實與久坐有關。許多人認為坐姿是種休息的姿
勢，但研究中指出，比起站姿與躺姿，坐姿讓椎間盤承受的壓力更大，而不適當的坐
姿則更提升了椎間盤的壓力。
由於久坐逐漸成為現代人的生活習慣，所以適當的坐姿就顯得格外的重要。在日常
生活中，不適當的坐姿對於大多數的人而言，屬於較為舒適的姿勢，所以往往無心注
意自己的坐姿是否適當。故須透過工具協助來了解自己的坐姿情況。本研究設計一智
慧椅墊之雛形，旨在透過較低的成本 Arduino開發版與少量的壓力感測器，並且準確
的分類使用者的坐姿。
過去使用壓力感測器進行坐姿分類的相關研究中，透過傳統的機器學習方法進行坐
姿的分類，且使用較多數量的感器收集各類坐姿的資料。準確率落在百分之八十至百
分之九十。本研究使用一種傳統機器學習演算法與兩種深度學習之方法進行實驗，找
出適合進行坐姿分類之方式，並以特徵選擇實驗找到能夠準確分類坐姿之感測器數量
及擺放方式。
本研究除了使用限制坐姿使用資料進行坐姿分類模型訓練以及評估初步的分類結
果，並透過實際座椅使用情況資料，再次檢視此智慧椅墊在實際使用情形下，亦能有
良好的做姿分類表現。透過智慧椅墊設計實驗與特徵選擇實驗，本研究完成一智慧椅
墊，使用少量的感測器與基礎的物聯網開發板，降低了硬體成本，達成良好的坐姿分
類表現。

Most people's lifestyles in modern society, no matter they are working or resting, often maintain a prolong time as “sitting” posture. During the past years, more and more diseases have been confirmed to be related to sedentary. Many people regard sitting posture as a relaxing posture, but the research pointed out that sitting posture put much more pressure on the intervertebral disc than standing or lying posture, the improper sitting posture may increases the pressure of the intervertebral disc as well.
Since sedentary sitting has gradually become a habit of most of people, proper sitting posture become more and more important. Improper sitting posture has been regard as a more comfortable posture for most of people, and it is often hard to pay attention to whether or not our sitting posture is appropriate in daily life. Therefore, we may need a tool help us to understand our sitting posture. The aim of this study is to design a prototype of a smart cushion which can classify the user's sitting position accurately, through Arduino101 and a small number of pressure sensors.
Compare with the similar related work, some studies use the traditional machine learning method to classify sitting postures, also a large number of sensors are used to collect data of different sitting postures. The accuracy rate falls between 80% and 90%. In our study, we demonstrate one traditional machine learning algorithm and two methods of deep learning in order to find out the suitable method for sitting posture classification, through the feature selection experiment we can make sure the smallest number of sensors to classify the sitting posture accurately.
In addition to using the limited sitting posture data to train the classification model and evaluate the preliminary classification results, our study also examines the smart cushion under the actual using situation data, and reach a favorable classification performance. Through the smart cushion design experiment and feature selection experiment, this study propose a smart cushion, using small number of sensors and the basic IoT development board, reducing the hardware cost and achieving a good sitting posture classification performance.

