Gaurav Ruhela

From Msplacements


E-mail: ruhela_gaurav@research.iiit.ac.in
Contact No: +91 9346517805

Career objective
To pursue a challenging career in the computer industry, wherein I can apply my knowledge, acquire new skills and work closely with a team of highly experienced professionals.

Education

  • MS by Research (CSE), IIIT-Hyderabad, September, 2009 (expected)
  • B-Tech, International Institute of Information Technology, Hyderabad CGPA – 7.81
  • Senior Secondary, Ravindra Public School, New Delhi, 2003, 69.8%
  • Secondary, Ravindra Public School, New Delhi, 2001, 79.8%

Academic & Research Experience

  • Research Assistant and Developer for eSagu: An IT Based Personalized Agro-Advisory System, Agriculture and Rural Development lab (ARD), IIIT Hyderabad, India (September 2006 - Present)
  • Teaching Assistant for Web Data and Knowledge management (WDKM) course (Spring '08)

Primary Research & MS Thesis

  • Improving Text Document Clustering by Exploiting Open Web Directories
    Advisor: Prof. P. Krishna Reddy
    We are making efforts to propose improved algorithms for feature extraction and weight assignment methods by exploiting concept hierarchy of terms using Open Web Directory.
  • Improving Cohesiveness of Text Document Clusters
    Clustering is an unsupervised process, thus it is difficult to capture the possible distribution of documents. So, an intermediate step has to be introduced from which a clustering algorithm can find the discriminative features for the cluster. An algorithm is developed to identify discriminative feature set for each cluster. Using these feature sets, a given set of clusters is refined by incrementally moving documents between clusters.

Publications

  • Gaurav Ruhela and P. Krishna Reddy, "Improving Text Document Clustering by Exploiting Open Web Directory", in the 21st International Conference on Software Engineering and Knowledge Engineering, (SEKE 2009) Boston, USA, July 2009.
  • Gaurav Ruhela and P. Krishna Reddy,"BoostWeight: An Approach to Boost the Term Weights in a Document Vector by Exploiting Open Web Directory", in the International Conference on Information and Knowledge Engineering, (IKE'09) Las Vegas, Nevada, USA, July 2009.
  • Gaurav Ruhela, "Improving Cohesiveness of Text Document Clusters", in the 5th International Conference on Data Mining, (DMIN'09) Las Vegas, Nevada, USA, July 2009.

Academic Achievements

  • Dean’s award for academic excellence (for semesters VII and VIII).
  • Secured an All India Rank of 2560 out of 3,50,000(approx) candidates in AIEEE 2004.
  • Secured an All India Rank of 16 in IP-CET in year 2004.

Course work

Theory of Computation, Algorithms, Computer Graphics, DataBase Management Systems, Artificial Intelligence, Software Engineering, C Programming, Data Structures, Digital Logic Design, Computer Organization, Discrete Maths, Operating Systems IT Workshop, Electronic Circuits , Signals and Systems , Computer Networks , Compilers , Principles of Programming Languages, Information Retrieval and Extraction , Data Warehouse and Data Mining , Web Data and Knowledge Management, Pattern Recognition.

Areas of Interest
Information Extraction and Retrieval, Data Mining, Web Mining, Databases, Distributed Databases.

Computer Skills

  • Internet Technologies Used :- HTML, JavaScript, PHP.
  • Database Technologies Used :- MySQL, MSSQL
  • Programming Languages Used :- C/C++, Perl.
  • Programming Languages Used :- OpenGL.
  • OS platforms Used :- UNIX (Linux), Windows.

Projects

  • Distributed DBMS Layer
    Advisor: Satyanarayana R. Valluri
    A distributed relational database management system is implemented, having support for horizontal, vertical and derived fragmentation. Central database is distributed over three sites without any data replication and having MYSQL database on them. Input query is decomposed using fragmentation schema and fragmented query is executed on the appropriate site.
  • Assigning Names to Clusters by Capturing Discriminative Features
    Advisor: Dr. Vikram Pudi
    This project's aim is to assign names to the clusters. We need to overcome the problem of high-dimensionality and find understandable description of clusters. Application of this would be to make a high speed searching facility.
  • Single Document Text Summarization System
    Advisor: Prof. P. Krishna Reddy
    With the rapid growth of Internet, most of the textual data in the form of newspapers, magazines, and journals tend to be available on-line. Summarizing these talks can aid the users access the information content at faster pace. However doing this task manually is expensive and time consuming. Automatic text summarization is a solution for dealing with this problem. Summary of a document is made to cover all the important concepts in a document. Algorithm designed shall also work for multiple document summarizations.
  • Designing and Implementing Automatic Advice Delivery System for eSagu (Project funded by Media Lab Asia)
    Advisor: Prof. P. Krishna Reddy
    Clusters are made by using important features and previous given advices. Scientists need not give same advice for the same kind of problem. This system automatically gives the best possible advice. So lot of time is saved, thus increasing the efficiency of scientists as well as the system.
  • Data Mining in Chess Dataset
    Advisor: Prof. Kamal Karlapalem
    Given a dataset of 13000 xml files of chess games we had to come up with a hypothesis which could help a chess player in improving his game strategy. I found the importance of each piece for every player. So, one can find out opponent's strength, even before starting the game.
  • Query Classification Tool
    Advisor: Dr. Vasudev Verma
    We developed a module to categorize 800,000 queries into 67 predefined categories. This categorization is done with reasonable accuracy using the classification techniques of data mining, and making intelligent use of the results of search engines, viz., Google and Dmoz.
  • Spam Filter for Electronic Mails
    Advisor: Dr. Vikram Pudi
    This project deals with the problem of spam mails. Given a mail it would tell us whether the given mail is Spam or Ham. We implemented 5 algorithms for spam classification including comparisons between them and their own efficiency. Dataset included around 1600 spam mails and same number of ham mails.
  • Topic Detection and Tracking
    Advisor: Prof. P. Krishna Reddy
    Task is to detect novel events from a temporally-ordered stream of news stories, either retrospectively or as the stories arrive. For this we implemented similarity based KNN approach, Single pass clustering method and KNN + Time approach.
  • To Build a Room Allocation System For IIIT-H
    Advisor: Dr. Anoop M. Namboodiri
    We developed a system to keep track of the rooms which are being used for classes, talks, seminars, etc. and on which dates/times they are used. This is required to allocate available rooms as requested for new talks, meetings, etc in IIIT. User can enter their specifications and according to that room is allocated after approval of moderator. Moderator is informed about the allocation by an automatic generated mail.

Extra Curricular

  • Member of Sports Council in Student Parliament, 2005-2007.
  • Sports Representative for AGNI House in Student Parliament, 2006-2007.
  • Awarded with "Cricketer of the year" award for 2008-2009 season.
  • Member of IIIT-H, House and Batch's cricket team (2004-2009)
    • Captain of IIIT-H and house cricket teams for several tournaments
    • Captain of batch cricket team (2004-2009)
  • Organizer of the Inter House Cricket Tournament (2006-2007)
Retrieved from "http://www.iiit.ac.in/msplacements/index.php/Gaurav_Ruhela"
Personal tools