Vehicle identification and classification are some of the major tasks in the areas of toll management and traffic management, where these smart transportation systems are implemented by integrating various information communication technologies and multiple types of hardware. The currently shifting era toward artificial intelligence has also motivated the implementation of vehicle identification and classification using AI-based techniques, such as machine learning, artificial neural network and deep learning. In this research, we used the deep learning YOLOv3 algorithm and trained it on a custom dataset of vehicles that included different vehicle classes as per the Indian Government’s recommendation to implement the automatic vehicle identification and classification for use in the toll management system deployed at toll plazas. For faster processing of the test videos, the frames were saved at a certain interval and then the saved frames were passed through the algorithm. Apart from toll plazas, we also tested the algorithm for vehicle identification and classification on highways and urban areas. Implementing automatic vehicle identification and classification using traditional techniques is a highly proprietary endeavor. Since YOLOv3 is an open-standard-based algorithm, it paves the way to developing sustainable solutions in the area of smart transportation.
Diabetic foot ulcer (DFU) is one of the most expensive and debilitating complications of diabetes. According to procedures developed by the National Institute of Health and Clinical Excellence, early and effective treatment of DFU can minimize the severity of complications, such as unnecessary amputations, and improve overall quality of life. In this paper, a stacked parallel convolution layers based Convolution Neural Network (CNN) is proposed, known as DFU MobileNet, to classify skin infected with DFU against normal skin. The main objective of this work is to develop a DFU recognition system that accurately identifies infected skin. DFU MobileNet consists of three blocks of parallel convolution layers, each with a unique kernel size to extract local and global features distinctly. Using the DFUC 2020 dataset, the proposed DFU MobileNet outperformed existing state-of-the-art models, achieving an accuracy of 92.2% using CNN DenseNet, 95.4% using MobileNet, and 97.8% when combining DenseNet and MobileNet.
Music holds signiffcant importance in our daily lives, serving as an earnest element. Amidst the vast expanse of available information, our objective lies in sieving through data to present users with relevant music or song content aligning with their interests and objectives. To improve music recommendation accuracy and real-time recommendation ability, we propose a hybrid music recommendation model based on a Popularity-based Song Recommender System, a Personalized Song Recommender System, and a Content-based Music Recommendation System. Our endeavor focuses on constructing a music recommendation system, which operates as a ffltering mechanism predicting user preferences in music based on their inclinations. This approach employs content ffltering techniques leveraging data characteristics to reffne recommendations. Our model, tailored to accommodate diverse instances and datasets, demonstrates robust performance. The devised song recommendation system exhibits notable efffcacy and sustained reliability. Encouraging outcomes, boasting an accuracy of 90.4%, furnish novel insights, laying the groundwork for future exploration in song recommendation systems.
28 November 2016 in Indian Journal of Science and Technology