Research

My broad research interests are in Deep Learning and Autonomous Systems. Some of the areas I wish to work are,

• Data analytics and deep learning applications in real-world problem-solving
• AI and machine learning in agricultural technology, focusing on crop yield prediction and resource optimization
• Development of AI-driven models for autonomous systems, enhancing automation and efficiency
• Cybersecurity, with an emphasis on integrating security measures in AI and autonomous systems to address safety and privacy

Works in Progress

Journals

Comprehensive dataset of annotated rice panicle image from Bangladesh

Authors: Mohammad Rifat Ahmmad Rashid, Md Shafayat Hossain, MD Fahim , Md Shajibul Islam, Rizvee Hassan Prito, Md Shahadat Anik Sheikh, Md Sawkat Ali, Mahamudul Hasan, Maheen Islam

Description: Bangladesh’s economy is primarily driven by the agriculture sector. Rice is one of the staple food of Bangladesh. The count of panicles per unit area serves as a widely used indicator for estimating rice yield, facilitating breeding efforts, and conducting phenotypic analysis. By calculating the number of panicles within a given area, researchers and farmers can assess crop density, plant health, and prospective production. The conventional method of estimating rice yields in Bangladesh is time-consuming, inaccurate, and inefficient. To address the challenge of detecting rice panicles, this article provides a comprehensive dataset of annotated rice panicle images from Bangladesh. Data collection was done by a drone equipped with a 4 K resolution camera, and it took place on April 25, 2023, in Bonkhoria Gazipur, Bangladesh. During the day, the drone captured the rice field from various heights and perspectives …

Journal: Data in Brief
Publisher: Elsevier
Publication date: 2023/12/1
Link: Science Direct

Chaotic opposition-based plant propagation algorithm for engineering problem

Authors: Alfe Suny, Maimuna Akter Liza, MD Fahim , Ahmed Wasif Reza, Nazmul Siddique.

Description: The Plant Propagation Algorithm (PPA), often exemplified by the Strawberry Algorithm, has demonstrated its effectiveness in solving lower-dimensional optimization problems as a neighborhood search algorithm. While multiple enhancements have been introduced to boost its performance, PPA remains a population-based metaheuristic algorithm. A key element of PPA involves balancing exploration and exploitation, akin to a strawberry plant seeking the best survival strategy. This paper delves into the integration of chaotic numbers and opposition theory in PPA, focusing on how these additions impact its efficiency. The primary research questions revolve around enhancing PPA’s performance and reducing its search space to expedite the algorithm, ultimately leading to faster overall results. Experiments were carried out on three challenging engineering problems: the Pressure Vessel Optimization, the Spring Design Optimization, and the Welded Beam Problem, to fully assess the effectiveness of the improved PPA. The effectiveness of the original PPA, the Chaotic Opposition-Based PPA (COPPA), and several other metaheuristic algorithms were examined in each of these problems. In terms of efficiency and solution quality, the findings consistently demonstrate that COPPA performs better than the traditional PPA and other algorithms. The results indicate that using chaotic-based oppositional processes decreases the search space and enhances performance, resulting in faster and more resource-efficient optimization. The investigation reveals that incorporating chaotic-based oppositional PPA yields improved results while conserving resources and accelerating execution.

Journal: Applied Intelligence Publisher: Springer US
Publication date: 2025/02/04
Link: Springer

Drone-based dataset of annotated Sunflower images from Bangladesh

Authors: Md Shafayat Hossain, Mohammad Rifat Ahmmad Rashid, MD Fahim , Md Sawkat Ali, Maheen Islam, Mohammad Manzurul Islam, Md Hasanul Ferdaus, Nishat Tasnim Niloy.

Description: Accurate and automated detection of sunflower plants, along with assessments of their growth stages and health conditions, is crucial for enabling precision agriculture and improving crop management. In this work, we present a drone-based dataset of annotated sunflower images, derived from high-resolution videos captured at two distinct locations in Bangladesh. The original dataset comprises 1,649 images extracted from drone footage of the BARI Surjomukhi-3 variety under various orientations, health conditions, and weather scenarios. After meticulous annotation using the Roboflow platform and augmentation with seven distinct techniques, the dataset expanded to 4,286 images in Pascal VOC format. Detailed metadata—including geospatial coordinates, timestamped acquisition conditions, and camera settings—accompanies the dataset to support reproducibility and model generalization. By offering a comprehensive suite of annotated and augmented images, this dataset provides a valuable resource for developing and refining computer vision models geared toward sunflower detection, maturity evaluation, and yield prediction, ultimately advancing sustainable farming practices and decision-making tools in agricultural research.

Journal: Data in Brief Publisher: Elsevier
Publication date: 2025/2/21 Link: Science Direct

Conferences

Review of Machine Learning-Based Distributed Denial-of-Service (DDoS) Detection and Prevention

Authors: Fahim, M.D., Shafayat Hossain, M., Rosni, T.R., Khadija, S.R., Hasan, M.
Publisher Name: Springer, Singapore
Publication date: 23 January 2025
Link: Springer