arXiv subjects

Ariful Islam

Publications and source records attributed to Ariful Islam.

10 recordsLinked to original sources

arXiv2026

PULSE: Agentic Investigation with Passive Sensing for Proactive Affective Intervention in Cancer Survivorship

Cancer survivors face elevated rates of depression, anxiety, and emotional distress, yet self-report may be unavailable at some moments when support is relevant, a challenge we term the diary paradox. We present PULSE, a system for agentic sensing investigation: LLM agents equipped with eight purpose-built tools query smartphone sensing data, compare current behavior with personal baselines, and retrieve outcome-labeled historical cases. Rather than receiving only a fixed feature summary, agents choose which modalities and time windows to inspect. We evaluate PULSE through a two-by-two evaluation design crossing system architecture (structured single-pass vs. multi-turn agentic) with concurrent input modality (no current diary vs. sensing plus current diary) on 50 cancer survivors. The agentic multimodal condition achieves balanced accuracy of 0.743 for emotion-regulation desire; the agentic no-current-diary condition achieves 0.713 for self-reported intervention availability. This is a system-level comparison because the architecture conditions also differ in tool-mediated information access. The results provide a retrospective benchmark for interactive sensing investigation and motivate prospective evaluation at diary non-response moments.

cs.HC↗

arXiv2026

Urban Flood Observations: A hand-labeled training and validation dataset of post-flood inundation

Urban flooding affects lives and infrastructure worldwide. Mapping inundation in complex urban environments from satellite imagery remains challenging due to limited spatial resolution, infrequent acquisitions, and cloud cover. We present Urban Flood Observations (UFO), a global, hand-labeled dataset of post-flood inundation in diverse urban settings. UFO comprises 215 image chips (1024 by 1024 pixels) from 14 flood events between 2017 and 2021, derived from 3 m PlanetScope imagery. Each chip is annotated with two classes: 'inundated' (all visible surface water, including floodwater and pre-existing water bodies (permanent or seasonal)) and 'non-inundated'. To demonstrate the dataset's utility, we trained a segmentation model using leave-one-event-out cross-validation, achieving a mean Intersection over Union (IoU) of 77.3. We also used UFO to evaluate two widely used surface water products, the Sentinel-1-based NASA IMPACT model and Google's 10 m Dynamic World water class, which yielded IoUs of 44.1 and 48.1, respectively. UFO is publicly available to support the development and validation of urban inundation mapping methods.

cs.CV↗

arXiv2026

Impacts of Fermi Level Pinning at Hole-Selective Contacts in CdSeTe/CdTe Solar Cells

P-type doped CdTe free surfaces Schottky contacts, and even interfaces with isostructural p-ZnTe frequently exhibit downward band bending and moderate to high recombination velocities. Fermi level pinning by donor-like states can explain these band diagram features, as well as device response characteristics such as 1st quadrant rollover in current-voltage (JV) versus temperature (JVT). Parasitic downward band bending also produces voltage-dependent photocurrent collection, producing fill factor (FF) efficiency losses, JV dark/light non-superposition (or JV take-off), and irregularities in Jsc-Voc and Suns-Voc measurements. Herein, we develop a device physics model of state-of-the-art CdSeTe/CdTe solar cells consistent with known characterization of materials and devices, including the optical, thermalization, and trapping effects of band tail states and isolated defects. We use this model to demonstrate that Fermi-level pinning at the p-ZnTe/p-CdSeTe hole contact by donor-like defects reproduces the aforementioned observables, and conclude that (for contemporary few-um absorber thicknesses and low mobilities) it primarily affects FF rather than Voc. We investigate the performance gains possible from hypothetical passivated, hole-selective layers at the ZnTe/CdTe interface, which eliminate the downwards band bending caused by donor-like defects. For thinner devices and larger minority carrier diffusion lengths, these strategies will become more important for continued efficiency improvements.

cond-mat.mtrl-sci↗

arXiv2026

BirdsEye-RU: A Dataset For Detecting Faces from Overhead Images

Detecting faces in overhead images remains a significant challenge due to extreme scale variations and environmental clutter. To address this, we created the BirdsEye-RU dataset, a comprehensive collection of 2,978 images containing over eight thousand annotated faces. This dataset is specifically designed to capture small and distant faces across diverse environments, containing both drone images and smartphone-captured images from high altitude. We present a detailed description of the BirdsEye-RU dataset in this paper. We made our dataset freely available to the public, and it can be accessed at https://www.kaggle.com/datasets/mdahanafarifkhan/birdseye-ru.

