Search

A popular approach in machine translation is neural machine translation. It predicts and translates word sequences using artificial neural networks, generally modelling full sentences in a single integrated model. It enables the translation of languages from one natural language into another with or without the assistance of human beings. Even though deep neural architecture-based machine translation produces accurate results when translating western languages, we are unable to straight away apply these algorithms to translate languages in India, primarily because good corpora are not readily available and our languages are generally morphologically bountiful in nature. This paper aims at providing a general overview on language translation, which consists of Neural Machine Translation and Natural Language Generation involving the translation of Indian languages. [ABSTRACT FROM AUTHOR]

Devanagari is an ancient script that is used to write Hindi, Nepali, Marathi, Maithili, Awadhi, Newari, and Bhojpuri, among other Indo-Aryan languages. Thousands of individuals in India use this script to write documents in Marathi and Hindi. Indian mythology is based on this script. Because of the script's prominence, handwritten Devanagari character identification has grown in popularity over time. Handwritten recognition of languages such as English has received a lot of attention, but Indian languages written in the Devanagari script are also a rich source of information. Most of the work on this problem statement has been done either using deep neural networks like CNN at its heart coupled with other machine learning techniques like SVM,Random Forest etc. In this paper we are utilising a recently introduced transformer model for computer vision known as Vision Transformer for the task of Devanagari Character Recognition. We have also compared our model with various pretrained CNN-based architectures like ResNet50,VGG16 and InceptionV3 and ViT has outperformed these models both on DHCD dataset and the modified slightly more complex version of it with accuracy scores of 99.68% on the original testing dataset of the DHCD dataset and accuracy score of 96.55% on the modified(blurred) slightly more complex version of the original testing dataset. The ViT model thus generalized better than standard CNN-based models on the problem of Devanagari Character recognition. [ABSTRACT FROM AUTHOR]

Sustainable River water quality is to be maintained and it is the responsibility of all concerned stakeholders. The prime objective of Hydrology Project of Government of India is to ensure the river water quality and quantity by continuous capacity building and development of relevant both structural infrastructure (such as water quality laboratories) and cyber infrastructure (such as Decision Support Systems). Engineers and scientists working in the area of water quality need to be open minded with the ever uplifting attitude of lifelong learning to upskill with the ever-evolving relevant software and hardware technologies. Dissolved oxygen in rivers is essential for sustainability of aquatic life. Twelve year annual mean values from 2003 to 2014 of Dissolved Oxygen, pH, Electrical Conductivity, Nitrates, Biochemical Oxygen Demand and Temperature at nine stations along Krishna River are considered. Four types of models with varied input variables are developed in Multiple Linear Regression (MLR) using Microsoft Excel and Artificial Neural Networks (ANN) using nonlinear autoregressive model Artificial neural network identification model (NARX-ANN) to predict the dissolved oxygen. Levenberg – Marquardt Method (LMM) algorithm is used. The performances of both methods are compared. This paper takes care of Goal 6 of United Nations Sustainable Development of ensuring availability and sustainable management of water and sanitation for all as river water quality prediction is involved. ANN model with Mean Square Error (MSE) of 0.01 and R value of 0.987 is adopted. MLR model with R value of 0.574 is adopted. [ABSTRACT FROM AUTHOR]

Time series forecasting is a decisive step in data modeling and a significant area in machine learning. This paper presents Long short-term memory (LSTM) network, a deep learning neural network for predicting Covid-19 cases in India. The neural network models are trained and tested with Covid-19 case data sets obtained from PRS Legislative Research database. Further, the parameter optimization is carried out for choosing the optimal network. The parameters considered for evaluating the performance of LSTM network are RMSE, number of epochs, accuracy and loss. The results are compared with various recurrent neural network models and autoregressive model. The results revealed an improved accuracy of 92.8% for LSTM network in predicting the transmission of Covid-19 in India. [ABSTRACT FROM AUTHOR]