Computer Science Engineering

*** ****** **, *** *** 318-***-****

MD SHAFAEAT HOSSAIN

Ruston, LA 71270 ********@*****.***

EXPERTISE

Machine learning, Reject option in pattern classification, Multi-stage/serial fusion based biometric

verification, Cyber-behavioral authentication, Computer vision, Optimization.

C, C++, Java, MATLAB, WEKA, R, MySQL, JavaScript, PHP, OpenCV, OpenGL, Amazon EC2, RDS, LATEX.

EDUCATION

Ruston, LA Louisiana Tech University March 2009 – Present

PhD in Computational Analysis and Modeling, GPA: 3.93 in 4, Expected graduation: November 2013.

MS in Computer Science, November 2012. GPA: 3.93 in 4.

MS in Mathematics, May 2011. GPA: 3.92 in 4.

Graduate Coursework: Artificial Intelligence; Data mining, Fusion, and Application; Theory of statistics;

Regression Analysis; Statistical Methods; Theory of Probability; Linear Algebra; Software Engineering; Comp.

Architecture; Comp. Networks; Graph Theory; Numerical Analysis; PDE; Numerical Solution for PDE.

Dhaka, Bangladesh University of Dhaka Jan 2001-Jan 2009

st rd

MS in Computer Science and Engineering, Jan 2009. 1 Class 3 Position in order of merit.

st th

B.Sc. (Honors) in Computer Science and Engineering, April 2007. 1 Class 5 Position in order of merit.

Coursework (selected): Design and Analysis of Algorithms; Programming Languages; Data Structures;

Database Design; Operating Systems; Image Processing; Compiler Design; Bioinformatics; Distributed OS;

Parallel Programming; Object oriented Programming (Java, C Automata Theory; Microprocessor; Calculus.

EMPLOYMENT

Graduate Research Assistant Louisiana Tech University March 2009 - Present

Working in the Machine Learning group of Center for Secure Cyberspace funded by DARPA and US Air Force.

Developing new rejection rules to enhance the performance of serial fusion based biometric verification and

cyber-behavioral authentication.

Analyzing databases of Keystroke dynamics, Face, Fingerprint, and Age.

Lecturer of Computer Science Eastern University Bangladesh June 2007 – February 2009

Taught Computer Science courses: Design and Analysis of Algorithms; Compiler Design; Operating System.

Trained students for ACM International Collegiate Programming Contest (ICPC) 2008 and 2009.

ACHIEVEMENT: MACHINE LEARNING THEORY AND APPLICATION

PhD Thesis: New Rejection Methods for Multi-stage Biometric Verification

Developed the symmetric rejection method which allows the system administrator to control the reject rate

of genuine users in multi-stage biometric verification.

Developed a new impostor score based rejection method to handle the ‘weak template’ problem in cyber-

behavioral authentication.

Gave theoretical foundation for finding the reject region which produces the equal error rate (EER) in multi-

stage biometric verification.

Analyzed the behaviors of biometric performance metrics (IPR, FRR, EER) with reject option.

MS Thesis: Video Image Clustering Based on Human Face and Shirt Color

Developed a novel video image clustering method based on face image and shirt color.

Developed an optimized mask selection method for person identification.

COURSE PROJECTS (SELECTED)

Developed a Cloud Based EKG Service and Data Storage. Amazon EC2, RDS, C++, PHP, MySQL, Apache.

Developed an Online Blood Bank. PHP, MySQL, Apache.

Developed a Reliable Packet Delivery System between Clients and Servers. Java.

Implemented the basic components of a compiler for a subset of Pascal. C, Lex, Yacc.

SCHOLARLY ARTICLES APPLYING MACHINE LEARNING TECHNIQUES

Journal Publications

1. Md S. Hossain, Khandaker A. Rahman, Md. Hasanuzzaman, Md A. Bhuyian, and H. Ueno. Video Image

Clustering Based on Human Face and Shirt Color. In International Journal of Image and Graphics (IJIG),

2010.

Conference Publications

1. Md S. Hossain, Kiran S. Balagani, and Vir V. Phoha. On Controlling the Genuine Reject Rate in Multi-stage

Biometric Verification. In CVPR 2013 Biometrics Workshop, Portland, Oregon, June, 2013.

2. Md S. Hossain, Kiran S. Balagani, and Vir V. Phoha. New Impostor Score Based Rejection Methods for

Continuous Keystroke Verification with Weak Templates. In Proceedings of IEEE Fifth International

Conference on Biometrics: Theory, Applications, and Systems (BTAS 2012), Washington DC, 2012.

3. Md S. Hossain, Khandaker A. Rahman, Md Hasanuzzaman, and Vir V. Phoha. A Simple and Efficient Video

Image Clustering Algorithm for Person Specific Query and Image Retrieval. In Proc. of International

Conference on Internet Multimedia Computing and Service (ACM ICIMCS 2009).

4. Khandaker A. Rahman, Md S. Hossain, Md. A. Bhuyian, Tao Zhang, Md Hasanuzzaman, and H. Ueno. Eye-

Distance Based Mask Selection for Person Identification. In Proc. of International Conference on Multimedia

and Ubiquitous Engineering (MUE 2009).

5. Khandaker Abir Rahman, Md S. Hossain, Md. A. Bhuyian, Tao Zhang, Md Hasanuzzaman, and H. Ueno.

Person to Camera Distance Measurement Based on Eye-Distance. In Proc. of International Conference on

Multimedia and Ubiquitous Engineering (MUE 2009).

Journal Papers Under Review

1. Md S. Hossain, Kiran S. Balagani, and Vir V. Phoha. Symmetric Rejection and Some Design Issues in Multi-

stage Biometric Verification. In IEEE Transactions on Information Forensics and Security (TIFS). [Under

Review].

2. Md S. Hossain, Kiran S. Balagani, and Vir V. Phoha. On Finding Optimal Reject Region in Multi-stage

Biometric Verification. In IEEE Transactions on Information Forensics and Security (TIFS). [Revise and

Resubmit].

Contact this candidate