cs.CV↗

arXiv2025

BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning

Multi-aspect sentiment analysis of Bangla e-commerce reviews remains challenging due to limited annotated datasets, morphological complexity, code-mixing phenomena, and domain shift issues, affecting 300 million Bangla-speaking users. Existing approaches lack explainability and cross-domain generalization capabilities crucial for practical deployment. We present BanglaSentNet, an explainable hybrid deep learning framework integrating LSTM, BiLSTM, GRU, and BanglaBERT through dynamic weighted ensemble learning for multi-aspect sentiment classification. We introduce a dataset of 8,755 manually annotated Bangla product reviews across four aspects (Quality, Service, Price, Decoration) from major Bangladeshi e-commerce platforms. Our framework incorporates SHAP-based feature attribution and attention visualization for transparent insights. BanglaSentNet achieves 85% accuracy and 0.88 F1-score, outperforming standalone deep learning models by 3-7% and traditional approaches substantially. The explainability suite achieves 9.4/10 interpretability score with 87.6% human agreement. Cross-domain transfer learning experiments reveal robust generalization: zero-shot performance retains 67-76% effectiveness across diverse domains (BanglaBook reviews, social media, general e-commerce, news headlines); few-shot learning with 500-1000 samples achieves 90-95% of full fine-tuning performance, significantly reducing annotation costs. Real-world deployment demonstrates practical utility for Bangladeshi e-commerce platforms, enabling data-driven decision-making for pricing optimization, service improvement, and customer experience enhancement. This research establishes a new state-of-the-art benchmark for Bangla sentiment analysis, advances ensemble learning methodologies for low-resource languages, and provides actionable solutions for commercial applications.

cs.LG↗

arXiv2025

Transformer-Driven Triple Fusion Framework for Enhanced Multimodal Author Intent Classification in Low-Resource Bangla

The expansion of the Internet and social networks has led to an explosion of user-generated content. Author intent understanding plays a crucial role in interpreting social media content. This paper addresses author intent classification in Bangla social media posts by leveraging both textual and visual data. Recognizing limitations in previous unimodal approaches, we systematically benchmark transformer-based language models (mBERT, DistilBERT, XLM-RoBERTa) and vision architectures (ViT, Swin, SwiftFormer, ResNet, DenseNet, MobileNet), utilizing the Uddessho dataset of 3,048 posts spanning six practical intent categories. We introduce a novel intermediate fusion strategy that significantly outperforms early and late fusion on this task. Experimental results show that intermediate fusion, particularly with mBERT and Swin Transformer, achieves 84.11% macro-F1 score, establishing a new state-of-the-art with an 8.4 percentage-point improvement over prior Bangla multimodal approaches. Our analysis demonstrates that integrating visual context substantially enhances intent classification. Cross-modal feature integration at intermediate levels provides optimal balance between modality-specific representation and cross-modal learning. This research establishes new benchmarks and methodological standards for Bangla and other low-resource languages. We call our proposed framework BangACMM (Bangla Author Content MultiModal).

cs.LG↗

arXiv2025

BanglaMM-Disaster: A Multimodal Transformer-Based Deep Learning Framework for Multiclass Disaster Classification in Bangla

Natural disasters remain a major challenge for Bangladesh, so real-time monitoring and quick response systems are essential. In this study, we present BanglaMM-Disaster, an end-to-end deep learning-based multimodal framework for disaster classification in Bangla, using both textual and visual data from social media. We constructed a new dataset of 5,037 Bangla social media posts, each consisting of a caption and a corresponding image, annotated into one of nine disaster-related categories. The proposed model integrates transformer-based text encoders, including BanglaBERT, mBERT, and XLM-RoBERTa, with CNN backbones such as ResNet50, DenseNet169, and MobileNetV2, to process the two modalities. Using early fusion, the best model achieves 83.76% accuracy. This surpasses the best text-only baseline by 3.84% and the image-only baseline by 16.91%. Our analysis also shows reduced misclassification across all classes, with noticeable improvements for ambiguous examples. This work fills a key gap in Bangla multimodal disaster analysis and demonstrates the benefits of combining multiple data types for real-time disaster response in low-resource settings.

