arXiv subjects

Saiful Islam

Publications and source records attributed to Saiful Islam.

15 recordsLinked to original sources

arXiv2026

An Image Dataset of Common Skin Diseases of Bangladesh and Benchmarking Performance with Machine Learning Models

Skin diseases are a major public health concern worldwide, and their detection is often challenging without access to dermatological expertise. In countries like Bangladesh, which is highly populated, the number of qualified skin specialists and diagnostic instruments is insufficient to meet the demand. Due to the lack of proper detection and treatment of skin diseases, that may lead to severe health consequences including death. Common properties of skin diseases are, changing the color, texture, and pattern of skin and in this era of artificial intelligence and machine learning, we are able to detect skin diseases by using image processing and computer vision techniques. In response to this challenge, we develop a publicly available dataset focused on common skin disease detection using machine learning techniques. We focus on five prevalent skin diseases in Bangladesh: Contact Dermatitis, Vitiligo, Eczema, Scabies, and Tinea Ringworm. The dataset consists of 1612 images (of which, 250 are distinct while others are augmented), collected directly from patients at the outpatient department of Faridpur Medical College, Faridpur, Bangladesh. The data comprises of 302, 381, 301, 316, and 312 images of Dermatitis, Eczema, Scabies, Tinea Ringworm, and Vitiligo, respectively. Although the data are collected regionally, the selected diseases are common across many countries especially in South Asia, making the dataset potentially valuable for global applications in machine learning-based dermatology. We also apply several machine learning and deep learning models on the dataset and report classification performance. We expect that this research would garner attention from machine learning and deep learning researchers and practitioners working in the field of automated disease diagnosis.

cs.CV↗

arXiv2026

EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery

Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical world. However, spatial reasoning on Earth imagery has lagged behind, as it uniquely involves grounding objects in georeferenced images and quantitatively reasoning about distances, directions, and topological relations using both visual cues and vector geometry coordinates (e.g., 2D bounding boxes, polylines, and polygons). Existing benchmarks for Earth imagery primarily focus on 2D spatial grounding, image captioning, and coarse spatial relations (e.g., simple directional or proximity cues). They lack support for quantitative direction and distance reasoning, systematic topological relations, and complex object geometries beyond bounding boxes. To fill this gap, we propose \textbf{EarthSpatialBench}, a comprehensive benchmark for evaluating spatial reasoning in MLLMs on Earth imagery. The benchmark contains over 325K question-answer pairs spanning: (1) qualitative and quantitative reasoning about spatial distance and direction; (2) systematic topological relations; (3) single-object queries, object-pair queries, and compositional aggregate group queries; and (4) object references expressed via textual descriptions, visual overlays, and explicit geometry coordinates, including 2D bounding boxes, polylines, and polygons. We conducted extensive experiments on both open-source and proprietary models to identify limitations in the spatial reasoning of MLLMs.

cs.CV↗

arXiv2026

Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting

We introduce Green-NAS, a multi-objective NAS (neural architecture search) framework designed for low-resource environments using weather forecasting as a case study. By adhering to 'Green AI' principles, the framework explicitly minimizes computational energy costs and carbon footprints, prioritizing sustainable deployment over raw computational scale. The Green-NAS architecture search method is optimized for both model accuracy and efficiency to find lightweight models with high accuracy and very few model parameters; this is accomplished through an optimization process that simultaneously optimizes multiple objectives. Our best-performing model, Green-NAS-A, achieved an RMSE of 0.0988 (i.e., within 1.4% of our manually tuned baseline) using only 153k model parameters, which is 239 times fewer than other globally applied weather forecasting models, such as GraphCast. In addition, we also describe how the use of transfer learning will improve the weather forecasting accuracy by approximately 5.2%, in comparison to a naive approach of training a new model for each city, when there is limited historical weather data available for that city.

cs.LG↗

arXiv2025

I2E2S2R Rumor Spreading Model in Homogeneous Network with Hesitating and Forgetting Mechanisms