Andersson, B. J., Ortengren, R., Nachemson, A. L., Elfström, G., & Broman, H. (1975). The sitting posture: an electromyographic and discometric study. The Orthopedic Clinics of North America, 6(1), 105—120. Retrieved from http://europepmc.org/abstract/MED/1113963
Barsocchi, P., Bianchini, M., Crivello, A., Rosa, D. La, Palumbo, F., & Scarselli, F. (2017). An unobtrusive sleep monitoring system for the human sleep behaviour understanding. 7th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2016 - Proceedings, (CogInfoCom), 91–96. https://doi.org/10.1109/CogInfoCom.2016.7804531
Boulay, B., Brémond, F., & Thonnat, M. (2006). Applying 3D human model in a posture recognition system. Pattern Recognition Letters, 27(15), 1788–1796. https://doi.org/10.1016/j.patrec.2006.02.008
Chamasemani, F. F., & Singh, Y. P. (2011). Multi-class Support Vector Machine (SVM) classifiers - An application in hypothyroid detection and classification. Proceedings - 2011 6th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2011, 351–356. https://doi.org/10.1109/BIC-TA.2011.51
Dardas, N., Chen, Q., Georganas, N. D., & Petriu, E. M. (2010). Hand gesture recognition using bag-of-features and multi-class support vector machine. HAVE 2010 - 2010 IEEE International Symposium on Haptic Audio-Visual Environments and Games, Proceedings, 163–167. https://doi.org/10.1109/HAVE.2010.5623982
Diaz, K. M., Howard, V. J., Hutto, B., Colabianchi, N., Vena, J. E., Safford, M. M., … Steven, P. (2018). Patterns of sedentary behavior and mortality in U.S. middle-aged and older adults: A national cohort study. 167(7), 465–475. https://doi.org/10.7326/M17-0212.Patterns
Edwards, J. (2005). The importance of postural habits in perpetuating myofascial trigger point pain. Acupuncture in Medicine : Journal of the British Medical Acupuncture Society, 23, 77–82. https://doi.org/10.1136/aim.23.2.77
Fricton, J. R., Kroening, R., Haley, D., & Siegert, R. (1985). Myofascial pain syndrome of the head and neck: a review of clinical characteristics of 164 patients. Oral Surgery, Oral Medicine, Oral Pathology, 60(6), 615–623. https://doi.org/10.1016/0030-4220(85)90364-0
Gardner, M. ., & Dorling, S. . (1998). Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric Environment, 32(14–15), 2627–2636. https://doi.org/10.1016/S1352-2310(97)00447-0
Gong, Y., & Zhang, Q. (2016). Hashtag recommendation using attention-based convolutional neural network. IJCAI International Joint Conference on Artificial Intelligence, 2782–2788. Retrieved from https://www.ijcai.org/Proceedings/16/Papers/395.pdf
Hollis, T., Viscardi, A., & Eun Yi, S. (2018). A Comparison of LSTMs and Attention Mechanisms for Forecasting Financial Time Series.
Huang, M., Lee, T., Gibson, I., & Hajizadeh, K. (2012). Effect of Sitting Posture on Spine Joint Angles and Forces. Proceedings of the 6th International Conference on Rehabilitation Engineering & Assistive Technology, (Figure 1), 42:1--42:4. Retrieved from http://dl.acm.org/citation.cfm?id=2501134.2501184
Hubert, H. B., Feinleib, M., Mcnamara, P. M., Castelli, W. P., & Chalon, J. (1984). Obesity as an Independent Risk Factor for Cardiovascular Disease. Survey of Anesthesiology, 28(1), 11. https://doi.org/10.1097/00132586-198402000-00001
InterlinkElectronics. (2015). FSR 406 Data Sheet. 1–4.
Jenkin, M., & Harris, L. (2001). Vision and attention. Springer Science & Business Media.
Kulinski, J., Kozlitina, J., Berry, J., de Lemos, J., & Khera, A. (2015). Sedentary Behavior Is Associated With Coronary Artery Calcification in the Dallas Heart Study. Journal of the American College of Cardiology, 65(10), A1446. https://doi.org/10.1016/s0735-1097(15)61446-2
Lee, J. H., Park, S. Y., & Yoo, W. G. (2011). Changes in craniocervical and trunk flexion angles and gluteal pressure during VDT work with continuous cross-legged sitting. Journal of Occupational Health, 53(5), 350–355. https://doi.org/10.1539/joh.11-0050-OA
Lopez-Meyer, P., Fulk, G. D., & Sazonov, E. S. (2011). Automatic detection of temporal gait parameters in poststroke individuals. IEEE Transactions on Information Technology in Biomedicine, 15(4), 594–601. https://doi.org/10.1109/TITB.2011.2112773
Ma, C., Li, W., Gravina, R., & Fortino, G. (2017). Posture detection based on smart cushion for wheelchair users. Sensors (Switzerland), 17(4), 6–18. https://doi.org/10.3390/s17040719
Ma, L., & Zhang, L. (2019). Text Feature Extraction and Selection Based on Attention Mechanism. https://doi.org/10.1007/978-3-030-16145-3_48
Ma, Y., & Guo, G. (2014). Support vector machines applications. Support Vector Machines Applications, 9783319023, 1–302. https://doi.org/10.1007/978-3-319-02300-7
Mahmood, S., MacInnis, R. J., English, D. R., Karahalios, A., & Lynch, B. M. (2017). Domain-specific physical activity and sedentary behaviour in relation to colon and rectal cancer risk: A systematic review and meta-analysis. International Journal of Epidemiology, 46(6), 1797–1813. https://doi.org/10.1093/ije/dyx137
Martins, L., Lucena, R., Belo, J., Almeida, R., Quaresma, C., Jesus, A. P., & Vieira, P. (2014). Intelligent Chair Sensor -- Classification and Correction of Sitting Posture. In L. M. Roa Romero (Ed.), XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013 (pp. 1489–1492). Cham: Springer International Publishing.
