Dr. Mohammad Shahidul Islam
Dr. Mohammad Shahidul Islam Associate Professor, Institute of Information Technology

PROFILE


SHORT BIOGRAPHY

Dr. Mohammad Shahidul Islam

Received his Ph.D. in Computer Science & Information Systems from National Institute of Development Administration (NIDA), Bangkok, Thailand, B.Tech.  in Computer Science and Technology from Indian Institute of Technology-Roorkee (IITR), Uttar Pradesh, India in 2002, M.Sc. in Mobile Computing and Communication from University of Greenwich, London, U.K in 2008. 



Journals : 

 

  1. “A Generic Approach for Weight Assignment to the Decision Making Parameters” International Journal of Advanced Computer Science and Applications(IJACSA), 10(11), 2019. http://dx.doi.org/10.14569/IJACSA.2019.0101170
  2. "Techno-financial analysis and design of on-board intelligent-assisting system for a hybrid solar–DEG-powered boat”, Int J Energy Environ Eng,  7: 361. 

  3.  “Learning To Classify Diabetes Disease Using Data Mining Techniques”, International Journal of Computer Science and Information Security 15 (1), 34

  4.  "Boosting Facial Expression Recognition in a Noisy Environment Using LDSP-Local Distinctive Star Pattern", International Journal of Computer Science Issues (IJCSI); Mahebourg Vol. 11, Iss. 4,  (Jul 2014): 45-51.

  5. “Gender Classification Using Gradient Direction Pattern", Science .International , 25(4), pp-797-799

  6. “Facial Expression Recognition Using Local Arc Pattern ", Trends in Applied Sciences Research, 12(4), PP-126-130

  7. “Gradient Direction Pattern: A Gray-Scale Invariant Uniform Local Feature Representation for Facial Expression Recognition", The Journal of Applied Sciences, 13(6), pp 837-845

  8. “Robust Gender Classification Using LMnP-Local Minima Pattern", International Journal of Scientific & Engineering Research, 4(11), pp-713-716

  9. “Uniform Local Active Forces: A Novel Gray-Scale Invariant Local Feature Representation for Facial Expression Recognition", International Journal of Computer Science and Communication Engineering, 2(3), pp-8-18

  10. “Local Gray Code Pattern (LGCP): A Robust Feature Descriptor for Facial Expression Recognition", International Journal of Science and Research, 2(8), pp-413 – 419

  11. “Local Gradient Pattern - A Novel Feature Representation for Facial Expression Recognition", Journal of Artificial Intelligence & Data Mining , 2(1), pp-33-38

  12. “A Novel Feature Extraction Technique for Facial Expression Recognition”, International Journal of Computer Science Issues, 10(1), pp- 9-14

  13. "Analytical Analysis of Multimedia Mobile Networks" , Journal of Telecommunications, 8(1), pp- 16-20

  14. “Analyze the Performance of Cellular IP Networks”, Journal of Telecommunications, 5(2), pp- 11-17

  15. “Traffic Analysis of Wireless IP Network”, The Journal of Telecommunications,5(1), pp- 33-37, UK

  16. “The Future Aspects of Wireless Electricity Transmission” Journal of Telecommunications, 4(2), pp-19-21




Conferences : 

  1. “Boosting Facial Expression Recognition Using LDGP - Local Distinctive Gradient Pattern", Accepted in International Conference on Electrical Engineering and Information & Communication Technology (iCEEiCT 2014)

RESEARCH INTEREST
Artificial Intelligence, Robotics, Machine Learning, Pattern recognition, Renewable Energy. (All must have impact on better Agriculture & Environment in Bangladesh only)

Journal Paper

Dr. Mohammad Shahidul Islam

Md Zahid Hasan, Shakhawat Hossain, Mohammad Shorif Uddin and Mohammad Shahidul Islam, “A Generic Approach for Weight Assignment to the Decision Making Parameters” International Journal of Advanced Computer Science and Applications(IJACSA), 10(11), 2019. http://dx.doi.org/10.14569/IJACSA.2019.0101170

 

Abstract:

