Handwritten character recognition is currently getting the attention of researchers because of possible applications in assisting technology for blind and visually impaired users, human–robot interaction, automatic data entry for business documents, etc. In this work, we propose a technique to recognize handwritten Devanagari characters using deep convolutional neural networks (DCNN) which are one of the recent techniques adopted from the deep learning community. We experimented the ISIDCHAR database provided by (Information Sharing Index) ISI, Kolkata and V2DMDCHAR database with six different architectures of DCNN to evaluate the performance and also investigate the use of six recently developed adaptive gradient methods. A layer-wise technique of DCNN has been employed that helped to achieve the highest recognition accuracy and also get a faster convergence rate. The results of layer-wise-trained DCNN are favorable in comparison with those achieved by a shallow technique of handcrafted features and standard DCNN.

Road crashes are a significant global problem, resulting in the loss of over 1.19 million lives and causing around 50 million severe injuries each year. However, despite the efforts made by the Government to improve the situation, no significant results have been observed in respect to decline in number of accidents and deaths in India. Road safety is a complex issue and requires a multifaceted approach including adequate research and development in the field. At present the mostly traditional approach is applied in terms of data collection, statistical analysis and decision making. Over time, the Government may start building advanced data analytics solutions for prediction of various road crash attributes. With this intent this paper aims to depict the application of combination of different algorithms including Support Vector Machine, Random Forest, Decision Tree, Artificial Neural Network, K Nearest Neighbor, Logistic Regression, and Gradient Boosting Algorithm for prediction of road crash attributes.