Text Analytics – Getting insights from text

Technology revolution is changing every aspect of the human life. Media and Marketing are no different. Among all the technologies that are contributing to the advancement, Data Science is at the forefront. As Text Data is being continuously generated and consumed in various formats and sizes from a number of varied sources, it is becoming an important asset to organizations. But this asset can be leveraged upon, only if stored, processed and analysed efficiently with the help of intelligent algorithms. There is a growing interest to utilize such data for the improvement of business, health, education, society, etc. There are many ways to process and analyse such data, covering broad techniques such as text visualisation, classification, named entity recognition, sentiment analysis, etc. Effective applications of these techniques can give organisations valuable insights leading to competitive advantage, efficient service delivery and above all higher customer satisfaction.

With this in the view, CDAC Mumbai is conducting a series of short-term courses in Data Science and Machine Learning. This is second series of such courses and latest in this series is  “Text Analytics” going to be conducted during May 18-20, 2017. Registrations for the course are open. More details can be accessed at http://www.kbcs.in/datascience.

R – your tool for data analysis

R‬ is a language and environment for Statistical Computing and Graphics. R provides a free/open source, cross­-platform, object-oriented environment to perform data analysis and visualisation tasks. Strength of R lies in its vibrant community, robust package repository and strong graphics capabilities. ‪

R provides all necessary tools required for various stages of a data analysis project. It provides techniques for data acquisition and processing as well as for data analysis and visualisation. It ranges from accessing data in various formats (CSV, XML…) to all possible ways of data manipulation (tabulation, aggregation…)to rich support for graphics (histogram, box plot etc.) to statistical models (regression, ANOVA…).

It is not always necessary to use built-in and supported functions and packages. Depending on the requirements, one can also develop his/her own functions, scripts and packages.

Recently, CDAC Mumbai has announced a 3-day course on R entitled “Using R for Data Visualisation and Analytics”. This course is aimed to cover in detail the features of R related to data analysis and visualisation. More details can be accessed here.

Open House at CDAC on the occasion of National Science Day

CDAC Mumbai is organising an Open House on the occasion of National Science Day(28th February, 2014) at its Kharghar, Navi Mumbai campus. This Open House will not only showcase CDAC products and projects, but also include Quiz Show, Programming Competition and Much More.

Sangrah – Knowledge Repository for FOSS in Education from CDAC, Mumbai

CDAC, Mumbai has announced the beta release of portal SangrahKnowledge Repository for FOSS in Education . This portal contains resources about different categories like Learning Management System, Content Management System, etc. It also contains user experiences for these categories, comparative analysis of various tools from these categories, specialised search, and collaboration facility for community supported content updates.

The portal is maintained with least manual intervention as most of the tasks including, resource collection, categorization, user experience identification, comparative analysis, etc are largely automated.

The portal is intended for academic institutions, entrepreneurs, among others to help them to adopt Free and Open Source Softwares (FOSS).

The portal is still evolving, hence feedback about the portal, improvement suggestions can be given through the feedback section on portal.

Users can visit and register on the portal at – http://nrcfoss.cdacmumbai.in/sangrah

Release of new version of GNU/Linux distribution for Cognitively Challenged by CDAC, Mumbai

Centre for Development of Advanced Computing (CDAC) has released the new version (version 0.1.2) of GNU/Linux distribution for CognitivelyChallenged. Cognitively challenged people face different kinds of problems such as memory loss, forgetfulness, attention problems etc. Therefore, the major objective of this distribution is to provide an accessible desktop environment suitable to such users. The major highlights of this distribution are simplified and accessible desktop environment, simplified applications, tagged file system, tag-based searching, user’s activity log, reminder facility etc. that are specifically aimed to reduce distraction and memory load during computer interaction. These salient features of the distribution can be of immense help to such users and their caretakers, while using computer. This distribution is based on Ubuntu 10.04 and offers a number of improvements/enhancements over previously released version (version 0.1.1). These improvements/enhancements have been incorporated based on feedbacks and suggestions received from various organisations and users.

Major highlights in the current release:

  • Faster tag based searching
  • Facility to add new user-defined image tags
  • Enhanced tag control center to edit/delete existing tags(textual and image both).
  • Enhanced tag control center to add new file extensions for which tag setting option should be enabled.
  • New educational games included (The Number Race and Tux Type)

GNU/Linux distribution for Cognitively Challenged-0.1.2 can be downloaded from here.

More details about the distribution can be accessed at http://www.cdacmumbai.in/glcc.

Details of various enhancements made in the current version can be found at http://nrcfoss.cdacmumbai.in/access/LinuxForCC-0.1.2-docs/ChangeLog_0.1.2.pdf.

