Faculty

·  Sheikh Muhammad Sarwar, Mahamudul Hassan, Masum Billal, Dmitry Ignatov, “Similarity Aggregation for Collaborative Filtering”, AIST 2015, Yekaterinburg, Russia.

·  Falguni Roy, Sheikh Muhammad Sarwar, Mahamudul Hassan, “User Similarity Computation for Collaborative Filtering Using Dynamic Implicit Trust”, AIST 2015, Yekaterinburg, Russia.

·  Khaleda Akhter, Sheikh Muhammad Sarwar, “Analysis of the Adaptive Nature of Collaborative Filtering Techniques In Dynamic Environment”, AIST 2015, Yekaterinburg, Russia.

·  Noman Bin Mannan, Sheikh Muhammad Sarwar, Najeeb Elahi, “A New User Similarity Computation Method for Collaborative Filtering Using Artificial Neural Network”, EANN 2014, Sofia, Bulgaria.

·  Hafiz Md. Hasan Babu, Nazir Saleheen, Lafifa Jamal, Sheikh Muhammad Sarwar, Tsutomu Sasao, “Approach to design a compact reversible low power binary comparator”, IET Computers and Digital Techniques, Volume 8, Issue 3, May 2014. 

·  Sheikh Muhammad Sarwar, Md. Mustafizur Rahman, Md. Haider Ali, Ashique Mahmood Adnan, “A Scalable Image Snippet Extraction Framework for Integration with Search Engines”, Computer and Information Science 6(1): 89-99 (2013)

·  ShafaetAshraf,Sheikh Muhammad Sarwar, Md. Abeed Hassan, Dr. Saifuddin Md. Tareeq, Anna Fariha, “An Efficient Method for Extracting Subtrees against Forest Query”, IMCOM 2015, Bali, Indonesia.

·  Sheikh Muhammad Sarwar, Md. Anowarul Abedin, Abdullah-Al-Mamun, “Personalized Query Expansion for Web Search Using Social Keywords”, iiWAS 2013, Vienna, Austria.

·  Sheikh Muhammad Sarwar, Ishtiaque Hossain, “A Novel Reduced Reference Image Quality Analysis Metric for JPEG Compressed Images Based on Image Segmentation”, ICIEV, 2013, Bangladesh.

Books

Conference Papers

Journal Papers

Others

CSE 804: Information Retrieval

Objective: The aim of this course is to give an understanding about the basic architechture of a search engine. Students will learn about efficient data structures for storing and indexing unstructured and semi-structured documents. They will also learn about the algorithms for ranking and scoring retrieved documents. However, crucial tasks like online and offline evaluation of search engines will also constitute a major part of the course. 

Outline: Boolean Retrieval: Inverted Index, Processing boolean queries, extended Boolean retrieval; Term Vocabulary and Postings lists: Document delineation and character sequence decoding, Tokenization, Dropping common terms: stop words, Normalization (equivalence classing of terms), Stemming and lemmatization, skip pointers, Biword indexes, Positional indexes; Dictionaries and tolerant retrieval: Search structures for dictionaries, General wildcard queries, k-gram indexes for wildcard queries, Spelling correction; Index Construction: Blocked sort-based indexing, Single-pass in-memory indexing, Distributed indexing, Dynamic indexing; Scoring and Ranking: Parametric and zone indexes, Term frequency and weighting, The vector space model for scoring, variant tf-idf functions; Computing scores in a complete search system: Efficient scoring and ranking, Components of an information retrieval system; Evaluation in information retrieval: Evaluation of unranked retrieval sets, Evaluation of ranked retrieval results, Assessing relevance, Results snippets; Relevance feedback and query expansion: The Rocchio algorithm for relevance feedback, Relevance feedback on the web, Evaluation of relevance feedback strategies, Global methods for query reformulation; Language models for information retrieval; Enterprise Information Retrieval: Explore the capacity of Apache Lucene as a text search framework.

e-mail: smsarwar@du.ac.bd

mobile: +8801717086885