arXiv subjects

A. B. M. Alim Al Islam

Publications and source records attributed to A. B. M. Alim Al Islam.

At least 19 recordsLinked to original sources

arXiv2026

From Mind Mapping to Dream Interpretation: Understanding Muslim Users' Engagement with GenAI Tools in Religious Context

Generative Artificial Intelligence (GenAI) tools are increasingly integrated into everyday life, including sensitive domains such as religion. Prior works examined alignment with religious values and discussed the potential risks. However, to gain empirical insights into the adoption of these tools in users' religious lives, in this study, we conducted an online survey with 178 Muslim participants in Bangladesh and collected 726 prompts on religious use cases, along with open-ended responses about using these tools in religious contexts. Using reflexive thematic analysis, we identify three key roles these tools play in users' religious lives: (1) religious assistants, (2) perceived religious scholars, and (3) faith counselors. However, participants expressed concerns about misguidance, overreliance, and violations of Islamic tradition, and reported adopting protective strategies to avoid these pitfalls. Based on these, we propose a set of design guidelines for faith-sensitive GenAI systems that would preserve religious boundaries while supporting religious practices.

cs.HC↗

arXiv2026

CBRS: Cognitive Blood Request System with Bilingual Dataset and Dual-Layer Filtering for Multi-Platform Social Streams

Urgent blood donation seeking posts and messages on social media often go unnoticed due to the overwhelming volume of daily communications. Traditional app-based systems, reliant on manual input, struggle to reach users in low-resource settings, delaying critical responses. To address this, we introduce the Cognitive Blood Request System (CBRS), a multi-platform framework that efficiently filters and parses blood donation requests from social media streams using a cost-efficient dual-layered architecture. To do so, we curate a novel dataset of 11K parsed blood donation request messages in Bengali, English, and transliterated Bengali, capturing the linguistic diversity of real social media communications. The inclusion of adversarial negatives further enhances the robustness of our model. CBRS achieves an impressive 99% accuracy and precision in filtering, surpassing benchmark methods. In the parsing task, our LoRA finetuned Llama-3.2-3B model achieves 92% zero-shot accuracy, surpassing the base model by 41.54% and exceeding the few-shot performance of GPT-4o-mini, Gemini-2.0-Flash, and other LLMs, while resulting in a 35X reduction in input token usage. This work lays a robust foundation for scalable, inclusive information extraction in time-sensitive, object-focused tasks. Our code, dataset, and trained models are publicly available at [https://github.com/aaniksahaa/CBRS](https://github.com/aaniksahaa/CBRS).

cs.CL↗

arXiv2026

Evaluating Web Accessibility and Usability in Bangladesh: A Comparative Analysis of Government and Non-Government Websites

Ensuring digital accessibility is essential for inclusive access to online services. However, many government and non-government websites that provide critical services - such as education, healthcare, and public administration - continue to exhibit significant accessibility and usability barriers. This study evaluates the accessibility of Bangladeshi government and non-government websites under WCAG~2.2 by combining automated accessibility assessments with user-reported feedback. A total of 212 websites were analyzed using multiple automated tools, complemented by a survey of 103 users to capture real-world usability, accessibility, and security experiences. The results reveal substantial disparities between government and non-government websites, highlighting persistent issues related to navigation complexity, interaction cost, visual readability, accessibility feature adoption, and authentication mechanisms. While non-government websites generally demonstrate better usability and functional performance, accessibility support remains inconsistent across both categories. The findings underscore the need for regular accessibility audits, user-centered design practices, and policy-driven interventions to improve digital inclusivity and ensure equitable access to online services for diverse user populations.

cs.HC↗

arXiv2025

CollaClassroom: An AI-Augmented Collaborative Learning Platform with LLM Support in the Context of Bangladeshi University Students

CollaClassroom is an AI-enhanced platform that embeds large language models (LLMs) into both individual and group study panels to support real-time collaboration. We evaluate CollaClassroom with Bangladeshi university students (N = 12) through a small-group study session and a pre-post survey. Participants have substantial prior experience with collaborative learning and LLMs and express strong receptivity to LLM-assisted study (92% agree/strongly agree). Usability ratings are positive, including high learnability(67% "easy"), strong reliability (83% "reliable"), and low frustration (83% "not at all"). Correlational analyses show that participants who perceive the LLM as supporting equal participation also view it as a meaningful contributor to discussions (r = 0.86). Moreover, their pre-use expectations of LLM value align with post-use assessments (r = 0.61). These findings suggest that LLMs can enhance engagement and perceived learning when designed to promote equitable turn-taking and transparency across individual and shared spaces. The paper contributes an empirically grounded account of AI-mediated collaboration in a Global South higher-education context, with design implications for fairness-aware orchestration of human-AI teamwork.

