Akıllı Ev Bileşenlerinde Kullanılan Farklı Kablosuz İletişim Standartları için Makine Öğrenmesi Tabanlı Öneri Sistemi

Year 2024, Volume: 14 Issue: 1, 11 - 22, 29.04.2024

Ahmet Yazar , Ahmet Ata Şentürk , Şulenur Çörez , Olçan Satır , Burak Kosova

Abstract

Akıllı ev sistemlerinin giderek yaygınlaştığı son yıllarda bu sistemlere ait kablosuz iletişim altyapısı da daha çok önem kazanmıştır. Birbirlerine karşı farklı üstünlükleri olan kablosuz iletişim standartlarının bir akıllı ev sistemi için ne tür ihtiyaçlar ve hangi şartlar altında daha kullanılabilir olduğunun kestirilmesi yeni bir problem haline gelmiştir. Bu çalışmada, yeni nesil akıllı ev bileşenlerinde kullanılan farklı kablosuz iletişim standartları için makine öğrenmesi tabanlı özgün öneri yöntemleri geliştirilmiştir. Ayrıca bu amaca yönelik olarak ortamsal ve çevresel farkındalığı yükseltecek düzeyde bilgi girdilerinden yararlanılmıştır. Makine öğrenmesi uygulamasına yönelik yeni bir yapay veri kümesi oluşturulmuştur. Alınan sonuçlara bakıldığında, geliştirilen özgün çözümlerin akıllı ev tasarımlarına fayda getireceği görülmüştür.

Keywords

5G, Akıllı Evler, Kablosuz İletişim, Makine Öğrenmesi, Öneri Sistemi

Machine Learning-Based Recommendation System for Different Wireless Communications Standards Used in Smart Home Components

Abstract

In recent years, as smart home systems have become increasingly widespread, the wireless communication infrastructure associated with these systems has gained more importance. Assessing the needs and determining the conditions under which different wireless communication standards, each with its own advantages, can be more suitable for a smart home system has become a new challenge. In this study, a machine learning-based recommendation methods have been developed for various wireless communication standards used in next-generation smart home components. Additionally, a level of ambient and environmental awareness has been utilized to enhance the information inputs for this purpose. A new artificial dataset has been created for the machine learning application. When examining the results, it can be observed that the proposed novel solution would be beneficial in smart home designs.

Keywords

5G, Smart Homes, Wireless Communications, Machine Learning, Recommendation System

References

• Altunan, U., Sazak, H., Yazar, A. 2023. ML-Based Service Type Priority Decision Method Using Ambient Information for 5GB. International Conference on Smart Applications, Communications and Networking (SmartNets), Istanbul, Turkey.
• Dzogovic, B., Santos, B., Noll, J., Do, VT., Feng, B., Do, TV. 2019. Enabling Smart Home with 5G Network Slicing. IEEE 4th International Conference on Computer and Communication Systems (ICCCS), s.543, Singapore.
• Emam, KE. 2020. Accelerating AI with Synthetic Data. O’Reilly Media, Inc.
• Eren, HA., Adar, N., Yazar, A. 2023. Vehicle-to-Everything Communications Standard Selection Under Different Intelligent Transportation Scenarios with Artificial Learning. Journal of Intelligent Systems: Theory and Applications, 6(1):67-74.
• Hançer, A., Yazar, A. 2023a. Waveform Decision Method with Machine Learning for 5G Uplink Communications. International Journal of Engineering Research and Development, 15(2):820-827.
• Hançer, A., Yazar, A. 2023b. Multi-Carrier and Single-Carrier Waveform Decision Method in Non-Terrestrial Networks. 31st Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkey.
• Horyachyy, O. 2017. Comparison of Wireless Communication Technologies used in a Smart Home. MS Thesis, Blekinge Institute of Technology.
• Insight, B. 2022. Smart Homes and Home Automation. Technical Report (9th Ed.).
• Kihero, AB., Tusha, A., Arslan, H. 2021. Wireless Channel and Interference. Wireless Communication Signals: A Laboratory-based Approach. Wiley, ch. 10, s.267.
• Nikolenko, SI. 2022. Synthetic Data for Deep Learning. Springer Cham.
• Parikh, PP., Kanabar, MG., Sidhu, TS. 2010. Opportunities and challenges of wireless communication technologies for smart grid applications. IEEE PES General Meeting, USA.
• Pedregosa, F., vd. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12:2825-2830.
• Shilpa, B., Radha, R., Movva, P. 2022. Comparative Analysis of Wireless Communication Technologies for IoT Applications. Artificial Intelligence and Technologies. Lecture Notes in Electrical Engineering, vol 806. Springer, Singapore.
• Sazak, H., Yazar, A. 2023. Ambient Aware User-Numerology Association for 5G and Beyond. Signal Processing and Communications Applications Conference (SIU), Turkey.
• Stefanov, DH., Bien, Z., Bang, WC. 2004. The smart house for older persons and persons with physical disabilities: structure, technology arrangements, and perspectives. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 12(2):228-250.
• Shwartz-Ziv, R., Armon, A. 2022. Tabular Data: Deep Learning is Not All You Need. Information Fusion, 81:84–90.
• Yang, L., Shami, A. 2020. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 415(1):295–316.
• Yarkan, S., Arslan, H. 2008. Exploiting Location Awareness toward Improved Wireless System Design in Cognitive Radio. IEEE Communications Magazine, 46(1):128–136.
• Yazar, A., Çetin, AE., Töreyin, BU. 2012. Human activity classification using vibration and PIR sensors. 20th Signal Processing and Communications Applications Conference (SIU), Mugla, Turkey.
• Yazar, A., Çetin, AE. 2013. Ambient assisted smart home design using vibration and PIR sensors. 21st Signal Processing and Communications Applications Conference (SIU), Girne.
• Yazar, A., Dogan-Tusha, S., Arslan, H. 2020. 6G Vision: An Ultra-Flexible Perspective. ITU Journal on Future and Evolving Technologies – Volume 2020, Article 9, 1(1):1-20.
• Yazar, A. 2021. Requirement Analysis and Clustering Study for Possible Service Types in 6G Communications. 29th Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkey.