本研究旨在開發一個開發基於個人化機械學習演算法模型的智慧型刷牙區域偵
測應用程序，本研究開發了一支內置三軸加速度計、陀螺儀、藍芽無線傳輸模組的
智慧牙刷。刷牙時牙刷的三軸加速度訊號及陀螺儀訊號會經由藍芽傳輸到 Android手
機上由本研究開發的手機應用程序進行處理資料，本研究採用支持向量機以及線性
識別分析作為辨識器，並將口腔內分為十三個區域，透過十位受測者的測試，本研
究使用支持向量機辨識口腔區域時可達到 97.5%辨識正確率、使用線性識別分析時
可達到 94.4 的辨識正確率。

The prevalence of dental caries remains high because existing toothbrush products do not offer users a reference index for measuring the degree of brushing efficacy. As a result of the toothbrushing region classification and the computation of brushing duration, we can offer users a reference standard for measuring the degree of cleanliness. The purpose of this study are classification brushing regions in smartpho developed a smart toothbrush app software using an inertial measurement unit and offered an artificial intelligence-based personalized toothbrushing regions classification technique and can be implemented on a smartphone directly. nes. The MPU6050 IMU was used in the hardware and firmware part to construct a smart toothbrush system and collect the inertia signal when brushing. In the Arduino Nano, we used the Madgwick algorithm with acceleration and angular velocity to calculate the toothbrush's orientation. The data was then transferred to the smartphone through Bluetooth for examination. We utilized python to design the algorithm, including signal processing, feature selection, AI classifier construction, and cross-validation. We removed the data affected by computation delay in the signal processing section and retained the data containing orientation information. We chose tri-axial acceleration and orientation (Roll, Pitch, and Yaw) as the classification features of the classifiers in the feature selection section. Three different machine learning classifiers were utilized in the part of the classifier construction: linear discriminant analysis (LDA), support vector machine (SVM), and logistic regression. In the cross-validation part, we used hold-out cross-validation and leave-one-out cross-validation to evaluate the stability and performance of the proposed algorithm. We conducted two kinds of experiments: subjects with single trial (SST) and subjects with real-time trials (SRT). The results showed that: in the SST, the average accuracy of SVM was the best, reaching 97.5% by using hold-out cross-validation and 96.9 % by using leave-one-out cross-validation. In the SRT, the accuracy LDA is the best result in a real-time process. The average LDA accuracy achieved 94.4 %. The performance of the logistic regression classifier was the worst, with average accuracy equaled to 84.06 %. By comparing machine learning results, the LDA classifier was suitable for this study. It can enhance the association between the inertial data in the same region and better classification results. In summary, this study successfully developed a smart toothbrush app software and a personalized toothbrushing region classification algorithm.

[1] D. A. Maharani, S. Zhang, S. S. Gao, C.-H. Chu, and A. Rahardjo, “Dental caries and the erosive tooth wear status of 12-year-old children in Jakarta, Indonesia,” International Journal of Environmental Research and Public Health, vol. 16, no. 16, p. 2994, 2019.
[2] W. H. Organization, “Oral Health Surveys: Basic Methods, ” World Health Organization: Geneva, 2013. [Online]. Available: https://reurl.cc/rl9mGx. [Accessed: 18-Dec-2021]
[3] C. R. Dugmore and W. P. Rock, “The prevalence of tooth erosion in 12-year-old children,” British Dental Journal, vol. 196, no. 5, pp. 279–282, 2004.
[4] C. H. Chu, A. W. Wong, E. C. Lo, and F. Courtel, “Oral Health Status and behaviours of children in rural districts of Cambodia,” International Dental Journal, vol. 58, no. 1, pp. 15–22, 2008.
[5] J. Gibson and A. B. Wade, “Plaque removal by the Bass and Roll brushing techniques, ” Journal of Periodontology, vol. 48, no. 8, pp. 456-459, 1977.
[6] M. Poyato‐Ferrera, J. Segura‐Egea, and P. Bullón‐Fernández, “Comparison of modified Bass technique with normal toothbrushing practices for efficacy in supragingival plaque removal, ” International Journal of Dental Hygiene, vol. 1, no. 2, pp. 110-114, 2003.
[7] C.-H. Chen, C.-C. Wang, and Y.-Z. Chen, “Intelligent Brushing Monitoring Using a Smart Toothbrush with Recurrent Probabilistic Neural Network, ” Sensors, vol. 21, no. 4, p. 1238, 2021.
