In this paper, Deep Learning-based models are used for predicting the number of novel coronavirus (COVID-19) positive reported cases for 32 states and union territories of India. Recurrent neural network (RNN) based long-short term memory (LSTM) variants such as Deep LSTM, Convolutional LSTM and Bidirectional LSTM are applied on Indian dataset to predict the number of positive cases. LSTM model with minimum error is chosen for predicting daily and weekly cases. It is observed that the proposed method yields high accuracy for short term prediction with error less than 3% for daily predictions and less than 8% for weekly predictions. Indian states are categorised into different zones based on the spread of positive cases and daily growth rate for easy identification of novel coronavirus hot-spots. Preventive measures to reduce the spread in respective zones are also suggested. A website is created where the state-wise predictions are updated using the proposed model for authorities,researchers and planners. This study can be applied by other countries for predicting COVID-19 cases at the state or national level.

In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and on algorithms for estimating true labels from noisy labels. An alternate approach would be to look for loss functions that are inherently noise-tolerant. For binary classification there exist theoretical results on loss functions that are robust to label noise. In this paper, we provide some sufficient conditions on a loss function so that risk minimization under that loss function would be inherently tolerant to label noise for multiclass classification problems. These results generalize the existing results on noise-tolerant loss functions for binary classification. We study some of the widely used loss functions in deep networks and show that the loss function based on mean absolute value of error is inherently robust to label noise. Thus standard back propagation is enough to learn the true classifier even under label noise. Through experiments, we illustrate the robustness of risk minimization with such loss functions for learning neural networks.

One thousand five euthyroid patients (870 females and 135 males, mean age 47 years), who presented with thyroid enlargement were evaluated by fine-needle aspiration cytology (FNAC) of the thyroid as the first-line investigation. The final cytological or histological diagnosis was determined after surgery (n = 312) or clinical follow-up for a minimum period of 2 years (range 2-14 years, mean 6.7 years). Goiter type was assessed clinically and was classified as diffuse in 147, multinodular in 247, or solitary nodule in 611. The overall sensitivity and specificity of the procedure in the detection of thyroid neoplasia was 88% and 89%, respectively. Males who presented with thyroid enlargement had significantly higher rates of malignancy (p = 0.007) and neoplasia (benign + malignant) (p = 0.002) than females, as did subjects with solitary nodule compared with diffuse or multinodular goiters (malignancy p = 0.001, neoplasia p < 0.001). Subjects with normal thyrotropin (TSH) (>0.4 mU/L) at presentation had a nonsignificantly increased risk of thyroid neoplasia (p = 0.07) and malignancy, in contrast to those with low TSH (<0.4 mU/L). We confirmed FNAC of the thyroid to be an accurate test in the detection of thyroid neoplasia. Gender and goiter type at presentation both contribute significantly to the prediction of the diagnosis of thyroid neoplasia.

It is evident that higher doses and longer duration of inhaled corticosteroid in COPD patients are associated with a higher prevalence of cataract and glaucoma.

No abstract