Akıllı Saat Algılayıcıları ile İnsan Hareketlerinin Sınıflandırılması

Year 2017, Volume: 21 Issue: 3, 980 - 990, 08.05.2017

Ensar Arif Sağbaş , Serkan Ballı

https://doi.org/10.19113/sdufbed.32689

Cited By: 9

Abstract

Giyilebilir teknolojideki gelişmelerle birlikte ortaya çıkan cihazlar hızla gündelik hayatın bir parçası haline gelmiştir. Özellikle sahip oldukları algılayıcılar, bu cihazların kullanışlılığını artırmaktadır. Bu çalışmanın amacı, akıllı saatlerin sahip olduğu algılayıcılar kullanılarak insan hareketlerinin tespit edilmesidir. Bu amaçla, akıllı saatler üzerinde çalışabilen bir mobil uygulama geliştirilmiştir. Geliştirilen uygulama ile 9 farklı insan hareketi için algılayıcı verileri akıllı saat aracılığı ile toplanmış ve 4 saniyelik pencere aralıkları ile desenler oluşturulmuştur. Oluşturulan desenler 10 farklı makine öğrenmesi yöntemi ile test edilmiş ve performansları karşılaştırılmıştır.

Keywords

Hareket sınıflandırma, Akıllı saat; İvmeölçer; Adımsayar; Makine öğrenmesi

References

• [1] Sağbaş, E.A., Ballı, S. 2016. Giyilebilir Akıllı Cihazlar: Dünü, Bugünü ve Geleceği, Akademik Bilişim Konferansı, 3-5 Şubat, Aydın, Baskıda.
• [2] Su, X., Tong, H., Ji, P. 2014. Activity Recognition with Smartphone Sensors. Tsinghua Science and Technology, 19(3), 235-249.
• [3] Khan A.M., Lee Y.K., Kim T.S. 2008. Accelerometer signal-based human activity recognition using augmented autoregressive model coefficients and artificial neural nets. Engineering in Medicine and Biology Society, 5172-5175.
• [4] Yang, J.Y., Wang, J.S. ve Chen, Y.P. 2008. Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers. Pattern recognition letters, 29(16), 2213-2220.
• [5] Riboni D., Bettini C. 2011. COSAR: hybrid reasoning for context-aware activity recognition. Personal and Ubiquitous Computing, 15(3), 271-289.
• [6] Sağbaş, E.A., Ballı, S. 2016. Akıllı Telefon Sensör Verileri ile Eylem Tanımada Lojistik Regresyon ve kNN Yöntemlerinin Karşılaştırılması, 1st International Conference on Engineering Technology and Applied Science, 21-22 April, Afyonkarahisar, 894-899.
• [7] Chernbumroong S., Atkins A.S., Yu H. 2011. Activity classification using a single wrist-worn accelerometer. In Software, Knowledge Information, Industrial Management and Applications, 1-6.
• [8] Kwapisz J.R., Weiss G.M. ve Moore, S.A. 2014. Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter, 12(2), 74-82.
• [9] Lara, O.D., Pérez A.J., Labrador M.A., Posada J.D. 2012. Centinela: A human activity recognition system based on acceleration and vital sign data. Pervasive and mobile computing, 8(5), 717-729.
• [10] da Silva F. G., Galeazzo E. 2013. Accelerometer based intelligent system for human movement recognition. In Advances in Sensors and Interfaces, 20-24.
• [11] Dadashi, F., Arami, A., Crettenand, F., Millet, G. P., Komar, J., Seifert, L., Aminian, K. 2013 A hidden Markov model of the breaststroke swimming temporal phases using wearable inertial measurement units. In Body Sensor Networks, 6-9 May, MIT, Cambridge, USA, 1-6.
• [12] Mortazavi, B. J., Pourhomayoun, M., Alsheikh, G., Alshurafa, N., Lee, S. I., Sarrafzadeh, M. 2014 Determining the single best axis for exercise repetition recognition and counting on smartwatches. In Wearable and Implantable Body Sensor Networks, 16-19 Haziran, Zürich Switzerland, 33-38.
• [13] Dong, Y., Scisco, J., Wilson, M., Muth, E., Hoover, A. 2014 Detecting periods of eating during free-living by tracking wrist motion. Biomedical and Health Informatics, 18(4), 1253-1260.
