Book ChapterDOI
LSTM Approach to Cancel Noise from Mouse Input for Patients with Motor Disabilities
Soham Harnale,Ashwin Vaidya,Aditya Bhide,Aniket Sanap,Mangesh Bedekar +4 more
- pp 423-430
Reads0
Chats0
TLDR
This paper attempts to suppress noise from mouse input due to involuntary tremors from patients with motor disabilities by using techniques like breakpoint detection and mean filtering to preprocess data which was then fed into a deep recurrent neural network.Abstract:
In this paper, we attempt to suppress noise from mouse input due to involuntary tremors from patients with motor disabilities. In order to achieve this task, we used techniques like breakpoint detection and mean filtering to preprocess our data which was then fed into a deep recurrent neural network. Additionally, we tested various architectures and explored existing hardware and software based assistive technologies.read more
References
More filters
Posted Content
Deep Karaoke: Extracting Vocals from Musical Mixtures Using a Convolutional Deep Neural Network
TL;DR: In this paper, a convolutional DNN was used to estimate the ideal binary mask for singing voice separation from real-world musical mixtures, which may be useful for automatic removal of vocal sounds from musical mixture for 'karaoke' type applications.
Journal ArticleDOI
A mouse adapter for people with hand tremor
J. L. Levine,M. A. Schappert +1 more
TL;DR: An assistive adapter that, when inserted between the mouse and the computer, provides digital motion-smoothing filtering, rejection of inadvertent mouse button clicks, and enhanced double clicking.
Journal ArticleDOI
Improving mouse controlling and movement for people with Parkinson's disease and involuntary tremor using adaptive path smoothing technique via B-spline.
TL;DR: A new assistive technique-adaptive path smoothing via B-spline (APSS) to enhance mouse controlling based on user's tremor level and type and shows that APSS is very promising and greatly increases their control of the computer mouse.