Rachana Solanki
Magic Gloves
Team
Stavan Himal
Rachana Solanki
My Role
Design - Requirement gathering, defining the scope, designing the solution
Develop - Arduino, MATLAB, Hardware integration, Wireless communication
& Manage the project
Timeline
4-month project supervised by Prof. Anurag Lakhlani
Motivation
We (me and Stavan Himal) believed that the benefits of technology should be available to all. In this quest of achieving and developing for common people, we as designers almost forget that specially abled people have the equal right to enjoy these benefits if technology.
Lo-Fi
Prototyping
Wireframing
Problem Space
Define
Ideation
Key
Findings
Final Design
Direction
Design a solution that overcomes the existing challenges of the systems available to assist/help specially abled people and reduce the barrier of communication.
Storyboarding
Brainstorming
Empathize
We first conducted a secondary research and educated ourselves on existing online information. For primary research, we decided to visit K.L. Institute of Deaf and Dumb in Bhavnagar, Gujarat, India. We interviewed the Stakeholder (the caretakers) at this school of specially-abled people in Bhavnagar, Gujarat, India.
Key Insight From Stakeholder Interview
Difficulty in communication between a common person and speech impaired person due to lack of knowledge of Sign language. they cannot communicate with their parents, family members and/or people from their neighbourhood as they lack the knowledge of sign language.
Secondary Research
1.221 Billion
Total Population of India
2,68,10,557
people in India have some kind of disability
19,98,935
people in India have speech disability
Define
After empathizing with the user, we defined our problem statement and analyzed the data we received in empathize phase. We jotted down the key requirements, created empathy map and build the persona. From all of we found the pain points. Persona was used throughout our design process to recall who is our USER and stay focused on user-centric approach.
Problem Statement
To eradicate the necessity of knowledge of Sign Language to communicate with specially-abled people and facilitate remote communication for specially-abled people.
Empathy Map
Persona
Key Findings
Key Requirements
​​​
-
Knowledge of sign language was necessary to communicate with people.
-
Not able to contribute effectively in group discussions.
-
Barrier leads to frustration which affects mental health.
​
1. People don't know sign language.
2. Challenge to express in public/group
discussions.
​
Ideate
For this project, there was no scope to go wild and creative with ideas keeping in mind that the ideas should be feasible and support existing technology. We wanted to propose something that would be easy to develop in coming years and something not too futuristic. So we began with competitive analysis, came up with a solution and rated our proposed solution based on selection metrics. After having satisfied the selection metrics and our supervisor Dr. Anurag Lakhlani, we decided to proceed with the proposed design direction.
Competitive Analysis
​​​
-
a. Voice Input Output Communication Aid (VIVOCA)
-
b. SpeechEasy
-
c. Proloquo2Go
-
d. EnableTalk
-
e. SignAloud
-
and many more...
Proposed Idea
​
a. Voice Output Communication Aid (VOCA)
b. Sign facilitated Augmentative and Alternative Communication (AAC)
​
Selection Metrics
Final Design Direction - Magic Glove
An embedded glove which allows speech impaired people to communicate with normal people. The device converts Sign Language to Voice Output.
Functionalities:-
1) Converts sign to speech
2) Inbuild effective vocabulary
3) Voice output into two spoken languages
4) Adaptive for different hand sizes
5) Remote communication
Develop
first, divided the system into two modules - Main module and sub-module (for remote communication). With the aim to focus above mentioned functionalities, we listed down what sensors and actuators will help us achieve the same. We started building the magic gloves and tones of challenges were being faced by us like not flexible for different hand size, wireless communication, connecting Arduino and MatLab, and failure of electronic components.
Why Machine Learning?
We were always connected to our users to test and iterate the prototypes. One of the issues happened during the first test that while we were building the product, we were using my hand to define the gestures and also sensors were threaded with the glove and they were not so tight. So every time we did the test, we failed because if the sensor moves from its place or if someone has different hand-size than mine, it didn’t work at all. For that reason, we started ideating the solution for that and we found the opportunity to use Machine Learning and provide predictive output. For the test, we used different types of algorithms to check which works the best for our problem and we found that K-Nearest Neighbour works the best for our system with the accuracy of ~97%. (We recorded 33,000 instances of 20 different people with different hand-sizes for our model) Introducing ML just removed all the cases of the glove not working. Even if it is a different hand-size or even if the sensors move from its place, it worked most of the time.
Why Wireless Communication?
During our primary research, we also found that it gets really difficult for speech impaired people to communicate with others who are not in front of them. There is only one possibility that they need to have some sort of camera-enabled devices through that they can make a video call to someone and can communicate. But, again as our target group was mainly the people from the Rural area, it was difficult for them to have such high-end devices and internet connectivity. Again, we saw the opportunity and tried to implement wireless communication protocols so that they can talk to anyone at a remote distance. Currently, the system is enabled for one-sided communication through Bluetooth protocol within the range of 20–30 meters.
Reflection
Our future goal is to develop a working demonstration of two-way communication system & conduct User Study using user study plan, get the feedback/results and reiterate this step until user experience reaches the level which is acceptable. Also, we would in parallel work on implementing using other modes of communication.
More Projects