Feedback and suggestions about the distribution can be sent at ossd[at]cdac[dot]in.

ALViC – Accessible Linux for Visually Challenged launched

ALViC- Accessible Linux for Visually Challenged was launched on 11th February, 2013 by Prof R. Chidambaram, Principal Scientific Adviser, Govt. of India & Shri J. Satyanarayana, Secretary, DeitY, Ministry of Comm. & I.T., Govt. of India during the CDAC Technology Conclave on 11th Feb, 2013 at Indian Habitat Centre, New Delhi. During the 2-days technology conclave, a number of technologies and products developed by CDAC under various thematic area were showcased.

ALViC is a complete desktop environment which provides a comprehensive solution for Visually Challenged users. This is a GNU/Linux distribution based on Ubuntu 10.04; and uses Orca 3.2.0 xdesktop screen reader as the main interaction mechanism for visually challenged users. They can use it out of the box because accessibility features suitable for fully blind as well as for partially blind users are enabled by default.

Main Features :

  • Free and open source desktop environment
  • Enhanced Orca with skim read, sentence navigation, list shortcut and structural navigation of text documents
  • PDF documents made accessible in Linux environment
  • Easy navigation and search facility on Desktop icon view
  • Accessible login for visually challenged users
  • Suitable desktop themes for partial blind
  • Other assistive tools like OCRFeeder, Audio book converter, Emerson DAISY reader, sound converter etc. useful for visually challenged users are also included.

This product has been released under the project ‘Enhancing Accessibility for FOSS Desktops’ at CDAC, Mumbai being carried out under NRCFOSS-Phase II. The research and development activities under this project are aimed at developing software-based assistive technologies/solutions for the differently-abled people.


ALViC can be downloaded from here.

Launch of ALViC can be watched here.

More details and documentation about ALViC can be accessed here.

Anumaan listed on Softpedia

Anumaan – open source predictive text entry system from CDAC, Mumbai has been added to the database of Softpedia. Softpedia is a library of over 400,000 free and free-to-try softwares. Anumaan on Softpedia can be accessed from here. Anumaan has also been awarded “100% Free” award from Softpedia signifying that Anumaan is a clean product.

Anumaan home page


RPM package of GEM (GEstures with Mouse) released

RPM package of GEM (GEstures with Mouse) has been released. GEM (GEstures with Mouse) is a mouse-gesture based input mechanism developed by CDAC, Mumbai for people with motor disabilities. It can be downloaded now from http://sourceforge.net/projects/gem-cdac/files/gem-0.1-1.i686.rpm/download or from http://www.cdacmumbai.in/accessibility.


New version of Anumaan – open source predictive text entry system from CDAC, Mumbai released

CDAC, Mumbai has announced the new release of open source predictive text entry system – Anumaan. This release includes new version of standalone flavour of Anumaan i.e. Anumaan-standalone-0.2. This version has been released as part of the activities of project “Enhancing Accessibility for FOSS Desktops” under NRCFOSS-Phase II being carried out at CDAC, Mumbai.

Anumaan gives predictions based on preceding text/words used by the user in his/her text and user can use these predictions, while composing text. By incorporating predictions, user can improve his/her rate of text entry to a great extent.

Anumaan is mainly intended to help persons with motor disabilities, specially ones facing problems in hand and finger movement. Such persons face difficulty in using regular input devices like keyboard for text entry related tasks. Anumaan can help such persons immensely in their text entry related tasks by way of predictions. However, It is equally useful for common users also and can support them in creating mails, letters, documents etc. in less time.

Salient features of current version include:

  • More user-friendly and simplified interface for easy interaction and navigation.
  • Re-oriented layout of text entry area and prediction display in order to reduce visual and cognitive overhead.
  • A single comprehensive prediction list combining predictions from all relevant grams for easy selection.
  • Keyboard support for selecting predictions from prediction list. It reduces time taken in selecting and committing predictions to text.
  • Larger text entry area compared to previous version for easy text entry.
  • Integrated context-sensitive help.
  • Re-oriented menu bar for easy access and navigation.

All these features are intended to improve user interaction and experience for motor disabled people.

Anumaan is developed on java platform and supports UTF-8, so it can effectively be run on any platform. Newly released version of Anumaan can be downloaded from http://www.cdacmumbai.in/anumaan.

Details about project “Enhancing Accessibility for FOSS Desktops” can be accessed at http://www.cdacmumbai.in/accessibility.

Feedback, bug reports or feature enhancement requests about the application can be sent to ossd[at]cdac[dot]in or predictanumaan[at]gmail[dot]com.