The spreading and controlling of rumors have great impacts on our society. The transmission of infectious diseases and the spreading of rumors have some common scenarios. Like cross-infection propagation of diseases, two or many kinds of rumors or information may spread at the same time. In this paper, we propose a novel I2E2S2R rumor-spreading model in a homogeneous network. The rumor-free equilibrium, as well as the basic reproduction number, have been calculated from the mean-field equations of the model. Lyapunov function and the LaSalle invariance principle are used to establish the global stability of the rumor-free equilibrium. In numerical simulations, it is perceived that a higher degree of network helps to spread rumors quickly. We have also found that making people aware can help to disappear rumors faster from the network. In addition, making people divert from the rumor to exact information can lessen the spreading of the rumor.

physics.soc-ph↗

arXiv2025

Multi-Objective Optimization Algorithms for Energy Management Systems in Microgrids: A Control Strategy Based on a PHIL System

In this research a real time power hardware in loop configuration has been implemented for an microgrid with the combination of distribution energy resources such as photovoltaic, grid tied inverter, battery, utility grid, and a diesel generator. This paper introduces an unique adaptive multi-objective optimization approach that employs weighted optimization techniques for real-time microgrid systems. The aim is to effectively balance various factors including fuel consumption, load mismatch, power quality, battery degradation, and the utilization of renewable energy sources. A real time experimental data from power hardware in loop system has been used for dynamically updating system states. The adaptive preference-based selection method are adjusted based on state of battery charging thresholds. The technique has been integrated with six technical objectives and complex constraints. This approach helps to practical microgrid decision making and optimization of dynamic energy systems. The energy management process were also able to maximize photovoltaic production where minimizing power mismatch, stabilizing battery state of charge under different condition. The research results were also compared with the baseline system without optimization techniques, and a reliable outcome was found.

eess.SY↗

arXiv2025

A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs

With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In this article, we introduce a novel multi-layered hierarchical HITL DRL algorithm that comprises three types of learning: self learning, imitation learning and transfer learning. In addition, we consider three forms of human inputs: reward, action and demonstration. Furthermore, we discuss main challenges, trade-offs and advantages of HITL in solving complex problems and how human information can be integrated in the AI solution systematically. To verify our technical results, we present a real-world unmanned aerial vehicles (UAV) problem wherein a number of enemy drones attack a restricted area. The objective is to design a scalable HITL DRL algorithm for ally drones to neutralize the enemy drones before they reach the area. To this end, we first implement our solution using an award-winning open-source HITL software called Cogment. We then demonstrate several interesting results such as (a) HITL leads to faster training and higher performance, (b) advice acts as a guiding direction for gradient methods and lowers variance, and (c) the amount of advice should neither be too large nor too small to avoid over-training and under-training. Finally, we illustrate the role of human-AI cooperation in solving two real-world complex scenarios, i.e., overloaded and decoy attacks.

cs.AI↗

arXiv2024

Energy landscape analysis based on the Ising model: Tutorial review

We review a class of energy landscape analysis method that uses the Ising model and takes multivariate time series data as input. The method allows one to capture dynamics of the data as trajectories of a ball from one basin to a different basin to yet another, constrained on the energy landscape specified by the estimated Ising model. While this energy landscape analysis has mostly been applied to functional magnetic resonance imaging (fMRI) data from the brain for historical reasons, there are emerging applications outside fMRI data and neuroscience. To inform such applications in various research fields, this review paper provides a detailed tutorial on each step of the analysis, terminologies, concepts underlying the method, and validation, as well as recent developments of extended and related methods.

cond-mat.dis-nn↗

arXiv2024

Personalized graph feature-based multi-omics data integration for cancer subtype identification

