Integrated Vehicle Health Management (IVHM) for an aircraft is an upcoming area of research where an airplane is tracked with multiple sensors in all the parts of the plane. The data from the sensors shall render help in understanding the status of the aircraft, any malicious behavior that would probably result in an accident and also to log the flying data for future analysis. The data is really voluminous and now there is a lot of challenges faced in ensuring the integrity of the data store...
This project deals with the deployment of Deep Reinforcement Learning and Computer Vison models for creating smart traffic signals for Indian traffic conditions. We have used Sumo as our simulator and Intel Devcloud for the training of the RL models.
We propose a deep neural network for the prediction of sign language and gesture recognition in natural video sequences using CPU, and further integrated with Voice to Sign Language Gestures. To effectively handle complex evolution of pixels in videos, we propose to decompose the motion and content, two key components generating dynamics in videos. Furthermore, we integrate Alexa to provide a voice to sign language translation system using Speech and Image processing technique.
Cities across the world are growing rapidly, thousands of vehicles are being added to the road everyday resulting in increased road traffic. This causes traffic congestions, Pollution, consumption of resources and Economic loss. The need of the hour is a technology for managing the road traffic. IRTC is an application that analyses, estimates the demands of road traffic users and calculate the timings of the traffic lights grid. The Traffic flow routes are predicted at peak hours (office hour...
Controlling 3D printers via Alexa voice services is a powerful optimization to a busy workflow. Using the 3D printer orchestration tool, OctoPrint, voice services have been added to control and monitor 3D printer jobs, detect errors and recover using intuitive voice commands. OctoPrint can be run on Windows 10 helping to automate and control your 3D printer workflow with UI and Voice.
AR has already changed the way individuals view the world. In this project, we have designed a system where remote files and
directories are augmented in real-time over the camera view of the smartphone, tablet or PC. The users can access the remote file system and perform operations using gestures. This system provides a smooth and continuous interaction between the user and the digital space by only using hand gestures, without the use of any special purpose devices like a mouse or a joystick.
The challenge of dysphonia voice studies is always the small dataset. It is difficult to apply more sophisticated deep learning techniques without overfitting or underfitting. Convolutional neural network (CNN) is a powerful classifier that requires a large amount of training data. Data augmentation techniques for voice are limited. Fourier-based synchrosqueezing transform (FSST) can be used as a data aug- mentation technique to increase the data size. The results indicated that not only can ...
The good old MNIST dataset is the Hello-World dataset for deep learning with computer vision tasks. Many researchers use it to benchmark their findings. But time has changed. It is time to move on to Fashion MNIST which is a strong replacement for the original MNIST dataset. It is comparatively new. This project includes my exploration of the dataset, coming up with deep learning models and more.
A NLP based bot on Twitter which utilizes methodologies like Text Summarization, Text Classification & Automated Twitter Streamings for Disaster Management Related tasks.
This repository has its own implementation, impressed by ildoonet's achievements.
Thank you, ildoonet.
https://github.com/ildoonet/tf-pose-estimation.git
I will make his implementation even faster with CPU only.
