Technology Innovations

Archive for the ‘2016’ Category


Bangalore-based Dhananjai Bajpai, 24, is using the gesture-recognition technology to develop Kommunic8, a wireless wearable device that converts hand motions into speech. The device holds promise of improving communication for over 19 lakh speech-disabled people in India alone. A pilot project is currently being done with EnAble India, Bangalore, to test the functioning and accuracy of the device in the hands of actual users.

Dhananjai, who belongs to Kanpur city of Uttar Pradesh (UP), India, has completed his Bachelor’s in Electronics and Communication Technology degree from Shri Ramswaroop Memorial College of Engineering and Management, Lucknow, UP. He works at KFX Circuits and Systems in Bangalore and is also associated with Excubator, a startup incubator and corporate venturing advisory organization, where he works on Kommunic8 in his spare time. His aim is to use gesture-recognition technology for social benefit.

According to the 2011 Census of India, of the 268+ lakh total disabled population about 19+ lakh people suffer from speech disability. This population struggles not only in communicating with their surrounding environment, but also faces low job prospects that lead to another fight for quality sustenance. Kommunic8 aims to enable this populace to “talk” with anyone without any hesitation. 

Challenges

One of the challenges in bridging the divide between the speech-impaired and the common folks is that the sign language is difficult for a common man to understand and is restricted to the speech and hearing disabled community. Also, there is no standard international sign language that is followed consistently across the globe – each region and culture has its local sign language. These reasons prevent the differently-abled to communicate with others and live their social and professional life normally.

Kommunic8 equips the speech-impaired with a lightweight, wireless wearable ring-shaped device that can convert their sign language gestures into reasonable sentences in real-time and provide output in the form of an audible speech as well as a readable text on the K8 smartphone app.

With 97 percent accuracy and self-learning capability, the current prototype of Kommunic8 can be customized and programmed for any local language.

How it works

Kommunic8 is still in the development phase. Dhananjai began working on the technology in 2013, as a final year project, by creating a wearable glove which could detect the degree of bending of fingers and show respective alphabets on a mobile phone screen as per the American Sign Language. That was just the beginning which got its fair share of media attention. However, the wearable glove had its shortcomings in terms of size, speed, cost, and usability.

 

Initial prototype of Kommunic8

Initial prototype of Kommunic8

The current prototype of Kommunic8 uses a small circuitry packed neatly inside a ring like structure. The circuit uses gesture algorithm and a motion sensor that recognizes the sign and orientation of the user’s hand on which the device is worn. When the user moves or bends his/her hand to make a gesture, the sensor collects information and the software processes it to convert data into a sentence. The sentence is then spoken by a mechanized voice that is made audible through an inbuilt speaker. The same output can be presented in the form of a text on the K8 smartphone app.

The device operates on inbuilt battery that lasts for 10 hours – Dhananjai is working on increasing the battery power to last up to 24 hours. The device can be charged by any micro-USB charger.

The initial device will come with 50 actions predefined for ready use. The software, however, uses machine learning and will keep updating the database of gestures and sentences as the user starts using Kommunic8 regularly. Speaking of the storage capacity, Dhananjai says, “For now, Kommunic8 will come with a memory of 2 GB which can store up to 3,000 actions. This is sufficient, as on average a user may use maximum 100-300 actions in general. However, there is a provision for users to update the dictionary by connecting the device to a computer and make changes through the K8 desktop app.”

The device is supported by the K8 app available for Android and Windows phones that can be used to display the text, configure the device, recreate database and produce the speech output for interactions.  Here is a demo video.

 

 

Next steps

There is still a lot to accomplish before a market-ready version of Kommunic8 is complete. 

Dhananjai has filed a provisional patent for the technology innovation.

Now he is primarily focused on drastically improving the aesthetics of the device and using a more human voice output instead of the mechanized one. He is also working on including a small screen in the device with four push-buttons that can be used to reconfigure, expand and delete the database on-the-go, thereby removing the need for a secondary device for any kind of updates or assistance. 

Meanwhile, Dhananjai is reaching out to non-government organizations that might be willing to support pilot projects and provide sponsorship for further improvement of the device.

EnAble India is using Kommunic8 to:

  • Help teachers learn and improve their sign language and make classroom learning more attractive
  • Empower EnAble associated speech-impaired employees to use Kommunic8 for their daily communication at work.

“Results from the pilot will help me improve the device for the users. I am hopeful that Kommunic8 will allow them to get front-end jobs,” says Dhananjai.