cs.HC↗

arXiv2025

BanglaSTEM: A Parallel Corpus for Technical Domain Bangla-English Translation

Large language models work well for technical problem solving in English but perform poorly when the same questions are asked in Bangla. A simple solution would be to translate Bangla questions into English first and then use these models. However, existing Bangla-English translation systems struggle with technical terms. They often mistranslate specialized vocabulary, which changes the meaning of the problem and leads to wrong answers. We present BanglaSTEM, a dataset of 5,000 carefully selected Bangla-English sentence pairs from STEM fields including computer science, mathematics, physics, chemistry, and biology. We generated over 12,000 translations using language models and then used human evaluators to select the highest quality pairs that preserve technical terminology correctly. We train a T5-based translation model on BanglaSTEM and test it on two tasks: generating code and solving math problems. Our results show significant improvements in translation accuracy for technical content, making it easier for Bangla speakers to use English-focused language models effectively. Both the BanglaSTEM dataset and the trained translation model are publicly released at https://huggingface.co/reyazul/BanglaSTEM-T5.

cs.CL↗

arXiv2025

Forecasting Occupational Survivability of Rickshaw Pullers in a Changing Climate with Wearable Data

Cycle rickshaw pullers are highly vulnerable to extreme heat, yet little is known about how their physiological biomarkers respond under such conditions. This study collected real-time weather and physiological data using wearable sensors from 100 rickshaw pullers in Dhaka, Bangladesh. In addition, interviews with 12 pullers explored their knowledge, perceptions, and experiences related to climate change. We developed a Linear Gaussian Bayesian Network (LGBN) regression model to predict key physiological biomarkers based on activity, weather, and demographic features. The model achieved normalized mean absolute error values of 0.82, 0.47, 0.65, and 0.67 for skin temperature, relative cardiac cost, skin conductance response, and skin conductance level, respectively. Using projections from 18 CMIP6 climate models, we layered the LGBN on future climate forecasts to analyze survivability for current (2023-2025) and future years (2026-2100). Based on thresholds of WBGT above 31.1°C and skin temperature above 35°C, 32% of rickshaw pullers already face high heat exposure risk. By 2026-2030, this percentage may rise to 37% with average exposure lasting nearly 12 minutes, or about two-thirds of the trip duration. A thematic analysis of interviews complements these findings, showing that rickshaw pullers recognize their increasing climate vulnerability and express concern about its effects on health and occupational survivability.

cs.CY↗

arXiv2025

Affordable EEG, Actionable Insights: An Open Dataset and Evaluation Framework for Epilepsy Patient Stratification

Access to clinical multi-channel EEG remains limited in many regions worldwide. We present NEUROSKY-EPI, the first open dataset of single-channel, consumer-grade EEG for epilepsy, collected in a South Asian clinical setting along with rich contextual metadata. To explore its utility, we introduce EmbedCluster, a patient-stratification pipeline that transfers representations from EEGNet models trained on clinical data and enriches them with contextual autoencoder embeddings, followed by unsupervised clustering of patients based on EEG patterns. Results show that low-cost, single-channel data can support meaningful stratification. Beyond algorithmic performance, we emphasize human-centered concerns such as deployability in resource-constrained environments, interpretability for non-specialists, and safeguards for privacy, inclusivity, and bias. By releasing the dataset and code, we aim to catalyze interdisciplinary research across health technology, human-computer interaction, and machine learning, advancing the goal of affordable and actionable EEG-based epilepsy care.

eess.SP↗

arXiv2025

Towards Intelligent Traffic Signaling in Dhaka City Based on Vehicle Detection and Congestion Optimization

The vehicular density in urbanizing cities of developing countries such as Dhaka, Bangladesh result in a lot of traffic congestion, causing poor on-road experiences. Traffic signaling is a key component in effective traffic management for such situations, but the advancements in intelligent traffic signaling have been exclusive to developed countries with structured traffic. The non-lane-based, heterogeneous traffic of Dhaka City requires a contextual approach. This study focuses on the development of an intelligent traffic signaling system feasible in the context of developing countries such as Bangladesh. We propose a pipeline leveraging Real Time Streaming Protocol (RTSP) feeds, a low resources system Raspberry Pi 4B processing, and a state of the art YOLO-based object detection model trained on the Non-lane-based and Heterogeneous Traffic (NHT-1071) dataset to detect and classify heterogeneous traffic. A multi-objective optimization algorithm, NSGA-II, then generates optimized signal timings, minimizing waiting time while maximizing vehicle throughput. We test our implementation in a five-road intersection at Palashi, Dhaka, demonstrating the potential to significantly improve traffic management in similar situations. The developed testbed paves the way for more contextual and effective Intelligent Traffic Signaling (ITS) solutions for developing areas with complicated traffic dynamics such as Dhaka City.