Cancer is a highly heterogeneous disease with significant variability in molecular features and clinical outcomes, making diagnosis and treatment challenging. In recent years, high-throughput omic technologies have facilitated the discovery of mechanisms underlying various cancer subtypes by providing diverse omics data, such as gene expression, DNA methylation, and miRNA expression. However, the complexity and heterogeneity of multi-omics data present significant challenges for their integration in exploring cancer subtypes. Various methods have been proposed to address these challenges. In this paper, we propose a novel and straightforward approach for identifying cancer subtypes by integrating patient-specific subnetworks features from different omics data. We construct patient-specific induced subnetwork using a random walk with restart algorithm from patient similarity networks (PSNs) and compute nine structural properties that capture essential network topology. These features are integrated across the three omic datasets to form comprehensive patient profiles. K-means clustering is then applied for cancer subtype identification. We evaluate our approach on five cancer datasets, including breast invasive carcinoma, colon adenocarcinoma, glioblastoma multiforme, kidney renal clear cell carcinoma, and lung squamous cell carcinoma, for three different omic data types. The evaluation shows that our method produces promising and effective results, demonstrating competitive or superior performance compared to existing methods and underscoring its potential for advancing personalized cancer diagnosis and treatment.

q-bio.QM↗

arXiv2024

A Structural Feature-Based Approach for Comprehensive Graph Classification

The increasing prevalence of graph-structured data across various domains has intensified greater interest in graph classification tasks. While numerous sophisticated graph learning methods have emerged, their complexity often hinders practical implementation. In this article, we address this challenge by proposing a method that constructs feature vectors based on fundamental graph structural properties. We demonstrate that these features, despite their simplicity, are powerful enough to capture the intrinsic characteristics of graphs within the same class. We explore the efficacy of our approach using three distinct machine learning methods, highlighting how our feature-based classification leverages the inherent structural similarities of graphs within the same class to achieve accurate classification. A key advantage of our approach is its simplicity, which makes it accessible and adaptable to a broad range of applications, including social network analysis, bioinformatics, and cybersecurity. Furthermore, we conduct extensive experiments to validate the performance of our method, showing that it not only reveals a competitive performance but in some cases surpasses the accuracy of more complex, state-of-the-art techniques. Our findings suggest that a focus on fundamental graph features can provide a robust and efficient alternative for graph classification, offering significant potential for both research and practical applications.

cs.LG↗

arXiv2024

Federated Learning and Differential Privacy Techniques on Multi-hospital Population-scale Electrocardiogram Data

This research paper explores ways to apply Federated Learning (FL) and Differential Privacy (DP) techniques to population-scale Electrocardiogram (ECG) data. The study learns a multi-label ECG classification model using FL and DP based on 1,565,849 ECG tracings from 7 hospitals in Alberta, Canada. The FL approach allowed collaborative model training without sharing raw data between hospitals while building robust ECG classification models for diagnosing various cardiac conditions. These accurate ECG classification models can facilitate the diagnoses while preserving patient confidentiality using FL and DP techniques. Our results show that the performance achieved using our implementation of the FL approach is comparable to that of the pooled approach, where the model is trained over the aggregating data from all hospitals. Furthermore, our findings suggest that hospitals with limited ECGs for training can benefit from adopting the FL model compared to single-site training. In addition, this study showcases the trade-off between model performance and data privacy by employing DP during model training. Our code is available at https://github.com/vikhyatt/Hospital-FL-DP.

eess.SP↗

arXiv2023

State-transition dynamics of resting-state functional magnetic resonance imaging data: Model comparison and test-to-retest analysis

Electroencephalogram (EEG) microstate analysis entails finding dynamics of quasi-stable and generally recurrent discrete states in multichannel EEG time series data and relating properties of the estimated state-transition dynamics to observables such as cognition and behavior. While microstate analysis has been widely employed to analyze EEG data, its use remains less prevalent in functional magnetic resonance imaging (fMRI) data, largely due to the slower timescale of such data. In the present study, we extend various data clustering methods used in EEG microstate analysis to resting-state fMRI data from healthy humans to extract their state-transition dynamics. We show that the quality of clustering is on par with that for various microstate analyses of EEG data. We then develop a method for examining test-retest reliability of the discrete-state transition dynamics between fMRI sessions and show that the within-participant test-retest reliability is higher than between-participant test-retest reliability for different indices of state-transition dynamics, different networks, and different data sets. This result suggests that state-transition dynamics analysis of fMRI data could discriminate between different individuals and is a promising tool for performing fingerprinting analysis of individuals.

