Back close

Spatio-Temporal Prediction in Epidemiology Using Graph Convolution Network

Publication Type : Conference Proceedings

Publisher : Springer

Source : International Conference on Information and Communication Technology for Intelligent Systems

Url : https://link.springer.com/chapter/10.1007/978-981-99-3761-5_34

Campus : Amritapuri

School : School of Computing

Center : Algorithms and Computing Systems

Year : 2023

Abstract : Over the last decade, e-commerce has expanded significantly. An effective recommendation system is needed for better information filtering as more products are available online, particularly clothing and fashion accessories. The literature already includes a number of different recommendations for clothing. However, new problems like computation complexity and data’s exponential growth appear. The recommendation model must be updated frequently because trends change quickly. This paper proposes a collaborative filtering-based recommendation system. The Nearest Neighbor PageRank (NNPR) ranking algorithm, which creates individualized recommendations, combines the PageRank algorithm and the user’s closest neighbors. Unlike the Alternating Least square method, the suggested model is assessed by utilizing the (ALS) algorithm. The experiments use a dataset of Amazon fashion reviews, and the results are recorded in terms of Hit Ratio (HR) and Average Reciprocal Rank (MRR). NNPR has been shown to outperform ALS in active users and cold starters scenarios.

Cite this Research Publication : Siji Rani, S., Dhanyalaxmi, P., Akshay, A.S., Ananthakrishnan, K.M., Siva Sankar, A. (2023). Spatio-Temporal Prediction in Epidemiology Using Graph Convolution Network. In: Choudrie, J., Mahalle, P.N., Perumal, T., Joshi, A. (eds) IOT with Smart Systems. ICTIS 2023. Lecture Notes in Networks and Systems, vol 720. Springer, Singapore.

Admissions Apply Now