Tavsiye Sistemlerinde Derin Otokodlayicilar: Nesnelerin Interneti Hizmet Tavsiyesi Üzerine Bir Uygulama

Year 2021, , 267 - 277, 31.07.2021

Sule Birim

https://doi.org/10.17671/gazibtd.685500

Abstract

Nesnelerin İnterneti (IoT) küçük ve birbirine bağlı cihazlardan oluşan ve internet aracılığıyla bilgi paylaşımı sağlayan cihazlardan oluşan bir sistemdir. Gelecek IoT cihazlarının gerçekleştirdiği hizmetlerin sayısının oldukça artmasını beklemektedir. Bu nedenle IoT hizmeti önerme, gelecekte çok önemli bir faaliyet halini alacaktır. Bu çalışma, IoT hizmetleri tavsiyesi için en iyi yöntemi bulmayı hedeflemektedir. Bu amaç doğrultusunda bu çalışma derin otokodlayıcılar yöntemini, kullanıcılara IoT hizmet ve uygulamalarını kullandıkları cihazlara bağlı olarak önermek için kullanmayı hedeflemektedir. Derin otokodlayıcılar, kullanıcı hizmet tercih matrisini tahmin edebilmek için sinir ağlarını kullanır. Bu çalışmada kullanılan veri, gerçek bir Sosyal IoT veri setinden yararlanılarak oluşturulmuştur. Sonuçlara göre derin otokodlayıcılar, teknoloji harikası öneri yöntemlerine göre daha başarılı bir performans ortaya koymuştur. Bu sonuca ek olarak özel bir çeşit aktivasyon fonksiyonu ile oto kodlayıcıların performansının arttırılabileceği görülmüştür. Bu çalışma IoT hizmet önerisi literatürüne geleneksel ve teknoloji harikası kabul edilen yöntemlere bir alternatif sunarak katkı sağlamaktadır.

Keywords

Nesnelerin İnterneti (IoT), Öneri sistemleri, Hizmet önerisi, İşbirlikçi Filtreleme, Derin Otokodlayıcılar, Sinir Ağları

Deep AutoEncoders in Recommender Systems: An Application about Internet of Things Service Recommendation

Abstract

The Internet of Things (IoT) is a system that includes small interconnected devices sharing information through the Internet. Future expects an increasing number of services in IoT devices. Therefore, recommending IoT services will be a vital task for the future of IoT and the convenience of the users. This study aims to find the best methodology to provide IoT service recommendation. With this aim, this study proposes deep autoencoders methodology to recommend services and applications to users based on the devices they own. Deep autoencoders utilize neural networks to predict user service preference matrix. The data used in this study is constructed from a real-world Social IoT dataset. The results showed that deep autoencoders outperformed the state-of-the-art recommendation methods. According to the results, Deep autoencoders improved performance indicators varying between 13.5% and 69.5% compared to other methods. Findings also indicate that the performance of the deep autoencoders can be enhanced by using ELU (exponential linear units), a specific type of activation function. This study contributes to the IoT service recommendation literature by proposing a superior approach when compared to the traditional recommendation techniques.

Keywords

The Internet of Things (IoT), Recommendation Systems, Service Recommendation, Collaborative Filtering, Deep AutoEncoders, Neural Networks

References

• I. Mashal, T. Y. Chung, and O. Alsaryrah, “Toward service recommendation in Internet of Things”, International Conference on Ubiquitous and Future Networks, ICUFN, 328–331, 2015.
• Govloop Community, “The Internet of Things: What the IoT means for the public sector”, Isaca, 6, 2013.
• E. Ahmed et al., “The role of big data analytics in Internet of Things”, Computer Networks, 129, 459–471, 2017.
• D. Çulha, “Blockchain of Meetings of IoT Devices”, Bilişim Teknolojileri Dergisi, 14(2), 129–136, 2021.
• I. Şafak, E. Ünsal, “Türkiye’de Dağıtık Hesap Defteri Teknolojili Nesnelerin İnterneti Ödeme Sistemleri için Sistem Tasarım Önerileri”, Bilişim Teknolojileri Dergisi, 23–36, 2021,
• Telus, “IoT Marketplace”, Telus, 2018.
• İnternet: Amazon Web Services (AWS), https://docs.aws.amazon.com/en_us/aws-technical content/latest/aws-overview/internet-of-things-services.html, 26.12.2018.
• Srinivasa K G, Sowmya BJ, A. Shikhar, R. Utkarsha, A. Singh, “Data Analytics Assisted Internet of Things Towards Building Intelligent Healthcare Monitoring Systems”, Journal of Organizational and End User Computing, 30(4), 83–103, 2018.
• S. S. Gill, I. Chana, R. Buyya, “IoT Based Agriculture as a Cloud and Big Data Service”, Journal of Organizational and End User Computing, 29(4), 1–23, 2017.
• A. Agarwal, M. Chauhan, “Similarity Measures used in Recommender Systems: A Study”, International Journal of Engineering Technology Science and Research, 4(6), 2394–3386, 2017.
• B. Zhang, B. Yuan, “Improved collaborative filtering recommendation algorithm of similarity measure”, AIP Conference Proceedings, 1839, 2017.
• Y. Wang, J. Deng, J. Gao, and P. Zhang, “A hybrid user similarity model for collaborative filtering”, Information Sciences, 418, 102–118, 2017.
• I. Mashal, O. Alsaryrah, and T. Y. Chung, “Performance evaluation of recommendation algorithms on Internet of Things services”, Physica A: Statistical Mechanics and its Applications, 451, 646–656, 2016.
• Y. Salman, A. Abu-Issa, I. Tumar, and Y. Hassouneh, “A proactive multi-type context-aware recommender system in the environment of Internet of Things”, 15th IEEE International Conference on Computer and Information Technology, CIT 2015, 2015, 351–355.
• J. S. Lee and I. Y. Ko, “Service recommendation for user groups in internet of things environments using member organization-based group similarity measures”, IEEE International Conference on Web Services, ICWS 2016, 276–283, 2016.
• S. Forouzandeh et al., “Recommender system for Users of Internet of Things (IOT)”, IJCSNS International Journal of Computer Science and Network Security, 17(8), 46–51, 2017.
• C. Marche, L. Atzori, M. Nitti, “A Dataset for Performance Analysis of the Social Internet of Things”, IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), 1-5, 2018.
• Y. Ouyang, W. Liu, W. Rong, Z. Xiong, “Autoencoder-Based Collaborative Filtering”, International Conference on Neural Information Processing, 284–291, 2014.
• F. Strub and J. Mary, “Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs”, NIPS Workshop on Machine Learning for eCommerce, 2015.
• S. Sedhain, A. K. Menon, S. Sanner, L. Xie, “AutoRec: Autoencoders Meet Collaborative Filtering”, 24th International Conference on World Wide Web, 111–112, 2015.
• Y. Wu, C. DuBois, A. X. Zheng, M. Ester, “Collaborative Denoising Auto-Encoders for Top-N Recommender Systems”, 9th ACM International Conference on Web Search and Data Mining - WSDM ’16, 153-162, 2016.
• O. Kuchaiev B. Ginsburg, “Training Deep AutoEncoders for Collaborative Filtering”, arXiv preprint arXiv:1708.01715, 2017.
• P. Lops, M. De Gemmis, G. Semeraro, “Content-based Recommender Systems: State of the Art and Trends”, Recommender Systems Handbook, F. Ricci, L. Rokach, B. Shapira, and P. B. Kantor, Eds. Boston: Springer, 2011.
• V. Subramaniyaswamy, R. Logesh, M. Abejith, S. Umasankar, A. Umamakeswari, “Sentiment Analysis of Tweets for Estimating Criticality and Security of Events”, Journal of Organizational and End User Computing, 29(4), 51–71, 2017.
• W. W. Cohen W. Fan, “Web-collaborative filtering: recommending music by crawling the Web”, Computer Networks, 33(1), 685–698, 2000.
• K. Miyahara M. J. Pazzani, “Collaborative Filtering with the Simple Bayesian Classifier”, IPSJ Journal, 43(11), 679–689, 2002.
• B. Sarwar, G. Karypis, J. Konstan, J. Reidl, “Item-based collaborative filtering recommendation algorithms”, 10th International Conference on World Wide Web - WWW ’01, 285–295, 2001.
• X. Su T. M. Khoshgoftaar, “A Survey of Collaborative Filtering Techniques”, Advances in Artificial Intelligence, 1–19, 2009, doi: 10.1155/2009/421425.