Weight assignment to the decision parameters is a crucial factor in the decision-making process. Any imprecision in weight assignment to the decision attributes may lead the whole decision-making process useless which ultimately mislead the decision-makers to find an optimal solution. Therefore, attributes’ weight allocation process should be flawless and rational, and should not be just assigning some random values to the attributes without a proper analysis of the attributes’ impact on the decision-making process. Unfortunately, there is no sophisticated mathematical framework for analyzing the attribute’s impact on the decision-making process and thus the weight allocation task is accomplished based on some human sensing factors. To fill this gap, present paper proposes a weight assignment framework that analyzes the impact of an attribute on the decision-making process and based on that, each attribute is evaluated with a justified numerical value. The proposed framework analyzes historical data to assess the importance of an attribute and organizes the decision problems in a hierarchical structure and uses different mathematical formulas to explicit weights at different levels. Weights of mid and higherlevel attributes are calculated based on the weights of root-level attributes. The proposed methodology has been validated with diverse data. In addition, the paper presents some potential applications of the proposed weight allocation scheme.


Conference Paper

Dr. Mohammad Shahidul Islam

Abdur Rahman, Shanto Roy, M Shamim Kaiser, and Md. Shahidul Islam, “A lightweightmulti-tier S-MQTT framework to secure communication between low-end IoT de-vices“, International Conference on Networking, Systems and Security (NSysS - 2018).

 

Abstract:

The evolution and expansion of networking technologies have managed to create large scale connectivity among versatile devices and applications that led to the jargon internet of things (IoT). IoT has evolved due to the convergence of wireless sensor networks (WSN) and internet technologies with a view to approaching towards smart city prospects. In IoT, for maintaining device to device communication, HTTP protocol has been used for remote monitoring and analysis of data from large number of sensing elements but it consumes more power, have comparatively lesser efficiency of transmission and cannot utilize system bandwidth efficiently as well. Thus the protocols MQTT (Message Queuing Telemetry Transport), AMQP and CoAP are quite capable of handling wireless sensor traffic under very low bandwidth and constrained network conditions. Security is also another major concern as IoT applications collect private data and allow access to various control functions over the internet. Therefore, in this paper, we discuss a detailed analysis of data & devices security issues and present an enhanced security model with a view to improving the security issues. We propose a secure version of MQTT protocol modifying and enhancing the existing MQTT protocol based on Key/Cipher text Policy Attribute Based Encryption(KP/CP-ABE) using lightweight Elliptic Curve cryptosystem. We also introduced a multi-tier authentication system for secure communication and an extra security layer to prevent the data theft.
Boosting Facial Expression Recognition Using LDGP - Local Distinctive Gradient Pattern

Appearance based local feature methods are widely used for facial expression recognition because of their simplicity and high accuracy rates of recognition. However, the achieved accuracy rates and running time yet need to be improved. A new appearance based local feature method, called Local Distinctive Gradient Pattern (LDGP) is proposed in this paper. It derives two 4-bit local binary patterns from two different layers for a pixel by comparing the gray color intensity value of the pixel with its neighboring pixels in four distinct directions. Since each face image is divided into equal sized blocks, two histograms for the two 4-bit LDGP patterns of all pixels in each block can be constructed. The histograms of all blocks are then concatenated to build the feature vector for the given image. To evaluate the effectiveness of the proposed descriptor, experiments were conducted on the popular JAFFE dataset using Support Vector Machine (SVM) as the classifier. Extensive experimental results with seven prototype expressions show that proposed LDGP descriptor is superior to other appearance-based feature descriptors in terms of accuracy rates of recognition.


Academic Info

Institute: NIDA
Period: 2013

PhD

Institute: University of Greenwich
Period: 2008

Masters

Institute: Indian Institute of Technology
Period: Four Yeas B.Tech, 2002

CST-Computer Science & Technology (Engineering)

Institute: Notredame College
Period: 1994-1996

Secondary School

Institute: Motijheel Ideal School & College
Period: 1991-1994

Primary School

Institute: Comilla Zilla School
Period: 1988-1990

Primary School

Institute: Barisal Udayan School
Period: 1983-1987

Primary School

Contact

Dr. Mohammad Shahidul Islam

Associate Professor
Institute of Information Technology
Jahangirnagar University, Savar, Dhaka-1342, Bangladesh.
Cell Phone: 8801714028777
Work Phone: +88 02 7791045 51 EXT: 1239
Email: sislam@juniv.edu , suva93@gmail.com