q-bio.NC↗

arXiv2021

BRACU Mongol Tori: Next Generation Mars Exploration Rover

BRAC University (BRACU) has participated in the University Rover Challenge (URC), a robotics competition for university level students organized by the Mars Society to design and build a rover that would be of use to early explorers on Mars. BRACU has designed and developed a full functional next-generation mars rover, Mongol Tori, which can be operated in the extreme, hostile condition expected in planet Mars. Not only has Mongol Tori embedded with both autonomous and manual controlled features to functionalize, it can also capable of conducting scientific tasks to identify the characteristics of soils and weathering in the mars environment.

cs.RO↗

arXiv2021

BdSL36: A Dataset for Bangladeshi Sign Letters Recognition

Bangladeshi Sign Language (BdSL) is a commonly used medium of communication for the hearing-impaired people in Bangladesh. A real-time BdSL interpreter with no controlled lab environment has a broad social impact and an interesting avenue of research as well. Also, it is a challenging task due to the variation in different subjects (age, gender, color, etc.), complex features, and similarities of signs and clustered backgrounds. However, the existing dataset for BdSL classification task is mainly built in a lab friendly setup which limits the application of powerful deep learning technology. In this paper, we introduce a dataset named BdSL36 which incorporates background augmentation to make the dataset versatile and contains over four million images belonging to 36 categories. Besides, we annotate about 40,000 images with bounding boxes to utilize the potentiality of object detection algorithms. Furthermore, several intensive experiments are performed to establish the baseline performance of our BdSL36. Moreover, we employ beta testing of our classifiers at the user level to justify the possibilities of real-world application with this dataset. We believe our BdSL36 will expedite future research on practical sign letter classification. We make the datasets and all the pre-trained models available for further researcher.

cs.CV↗

arXiv2020

DistB-SDoIndustry: Enhancing Security in Industry 4.0 Services based on Distributed Blockchain through Software Defined Networking-IoT Enabled Architecture

The concept of Industry 4.0 is a newly emerging focus of research throughout the world. However, it has lots of challenges to control data, and it can be addressed with various technologies like Internet of Things (IoT), Big Data, Artificial Intelligence (AI), Software Defined Networking (SDN), and Blockchain (BC) for managing data securely. Further, the complexity of sensors, appliances, sensor networks connecting to the internet and the model of Industry 4.0 has created the challenge of designing systems, infrastructure and smart applications capable of continuously analyzing the data produced. Regarding these, the authors present a distributed Blockchain-based security to industry 4.0 applications with SDN-IoT enabled environment. Where the Blockchain can be capable of leading the robust, privacy and confidentiality to our desired system. In addition, the SDN-IoT incorporates the different services of industry 4.0 with more security as well as flexibility. Furthermore, the authors offer an excellent combination among the technologies like IoT, SDN and Blockchain to improve the security and privacy of Industry 4.0 services properly. Finally , the authors evaluate performance and security in a variety of ways in the presented architecture.

cs.CR↗

arXiv2019

3D human action analysis and recognition through GLAC descriptor on 2D motion and static posture images

In this paper, we present an approach for identification of actions within depth action videos. First, we process the video to get motion history images (MHIs) and static history images (SHIs) corresponding to an action video based on the use of 3D Motion Trail Model (3DMTM). We then characterize the action video by extracting the Gradient Local Auto-Correlations (GLAC) features from the SHIs and the MHIs. The two sets of features i.e., GLAC features from MHIs and GLAC features from SHIs are concatenated to obtain a representation vector for action. Finally, we perform the classification on all the action samples by using the l2-regularized Collaborative Representation Classifier (l2-CRC) to recognize different human actions in an effective way. We perform evaluation of the proposed method on three action datasets, MSR-Action3D, DHA and UTD-MHAD. Through experimental results, we observe that the proposed method performs superior to other approaches.

cs.CV↗