IoT-Guard: Event-Driven Fog-Based Video Surveillance System for Real-Time Security Management

Aim: To design and implement a distributed Internet of Things framework called IoT-guard an efficient resource constrained methodology to prevent and predict crime events in a smart home environment. Existing System: In existing system various cyber-physical systems widely adopt the use of intelligent video surveillance, for automatic and accurate identification of events and objects in […]

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. […]

Raspberry Pi based voice-operated personal assistant (Neobot)

Aim: Aim of this project is to develop a personal assistant system for visually impaired people to help identify faces of people standing in front of them and used to read book or any readable document. Existing System: Existing system developed a personal assistant for normal people which uses voice commands to control the system […]

Nearshore Ship Detection on High-Resolution Remote Sensing Image via Scene-Mask R-CNN

Aim: To automate the detection of presence of ships and to classify the types of ships available in the given Image. Existing System: Computer-aided ship detection methods greatly free up human resources and typically include two steps: extracting image features, and then using classifiers for classification and localization. These methods can produce stable results under […]

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 Detection of Apple Leaf Diseases Using Deep Learning Approach Based on Improved Convolutional Neural Networks

Aim: To detect the apple leaf diseases using convolutional neural network for high accuracy detection Existing System: In recent years, with the popularization of digital cameras and other electronic devices, automatic plant disease diagnosis has been widely applied as a satisfactory alternative. Nevertheless, in most cases, traditional machine learning approaches such as support vector machine […]

Efficient Fire Detection for Uncertain Surveillance Environment

Aim: To efficient CNN based system for fire detection in videos captured in uncertain surveillance scenarios Existing System: To detect fire, researchers have presented both traditional and learned representation based fire detection methods. In literature, the traditional methods use either color or motion characteristics for fire detection. For instance, [9-16] used color features for fire […]

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 […]