Characterizing and Countering Communal Micro blogs During Disaster Events

Aim: The objective of this project is to develop a system to identify the tweet harbor hatred in micro blogs during disaster events. Existing System: The existing system uses sentiment analysis technique to identify the sentiment of the tweet. However this is not sufficient to identify the anti-social messages. The sentiment analysis might give the […]

New Modality: Emoji Challenges in Prediction, Anticipation, and Retrieval

Aim: To predict and Anticipation Emoji for multimedia retrieval. Existing System: To facilitate further research on emoji, we propose three emoji challenge problems and present state-of-the- art neural network baselines for them, as well as a dataset for evaluation. Previously cannot find a Emoji correctly and not accuracy. To found a unrelated emoji are displayed. […]

A Novel Stream Clustering Framework for Spam Detection in Twitter

Aim: The project is to classify spam tweets based on twitter account and content based features on twitter handles. Existing System: DenStream was promoted by the proposed framework, called here as INB-DenStream. To show the effectiveness of INB-DenStream, state-of-the-art methods such as DenStream, StreamKM++, and CluStream were applied to the Twitter datasets and their performance […]

Real-time Credit Card Fraud Detection Using Machine Learning

Aim: To detect the real time credit card fraud transaction using machine learning algorithms. Existing System: The obtained results are compared with the results of existing models within the same domain and found to be improved. The data of credit card fraud transactions data collected from the kaggle is used to discover patterns with Neural […]

Hybrid Prediction Models for Rainfall Forecasting

Aim: Analyze the rainfall data from database for rainfall prediction Existing System: The dataset is stored and processed in structured database like MySQL, Oracle etc. The time consumed to process volumes of data to pre-process and classify were huge. The model is utilized to generate the prediction of future rainfall based on the dataset. MySQL […]

Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques

Aim: To apply machine learning techniques resulting in improving the accuracy in the prediction of cardiovascular disease Existing System: The obtained results are compared with the results of existing models within the same domain and found to be improved. The data of heart disease patients collected from the UCI laboratory is used to discover patterns […]

Leveraging Affective Hash tags for Ranking Music Recommendations

Aim: To implement a recommendation for music, based on the content of microblog, to extract affective contextual information from hashtags contained in these tweets. Existing System: Existing system uses manual intervention and usage based suggestion. The recommendation of any service is based on the number of users who already requested similar services on the same […]

Deep Ensemble Machine for Video Classification

Aim: This paper aim to classify the different types of videos using deep learning framework with convolution neural network (CNN) Existing System: The convolution 3-D (C3-D) and VGG (vision and graphics group) are first deployed to extract temporal and spatial features from the input videos cooperatively, which establishes comprehensive and informative representations of videos. VGG […]

Development of IoT Mining Machine for Twitter Sentiment Analysis

Aim: The objective of this project is to develop a system to identify the sentiment of a tweet in micro blogs using machine learning and use IoT device to display in a two-way smart mirror. Existing System: The existing system uses sentiment analysis technique to identify the sentiment of the tweet. However this is not […]