Otokodlayıcı Tabanlı Boyut Azaltma ve Akıllı Saat Tabanlı Giyilebilir Hareket Algılayıcıları Kullanarak Yaşlılarda Düşme Tespiti

Düşme, özellikle yaşlılar için ölümle bile sonuçlanabilecek ciddi bir sağlık riskidir. Bu nedenle düşmelerin önlenmesi, engellenemeyen durumlarda ise en kısa sürede tespit edilerek müdahale edilmesi büyük önem taşımaktadır. Akıllı saatler, her zaman kişinin yanında bulunması, zengin algılayıcı kaynakları ve haberleşme imkânı sayesinde düşme tespiti için ideal bir araçtır. Bu çalışmanın amacı, akıllı saatlerden elde edilen hareket algılayıcısı verilerini kullanarak yaşlı bireylerde düşmeleri yüksek doğrulukla tespit etmektir. Bunun için düşme ve günlük aktivitelerden oluşan bir veri seti oluşturulmuştur. Daha sonra sinyal işleme çalışmalarında başarılı sonuçlar veren öznitelik vektörü çıkarılmıştır. Devamında akıllı saatlerin iş yükünü azaltmak, daha doğru ve hızlı sınıflandırma sağlamak için otokodlayıcı tabanlı bir yaklaşım kullanılarak veri setinin boyutu azaltılmıştır. Naive Bayes, lojistik regresyon ve C4.5 karar ağacı makine öğrenmesi yöntemleri kullanılarak veri seti sınıflandırılmış ve başarılı sonuçlar elde edilmiştir. Sonrasında performansları karşılaştırılmıştır. Boyutsallığın azaltılmasının hem sınıflandırma doğruluğu hem de hesaplama süresi üzerinde olumlu etkileri olduğu gözlemlenmiştir.

Anahtar Kelimeler:

Otokodlayıcı, Boyut azaltma, Düşme tespiti, Lojistik regresyon, Akıllı saat, Giyilebilir cihazlar

Elderly Fall Detection Using Autoencoder Based Dimensionality Reduction and Smartwatch Based Wearable Motion Detectors

Falling is a serious health risk that can even result in death, especially for the elderly. For this reason, it is crucial to prevent falls and, in cases where prevention is not possible, to detect and intervene as soon as possible. Smartwatches are an ideal tool for fall detection due to their constant presence, rich sensor resources, and communication capabilities. The aim of this study is to detect falls in elderly people with high accuracy using motion sensor data obtained from smartwatches. To achieve this, a dataset was created consisting of falls and daily activities. Then, the feature vector was extracted which has provided successful results in signal processing studies. Afterward, the dimensionality of the dataset was reduced using an autoencoder-based approach in order to decrease the workload on smartwatches and ensure more accurate and faster classification. The dataset was classified using machine learning methods including naive Bayes, logistic regression, and C4.5 decision tree, and successful results were obtained. Their performances were then compared. It was observed that reducing the dimensionality had positive effects on both the classification accuracy and the computation time.

Keywords:

Autoencoder, Dimensionality reduction, Fall detection, Logistic regression, Smartwatch, Wearable devices,

PDF

___

Alickovic, E. and Subasi, A., 2016. Medical decision support system for diagnosis of heart arrhythmia using DWT and random forests classifier. Journal of medical systems, 40(4), 108.
Anitha, G. and Priya, S.B., 2022. Vision Based Real Time Monitoring System for Elderly Fall Event Detection Using Deep Learning. Computer Systems Science & Engineering, 42(1), 87-103.
Ballı, S., Sagbaş, E.A. and Korukoglu, S., 2018. Design of smartwatch-assisted fall detection system via smartphone. In 2018 26th Signal Processing and Communications Applications Conference (SIU), İzmir, Türkiye. 1-4.
Ballı, S., Sağbaş, E.A. and Peker, M., 2019a. Human activity recognition from smart watch sensor data using a hybrid of principal component analysis and random forest algorithm. Measurement and Control, 52(1-2), 37-45.
Ballı, S., Sağbaş, E.A. and Peker, M., 2019b. A Mobile Solution Based on Soft Computing for Fall Detection. In Mobile Solutions and Their Usefulness in Everyday Life, Sara Paiva, EAI/Springer Innovations in Communication and Computing, 275-294.
Berke, D. and Aslan, F.E., 2010. A Risk of Surgical Patients: Falling, reasons and preventions. Journal of Anatolia Nursing and Health Sciences, 13(4), 72-77.
Beyazova, M., 2011. Düşmelerin nedenleri ve önlenmesi, Turkish Geriatrics Society, Accessed: 08.12.2021. http://www.geriatri.org.tr/SempozyumKitap2011/11.pdf
De Miguel, K., Brunete, A., Hernando, M. and Gambao, E., 2017. Home camera-based fall detection system for the elderly. Sensors, 17(12), 2864.
Durgun, Y., 2023. Fall Detection Systems Supported by TinyML and Accelerometer Sensors: An Approach for Ensuring the Safety and Quality of Life of the Elderly. International Scientific and Vocational Studies Journal, 7(1), 55-61.
Galvão, Y. M., Ferreira, J., Albuquerque, V.A., Barros, P. and Fernandes, B.J., 2021. A multimodal approach using deep learning for fall detection. Expert Systems with Applications, 168, 114226.
Hakim, A., Huq, M.S., Shanta, S. And Ibrahim, B.S.K.K., 2017. Smartphone based data mining for fall detection: Analysis and design. Procedia computer science, 105, 46-51.
Harrou, F., Zerrouki, N., Sun, Y. and Houacine, A., 2019. An integrated vision-based approach for efficient human fall detection in a home environment. IEEE Access, 7, 114966-114974.
Hinton, G.E. and Salakhutdinov, R.R., 2006. Reducing the dimensionality of data with neural networks. science, 313(5786), 504-507.
Hussain, F., Hussain, F., Ehatisham-ul-Haq, M. and Azam, M.A., 2019. Activity-aware fall detection and recognition based on wearable sensors. IEEE Sensors Journal, 19(12), 4528-4536.
Jain, R., and Semwal, V.B., 2022. A novel feature extraction method for preimpact fall detection system using deep learning and wearable sensors. IEEE Sensors Journal, 22(23), 22943-22951.
Kausar, F., Awadalla, M., Mesbah, M. and AlBadi, T. 2022. Automated machine learning based elderly fall detection classification. Procedia Computer Science, 203, 16-23.
Kerdjidj, O., Ramzan, N., Ghanem, K., Amira, A. and Chouireb. F., 2020. Fall detection and human activity classification using wearable sensors and compressed sensing. Journal of Ambient Intelligence and Humanized Computing, 11(1), 349-361.
Khojasteh, S.B., Villar, J.R., Chira, C., González, V.M. and De la Cal., E., 2018. Improving fall detection using an on-wrist wearable accelerometer. Sensors, 18(5), 1350.
Khraief, C., Benzarti, F. and Amiri, H., 2020. Elderly fall detection based on multi-stream deep convolutional networks. Multimedia Tools and Applications, 79(27), 1-24.
Lu, N., Wu, Y., Feng, L. And Song, J., 2018. Deep learning for fall detection: Three-dimensional CNN combined with LSTM on video kinematic data. IEEE journal of biomedical and health informatics, 23(1), 314-323.
Mauldin, T.R., Canby, M.E., Metsis, V., Ngu, A.H. and Rivera, C.C., 2018. SmartFall: A smartwatch-based fall detection system using deep learning. Sensors, 18(10), 3363.
Musci, M., De Martini, D., Blago, N., Facchinetti, T. And Piastra, M.,2020. Online Fall Detection using Recurrent Neural Networks on Smart Wearable Devices. IEEE Transactions on Emerging Topics in Computing, 9(3), 1276-1289.
Núñez-Marcos A., Azkune, G. And Arganda-Carreras, I., 2017. Vision-based fall detection with convolutional neural networks. Wireless communications and mobile computing, 9474806, 1-16.
Ponce, H., Martínez-Villaseñor, L. and Nuñez-Martínez, J., 2020. Sensor location analysis and minimal deployment for fall detection system. IEEE Access, 8, 166678-166691.
Ravì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B. and Yang, G.Z., 2016. Deep learning for health informatics. IEEE journal of biomedical and health informatics, 21(1), 4-21.
Rifai, S., Vincent, P., Muller, X., Glorot, X. and Bengio, Y., 2011. Contractive auto-encoders: Explicit invariance during feature extraction. In Proceedings of the 28th international conference on international conference on machine learning, Bellevue Washington USA. 833-840.
Sağbaş, E.A., Ballı, S. and Yıldız, T., 2016. Wearable Smart Devices: The Past, Present and Future. Academic Computing Conference, Aydın, Türkiye. 749-756.
Sağbaş, E.A. and Ballı, S., 2017. Classification of Human Motions with Smartwatch Sensors. Süleyman Demirel University Journal of Natural and Applied Sciences, 21(3), 980-990.
Sağbaş, E.A., Korukoglu, S. and Balli, S., 2020. Stress detection via keyboard typing behaviors by using smartphone sensors and machine learning techniques. Journal of medical systems, 44(4), 1-12.
Salah, O.Z., Selvaperumal, S.K. and Abdulla, R., 2022. Accelerometer-based elderly fall detection system using edge artificial intelligence architecture. International Journal of Electrical and Computer Engineering, 12(4), 4430-4438.
Saleh, A.M.E. and Kibria, B.G., 2013. Improved ridge regression estimators for the logistic regression model. Computational Statistics, 28(6), 2519-2558.
Sözer, A.T., 2022. Denetimsiz Anomali Tespiti Yaklaşımı ile Düşme Algılama. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 11(1), 88-98.
Şen, B., Peker, M., Çavuşoğlu, A. and Çelebi, F.V., 2014. A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms. Journal of medical systems, 38(3), 1-21.
Taramasco, C., Rodenas, T., Martinez, F., Fuentes, P., Munoz, R., Olivares, R., ... and Demongeot, J., 2018. A novel monitoring system for fall detection in older people. IEEE Access, 6, 43563-43574. Venkatesh, R., Balasubramanian, C. and Kaliappan, M., 2019. Development of big data predictive analytics model for disease prediction using machine learning technique. Journal of medical systems, 43(8), 1-8.
Wang, G., Li, Q., Wang, L., Zhang, Y. and Liu, Z., 2019. Elderly fall detection with an accelerometer using lightweight neural networks. Electronics, 8(11), 1354.
Zurbuchen, N., Wilde, A. and Bruegger, P., 2021. A machine learning multi-class approach for fall detection systems based on wearable sensors with a study on sampling rates selection. Sensors, 21(3), 938.
https://weka.sourceforge.io/doc.packages/multiLayerPerceptrons/weka/filters/unsupervised/attribute/MLPAutoencoder.html, (28.12.2021)