In cricket, the region plays a significant role in ranking teams. The International Cricket Council (ICC) uses an ad-hoc points system to rank cricket teams, which entirely based on the number of wins and losses a match. The ICC ignores the strength and weaknesses of the team across the region. Even though the relative accuracy in the ad-hoc ranking is high, but they do not provide a clearly defined method of ranking. We proposed Region-wise Team Rank (RTR) and a Region-wise Weighted Team Rank (RWTR) to rank cricket teams. The intuition is to get more points to a team that wins a match from a stronger team as compared to a team that wins against a weaker team & vice versa. The proposed method considers not only the number of region-wise wins and losses but also incorporates the region-wise strength and weakness of a team while assigning them the ranking score. In conclusion, the ranking list of the teams compares to the ICC official ranking.
Identifying human behaviors is a challenging research problem due to the complexity and variation of appearances and postures, the variation of camera settings, and view angles. In this paper, we try to address the problem of human behavior identification by introducing a novel motion descriptor based on statistical features. The method first divide the video into N number of temporal segments. Then for each segment, we compute dense optical flow, which provides instantaneous velocity information for all the pixels. We then compute Histogram of Optical Flow (HOOF) weighted by the norm and quantized into 32 bins. We then compute statistical features from the obtained HOOF forming a descriptor vector of 192dimensions. We then train a non-linear multi-class SVM that classify different human behaviors with the accuracy of 72.1%. We evaluate our method by using publicly available human action data set. Experimental results shows that our proposed method out performs state of the art methods.
Recommender systems are one of the best choices to cope with the problem of information overload. These systems are commonly used in recent years help to match users with different items. As more data is available on the internet traditional methods suffer from challenges like accuracy and scalability. Deep learning a state of art machine learning method also achieve promising performance in the field of recommender system. In this study we provide an overview of traditional approaches their limitations and then discuss about the aspects of deep learning used in the recommender system domain to improve the accuracy in recommender system domains. These deep recommender systems can be used to understand the demands of users and improve the value in recommendations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.