<p>User Reviews in the form of ratings giving an opportunity to judge the user interest on the available products and providing a chance to recommend new similar items to the customers. Personalized recommender techniques placing vital role in this grown ecommerce century to predict the users’ interest. Collaborative Filtering (CF) system is one of the widely used democratic recommender system where it completely rely on user ratings to provide recommendations for the users. In this paper, an enhanced Collaborative Filtering system is proposed using Kernel Weighted K-means Clustering (KWKC) approach using Radial basis Functions (RBF) for eliminate the Sparsity problem where lack of rating is the challenge of providing the accurate recommendation to the user. The proposed system having two phases of state transitions: Connected and Disconnected. During Connected state the form of transition will be ‘Recommended mode’ where the active user be given with the Predicted-recommended items. In Disconnected State the form of transition will be ‘Learning mode’ where the hybrid learning approach and user clusters will be used to define the similar user models. Disconnected State activities will be performed in hidden layer of RBF and Connected Sate activities will be performed in output Layer. Input Layer of RBF using original user Ratings. The proposed KWKC used to smoothen the sparse original rating matrix and define the similar user clusters. A benchmark comparative study also made with classical learning and prediction techniques in terms of accuracy and computational time. Experiential setup is made using MovieLens dataset.<strong></strong></p>
American Sign Language (ASL) recognition system aims to recognise hand gestures’ meaningful motions, and it is a crucial solution to communicate between the deaf community and hearing people. However, existing sign language recognising algorithms still have some drawbacks, such as the difficulty of recognising hand movements low recognition accuracy for most of the sign language recognition. To address this problem, a Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system is developed. There are three main parts present in the method. The first part is preprocessing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.95 per cent accuracy and a 0.05 per cent False Positive Rate. Other CNN such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognises the difficult hand gestures through the image data and obtain high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language.
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.