Applied Mathematics
EXTERNAL PROFILES
Assistant Professor
Forhad Mahmud
I am Forhad Mahmud, an Assistant Professor of Applied Mathematics at Noakhali Science and Technology University, Bangladesh. My research explores nonlinear differential equations, mathematical modeling, and the integration of artificial intelligence with applied mathematical analysis.
Applied Mathematics
BIOGRAPHY
I am Forhad Mahmud, an Assistant Professor in the Department of Applied Mathematics at Noakhali Science and Technology University (NSTU), Bangladesh. I completed both my B.Sc. and M.Sc. (with thesis) in Applied Mathematics from the University of Rajshahi, where I ranked third in my undergraduate program and second in my graduate studies. My master’s thesis focused on obtaining exact traveling wave solutions of nonlinear evolution equations using the generalized Kudryashov method. My research interests center on mathematical modeling and analysis, nonlinear differential equations, and the integration of artificial intelligence and machine learning with applied mathematics. I have published several research articles in reputed international journals such as Partial Differential Equations in Applied Mathematics, Results in Physics, and Optik. These works include studies on soliton dynamics, Fokas–Lenells models, and analytical approaches to epidemic modeling and vaccination strategies. At NSTU, I teach a variety of undergraduate courses including Calculus, Differential Equations, Numerical Analysis, and Mathematical Modeling. I also supervise student projects that connect mathematics with data science and real-world applications, such as tuberculosis modeling and rent prediction using machine learning. In addition to my academic duties, I have served as an Assistant Provost, contributing to university administration and student welfare. My long-term goal is to strengthen interdisciplinary research in applied mathematics and data-driven modeling.
RESEARCH INTERESTS
2016 - 2017
M. Sc (Thesis)
Applied Mathematics
University of Rajshahi
Thesis: Thesis: Exact traveling wave to solve solutions for some nonlinear evolution equations through generalized Kudryashov method. I was placed second position in my class with GPA 3.93.
2011 - 2016
B. Sc (Honours)
Applied Mathematics
University of Rajshahi
Last updated on 2025-07-31 17:55:27
No Job information...
No Project information...
AWARDS AND ACHIEVEMENTS
No award information...
Insights into the Ebola epidemic model and vaccination strategies: An analytical approximate approach
Authors: Islam, Md Rezaul and Mahmud, Forhad and Akbar, M AliDynamical behavior of solitons of the perturbed nonlinear Schrödinger equation and microtubules through the generalized Kudryashov scheme
Authors: Akbar, M Ali and Wazwaz, Abdul-Majid and Mahmud, Forhad and Baleanu, Dumitru and Roy, Ripan and Barman, Hemonta Kumar and Mahmoud, W and Al Sharif, Mohammed A and Osman, MSHarmonizing wave solutions to the Fokas-Lenells model through the generalized Kudryashov method
Authors: Barman, Hemonta Kumar and Roy, Ripan and Mahmud, Forhad and Akbar, M Ali and Osman, MSThe generalized Kudryashov method to obtain exact traveling wave solutions of the PHI-four equation and the Fisher equation
Authors: Mahmud, Forhad and Samsuzzoha, Md and Akbar, M AliNo Data Found
No Data Found
No Data Found
No Courses Found....
No Course Materials Found....
Mohammad Zakaria Hasan
Graduated
Thesis Title: Hybrid Neuro-evolutionary Algorithm with Numerical Approach for Dynamical Analyses of Ebola Epidemic Model
Overview: This thesis introduces and employs a new hybrid neuro-evolutionary solver that combines FF-ANN with a mixed GA-SQP to solve and predict high fidelity solutions for a Susceptible–Exposed–Infectious–Recovered (SEIR) epidemic modelling fitted explicitly for the Ebola virus model dynamics. We first solve this system of nonlinear ordinary differential equations (ODEs) of SEIR model through the classical fourth-order Runge–Kutta (RK4) numerical scheme to obtain the precise forms of an epidemic. Then, an FF-ANN is developed to solve the compartmental populations of SEIR at different time steps. Network weights and biases are globally optimised using a global search genetic algorithm (GA) with a tight fitness tolerance to guarantee a strong initial exploration of the solution space. Then, a sequential quadratic programming (SQP) strategy is used for local refinement by optimising an error-based objective function. Explicit expression of the FF-ANN architecture with log-sigmoid activation functions, algorithmic sequence, and pseudocode of GA-SQP is also given. The solver shows fast convergence and low computing overhead which is very suitable for real-time epidemic prediction. The statistical methods outcome shows the convergence and accuracy for the FF-ANN-GA-SQP method.
Saleha Begum and Mohammad Zakaria Hasan
Graduated
Thesis Title: Comparative Analysis of Tuberculosis Transmission Models: Numerical vs. Neural Network Approaches
Overview: This work presents a novel method of simulating the dynamics of infectious diseases by fusing sophisticated deep learning with conventional numerical methods. The methodology establishes benchmark solutions for SIR, SEIR and SLITR models using the fourth-order Runge-Kutta (RK4) method. After that, datasets obtained from these models are used to train Feed Forward Neural Network (FNN), which is optimized using Keras Tuner to capture complex patterns and dynamics. Results show that the FNN is good at simulating the dynamics of infectious diseases, as indicated by low Mean Squared Error (MSE) and Mean absolute Error (MAE) values The FNNs showed significant ability to interpret complex dynamics, demonstrating proficiency in replicating infectious disease distribution patterns. The SIR model produced outstanding results, with the FNN achieving low MAE and MSE values across both training and validation sets. Similarly, the SEIR model demonstrated good accuracy, whereas the FNN for the SLITR model performed admirably. Discussion underscores the FNN's significance in enhancing our understanding of infectious disease spread, facilitating timely interventions, and optimizing resource allocation. Graphical representations demonstrated the agreement between FNN predictions and RK4 solutions, highlighting the FNNs' efficacy in simulating infectious disease dynamics. The FNN's ability to replicate RK4 solutions holds practical implications for evidence-based decision-making in public health policy planning. Consistently low MAE and MSE values across diverse models underscore the robustness of FNNs, positioning them as promising tools for predictive modelling and decision support in infectious disease dynamics.
Md. Rayhan
SI, Police
Thesis Title: House Rent Prediction of Maijdee Town-Noakhali, Bangladesh, a Study of Supervised Machine Learning
Overview: In this article, we proposed a machine learning-based approach to predict house rent prices. We use a dataset of real estate listings containing various features such as main-road, area, number of rooms, gas-line and other advantage to train our model. We first pre-process the data to remove missing values, handle outliers, and convert categorical variables to numerical ones. We then explore and analyze the data using various visualization techniques. We use multiple linear regression, random forest regression models and decision tree to predict house rents based on the available features. We evaluate the performance of the models using various metrics such as mean squared error, root mean squared error, and R-squared. Our results show that the linear regression model outperforms the random forest regression model and decision tree in terms of prediction accuracy. Overall, this article demonstrates the effectiveness of machine learning techniques in predicting house rent prices. The proposed approach can help landowners and renters make informed decisions on pricing and rental contracts, as well as assist real estate, agents and property managers in setting the right rent prices for their properties.
- Institutional Email: forhad.amath@nstu.edu.bd
- Personal Email: forhadmithu@gmail.com
- Mobile number: 01750660144
- Emergency Contact: 01781392246
- PABX: N/A
- Website: N/A
SOCIAL PROFILES
Department
Applied Mathematics
Noakhali Science and Technology University