• [14] Guiry, J.J., van de Ven P., ve Nelson J. 2014. Multi-sensor fusion for enhanced contextual awareness of everyday activities with ubiquitous devices. Sensors, 14(3), 5687-5701.
• [15] Wang, S., Chen, C. Ma, J. 2010. Accelerometer based transportation mode recognition on mobile phones. Wearable Computing Systems (APWCS), 44-46
• [16] Shoaib M., Bosch S., Scholten H., Havinga P. J., Incel O. D. 2015. Towards detection of bad habits by fusing smartphone and smartwatch sensors. In Pervasive Computing and Communication Workshops, St. Louis, 591-596.
• [17] Weiss G.M., Timko J.L., Gallagher C.M., Yoneda K., Schreiber A.J. 2016. Smartwatch-based activity recognition: A machine learning approach. Biomedical and Health Information. 426-429.
• [18] Ballı S., ve Sağbaş, E.A. 2017 The Usage of Statistical Learning Methods on Wearable Devices and a Case Study: Activity Recognition on Smartwatches, Advances in Statistical Methodologies and Their Applications to Real Problems, InTech, Rijeka, Croatia, Baskıda.
• [19] Chandra B., Gupta M., 2011. Robust approach for estimating probabilities in Naïve–Bayes Classifier for gene expression data. Expert Systems with Applications, 38(3), 1293-1298.
• [20] Feng T., Timmermans H.J.P. 2010. Comparative Evaluation of Algorithms for GPS Data Imputation. 13th WCTR, 15 Temmuz, Rio de Janerio, 1-11.
• [21] Sökün H., Kalkan H., Cetişli B. 2012. Classification of physical activities using accelerometer signals. In Signal Processing and Communications Applications Conference, 18-20 Nisan, Muğla, 1-4.
• [22] Breiman, L. 2001. Random Forests. Machine Learning. 45(1), 5-32.
• [23] Özkan, Y., Selçukcan Erol, Ç. 2015. Biyoenformatik DNA Mikrodizi Veri Madenciliği. Papatya Yayıncılık Eğitim, İstanbul, 432s.
• [24] Korb K.B, Nicholson A.E. 2011. Bayesian Artificial Intelligence. 2, David Blei, David Madigan, Marina Meila, Fionn Murtagh, Boca Raton, 452s.
• [25] Frank, E., Wang, Y., Inglis, S., Holmes, G., Witten, I. H. 1998. Using model trees for classification. Machine Learning, 32(1), 63-76.
• [26] Zhao, Y., Zhang, Y. 2008. Comparison of decision tree methods for finding active objects. Advances in Space Research, 41(12), 1955-1959.
• [27] Moto 360, http://www.motorola.com/us/products/moto-360 (Erişim Tarihi: 05.04.2016)
• [28] Bieber, G., Peter, C. 2008. Using physical activity for user behavior analysis. In Proceedings of the 1st international conference on PErvasive Technologies Related to Assistive Environments, Atina, 15-19 Temmuz, p. 94.
• [29] Use WEKA in your Java code, https://weka.wikispaces.com/Use+WEKA+in+your+Java+code (Erişim Tarihi: 05.04.2016)
• [30] Sağbaş E.A., Ballı S. 2016. Akıllı Telefon Algılayıcıları ve Makine Öğrenmesi Kullanılarak Ulaşım Türü Tespiti. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 22(5), 376-383
• [31] Using the Step Counter Sensor, http://developer.android.com/guide/topics/sensors/sensors_motion.html#sensors-motion-stepcounter (Erişim Tarihi: 05.04.2016)
• [32] Ballı S., 2016. A data mining approach to the diagnosis of failure modes for two serial fastened sandwich composite plates. Journal of Composite Materials. Baskıda.
• [33] Witten I.H., Frank E. 2005. Data mining: Practical machine learning tools and techniques. San Francisco, CA: Morgan Kaufmann Publishers, 525s.
• [34] Garner, S. R. (1995). Weka: The waikato environment for knowledge analysis. In Proceedings of the New Zealand computer science research students conference. Hamilton, New Zealand, 57-64.