Kapalı Mekân Ortamında 1D-CNN Kullanarak Yapılan Doluluk Tespiti Sınıflandırması

Year 2023, Volume: 13 Issue: 1, 60 - 71, 15.03.2023

Erkan Güler , Ar. Gör. Muhammet Talha Kakız , Faruk Baturalp Gunay , Burcu Şanal , Tuğrul Çavdar

https://doi.org/10.31466/kfbd.1162332

Abstract

Derin Öğrenme modelleri kompleks deneyimlerden bilgi çıkarımına imkân sağlayan spesifik Makine Öğrenmesi yöntemleridir. Kapalı bir mekândaki bazı veri değerlerindeki değişiminin öğrenilmesi ile odada herhangi bir kişinin bulunup bulunmamasının tespit edilmesi bu deneyimlerden biridir. Bu çalışmanın amacı zaman serileri olarak oluşturulmuş ve zaman içinde ışık, sıcaklık, nem ve CO2 değerlerindeki değişimler ile kapalı bir mekânda doluluk tespiti probleminin Bir Boyutlu Evrişimli Sinir Ağı (1D-CNN) ile gerçekleştirilmesidir. Bir adet eğitim ve iki adet test veri seti kullanılarak model eğitilmiş ve daha önce tecrübe edilmeyen test veri setleri ile modelin başarısı gözlenmiştir. Keras uygulama programlama arayüzünde 1D-CNN modeli ile gerçekleştirilen testlerde doluluk tespiti sınıflandırmasının RF (Random Forest), GBM (Gradient Boosting Machines), CART (Classification and Regression Trees), LDA (Linear Discriminant Analysis) yöntemlerinden daha başarılı sonuçlar verdiği gözlenmiştir.

Keywords

Doluluk Tespiti, 1D-CNN, Zaman Serisi, Sınıflandırma, Derin Öğrenme

Occupancy Detection Classification Using 1D-CNN in Indoor Environment

Abstract

Deep Learning models are specific Machine Learning methods that allow to extract knowledge from complex experiences. Learning the change in some data values in an indoor environment and detecting whether there is any person in the room is one of these experiences. The aim of this study is to realize the problem of determining the occupancy in an indoor space with changes in light, temperature, humidity and CO2 values over time, using a One-Dimensional Convolutional Network (1D-CNN). The model has been trained using one training and two test datasets, and the success of the model has been observed with test datasets that the model has not been experienced before. In the tests performed with the 1D-CNN model in the Keras application programming interface, it has been observed that the occupancy detection classification has given more successful results than the RF (Random Forest), GBM (Gradient Boosting Machines), CART (Classification and Regression Trees), LDA (Linear Discriminant Analysis) methods.

Keywords

Occupancy Detection, 1D-CNN, Time Series, Classification, Deep Learning

References

• Barino, F. O., Silva, V. N., López-Barbero, A. P., Honorio, L. D. M., & Dos Santos, A. B. (2020). Correlated time-series in multi-day-ahead streamflow forecasting using convolutional networks. IEEE Access, 8, 215748-215757.
• Billah, M. F. R. M., Saoda, N., Gao, J., & Campbell, B. (2021, May). BLE can see: a reinforcement learning approach for RF-based indoor occupancy detection. In Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021) (pp. 132-147).
• Candanedo, L. M., & Feldheim, V. (2016). Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models. Energy and Buildings, 112, 28-39.
• Esling, P., & Agon, C. (2012). Time-series data mining. ACM Computing Surveys (CSUR), 45(1), 1-34.
• Fukuoka, R., Suzuki, H., Kitajima, T., Kuwahara, A., & Yasuno, T. (2018). Wind speed prediction model using LSTM and 1D-CNN. Journal of Signal Processing, 22(4), 207-210.
• Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
• Hussain, D., Hussain, T., Khan, A. A., Naqvi, S. A. A., & Jamil, A. (2020). A deep learning approach for hydrological time-series prediction: A case study of Gilgit river basin. Earth Science Informatics, 13(3), 915-927.
• Junior, R. F. R., dos Santos Areias, I. A., Campos, M. M., Teixeira, C. E., da Silva, L. E. B., & Gomes, G. F. (2022). Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals. Measurement, 190, 110759.
• Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2021). 1D convolutional neural networks and applications: A survey. Mechanical systems and signal processing, 151, 107398.
• Kuang, D. (2019). A 1d convolutional network for leaf and time series classification. arXiv preprint arXiv:1907.00069.
• Lim, B., & Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A, 379(2194), 20200209.
• Liu, L., & Si, Y. W. (2022). 1D convolutional neural networks for chart pattern classification in financial time series. The Journal of Supercomputing, 1-24.
• Mahmoud, A., & Mohammed, A. (2021). A survey on deep learning for time-series forecasting. In Machine Learning and Big Data Analytics Paradigms: Analysis, Applications and Challenges (pp. 365-392). Springer, Cham.
• Occupancy Detection Data Set. (2016, February 29). https://archive.ics.uci.edu/ml/datasets/ Occupancy+Detection+
• Parzinger, M., Hanfstaengel, L., Sigg, F., Spindler, U., Wellisch, U., & Wirnsberger, M. (2022). Comparison of different training data sets from simulation and experimental measurement with artificial users for occupancy detection-Using machine learning methods Random Forest and LASSO. Building and Environment, 109313.
• Pouyanfar, S., Sadiq, S., Yan, Y., Tian, H., Tao, Y., Reyes, M. P., ... & Iyengar, S. S. (2018). A survey on deep learning: Algorithms, techniques, and applications. ACM Computing Surveys (CSUR), 51(5), 1-36.
• Rizvi, S. M. H. (2022). Time series deep learning for robust steady-state load parameter estimation using 1D-CNN. Arabian Journal for Science and Engineering, 47(3), 2731-2744.
• Singaravel, S., Delrue, S., Pollet, I., & Vandekerckhove, S. (2022). Machine Learning for Occupancy Detection through Smart Home Sensor Data. In ASHRAE Topical Conference Proceedings (pp. 1-8). American Society of Heating, Refrigeration and Air Conditioning Engineers, Inc..
• Tang, W., Long, G., Liu, L., Zhou, T., Jiang, J., & Blumenstein, M. (2020). Rethinking 1d-cnn for time series classification: A stronger baseline. arXiv preprint arXiv:2002.10061.
• Wu, L., & Wang, Y. (2021). Stationary and moving occupancy detection using the SLEEPIR sensor module and machine learning. IEEE Sensors Journal, 21(13), 14701-14708.
• Zhao, J., & Li, Y. G. (2020). Abrupt Fault Detection and Isolation for Gas Turbine Components Based on a 1D Convolutional Neural Network Using Time Series Data. In AIAA Propulsion and Energy 2020 Forum (p. 3675).