cs.LG↗

arXiv2025

BanglaASTE: A Novel Framework for Aspect-Sentiment-Opinion Extraction in Bangla E-commerce Reviews Using Ensemble Deep Learning

Aspect-Based Sentiment Analysis (ABSA) has emerged as a critical tool for extracting fine-grained sentiment insights from user-generated content, particularly in e-commerce and social media domains. However, research on Bangla ABSA remains significantly underexplored due to the absence of comprehensive datasets and specialized frameworks for triplet extraction in this language. This paper introduces BanglaASTE, a novel framework for Aspect Sentiment Triplet Extraction (ASTE) that simultaneously identifies aspect terms, opinion expressions, and sentiment polarities from Bangla product reviews. Our contributions include: (1) creation of the first annotated Bangla ASTE dataset containing 3,345 product reviews collected from major e-commerce platforms including Daraz, Facebook, and Rokomari; (2) development of a hybrid classification framework that employs graph-based aspect-opinion matching with semantic similarity techniques; and (3) implementation of an ensemble model combining BanglaBERT contextual embeddings with XGBoost boosting algorithms for enhanced triplet extraction performance. Experimental results demonstrate that our ensemble approach achieves superior performance with 89.9% accuracy and 89.1% F1-score, significantly outperforming baseline models across all evaluation metrics. The framework effectively addresses key challenges in Bangla text processing including informal expressions, spelling variations, and data sparsity. This research advances the state-of-the-art in low-resource language sentiment analysis and provides a scalable solution for Bangla e-commerce analytics applications.

cs.LG↗

arXiv2024

Quantification of the strong, phonon-induced Urbach tails in \b{eta}-Ga2O3 and their implications on electrical breakdown

In ultrawide bandgap (UWBG) nitride and oxide semiconductors, increased bandgap (Eg) correlates with greater ionicity and strong electron-phonon coupling. This limits mobility through polar optical phonon scattering, localizes carriers via polarons and self-trapping, broadens optical transitions via dynamic disorder, and modifies the breakdown field. Herein, we use polarized optical transmission spectroscopy from 77-633 K to investigate the Urbach energy (Eu) for many orientations of Fe- and Sn-doped \b{eta}-Ga2O3 bulk crystals. We find Eu values ranging from 60-140 meV at 293 K and static (structural defects plus zero-point phonons) disorder contributes more to Eu than dynamic (finite temperature phonon-induced) disorder. This is evidenced by lack of systematic Eu anisotropy, and Eu correlating more with X-ray diffraction rocking-curve broadening than with Sn-doping. The lowest measured Eu are ~10x larger than for traditional semiconductors, pointing out that band tail effects need to be carefully considered in these materials for high field electronics. We demonstrate that, because optical transmission through thick samples is sensitive to sub-gap absorption, the commonly-used Tauc extraction of bandgap from transmission through Ga2O3 greater than 1-3 micro meter thick is subject to errors. Combining our Eu(T) from Fe-doped samples with Eg(T) from ellipsometry, we extract a measure of an effective electron-phonon coupling indicating increases in weighted 2nd order deformation potential with temperature and a larger value for E parallel b than E parallel c. The large electron-phonon coupling in beta-Ga2O3 suggests that theories of electrical breakdown for traditional semiconductors need expansion to account not just for lower scattering time but also for impact ionization thresholds fluctuating in both time and space.

cond-mat.mtrl-sci↗

arXiv2022

Non-Relativistic Particle under the Influence of Aharonov-Bohm Flux Field Subject to Physical Potentials and the Nikiforov-Uvarov Method

In this work, the non-relativistic wave equation via the Schr\"{o}dinger wave equation under the influence of the Aharonov-Bohm flux field Subject to physical potentials of various kinds is investigated. These potentials are modified Coulomb potential, modified harmonic oscillator potential, the Kratzer-Feus potential, and the Mie-type potential which have wide applications in different branches of physics and chemistry. We solve the Schrodinger wave equation using the Nikiforov-Uvarov (NU) method and obtain the energy profiles and the wave function of the non-relativistic particle, and analyze the effects of potential and the quantum flux on them. We show that each non-relativistic energy level gets modified in comparison to the known results obtained in the literature.

quant-ph↗