Personal Site

MS in Computer Science and Engineering (2 years research based)
Ritsumeikan University, Japan
Session: September, 2010 - September, 2012
Medium of instruction: English.
Bachelor in Computer Science (4 years)
North South University, Dhaka, Bangladesh
Session: 2003 - 2007.
Medium of instruction: English.
Work Experience
Schibsted, SnT (Schibsted and Telenor joint venture), Barcelona, Spain
Designation: Software Engineer
Duration: April 29, 2014 -
Ekhanei, Cellbazaar, GPIT, Dhaka, Bangladesh
Designation: Senior Software Engineer
Duration: March 1, 2013 - April 22, 2014
Codemate Ltd. Dhaka, Bangladesh
Designation: Senior Software Engineer
Duration: February 17, 2008 - September 8, 2010

  • Team leading for the software development project
  • Collaborating with business users, requirement analysis, work estimation, designing
  • Development in JAVA, PHP, C#, Ext-JS, Flash, Flex
  • Writing test cases
  • Software quality assurance
  • Writing technical papers
Codemate Oy. Oulu, Finland
Designation: Software Engineer
Duration: May 1, 2008 - July 31, 2008

  • Handling requirement analysis
  • Producing various design level documents and flow charts
  • Design and development in C#
  • Writing test cases
Infrablue Technology Dhaka, Bangladesh.
Designation: Software Developer
Duration: September 15, 2005 - January 31, 2008

  • Requirement Analysis, designing and developing Software in Java (J2ME, J2SE)
  • Developing Web Sites, WAP sites using PHP, AJAX, CSS, and web services
  • Developing Database systems using Oracle, MSSQL, MySQL
  • Developing mobile content management software for the lead mobile companies within Bangladesh
  • Test case generation and testing of each systems (Unit testing and Integration testing)
  • Documenting each system
Vendor Certification
Sun Certified Java Programmer (SCJP).
Time Series Similarity Search Using Textual Approximation

We developed a novel time series search and classification method, which uses textual approximation as its core. Motivation for this research was to develop a single technique which will be able to produce good results for many domains. It uses the existing information/document retrieval and classification models to retrieve and classify time series. Time series are sequence of numbers. Our proposed model represents a time series as a text document. Then it applies the existing document retrieval/classification algorithms and data structures to retrieve similar documents, which represents time series.

One of the biggest problems of time series is to maintain its high volume data. It is very complicated to make a scalable system, which can deal with massive data. We used several algorithms from image processing to filter the data, so that we can make a choice for some important points, which characterized the original time series. It reduces the high dimensionality of a time series to a lower one without loosing its characteristics. Modern search engines are using these techniques and heuristics to retrieve and classify documents.

We used semi-supervised and unsupervised machine learning algorithms to train our system. We mainly applied different types of clustering for automatic document classification. Then, we used the trained system to classify and retrieve time series document from different domains. Our focus was to improve the time series classification accuracy. Our method achieved high recall values in classification task.

We used various algorithms from different domains in our proposed method. For data filtering, we used second difference, moving average and piecewise linear approximation. For time series textual representation, we used tf-idf and symbol sequences, which are vastly used in information retrieval. Clustering is used for automatic document classification.

We performed our classification test on twenty different domains. Our method performed significantly well compare to other existing methods.

International Achievements for Research Activities
Best Student Paper Award, Seventh International Conference on Digital Information Management (ICDIM 2012), Macau, China.
Best Paper Presented Award, IICST 2012, Tomsk, Russia.
Best Paper Award, Third International Conference on Emerging Databases (EDB 2011), Korea.
  • Abdulla-Al-Maruf, Kyoji Kawagoe, Hung-Hsuan Huang. Time Series Classification Method Using Longest Common Subsequence and Textual Approximation. In Proceedings of the Seventh International Conference on Digital Information Management, pages 130-137, ICDIM 2012, August 22-24, Macau, China.
  • Kyoji Kawagoe, Abdulla-Al-Maruf, Hung-Hsuan Huang. Generic Textual Approximation of Temporal Multimedia. In Proceedings of the Fourth International Conference on Emerging Databases, EDB 2012, August 23-25, Korea.
  • Abdulla-Al-Maruf, Kyoji Kawagoe, Hung-Hsuan Huang. Multimedia Trajectory Similarity Search Using Textual Approximation. In Proceedings of IICST 2012, pages 67-74, IICST 2012, September 10-13, Tomsk, Russia.
  • Kyoji Kawagoe, Abdulla-Al-Maruf, Ke Deng, and Xiaofang Zhou. Searching Time Series Using Textual Approximation. In Proceedings of the Third International Conference on Emerging Databases, pages 121-132, EDB 2011, August 25-27, Korea.

join my club

I just have the club :D

black man

Still I do not know what will be added here.

...Join Now