Dhananjai can be contacted at dhananjaisrmgpc@gmail.com and +91-8765379454.

 


For the 220 million smartphone users in India, a Bangalore-based startup Street Smart Mobile Technologies has launched an app, SMS Sunami, to organize the deluge of transactional and promotional text messages we receive on our phones daily. The app, which is built using Android Studio, is based on an artificial intelligent platform that uses natural language processing to understand the context of messages and automatically classify them into predefined categories such as bills, entertainment, food, health and fitness, lifestyle, telecom operator, tickets, travel, and more.

According to a recent study, there are over two billion mobile phone subscribers worldwide who use the short message service (SMS) to exchange more than 350 billion text messages every month. Of these over 15% are promotional messages. The SMS Sunami app is aimed organizing and categorizing text messages of the Android smartphone users, making the messages in the default inbox easier to sift.

Street Smart Mobile Technology team (L-R): Prakhar, Prabhu, and Sudeep

Street Smart Mobile Technology team (L-R): Prakhar, Prabhu, and Sudeep

Incubated at Tata Elxsi’s Incub@ate, StreetSmart Mobile Technologies was founded in May 2014 by 27-year-old Prabhu SNM of Chennai, Tamil Nadu, with software engineers Prakhar Dighe (25) of Indore, Madhya Pradesh, and Sudeep (24) of Narsapuram, Andhra Pradesh. The trio developed the SMS Sunami app as an offshoot of another app that was aimed at offering hyper-local offers to consumers on their smartphones.

The hyper-local offers app could not succeed but the research for it led the team to realize that consumers are receiving host of text messages directly from service providers and merchants. And besides these messages, people also receive transactional messages processed by banks and of course, personal messages as well. No wonder our message box keeps filling up. And as the name suggests (and refers to tsunami), to help the users clear their inbox without having to delete their messages, SMS Sunami automatically categorizes the overwhelming number of messages a user receives.

“Our algorithm categorizes all text messages except those received from 10-digit numbers, which are personal numbers. This feature ensures privacy,” explains Prabhu.

 

Key features

Besides organizing the incoming messages into defined groups, the key feature of SMS Sunami is that it is capable of reading promotional text messages to serve contextual offers based on the content. For example, if you have a confirmation message from an airline on your travel tickets, SMS Sunami will serve you a cab-rental offer on the date of your travel. The concept applied to smartphone is much similar to what Google does by reading your mailbox. 

SMS Sunami app screenshot-Lifestyle

Lifestyle category screenshot of the app

Addressing the privacy concern on messages being read by the app, Prabhu says, “The SMS Sunami app does not store any messages to read and understand them. The program is built to ensure that the app works offline, without the need for the Internet, and does not store any data on the server. Our program simply functions within the app, reads the message, and pulls contextual offer from the associated merchants. The only time when the app uses the Internet is to identify the message sender with the brand logo to serve the message to the user in a more aesthetic manner.”

Besides this feature, the app allows easy search through the message box that allows you to search through your messages, by vendor name or by keywords. It also allows you to delete messages in bulk. SMS Sunami also automatically identifies key information in messages, such as contact numbers, web links, PNR, tickets, and provides them as ‘call for action’ links, making it easier for the user to use the information instantly.

The free beta version of the app is currently available on Android Play store.

Asked about the release of the iOS version of the app, Prabhu says, “The message APIs [application program interfaces] in the iOS are restricted for developers. This means we cannot develop any iOS app that requires reading the user’s messages. In this matter, I have written to Tim Cook requesting the need for leniency. I am awaiting his reply.”

 

Next steps

The team is working on scaling up the app into free and premium versions. The beta version is in the pre-revenue stage with 1,000+ customers. The trio’s short-term target is to increase the user base to 10,000 customers by the year end.

Sharing his plans for the future, Prabhu adds, “In future we plan to introduce ‘personal’ as a category so that our algorithm can detect personal messages without intruding privacy and categorize them appropriately. We also plan to enable the app to both receive and send messages. The idea is to eventually replace the default messaging application on smartphones with the SMS Sunami app.”

Improved user interface and enabling the user to customize the categories are also part of the plan. The team is also mulling over the idea of patenting the app’s software in the U.S.

The SMS Sunami team can be contacted at ceo@smssunami.com and +91-9790949400.


Enter your email address to subscribe to this blog's new posts by Email.

Join 281 other followers

Visitors Log

  • 10,543 visits till date

Monthly Archives

%d bloggers like this: