SavedAdd your journal

Journals / Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi / 2022 / Cilt: 1 Sayı: 1

Recognition of Human Activities Using Machine Learning Methods on Smart Sensor Data

Akıllı Sensör Verileri Üzerinde Makine Öğrenmesi Yöntemleri Kullanılarak İnsan Aktivitelerinin Tanımlanması

Serdar ASARKAYA
Emre ÜNSAL
Pages
9–14
Publication Date
2022-12-31
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The obtained results were compared, and it was seen that the best result was achieved with the Multi-Layer Perceptron model.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:As a result of the developments in smart sensor technologies and the decrease in the costs of wearable devices, internet of things-based studies for the recognition of daily human activities by using sensor data obtained from these devices is an important research topic today.
📊
Key Findings & Data:The recognition of human activities can contribute to the solution of activity-related problems in areas such as health, patient follow-up, and safety.
💡
Conclusion & Impact:The obtained results were compared, and it was seen that the best result was achieved with the Multi-Layer Perceptron model.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Nesnelerin İnterneti · Akıllı Sensörler · Makine Öğrenmesi

Abstract

As a result of the developments in smart sensor technologies and the decrease in the costs of wearable devices, internet of things-based studies for the recognition of daily human activities by using sensor data obtained from these devices is an important research topic today. The recognition of human activities can contribute to the solution of activity-related problems in areas such as health, patient follow-up, and safety. This study aims to identify human activities using machine learning methods on data obtained from smart sensors. In this study, models were created with Decision Tree, OneVsOne, and Multilayer Perceptron classifiers, and training and testing stages were carried out with the data set containing the activities. The obtained results were compared, and it was seen that the best result was achieved with the Multi-Layer Perceptron model.

Özet

Akıllı sensör teknolojilerindeki gelişmeler ve giyilebilir cihazların maliyetlerinin düşmesi sonucunda bu cihazlardan elde edilen sensör verileri kullanılarak günlük insan aktivitelerinin tanımlanmasına yönelik nesnelerin interneti tabanlı çalışmalar günümüzde önemli bir araştırma konusudur. İnsan aktivitelerinin tanımlanması sağlık, hasta takibi ve güvenlik gibi alanlarda aktiviteye bağlı sorunların çözümüne katkı sağlayabilmektedir. Bu çalışma, akıllı sensörlerden elde edilen veriler üzerinde makine öğrenmesi yöntemlerini kullanarak insan aktivitelerinin tanımlanmasını amaçlamaktadır. Çalışmada Karar Ağacı, OneVsOne ve Çok Katmanlı Algılayıcı sınıflandırıcıları ile modeller oluşturulmuş ve aktiviteleri içeren veri seti ile eğitim ve test aşamaları gerçekleştirilmiştir. Elde edilen sonuçlar karşılaştırılmış ve en iyi sonuca Çok Katmanlı Algılayıcı modeli ile ulaşıldığı görülmüştür.

🔖

Cite This Article

ASARKAYA, S., ÜNSAL, E. (2022). Recognition of Human Activities Using Machine Learning Methods on Smart Sensor Data. Sivas Cumhuriyet Üniversitesi Bilim ve Teknoloji Dergisi, Cilt: 1 Sayı: 1, 9–14. https://ajindex.com/articles/978057

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (4)

  1. Abaklıoğlu, M. (2019). The importance of internet (IOT) technology for smartcity and objects for the future cities. İstabul: Ulusal Tez Merkezi. Abidine, M. B., & Fergani, B. (2021). Activity Recognition From Smartphone Data Using WSVM-HMM Classification. International Journal of E-Health and Medical Communications, 20. Anguita, D., Ghio, A., Oneto, L., Parra, X., & Ortiz, J. (2012). Human Activity Recognition on Smartphones using a Multiclass Hardware-Friendly Support Vector Machine. Ambient Assisted Living and Home Care., 7657. doi:https://doi.org/10.1007/978-3-642-35395-6_30
  2. Chai, S. S., Cheah, L. W., Goh, K. L., Chang, Y. R., Sim, K. Y., & Chin, K. O. (2021). A Multilayer Perceptron Neural Network Model to Classify Hypertension in Adolescents Using Anthropometric Measurements: A Cross-Sectional Study in Sarawak. Computational and Mathematical Methods in Medicine, 11. doi:10.1155/2021/2794888 Choudhury, T., Consolvo, S., Harrison, B., Hightower, J., LaMarca, A., & LeGrand, L. (2008). The Mobile Sensing Platform: An Embedded Activity Recognition System. IEEE Pervasive Computing, 32-41. doi:10.1109/MPRV.2008.39 Ferrari, A., Micucci, D., Mobilio, M., & Napoletano, P. (2021). Trends in human activity recognition using smartphones. Journal of Reliable Intelligent Environments, 189-213. doi:10.1007/s40860-021-00147-0
  3. Galar, M., Barrenechea, E., Fernandez, A., & Herrera, F. (2014). Enhancing difficult classes in one-vs-one classifier fusion strategy using restricted equivalence functions. FUSION 2014 - 17th International Conference on Information Fusion. Salamanca: ResearchGate. Jijo, B. T., & Abdulazeez, A. M. (2021). Classification Based on Decision Tree Algorithm for Machine Learning. Journal of Applied Science and Technology Trends, 20-28. doi:10.38094/jastt20165 Kaur, P., Kumar, R., & Kumar, M. (2019). A healthcare monitoring system using random forest and internet of things (IoT). Multimedia Tools and Applications, 19905–19916. doi:10.1007/s11042-019-7327-8
  4. Kurama, V. (2020, 1 1). A Complete Guide to Decision Trees. 4 18, 2022 tarihinde https://blog.paperspace.com/: https://blog.paperspace.com/decision-trees/ adresinden alındı Ma, J., Cheng, J., Ding, Y., Lin, C., Jiang, F., Wang, M., & Zhai, C. (2020). Transfer learning for long-interval consecutive missing values imputation without external features in air pollution time series. Advanced Engineering Informatics, 101092. doi:10.1016/j.aei.2020.101092 Mourtzis, D., Vlachou, E., & Milas, N. (2016). In