NON-INTRUSIVE AIR-CONDITIONER USAGE DETECTION USING CONVOLUTIONAL NEURAL NETWORKS
Keywords:
computer vision, convolutional neural network, remote monitoring systemAbstract
Nowadays, there is an increasing number of monitoring tools for electronic systems. Such tools allow users or administrators to monitor such systems remotely via the internet. However, for many real systems, such tools see limited usage, especially for air conditioners since air conditioners are expensive and long-lasting. In addition, on a building-level or organization-level, having to use air conditioners of different models or from different manufacturers is often unavoidable or impractical. Thus, changing all air conditioners to fit a particular monitoring tool is complicated and expensive. In this work, a non-intrusive air conditioner monitoring tool from security camera footage using artificial intelligence was designed and developed. Models were developed using convolutional neural networks, with MobileNet v3 as the base for transferred learning, in TensorFlow. Three models were tested with different volumes of training data: 1, 2, and 30 frames per second. The result showed that, overall, models performed better than the baseline. In addition, models could detect air conditioner usages with 100% accuracy for models with specific characteristics.
References
McNeil, M. A., & Letschert, V. E. (2008). Future air conditioning energy consumption in developing countries and what can be done about it: the potential of efficiency in the residential sector.
Luo, H., Xiong, C., Fang, W., Love, P. E., Zhang, B., & Ouyang, X. (2018). Convolutional neural networks: Computer vision-based workforce activity assessment in construction. Automation in Construction, 94, 282-289.
Srijakkot, K., Kanjanasurat, I., Wiriyakrieng, N., Lartwatechakul, M., & Benjangkaprasert, C. (2020). Intruder Detection by Using Faster R-CNN in Power Substation. In Recent Advances in Information and Communication Technology 2020: Proceedings of the 16th International Conference on Computing and Information Technology (IC2IT 2020) (pp. 159-167). Springer International Publishing.
Harjoseputro, Y., Yuda, I., & Danukusumo, K. P. (2020). MobileNets: Efficient convolutional neural network for identification of protected birds. IJASEIT (International Journal on Advanced Science, Engineering and Information Technology), 10(6), 2290-2296.
Favorskaya, M., & Pakhirka, A. (2019). Animal species recognition in the wildlife based on muzzle and shape features using joint CNN. Procedia Computer Science, 159, 933-942.
Qu, D., Huang, Z., Gao, Z., Zhao, Y., & Song, G. (2018, December). An automatic system for smile recognition based on CNN and face detection. In 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO) (pp. 243-247). IEEE.
Akhand, M. A. H., Roy, S., Siddique, N., Kamal, M. A. S., & Shimamura, T. (2021). Facial emotion recognition using transfer learning in the deep CNN. Electronics, 10(9), 1036.
Kaur, G., Sinha, R., Tiwari, P. K., Yadav, S. K., Pandey, P., Raj, R., ... & Rakhra, M. (2022). Face mask recognition system using CNN model. Neuroscience Informatics, 2(3), 100035.
Torrey, L., & Shavlik, J. (2010). Transfer learning. In Handbook of research on machine learning applications and trends: algorithms, methods, and techniques (pp. 242-264). IGI global.
Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009, June). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248-255). Ieee.
Yae, J. (2022). Unintended look-ahead bias in out-of-sample forecasting. Applied Economics Letters, 1-5.
Ying, X. (2019, February). An overview of overfitting and its solutions. In Journal of physics: Conference series (Vol. 1168, p. 022022). IOP Publishing.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Journal of science and technology RMUTSB
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
