İnsan aktivite tespiti son zamanlarda popülerliği artan bir makine öğrenmesi problemidir. Hareketi tespit etmek için ivmeölçer, jiroskop v.b sensörler veya kamera yardımıyla görüntü işleme yapılarak tahminler yapılabilmektedir. Bireylerden sensörler vasıtasıyla alınan veriler ön işlemden geçerek sınıflandırma algoritmaları ile sınıflandırılarak kişilerin hangi hareketi yaptıkları tespit edilmeye çalışılmaktadır. Bu çalışma kapsamında mobil cihaz için yapılan android yazılım ile cihazın ivmeölçer sensörü kullanılarak nesnelerin interneti tabanlı insan hareketlerinin tespiti gerçekleştirilmiştir. İlk önce tespiti yapılacak hareketler için veri toplanmıştır ve ön işlemden geçirilmiştir. Daha sonra oluşan veri setinden özellik çıkarımı yapılmıştır. Elde edilen veri üzerine Destek Vektör Makinaları, Rastgele Orman ve K En Yakın Komşuluk algoritmaları uygulanarak yapılan hareketler sınıflandırılmıştır. Sınıflandırma başarıları tespit edilmiş olup en başarılı sınıflandırma algoritması nesnelerin interneti tabanlı uygulama ile gerçek zamanlı sınıflandırma işlemi için kullanılmıştır.
Human activity detection is a machine learning problem that has recently become more popular. Estimations can be done using image processing by means of accelerometer, gyroscope, sensor or camera to detect movement. The data obtained from the individuals through sensors is pre-processed and classified with classification algorithms to determine which movement they make. Within the scope of this study, the internet based human movements were determined by using the accelerometer sensor of a device with an android software made for the mobile device. First, data was collected and pre-processed for the movements to be determined. Then feature extraction was performed from the data set. The movements were classified by using Support Vector Machines, Random Forest and K Nearest Neighbour algorithms on the resulting data. Classification successes have been determined and the most successful classification algorithm has been used for real time classification of objects with internet based application.
___
[1]. Uddin, M. Z. “A wearable sensor-based activity prediction system to facilitate edge computing in smart healthcare system”. Journal of Parallel and Distributed Computing”, 123, 46-53,2019.
[2]. Yamada, Y., Shinkuma, R., Iwai, T., Onishi, T., Nobukiyo, T., & Satoda, K. “Temporal traffic smoothing for IoT traffic in mobile networks”. Computer Networks, 146, 115-124, 2018..
[3]. M. M. Hassan, M. Z. Uddin, A. Mohamed, and A. Almogren, “A robust human activity recognition system using smartphone sensors and deep learning,” Futur. Gener. Comput. Syst., vol. 81, pp. 307–313, 2018.
[4]. S. H. Cha, J. Seo, S. H. Baek, and C. Koo, “Towards a well-planned, activity-based work environment: Automated recognition of office activities using accelerometers,” Build. Environ., vol. 144, no. April, pp. 86–93, 2018.
[5]. C. Catal, S. Tufekci, E. Pirmit, and G. Kocabag, “On the use of ensemble of classifiers for accelerometer-based activity recognition,” Appl. Soft Comput. J., vol. 37, pp. 1018–1022, 2015.
[6]. M. Babiker, O. O. Khalifa, K. Kyaw Htike, A. Hassan, and M. Zaharadeen, “Automated Daily Human Activity Recognition for Video Surveillance Using Neural Network,” Proc. 4th IEEE Int. Conf. Smart Instrumentation, Meas. Appl., no. November, pp. 28–30, 2017.
[7]. Y. Chen and C. Shen, “Performance Analysis of Smartphone-Sensor Behavior for Human Activity Recognition,” IEEE Access, vol. 5, pp. 3095–3110, 2017.
[8]. M. A. Ayu, S. A. Ismail, A. F. Abdul Matin, and T. Mantoro, “A comparison study of classifier algorithms for mobile-phone’s accelerometer based activity recognition,” Procedia Eng., vol. 41, no. Iris, pp. 224–229, 2012.
[9]. Ermes, M., Pärkkä, J., Mäntyjärvi, J., & Korhonen, I. "Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions". IEEE transactions on information technology in biomedicine.,vol. 12,pp. 20-26,2008.
[10]. Bulbul, E., Cetin, A., & Dogru, I. A. (2018, October). Human activity recognition using smartphones. In 2018 2nd international symposium on multidisciplinary studies and innovative technologies (ismsit) (pp. 1-6). IEEE.
[11]. Akhavian, R., & Behzadan, A. H. (2016). Smartphone-based construction workers' activity recognition and classification. Automation in Construction, 71, 198-209.
[12]. Bayat, A., Pomplun, M., & Tran, D. A. (2014). A study on human activity recognition using accelerometer data from smartphones. Procedia Computer Science, 34, 450-457.
[13]. Esfahani, P., & Malazi, H. T. (2017, December). PAMS: A new position-aware multi-sensor dataset for human activity recognition using smartphones. In 2017 19th International Symposium on Computer Architecture and Digital Systems (CADS) (pp. 1-7). IEEE.
[14]. C. Cortes, V. Vapnik, Support-vector networks, Machine learning, vol. 20(3), pp. 273-297,1995 Breiman, L.." Random forests". Machine learning,vol. 45,pp. 5-32, 2001.
[15]. Ericsson mobility report june 2017 (https://www.ericsson.com/assets/local/mobilityreport/docu ments/2017/ericsson-mobility-report-june-2017.pdf )