Developing synthetic data generation software for artificial intelligence techniques used in smart home systems
Öz
Nowadays artificial intelligence techniques such as artificial neural networks, support vector machines, fuzzy logic, Markov models etc. have been started to use in smart home systems to automate actions executed by inhabitants. In order to make sure that algorithms work correctly, they need to be tested and improved. For that, we need data sets to use in testing. These datas could be generated in real life environment, as well as in virtual environment with ease. Synthetic data generation softwares are used to generate these data sets. In this paper, in order to test artificial intelligence techniques used in smart home systems, a software that generates synthetic data sets by mimicking daily human activities is developed. A family including 5 people with daily life scenarios is created to test the developed software. Subsequently according to the scenarios, a data set for a year is created by the software and tested its validaty using statistical methods. Generated data sets and obtained test results are introduced and the developed software was found to be successful.
Anahtar Kelimeler
Kaynakça
- [1] Mennicken, S., Vermeulen, J., and Huang, E., From today's augmented houses to tomorrow's smart homes: New directions for home automation research. Ubicomp 2014, Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Seattle, 105-115, (2014).
- [2] Alam, M. R., Reaz M. B. I., and Ali, M. A. M., A Review of smart homes-past, present, and future, IEEE Transactions on Systems, Man, and Cybernetics Part-C: Applications and Reviews, 1190-1203, (2012).
- [3] Heierman, E. O., and Cook, D. J., Improving home automation by discovering regularly occurring device usage patterns, Proceedings of the Third IEEE International Conference on Data Mining, Florida, 537-540, (2003).
- [4] Jarmin, R. S., Louis, T. A., and Miranda, J., Expanding the role of synthetic data at the U.S. Census Bureau, Statistical Journal of the IAOS : Journal of the International Association for Official Statistics, 30, 117-121, (2014).
- [5] Parker, S. P., McGraw-Hill Dictionary of Scientific and Technical Terms, McGraw-Hill Education, (2002).
- [6] Korel, B., Automated software test data generation, IEEE Transactions on Software Engineering, 16, 8, 870-879, (1990).
- [7] Arasu, A., Kaushik, R., and Li, J., DataSynth: Generating synthetic data using declarative constraints, Proceedings of the VLDB Endowment, 4, 12, 1418-1421, (2011).
- [8] Hoag, J. E., and Thompson, C. W., A parallel general-purpose synthetic data generator, ACM SIGMOD Record, 36, 19-24, (2007).
Ayrıntılar
Birincil Dil
Türkçe
Konular
Mühendislik
Bölüm
Araştırma Makalesi
Yayımlanma Tarihi
21 Aralık 2016
Gönderilme Tarihi
22 Aralık 2016
Kabul Tarihi
30 Mart 2016
Yayımlandığı Sayı
Yıl 2016 Cilt: 18 Sayı: 2
Cited By
Nesnelerin İnterneti ile Akıllı bir Priz Prototipi
Düzce Üniversitesi Bilim ve Teknoloji Dergisi
https://doi.org/10.29130/dubited.431684Mimari Tasarım Karar Verme Süreçlerinde Yapay Zekâ Tabanlı Bulanık Mantık Sistemerinin Değerlendirilmesi
Mimarlık Bilimleri ve Uygulamaları Dergisi (MBUD)
https://doi.org/10.30785/mbud.1117910The Use and Development of Artificial Intelligence in Architectural Design Processes
Black Sea Journal of Engineering and Science
https://doi.org/10.34248/bsengineering.1559637