Search

Sentiment Analysis is the Natural Language Processing (NLP) is the active research area due to its vast application like stock market prediction, product re-views etc. The sentiment analysis in the regional languages are required for the film industries to increase their profit. Many existing methods has been applied on the sentiment analysis in the regional languages to increases the performance and still, it lags due in efficiency. In this research, the Bi-directional Recurrent Neural Network (BRNN) is applied to increase the performance of the sentiment analysis in the regional languages. The BRNN method has the advantages of rep-resenting the high and poor resources sentences in the common space and sentiment is analyzed based on the similarity measure. The proposed method is evaluated on the twitter data and compared this with the existing methods such as Random forest and Support Vector Machine (SVM). The proposed BRNN has the overall accuracy of 50.32%, while existing method of SVM has the overall accuracy of 38.73%.

Tracking objects in video surveillance is a challenging task for public security. The advent of the semantic approach has greatly raised the growth of anomaly detection. However, the current anomaly detection methods typically experience problems like inadequate use of movement patterns and inconsistency on various datasets. This research proposed a system to enhance the efficiency of anomaly detection in video surveillance. The proposed system consists of two parts that involves object tracking and suspicious activity detection. The overall framework detects and tracks the abnormal objects in video surveillance. The transfer learning-based ResNet tracking has been used for object tracking. Distance Metric Learning (DML) method has been used for detecting suspicious activities in video surveillance. The results are estimated to analyze the efficiency of the proposed method. The proposed network classifier is compared with the existing ResNet and VGG-16 network. The proposed method provides 99% accuracy that had high performance compared to other existing methods.