cs.AR↗

arXiv2025

Adversarial Reinforcement Learning for Offensive and Defensive Agents in a Simulated Zero-Sum Network Environment

This paper presents a controlled study of adversarial reinforcement learning in network security through a custom OpenAI Gym environment that models brute-force attacks and reactive defenses on multi-port services. The environment captures realistic security trade-offs including background traffic noise, progressive exploitation mechanics, IP-based evasion tactics, honeypot traps, and multi-level rate-limiting defenses. Competing attacker and defender agents are trained using Deep Q-Networks (DQN) within a zero-sum reward framework, where successful exploits yield large terminal rewards while incremental actions incur small costs. Through systematic evaluation across multiple configurations (varying trap detection probabilities, exploitation difficulty thresholds, and training regimens), the results demonstrate that defender observability and trap effectiveness create substantial barriers to successful attacks. The experiments reveal that reward shaping and careful training scheduling are critical for learning stability in this adversarial setting. The defender consistently maintains strategic advantage across 50,000+ training episodes, with performance gains amplifying when exposed to complex defensive strategies including adaptive IP blocking and port-specific controls. Complete implementation details, reproducible hyperparameter configurations, and architectural guidelines are provided to support future research in adversarial RL for cybersecurity. The zero-sum formulation and realistic operational constraints make this environment suitable for studying autonomous defense systems, attacker-defender co-evolution, and transfer learning to real-world network security scenarios.

cs.LG↗

arXiv2024

Revealing the Self: Brainwave-Based Human Trait Identification

People exhibit unique emotional responses. In the same scenario, the emotional reactions of two individuals can be either similar or vastly different. For instance, consider one person's reaction to an invitation to smoke versus another person's response to a query about their sleep quality. The identification of these individual traits through the observation of common physical parameters opens the door to a wide range of applications, including psychological analysis, criminology, disease prediction, addiction control, and more. While there has been previous research in the fields of psychometrics, inertial sensors, computer vision, and audio analysis, this paper introduces a novel technique for identifying human traits in real time using brainwave data. To achieve this, we begin with an extensive study of brainwave data collected from 80 participants using a portable EEG headset. We also conduct a statistical analysis of the collected data utilizing box plots. Our analysis uncovers several new insights, leading us to a groundbreaking unified approach for identifying diverse human traits by leveraging machine learning techniques on EEG data. Our analysis demonstrates that this proposed solution achieves high accuracy. Moreover, we explore two deep-learning models to compare the performance of our solution. Consequently, we have developed an integrated, real-time trait identification solution using EEG data, based on the insights from our analysis. To validate our approach, we conducted a rigorous user evaluation with an additional 20 participants. The outcomes of this evaluation illustrate both high accuracy and favorable user ratings, emphasizing the robust potential of our proposed method to serve as a versatile solution for human trait identification.

cs.LG↗

arXiv2024

A Paradigm Shift in Mouza Map Vectorization: A Human-Machine Collaboration Approach

Efficient vectorization of hand-drawn cadastral maps, such as Mouza maps in Bangladesh, poses a significant challenge due to their complex structures. Current manual digitization methods are time-consuming and labor-intensive. Our study proposes a semi-automated approach to streamline the digitization process, saving both time and human resources. Our methodology focuses on separating the plot boundaries and plot identifiers and applying our digitization methodology to convert both of them into vectorized format. To accomplish full vectorization, Convolutional Neural Network (CNN) models are utilized for pre-processing and plot number detection along with our smoothing algorithms based on the diversity of vector maps. The CNN models are trained with our own labeled dataset, generated from the maps, and smoothing algorithms are introduced from the various observations of the map's vector formats. Further human intervention remains essential for precision. We have evaluated our methods on several maps and provided both quantitative and qualitative results with user study. The result demonstrates that our methodology outperforms the existing map digitization processes significantly.

cs.CV↗

arXiv2024

Uncovering local aggregated air quality index with smartphone captured images leveraging efficient deep convolutional neural network

