In recent years, there has been increased interest in video summarization and automatic sports highlights generation. In this work, we introduce a new dataset, called SNOW, for umpire pose detection in the game of cricket. The proposed dataset is evaluated as a preliminary aid for developing systems to automatically generate cricket highlights. In cricket, the umpire has the authority to make important decisions about events on the field. The umpire signals important events using unique hand signals and gestures. We identify four such events for classification namely SIX, NO BALL, OUT and WIDE based on detecting the pose of the umpire from the frames of a cricket video. Pre-trained convolutional neural networks such as Inception V3 and VGG19 networks are selected as primary candidates for feature extraction. The results are obtained using a linear SVM classifier. The highest classification performance was achieved for the SVM trained on features extracted from the VGG19 network. The preliminary results suggest that the proposed system is an effective solution for the application of cricket highlights generation.

Glaucoma is one of the severe eye disease according to the number of blindness causes in India and western Countries. Therefore the early detection, long-term monitoring of the patients and the decision about the appropriate therapy at the correct time point are serious tasks for the ophthalmologists and optometrists.There are many diagnostic methods are available like, Fundal examination, perimetry OCT (Optical Coherence Tomography) Field analyzer and Tonometry to diagnose Glaucoma. Among these, Tonometry in the reliable and accurate method to measure the intra-ocular pressure of the eye. Which is the cause for Glaucoma.The present research works in under taken to classify and diagnose such dreaded disease Glaucoma through Artificial Neural networks (ANNs) model. The ANN model adopted in multilayer feed forward networks and back propagation algorithm for classification. The present study considers 150 patients input data and output data for training of ANN networks, for testing of ANN, 50 patients input data is considered. The adopted ANN networks with topology 6-150-1 classified Glaucoma and non-glaucoma cases with an accuracy of 80%.

Meteorological data analysis is obtaining the information from raw data. There is vast amount of data available for weather analysis. Market needs timely and accurate data. The collection and datawarehouse of weather data is important because it provides an economic benefit but the local or national economic needs are not as dependent on high data quality as is the weather risk market. The semi arid region of Karnataka namely Madikeri region is considered for data analysis. The relative importance of features is identified for analysis of rainfall data. The adaptive boosting random forest classifier is applied to generate decision rules governing the prediction of rainfall. The data is collected from Indian Meteorological Department (IMD) for span of 12 years from 2004 to 2016. There are 4825 samples considered for the data analysis. The number of features considered for data analysis is 13 for prediction of rainfall. The validation curve and RMSE values justify the results obtained.

No abstract