For developing Deep Learning(DL) interference applications at the edge, we can use Intel's energy-efficient and low-cost Movidius USB stick. In this project we are going to use Intel Movidius Neural Compute USB stick with Raspberry Pi-3 for image classification application.
We know that an effective accurate Deep Learning framework can be only done with advanced processors. When a deep learning framework is done with a very high-level programming language like MATLAB it becomes more complicated, still it can be done efficiently by any type of processors.
Harnessing power of AI to build a robust solar irradiation forecasting pipeline for efficient management and integration of solar energy in power grids.
Phillips Medical EA ran a campaign dubbed Back to Rhythm aimed at teaching communities in Kenya about the importance of healthy living habits .I was hired as a consultant to build the Mc Runner and rider to help participants ride ,run and win an EAD defibrilator for their public hospitals placesetc.
This code segments out the drivable portion of the road from the surrounding with the help of open-CV library.
Indian-roads face the fading of lanes, unsmooth road surfaces. So, this project directly takes use of the pixel-values of the road to segment out the drivable portion of the road.
With the Queue, we tried to digitize the queues where an organiser of any event creates an event and the participant can get into the queue using our application, without explicitally standing there.
A simple Command Line application which allows you to create files in your directory/folder, with all types of file extension in a more interactive way
To probide an edge to database management, I am trying to introduce intelligence databases, which can detect it components merely based on user feedback.
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.
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.