The prevalence and mobility of smartphones make these a widely used tool for environmental health research. However, their potential for determining aggregated air quality index (AQI) based on PM2.5 concentration in specific locations remains largely unexplored in the existing literature. In this paper, we thoroughly examine the challenges associated with predicting location-specific PM2.5 concentration using images taken with smartphone cameras. The focus of our study is on Dhaka, the capital of Bangladesh, due to its significant air pollution levels and the large population exposed to it. Our research involves the development of a Deep Convolutional Neural Network (DCNN), which we train using over a thousand outdoor images taken and annotated. These photos are captured at various locations in Dhaka, and their labels are based on PM2.5 concentration data obtained from the local US consulate, calculated using the NowCast algorithm. Through supervised learning, our model establishes a correlation index during training, enhancing its ability to function as a Picture-based Predictor of PM2.5 Concentration (PPPC). This enables the algorithm to calculate an equivalent daily averaged AQI index from a smartphone image. Unlike, popular overly parameterized models, our model shows resource efficiency since it uses fewer parameters. Furthermore, test results indicate that our model outperforms popular models like ViT and INN, as well as popular CNN-based models such as VGG19, ResNet50, and MobileNetV2, in predicting location-specific PM2.5 concentration. Our dataset is the first publicly available collection that includes atmospheric images and corresponding PM2.5 measurements from Dhaka. Our codes and dataset are available at https://github.com/lepotatoguy/aqi.

cs.CV↗

arXiv2023

Sherlock in OSS: A Novel Approach of Content-Based Searching in Object Storage System

Object Storage Systems (OSS) inside a cloud promise scalability, durability, availability, and concurrency. However, open-source OSS does not have a specific approach to letting users and administrators search based on the data, which is contained inside the object storage, without involving the entire cloud infrastructure. Therefore, in this paper, we propose Sherlock, a novel Content-Based Searching (CoBS) architecture to extract additional information from images and documents. Here, we store the additional information in an Elasticsearch-enabled database, which helps us to search for our desired data based on its contents. This approach works in two sequential stages. First, the data will be uploaded to a classifier that will determine the data type and send it to the specific model for the data. Here, the images that are being uploaded are sent to our trained model for object detection, and the documents are sent for keyword extraction. Next, the extracted information is sent to Elasticsearch, which enables searching based on the contents. Because the precision of the models is so fundamental to the search's correctness, we train our models with comprehensive datasets (Microsoft COCO Dataset for multimedia data and SemEval2017 Dataset for document data). Furthermore, we put our designed architecture to the test with a real-world implementation of an open-source OSS called OpenStack Swift. We upload images into the dataset of our implementation in various segments to find out the efficacy of our proposed model in real-life Swift object storage.

cs.DC↗

arXiv2022

Shashthosheba: Dissecting Perception of Bangladeshi People towards Telemedicine Apps through the Lens of Features of the Apps

Bangladesh, a developing country with a large and dense population, has recently seen significant economic as well as technological developments. The growth of technology has resulted in a dramatic increase in the number of smartphone users in Bangladesh, and as such, mobile apps have become an increasingly important part of peoples' life, even encompassing healthcare services. However, the apps used in healthcare (telemedicine to be specific) in Bangladesh are yet to be studied from the perspective of their features as per the voices of the users as well as service providers. Therefore, in this study, we focus on the features of the telemedicine apps used in Bangladesh. First, we evaluated the present status of existing telemedicine apps in Bangladesh, as well as their benefits and drawbacks in the context of HCI. We analyzed publicly accessible reviews of several Bangladeshi telemedicine apps (N = 14) to evaluate the user impressions. Additionally, to ascertain the public opinion of these apps, we performed a survey in which the patients (N = 87) participated willingly. Our analysis of the collected opinions reveals what users experience, what they appreciate, and what they are concerned about when they use telemedicine apps. Additionally, our study demonstrates what users expect from telemedicine apps, independent of their past experience. Finally, we explore how to address the issues we discovered and how telemedicine may be used to effectively offer healthcare services throughout the country. To the best of our knowledge, this study is the first to analyze the perception of the people of Bangladesh towards telemedicine apps from the perspective of features of the apps.

cs.HC↗

arXiv2020

Let's Vibrate with Vibration: Augmenting Structural Engineering with Low-Cost Vibration Sensing

Using low-cost piezoelectric sensors to sense structural vibration exhibits great potential in augmenting structural engineering, which is yet to be explored in the literature to the best of our knowledge. Examples of such unexplored augmentation include classifying diverse structures (such as building, flyover, foot over-bridge, etc.), and relating the extent of vibration generated at different height of a structure and the associated height. Accordingly, to explore these cases, we develop a low-cost piezoelectric sensor-based vibration sensing system aiming to remotely collect real vibration data from diversified civil structures. We dig into our collected sensed data to classify five different types of structures through rigorous statistical and machine-learning-based analyses. Our analyses achieve a classification accuracy of up to 97% with an F1 score of 0.97. Nonetheless, in the rarely explored time domain, our analyses reveal a novel modality of relation between vibration generated at different heights of a structure and the associated height, which was explored in the frequency domain earlier in the literature with expensive sensors.

eess.SP↗

arXiv2020

To Lane or Not to Lane? Comparing On-Road Experiences in Developing and Developed Countries using a New Simulator "RoadBird"

Even though the traffic systems in developed countries have been analyzed with rigor and operated efficiently, the same does not generally hold for developing countries due to inadequate planning, design, and operations of their transportation systems. Because of inherent differences between internal infrastructures, the systems deployed in developed countries may not be amenable to developing ones. Besides, the traffic systems of developing countries are not well-studied in the literature to the best of our knowledge. For example, it is yet to explore how a developed country's lane-based traffic flow would perform in the context of a developing country, which generally experiences non-lane-based traffic. As such, by using our newly developed traffic simulator 'RoadBird', we investigate outcomes of both lane-based and non-lane-based traffic from the contexts of both developing and developed countries. To do so, we run simulations over real road topologies (extracted from the GIS maps of major cities such as Dhaka, Miami, and Riyadh) considering different scenarios such as lane-based or non-lane-based flows, homogeneous or heterogeneous traffic, with or without pedestrians, etc. We also incorporate different car-following and lane-changing models to mimic traffic behaviors and investigate their performances. While the lane changing dilemma remains an open research question, our experimental evidences indicate: (i) lane-based approaches will not necessarily perform better in the case of currently-adopted non-lane-based scenarios; and (ii) non-lane-based strategies may benefit system performance in lane-based scenarios while having heavy mixed traffic. Nonetheless, we reveal several new insights for on-road experiences both in developing and developed countries.

cs.OH↗

arXiv2020

Enhancing Fidelity of Quantum Cryptography using Maximally Entangled Qubits

Securing information transmission is critical today. However, with rapidly developing powerful quantum technologies, conventional cryptography techniques are becoming more prone to attacks each day. New techniques in the realm of quantum cryptography to preserve security against powerful attacks are slowly emerging. What is important though now is the fidelity of the cryptography, because security with massive processing power is not worth much if it is not correct. Focusing on this issue, we propose a method to enhance the fidelity of quantum cryptography using maximally entangled qubit pairs. For doing so, we created a graph state along a path consisting of all the qubits of ibmqx4 and ibmq_16_melbourne respectively and we measure the strength of the entanglement using negativity measurement of the qubit pairs. Then, using the qubits with maximal entanglement, we send the modified encryption key to the receiver. The key is modified by permutation and superdense coding before transmission. The receiver reverts the process and gets the actual key. We carried out the complete experiment in the IBM Quantum Experience project. Our result shows a 15% to 20% higher fidelity of encryption and decryption than a random selection of qubits.

cs.CR↗

arXiv2020

The Past, Present, and Future of COVID-19: A Data-Driven Perspective

Epidemics and pandemics have ravaged human life since time. To combat these, novel ideas have always been created and deployed by humanity, with varying degrees of success. At this very moment, the COVID-19 pandemic is the singular global health crisis. Now, perhaps for the first time in human history, almost the whole of humanity is experiencing some form of hardship as a result of one invisible pathogen. This once again entails novel ideas for quick eradication, healing and recovery, whether it is healthcare, banking, travel, education or any other. For efficient policy-making, clear trends of past, present and future are vital for policy-makers. With the global impacts of COVID-19 so severe, equally important is the analysis of correlations between disease spread and various socio-economic and environmental factors. Furthermore, all of these need to be presented in an integrated manner in real-time to facilitate efficient policy making. To address these issues, in this study, we report results on our development and deployment of a web-based integrated real-time operational dashboard as an important decision support system for COVID-19. In our study, we conducted data-driven analysis based on available data from diverse authenticated sources to predict upcoming consequences of the pandemic through rigorous modeling and statistical analyses. We also explored correlations between pandemic spread and important socio-economic and environmental factors. Furthermore, we also present how outcomes of our work can facilitate efficient policy making in this critical hour.

cs.CY↗