Meyer, J., Arnrich, B., Schumm, J., & Troster, G. (2010). Design and modeling of a textile pressure sensor for sitting posture classification. IEEE Sensors Journal, 10(8), 1391–1398. https://doi.org/10.1109/JSEN.2009.2037330
Morris, J. M.; Lucas, D. B.; Bresler, B. (1961). No TitleRole of the Trunk in Stability of the Spine. The Journal of Bone & Joint Surgery, 43(3), 327–351.
Mutlu, B., Krause, A., Forlizzi, J., Guestrin, C., & Hodgins, J. (2007). Robust, low-cost, non-intrusive sensing and recognition of seated postures. 4(1), 149. https://doi.org/10.1145/1294211.1294237
Namkoong, S., Shim, J., Kim, S., & Shim, J. (2015). Effects of different sitting positions on skin temperature of the lower extremity. Journal of Physical Therapy Science, 27(8), 2637–2640. https://doi.org/10.1589/jpts.27.2637
Nguyen, N. T., Núñez, M., & Trawiski, B. (2017). Collective intelligent information and database systems. Journal of Intelligent and Fuzzy Systems, 32(2), 1157–1160. https://doi.org/10.3233/JIFS-169115
Ouriel, K. (2001). Peripheral arterial disease. The Lancet, 358(9289), 1257–1264. https://doi.org/10.1016/S0140-6736(01)06351-6
Park, Y., & Bae, Y. (2014). Comparison of Postures According to Sitting Time with the Leg Crossed. Journal of Physical Therapy Science, 26(11), 1749–1752. https://doi.org/10.1589/jpts.26.1749
Reddy, M., Gill, S. S., & Rochon, P. A. (2006). Preventing Pressure Ulcers: A Systematic Review. JAMA, 296(8), 974–984. https://doi.org/10.1001/jama.296.8.974
Roh, J., Park, H. J., Lee, K. J., Hyeong, J., Kim, S., & Lee, B. (2018). Sitting posture monitoring system based on a low-cost load cell using machine learning. Sensors (Switzerland), 18(1), 1–13. https://doi.org/10.3390/s18010208
Sozou, P. D., Cootes, T. F., Taylor, C. J., Di Mauro, E. C., & Lanitis, A. (1997). Non-linear point distribution modelling using a multi-layer perceptron. Image and Vision Computing, 15(6), 457–463. https://doi.org/10.1016/s0262-8856(96)00001-7
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … Polosukhin, I. (2017). Attention is All you Need. In I. Guyon, U. V Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 30 (pp. 5998–6008). Retrieved from http://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf
World Health Organization. (2011). The top 10 causes of death. Media Centre, (May), 6–11. Retrieved from http://www.who.int/mediacentre/factsheets/fs310/en/index.html
Wozniak, M. (2008). Classifier fusion based on weighted voting- analytical and experimental results. Proceedings - 8th International Conference on Intelligent Systems Design and Applications, ISDA 2008, 2, 687–692. https://doi.org/10.1109/ISDA.2008.216
Yap, P., Huang, W., Biswas, J., Hsia, C.-C., Liou, K., Foo, S., & Wai, A. (2010). Lying Posture Classification for Pressure Ulcer Prevention. Journal of Healthcare Engineering, 1(2), 217–238. https://doi.org/10.1260/2040-2295.1.2.217
Zemp, R., Tanadini, M., Plüss, S., Schnüriger, K., Singh, N., Taylor, W., & Lorenzetti, S. (2016). Application of Machine Learning Approaches for Classifying Sitting Posture Based on Force and Acceleration Sensors. BioMed Research International, 2016, 1–9. https://doi.org/10.1155/2016/5978489
Zhu, M., Martínez, A. M., & Tan, H. Z. (2003). Template-based Recognition of Static Sitting Postures. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 5(2), 1–6. https://doi.org/10.1109/CVPRW.2003.10049
江忠豪. (2011). 淺談適當坐姿. Retrieved from http://www.tyvh.gov.tw/code_upload/HealthInfo/file1_782_5341122.pdf