• P. H. Aditya, I. Budi, and Q. Munajat, “A comparative analysis of memory-based and model-based collaborative filtering on the implementation of recommender system for E-commerce in Indonesia: A case study PT X”, nternational Conference on Advanced Computer Science and Information Systems, ICACSIS, 303–308, 2016.
• Y. Koren, R. Bell, and C. Volinsky, “Matrix Factorization Tecniques for Recommender Systems”, Computer, 8, 30–37, 2009.
• X. Luo, M. Zhou, Y. Xia, and Q. Zhu, “An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems”, IEEE Transactions on Industrial Informatics, 10(2), 1273–1284, 2014.
• O. Kaynar, Z. Aydın, and Y. Görmez, “Sentiment Analizinde Öznitelik Düşürme Yöntemlerinin Oto Kodlayıcılı Derin Öğrenme Makinaları ile Karşılaştırılması”, Bilişim Teknolojileri Dergisi, 319–326, 2017.
• R. Salakhutdinov, A. Mnih, and G. Hinton, “Restricted Boltzmann Machines for Collaborative Filtering”, 24th International Conference on Machine Learning, 2007, 791–798.
• X. He, L. Liao, H. Zhang, L. Nie, X. Hu, and T.-S. Chua, “Neural Collaborative Filtering”, International World Wide Web Conference, 173–182, 2017.
• C.-Y. Wu, A. Ahmed, A. Beutel, A. J. Smola, and H. Jing, “Recurrent Recommender Networks”, 10th ACM International Conference on Web Search and Data Mining - WSDM ’17, 495–503, 2017.
• İnternet: V. Granville, “Great IoT, Sensor and other Data Sets Repositories”, Data Science Central, https://www.datasciencecentral.com/profiles/blogs/great-sensor-datasets-to-prepare-your-next-career-move-in-iot-int, 10.12.2018.
• Z. Chen, R. Ling, C.-M. Huang, and X. Zhu, “A scheme of access service recommendation for the Social Internet of Things”, Journal of Communication Systems, 29, 694–706, 2016.
• L. Noirie, M. Le Pallec, and N. Ammar, “Towards automated IoT service recommendation”, 20th Conference on Innovations in Clouds, Internet and Networks, ICIN 2017, 103–106, 2017.
• H. Jeong, B. Park, M. Park, K. B. Kim, and K. Choi, “Big data and rule-based recommendation system in Internet of Things”, Cluster Computing, 1–10, 2017.
• Y. Liu, T. Zhu, Y. Jiang, and X. Liu, “Service matchmaking for Internet of Things based on probabilistic topic model”, Future Generation Computer Systems, 94, 272–281, 2019.
• B. Hu, Z. Zhou, and Z. Cheng, “Web Services Recommendation Leveraging Semantic Similarity Computing”, Procedia Computer Science, 129, 35–44, 2018.
• X. Wu, L. Zhang, S. Tian, and L. Wu, “Scenario based e-commerce recommendation algorithm based on customer interest in Internet of things environment”, Electronic Commerce Research, 0123456789, 2019.
• Y. Yan, C. Huang, Q. Wang, and B. Hu, “Data mining of customer choice behavior in internet of things within relationship network”, International Journal of Information Management, Article in Press, 2018.
• Ş. Birim and A. Tümtürk, “Modeling and Forecasting Turkey’ s Electricity Consumption by using Artificial Neural Network”, American Scientific Research Journal for Engineering, Technology, and Sciences, 25(1), 192–208, 2016.
• İnternet: N. Hubens, Deep inside: Autoencoders, Towards Data Science, https://towardsdatascience.com/deep-inside-autoencoders-7e41f319999f, 10.12.2018
• G. E. Hinton and R. S. Zemel, “Autoencoders, Minimum Description Length and Helmholtz Free Energy”, Advances in neural information processing systems, 3–10, 1994.
• İnternet: R. Khandelwal, Deep Learning Autoencoders, https://medium.com/datadriveninvestor/deep-learning-autoencoders-db265359943e, 22.02.2019.
• G. E. Hinton and R. R. Salakhutdinov, “Reducing the Dimensionality of Data with Neural Networks”, Science, 313, 504–507, 2006.
• L. Atzori, M. Nitti, C. Marche, “Social Internet of Things IoT Network Dataset”, Social IoT, 2018.
• N. Liang, H.-T. Zheng, J.-Y. Chen, A. Sangaiah, C.-Z. Zhao, “TRSDL: Tag-Aware Recommender System Based on Deep Learning–Intelligent Computing Systems”, Applied Sciences, 8(5), 799, 2018.
• S. Chen, Y. Peng, “Matrix factorization for recommendation with explicit and implicit feedback”, Knowledge-Based Systems, 158, 109–117, 2018.
• A. Oppermann, “Deep Learning meets Physics : Restricted Boltzmann Machines Part I”, Towards Data Science, 2018.
• B. Marlin, K. Swersky, “Inductive principles for restricted Boltzmann machine learning,” International Conference on Artificial Intelligence and Statistics (AISTATS), 2010, 9, 305–306.
• C. C. Aggarwal, “Neighborhood-Based Collaborative Filtering”, Recommender Systems, 2016, 29–70.
• A. Singh, W. Follow, “Activation functions and it’s types-Which is better? ”, Towards Data Scienceards, 2017.
• D.-A. Clevert, T. Unterthiner, S. Hochreiter, “Fast and Accurate Deep Network Learning by Exponential Linear Units”, arXiv preprint arXiv:1511.07289, 2015.