[8] P. D. Marsh, “Microbiology of dental plaque biofilms and their role in oral health and caries, ” Dental Clinics, vol. 54, no. 3, pp. 441-454, 2010.
[9] C. Ganss, N. Schlueter, S. Preiss, and J. Klimek, “Tooth brushing habits in uninstructed adults—frequency, technique, duration and force, ” Clinical Oral Investigations, vol. 13, no. 2, pp. 203-208, 2009.
[10] G. A. Weijden, M. F. Timmerman, E. Reijerse, C. M. Snoek, and U. Velden, “Toothbrushing force in relation to plaque removal,” Journal of Clinical Periodontology, vol. 23, no. 8, pp. 724–729, 1996.

[11] S. Turesky, N. D. Gilmore, and I. Glickman, “Reduced plaque formation by the chloromethyl analogue of victamine C, ” Journal of Periodontology, vol. 41, no. 1, pp. 41-43, 1970.
[12] G. Van der Weijden, M. Timmerman, M. Danser, and U. Van der Velden, “Relationship between the plaque removal efficacy of a manual toothbrush and brushing force,” Journal of Clinical Periodontology, vol. 25, no. 5, pp. 413-416, 1998.
[13] G. Van der Weijden, M. Timmerman, M. Danser, M. Piscaer, Y. Ijzerman, and U. Van der Velden, “Approximal brush head used on a powered toothbrush, ” Journal of Clinical Periodontology, vol. 32, no. 3, pp. 317-322, 2005.
[14] A. Gallagher et al., “The effect of brushing time and dentifrice on dental plaque removal in vivo, ” American Dental Hygienists' Association, vol. 83, no. 3, pp. 111-116, 2009.
[15] T. Winterfeld, N. Schlueter, D. Harnacke, J. Illig, J. Margraf-Stiksrud, R. Deinzer, and C. Ganss, “Toothbrushing and flossing behaviour in young adults—a video observation,” Clinical Oral Investigations, vol. 19, no. 4, pp. 851–858, 2014.
[16] F. A. Van der Weijden and D. E. Slot, “Efficacy of homecare regimens for mechanical plaque removal in managing gingivitis a meta review, ” Journal of Clinical Periodontology, vol. 42, pp. S77-S91, 2015.
[17] E. Bernmark and C. Wiktorin, “A triaxial accelerometer for measuring arm movements, ” Applied Ergonomics, vol. 33, no. 6, pp. 541-547, 2002.
[18] H. J. Luinge and P. H. Veltink, “Measuring orientation of human body segments using miniature gyroscopes and accelerometers, ” Medical and Biological Engineering and Computing, vol. 43, no. 2, pp. 273-282, 2005.
[19] J.-W. Lee, K.-H. Lee, K.-S. Kim, D.-J. Kim, and K. Kim, “Development of smart toothbrush monitoring system for Ubiquitous Healthcare,” 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, 2006.
[20] K.-H. Lee, J.-W. Lee, K.-S. Kim, D.-J. Kim, K. Kim, H.-K. Yang, K. Jeong, and B. Lee, “Tooth brushing pattern classification using three-axis accelerometer and magnetic sensor for smart toothbrush,” 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007.
[21] Y.-C. Chang et al., “Playful toothbrush: ubicomp technology for teaching tooth brushing to kindergarten children, ” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2008, pp. 363-372.
[22] Y.-J. Lee, P.-J. Lee, J.-W. Lee, K.-S. Kim, J.-S. Jeong, W. Park, and K.-D. Kim, “Toothbrushing region detection using three-axis accelerometer and magnetic sensor, ” IEEE Transactions on Biomedical Engineering, vol. 59, no. 3, pp. 872-881, 2011.
[23] Y.-J. Lee, P.-J. Lee, J.-W. Lee, K.-S. Kim, J.-S. Jeong, W. Park, and K.-D. Kim, “Quantitative assessment of toothbrushing education efficacy using smart toothbrush,” 2011 4th International Conference on Biomedical Engineering and Informatics (BMEI), 2011.
[24] H. Huang and S. Lin, “Toothbrushing monitoring using wrist watch,” Proceedings of the 14th ACM Conference on Embedded Network Sensor Systems CD-ROM, 2016.
[25] Oral-B, “Oral-B GENIUS 9000, ” Oral-B.com. [Online]. Available: https://reurl.cc/247agX. [Accessed: 25-Dec-2021]
[26] Freddie, “FlexCare Platinum Connected, ” philips.com. [Online]. Available: https://reurl.cc/mdzpnA. [Accessed: 25-Dec-2021]
[27] Prophix, “An innovative way to brush, ” getprophix.com. [Online]. Available: https://reurl.cc/YlGKXD. [Accessed: 25-Dec-2021]
[28] Grush, “Grush Smart Toothbrush, ” grushgamer.com. [Online]. Available: https://reurl.cc/EKW5Rk. [Accessed: 25-Dec-2021]
[29] Oclean, “Oclean One, ” oclean.com. [Online]. Available: https://reurl.cc/yy0558. [Accessed: 25-Dec-2021].
[30] J. Escudero, E. Ifeachor, J. P. Zajicek, C. Green, J. Shearer, and S. Pearson, “Machine learning-based method for personalized and cost-effective detection of alzheimer's disease,” IEEE Transactions on Biomedical Engineering, vol. 60, no. 1, pp. 164–168, 2013.
[31] O. Rudovic, J. Lee, M. Dai, B. Schuller, and R. W. Picard, “Personalized machine learning for robot perception of affect and engagement in autism therapy, ” Science Robotics, vol. 3, no. 19, 2018.
[32] S. Madgwick, “An efficient orientation filter for inertial and inertial/magnetic sensor arrays, ” Report x-io and University of Bristol (UK), vol. 25, pp. 113-118, 2010.
[33] S. A. Ludwig, “Optimization of control parameter for filter algorithms for attitude and heading reference systems,” 2018 IEEE Congress on Evolutionary Computation (CEC), 2018.
[34] Scikit-learn, “Scikit-learn Machine Learning in Python, ” Scikit-learn.org. [Online]. Available: shorturl.at/swLX9. [Accessed: 2-Jan-2022].
[35] S. Mika, G. Ratsch, J. Weston, B. Scholkopf, and K. R. Mullers, “Fisher discriminant analysis with kernels,” Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).
[36] Scikit-learn, “Linear and Quadratic Discriminant Analysis, ” Scikit-learn.org. [Online]. Available: https://reurl.cc/pD3lob. [Accessed: 1-Jan-2022].
[37] A. Tharwat, T. Gaber, A. Ibrahim, and A. E. Hassanien, “Linear discriminant analysis: A detailed tutorial, ” AI Communications, vol. 30, no. 2, pp. 169-190, 2017.
[38] C. J. Burges, “A tutorial on support vector machines for pattern recognition, ” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998.
[39] A. Ganapathiraju, J. E. Hamaker, and J. Picone, “Applications of support vector machines to speech recognition, ” IEEE transactions on signal processing, vol. 52, no. 8, pp. 2348-2355, 2004.
[40] D. N. Tran and D. D. Phan, “Human activities recognition in Android smartphone using support vector machine,” 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS), 2016.
[41] M. Awad and R. Khanna, “Support vector machines for classification, ” Efficient Learning Machines: Springer, pp. 39-66 , 2015.
[42] C.-Y. J. Peng, K. L. Lee, and G. M. Ingersoll, “An introduction to logistic regression analysis and reporting, ” The Journal of Educational Research, vol. 96, no. 1, pp. 3-14, 2002.
[43] A. Pant, “Introduction to logistic regression,” Medium, 22-Jan-2019. [Online]. Available: shorturl.at/iDKS9.
[44] Wikipedia, “Cross-validation, ” wikipedia.org. [Online]. Available: https://reurl.cc/rl9mGx. [Accessed: 2-Jan-2022].
[45] S. Yadav and S. Shukla, “Analysis of k-fold cross-validation over hold-out validation on colossal datasets for Quality Classification,” 2016 IEEE 6th International Conference on Advanced Computing (IACC), 2016.
[46] L. Bo, L. Wang, and L. Jiao, “Feature scaling for kernel fisher discriminant analysis using leave-one-out cross validation, ” Neural Computation, vol. 18, no. 4, pp. 961-978, 2006.
[47] M. Smith, “The easiest way to use python in an Android app,” Chaquopy. [Online]. Available: shorturl.at/lvCT5. [Accessed: 2-Jan-2022].