BWCNN: Blink to Word, a Real-Time Convolutional Neural Network Approach

  title={BWCNN: Blink to Word, a Real-Time Convolutional Neural Network Approach},
  author={Albara Ah Ramli and Rex Liu and R. Krishnamoorthy and Bs Vishali and Xiaoxiao Wang and Ilias Tagkopoulos and Xin Liu},
Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease of the brain and the spinal cord, which leads to paralysis of motor functions. Patients retain their ability to blink, which can be used for communication. Here, We present an Artificial Intelligence (AI) system that uses eye-blinks to communicate with the outside world, running on real-time Internet-of-Things (IoT) devices. The system uses a Convolutional Neural Network (CNN) to find the blinking pattern, which is… 
Early Mobility Recognition for Intensive Care Unit Patients Using Accelerometers
This paper targets a new healthcare application of human activity recognition, early mobility recognition for Intensive Care Unit (ICU) patients, and proposes a segment voting process that leverages a majority voting strategy to recognize each segment’s activity.
BlinkListener: "Listen" to Your Eye Blink Using Your Smartphone
This research presents a probabilistic architecture for Ubiquitous Network and Service Software that automates the very labor-intensive and therefore time-heavy and expensive and therefore expensive and expensive process of developing and maintaining networks.
Gait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches
This paper presents a probabilistic procedure to characterize the response of the immune system to repeated exposure to carbon monoxide poisoning and shows clear patterns of decline in the immune systems of mice and rats.
CueBot: Cue-Controlled Response Generation for Assistive Interaction Usages
This work builds a system that can represent people with disabilities, or speech and language disorders, in a social conversation and generate responses that can be controlled by the users using cues/keywords and introduces a keyword-loss to lexically constrain the model response output.
CNN-based severity prediction of neurodegenerative diseases using gait data
A deep learning-based approach using gait data represented by a Quick Response code to develop an effective and reliable disease severity grading system for neurodegenerative diseases such as amyotrophic lateral sclerosis, Huntington’s disease, and Parkinson's disease is proposed.
Controllable Response Generation for Assistive Use-cases
This study shows that keyword-control on end-to-end response generation models is powerful and can enable and empower users with degenerative disorders to carry out their dayto-day communication.
An Overview of Human Activity Recognition Using Wearable Sensors: Healthcare and Artificial Intelligence
This overview paper covers considerations and settings for building a HAR healthcare system, including sensor factors, AI model comparison, and system challenges, and presents the emerging HAR projects for healthcare: identification of human activities for intensive care unit patients and Duchenne muscular dystrophy patients.


Augmentative and Alternative Communication device based on eye-blink detection and conversion to Morse-code to aid paralyzed individuals
An extremely low priced device that reads and converts eye-blinks from the patient to a universally accepted communication code-The Morse code is designed.
Rethinking the Inception Architecture for Computer Vision
This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition
Densely Connected Convolutional Networks
The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Communication via eye blinks - detection and duration analysis in real time
A method for a real-time vision system that automatically detects a user's eye blinks and accurately measures their durations is introduced. The system is intended to provide an alternate input
DualBlink: A Wearable Device to Continuously Detect, Track, and Actuate Blinking For Alleviating Dry Eyes and Computer Vision Syndrome
A series of glasses-mounted devices that track the wearer's blink rate and, upon absent blinks, trigger blinks through actuation: light flashes, physical taps, and small puffs of air near the eye, which believe can serve as an always-available and viable option to treat computer vision syndrome in the future.
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Efficient Eye Blink Detection Method for disabled- helping domain
An efficient eye tracking method is proposed which uses the position of detected face which provides a 98% overall accuracy and 100% detection accuracy for a distance of 35 cm and an artificial light.
A small CNN architecture called SqueezeNet is proposed, which achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters and is able to compress to less than 0.5MB (510× smaller than AlexNet).
and Z
  • Wojn3. Rethinking the inception architecture for computer vision. In CVPR,
  • 2016