projects center in chennai | U.G & P.G. | project center in chennai

SIMULATION OF SELF-DRIVING CAR USING DEEP LEARNING The rapid development of Artificial Intelligence has revolutionized the area of autonomous vehicles by incorporating complex models and algorithms. Self-driving cars are always one of the biggest inventions in computer science and robotic intelligence. 11 The neural network architecture is used to detect path in a video segment, linings of roads, locations of obstacles, and behavioural cloning is used for the model to learn from human actions in the video. 11 CONCEPTS INVOLVED: Convolutional Neural Network (convnet/CNN): Inspired by The organization of Visual Cortex, cnns take an image as Input, assigns importance to different features/objects of the Image, thereby learning about its characteristics. 11 ADVANTAGES: 11 ·    Initially the dataset contained around 4053 frames along with the respective labels ·    The Deep Learning model was trained for 20 epochs using Mean Square Error as loss function.

AN EFFICIENT PARALLEL APPROACH FOR SCLERA VEIN RECOGNITION 11 The blood vessel structure of sclera is formed randomly and is unique to each person which can be used for human’s identification. Several researchers have designed different Sclera vein recognition methods and have shown that it is promising to use Sclera vein recognition for human identification.  The proposed method will dramatically improve the matching efficiency without compromising recognition accuracy. 11 The experimental results show that our proposed method can achieve dramatic processing speed improvement without compromising the recognition accuracy. 11 ADVANTAGES 11 ·          The sclera has an advantage in that it can be captured using a visible-wavelength camera. ·          High efficiency without compromising recognition accuracy Home

INTERNET OF UNDERGROUND THINGS: SENSING AND COMMUNICATION ON THE FIELDS FOR PRECISION AGRICULTURE Scene classification is a highly useful task in Remote Sensing (RS) applications. Many efforts have been made to improve the accuracy of RS scene classification. Scene classification is a challenging problem, especially for large datasets with tens of thousands of images with a large number of classes and taken under different circumstances. One problem that is observed in scene classification is the fact that for a given scene, only one part of it indicates which class it belongs to, whereas the other parts are either irrelevant or they actually tend to belong to another class. 11   ADVANTAGES  111 ·          High accuracy in image classification ·          Images have high dimensionality  (as each pixel is considered as a feature) which suits the described abilities. 11

  INTRA-BODY COMMUNICATION IN BIOMEDICAL APPLICATIONS The project presents a new concept of communication method called as Intra-body communication in biomedical field. Human body is used as a medium of transmission of data. The use of this technology in medical monitoring systems eliminates the complexity of existing technologies that involves cables, wires for transmission of data. The proposed model provides a secure and simple communication system that consists of wearable devices to measure heart-beat and temperature and hence transmits the data to the master device in real time.   EXISTING SYSTEM 11 ·         Existing systems uses cables and wires to measure health related parameters like temperature, blood pressure, heart rate, etc. this makes the patient very uncomfortable and immovable. 111 ·         Till date, existing system uses wired technology to interconnect between sensors and monitoring systems. ...

  SIMULATION OF DRONE CONTROLLER USING REINFORCEMENT LEARNING AI WITH HYPERPARAMETER OPTIMIZATION.   Drone is one of the latest drone technologies that grows with multiple applications; one of the critical applications is for fire-fighting drones such as water hose carrying for firefighting. One of the main challenges of the drone technologies is the non-linear dynamic movement caused by a variety of fire conditions. DF ADVANTAGE: The resulting a tree-structure in which a trajectory for the drone can be again found by a search algorithm. 1 Work   include tests of the underlined advantages for the rectangular cuboid decomposition. 1 THEORY: Q-Learning theory The idea is to build a system that can control robot without the remote which it can control itself based on environment learning through trial and error process depend on reward and discount action already taken by robot. In creating the system, will be deploy of machine learning system based on the RL...