Md. Rokonuzzaman Reza

Md. Rokonuzzaman Reza

Lecturer, CSE, IUS

Contact:
Phone: +8801521255793, +8801770259980
Mail id: rokonuzzamanreza@ius.edu.bd

I graduated from MIST and majored in Computer Science and Engineering (CSE). During my undergraduate program, I was actively involved in extra-curricular and research activities. My research interest is Machine Learning (ML) and Human-Computer Interaction (HCI).

Educational Qualifications:

Job Experience:

Publications:

1. Developing a Machine Learning Based Support System for Mitigating the Suppression Against Women and Children
   Abstract: 
   Violence against women and children has emerged as a significant and growing concern worldwide. To avoid violence, various machine learning (ML) approaches could be used to estimate future violence. The main motive of this study is to provide a central platform for victims, store victim data in a database. In this research, we propose a system that is a web-based tool that stores data on violence against women and children in a database and generates crime forecast results by evaluating the collected data using machine learning techniques. The victim can also get proper information about their rights from this web application. A statistical analysis was carried out on certain datasets and few machine learning model were implemented and the best performed model was decided based on some performance measurement metrics where XG Boost (XB) performed well among others (R-squared test 0.99). Ultimately the XB model has been utilized to generate the forecasting crime report, thereby reducing the level of crime. Government and other law enforcement agencies can predict the future consequences of violence from the system and help victims to get proper justice and settlement. This web application is a support system that may greatly assist women in many parts of their daily lives while also resuming violence against women and children.
   Details - (link) 
   
   
2. Thermique: An Integrated AI-Based Temperature Sensing and Management System to Hold Back COVID-19 Contamination
   Abstract: 
   In the advent of a global pandemic, the necessity for early COVID19 suspect detection and quarantine is of paramount importance. Medical research indicates that a high fever provides a general litmus of whether or not a person is infected with Coronavirus. Among several available solutions, thermal imaging has proven to be a better contactless screening procedure. It enables fast and easy detection of fever from a reasonable distance. In this research, a solution named Thermique is proposed. It is a cheap, easy to massproduce, and automated AI-enabled thermal screening platform that combines facial detection, instant contactless temperature scanning, and RFID logging, while also providing an integrated defense against the spread of COVID-19 in a particular facility. Consisting of only off-the-shelf electronic components, this solution can be implemented with a significantly minimized cost, compared to its similar-function providing alternatives available on the market. To design and implement Thermique, a system architecture was developed for the platform, the details of which are highlighted within this paper. After the development of the prototype, several analytical evaluations of the system have been conducted, including the system’s performance, and overall usability.
   Details - (link) 
   
   
3. Neurophysiological Feature-Based Stress Classification using Unsupervised Machine Learning Technique
   Abstract:
   Mental stress is the primary concern of increasing mental health problems and other medical problems like strokes, heart attacks, and ulcers. Thus, identifying and classifying stress at an early age is the prime requirement to avoid such diseases. Although a number of studies focused to predict and classify stress based on neurophysiological (brain wave and heart rate) data and used the supervised machine learning technique, but a little attention has been paid to explore the performances of unsupervised learning techniques in stress prediction. In this article, an unsupervised machine learning approach is proposed to classify mental stress into three categories: acute (low stress), episodic acute (moderate stress), and severe (high stress). The K-means clustering algorithm was used in the proposed methodology to create three different clusters, which depicts the aforementioned stress levels. The goodness of the clustering technique was evaluated by Silhouette Coefficient, and a standard fitness score of 0.76 was achieved.
   Details - (link) 
   
   
4. Towards Designing Intuitive Mobile UIs Considering Tapping Behaviour of Elderly Users
   Abstract:
   A mobile user interface (UI) is a graphical and usually touch-sensitive display on a mobile device that allows the user to interact with the device’s apps, features, contents, and functions. Since people of the elderly age group were not as exposed to technology as much as the people of the present generation, they face hurdles while using mobile apps. Furthermore, designers also face difficulties while designing user interfaces for elderly users. It is difficult for them to determine whether a designed UI component will be perceived by the elderly users as per its purpose. An elderly user may perceive a tappable UI component as not tappable and vice versa. Therefore, the objective of this research is to propose a conceptual framework for developing an efficient system to evaluate whether an UI is usable to the elderly people or not considering the tappability of the its (UI) components. As outcomes, a deep learning-based conceptual framework for such a system is proposed based on the identified user-requirements through semi-structured interviews. An initial UI prototype of the system is also developed and evaluated by the real end-users. It is expected that the conceptual framework will be able to pave the way for developing a system to help the elderly user by increasing the usability of the UIs and to aid the designers in designing intuitive UIs considering the limitations of the elderly user.
   Details - (link) 

Training:

1. CompTIA+ from New Horizons Computer Learning Centers
2. Research Methodology in MIST
3. Capstone: Retrieving, Processing, and Visualizing Data with Python from Coursera
4. Problem Solving (Basic) from HackerRank
5. Python for Data Science from ASCEND and KIRON Ltd. 

Extracurricular Activities:

1. Vice President - MIST Computer Club (MCC) | July 2021 – May 2022

Major Responsibilities:

• Planned, developed, and implemented the events.
• Coordinated with different stakeholders, executives, and general members Organized and conducted online, and offline courses (competitive programming, web development, game development, etc.)
• Organized NCPC (National Collegiate Programming Contest) 2020 at MIST

2. First Runner-Up Soccer Bot Challenge of Robo Carnival, BUET, 2019
3. Second Runner-Up Digital Project Showcasing of Tri-Robo-Cup MIST, 2020
4. Best Ambassador IEEE CS BDC Winter Symposium, 2020