Shakib Khan

I am working on getting my Master's degree at Concordia University. For my thesis, I am studying Computer Vision, Graph Anomaly Detection, Graph Adversarial Attack, and Graph Neural Networks. These are exciting and changing fields that I am deeply involved in.

I did my Bachelor's from North South University. I am a passionate Machine Learning Engineer who excels at developing machine learning systems and creating new applications. Have the ability to understand the business, solve problems and describe solutions appropriately. Hands-on experience with Python, Machine Learning, Deep Learning, Computer Vision.

Having an excellent research potential and an ability to actively contribute to the research project's goal and a proven publication track record in the AI field. At NSU I work on computer vision with applications in medical imaging under the supervision of Dr. Nabeel Mohammed and also research on IOT devices under Dr. Mohammad Monirujjaman Khan supervision.

Email  /  Google Scholar  /  LinkedIn  /  Github /  Twitter  /  CV

My main focus is in the intersection of computer vision, machine learning and image processing with applications in visual perception and generation. I'm developing data-driven learning-based algorithms that enable computers to accurately and efficiently understand, model and recreate the visual world around us.

RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving
Authors : Hasib Zunair, Md Shakib Khan, A. Ben Hamza
ArXiv, 2024

RSUD20K is a new object detection dataset for road scene understanding, comprised of over 20K high-resolution images from the driving perspective on Bangladesh roads, and includes 130K bounding box annotations for 13 objects. We benchmark recent object detectors and explore Large Vision-Language models as image annotators.

Knowledge Distillation approach in Melanoma Detection
Authors : Md Shakib Khan, Kazi Nabiul Alam, Abdur Rab Dhruba, Hasib Zunair, Nabeel Mohammed
Computers in Biology and Medicine 2021

Despite the fact that neural models have been shown to be satisfactory in many disciplines, even those with complicated problem statements, the models are enormously big, with millions of parameters. This causes a barrier to these models being deployed on edge devices having low memory requirements. Knowledge Distillation (KD) is a possible solution to deal with this challenge. The concept behind KD is to compress heavy-weight models into light-weighted models with a significant tradeoff in accuracy.

Robust Graph Convolutional Networks Against Adversarial Attacks

Authors : Md Shakib Khan, Abdessamad Ben Hamza, Amr Youssef

Our research shows how 'Deep Learning' techniques are used in 'Sentiment Analysis' tasks. Basic NLP based tools are implemented here to understand the sentiment in 3 possible polarities like Positive, Negative, Neutral and our findings showed the 33.96% of people are positive, 17.55% people are negative and 48.49% people are neutral till the month July of 20201 in response of the vaccination procedure going all across the globe.

Deep Learning based Sentiment Analysis of COVID-19 Vaccination Responses from Twitter data

Authors : Kazi Nabiul Alam, Md Shakib Khan, Abdur Rab Dhruba, Mohammad Monirujjaman Khan

Our research shows how 'Deep Learning' techniques are used in 'Sentiment Analysis' tasks. Basic NLP based tools are implemented here to understand the sentiment in 3 possible polarities like Positive, Negative, Neutral and our findings showed the 33.96% of people are positive, 17.55% people are negative and 48.49% people are neutral till the month July of 20201 in response of the vaccination procedure going all across the globe.

IoT-Based Water Quality Assessment System for Industrial Waste WaterHealthcare Perspective

Authors: Abdur Rab Dhruba, Kazi Nabiul Alam, Md Shakib Khan, Sananda Saha, Mohammad Monirujjaman Khan

In this research, we developed an Internet of Things (IoT)-based real-time water quality monitoring system, integrated with a mobile application. The proposed system in this research measures some of the most important indexes of water, including the potential of hydrogen (pH), total dissolved solids (TDS), and turbidity, and temperature of water. The proposed system results will be very helpful in saving the environment, and thus, improving the health of living creatures on Earth.

Development of an IoT-Based Sleep Apnea Monitoring System for Healthcare Applications

Authors: Abdur Rab Dhruba, Kazi Nabiul Alam, Md Shakib Khan, Mohammad Monirujjaman Khan

This research shows how IoT devices can monitor sleep apnea. To implement the system, we used a basic microcontroller and some of the major health-related sensors. The mobile application has been created with a very simple app developing web application. After monitoring five persons the system gives quite satisfactory results for making decisions about sleep apnea.

Template taken from here.