arXiv subjects

Mushfiqur Rahman

Publications and source records attributed to Mushfiqur Rahman.

16 recordsLinked to original sources

arXiv2026

Rethinking Issue Resolution for AI/ML Systems

We advocate for AI/ML issue resolution frameworks tailored to maintenance workflows and the nature of modern AI/ML systems. Existing issue resolution frameworks largely emerged for traditional software maintenance practices and do not explicitly account for characteristics common in AI/ML systems, such as stochastic behavior, experimentation-driven workflows, and heterogeneous artifacts beyond source code. To identify the unique characteristics of issue resolution in AI/ML systems and motivate the need for tailored frameworks, we conducted a qualitative study of issue resolution workflows documented in 100 issue reports and pull requests across four widely used AI/ML systems: TensorFlow, scikit-learn, MLflow, and AutoGPT. Our findings suggest that issue resolution in AI/ML systems involves: recurring AI/ML-related activities that span multiple resolution stages; iterative experimentation and adaptive verification; and coordinated changes across artifacts such as datasets, prompts, and model configurations. We also observed challenges related to reproducibility, nondeterministic behavior, and artifact coordination. Building on these findings, we present a vision for AI/ML issue resolution frameworks and discuss research directions and tooling support needed to realize this vision.

cs.SE↗

arXiv2026

UAV-Based 3D Spectrum Sensing: Insights on Altitude, Bandwidth, Trajectory, and Effective Antenna Patterns on REM Reconstruction

Spectrum sensing and the generation of 3D Radio Environment Maps (REMs) are essential for enabling spectrum sharing within cognitive radio networks. While Uncrewed Aerial Vehicles (UAVs) offer high-mobility 3D sensing, REM accuracy is challenged by dynamic flight behaviors, where fluctuations in UAV speed and direction introduce measurement inconsistencies. Furthermore, the airframe itself impacts the onboard antenna's radiation characteristics. In this paper, using real-world data, we systematically analyze how REM reconstruction accuracy is shaped by three key pillars: physical sensing parameters like altitude and bandwidth, environmental shadowing, and distortions caused by the UAV airframe. First, we benchmark diverse spatial prediction models, including simple Kriging (SK), ordinary Kriging (OK), trans-Gaussian Kriging, and Gaussian process regression (GPR). We demonstrate that while SK and its trans-Gaussian variant are highly accurate at extreme sample sparsity, OK improves as sample size increases, and GPR serves as the most stable overall baseline. Building on this, we propose a novel matrix completion (MC)-assisted GPR framework that enhances REM reconstruction in the presence of non-uniform spatial smoothness. The method operates by decomposing the REM into two distinct layers: a global smooth component and a highly varying local component. Our analysis based on real-world measurements reveals three key findings: 1) REM accuracy and shadowing variance follow a distinct tri-phasic trend as the UAV altitude increases; 2) REM accuracy significantly improves with increased spectrum bandwidth; and 3) antenna pattern calibration from in-field measurements significantly enhances REM accuracy by accounting for the effect of the UAV airframe.

eess.SP↗

arXiv2026

GS-SBL: Bridging Greedy Pursuit and Sparse Bayesian Learning for Efficient 3D Wireless Channel Modeling

Robust cognitive radio development requires accurate 3D path loss models. Traditional empirical models often lack environment-awareness, while deep learning approaches are frequently constrained by the scarcity of large-scale training datasets. This work leverages the inherent sparsity of wireless propagation to model scenario-specific channels by identifying a discrete set of virtual signal sources. We propose a novel Greedy Sequential Sparse Bayesian Learning (GS-SBL) framework that bridges the gap between the computational efficiency of Orthogonal Matching Pursuit (OMP) and the robust uncertainty quantification of SBL. Unlike standard top-down SBL, which updates all source hyperparameters simultaneously, our approach employs a ``Micro-SBL'' architecture. We sequentially evaluate candidate source locations in isolation by executing localized, low-iteration SBL loops and selecting the source that minimizes the $L_2$ residual error. Once identified, the source and its corresponding power are added to the support set, and the process repeats on the signal residual to identify subsequent sources. Experimental results on real-world 3D propagation data demonstrate that the GS-SBL framework significantly outperforms OMP in terms of generalization. By utilizing SBL as a sequential source identifier rather than a global optimizer, the proposed method preserves Bayesian high-resolution accuracy while achieving the execution speeds necessary for real-time 3D path loss characterization.

eess.SP↗

arXiv2026

Elevation- and Tilt-Aware Shadow Fading Correlation Modeling for UAV Communications

Future wireless networks demand a more accurate understanding of channel behavior to enable efficient communication with reduced interference. Uncrewed Aerial Vehicles (UAVs) are poised to play an integral role in these networks, offering versatile applications and flexible deployment options. However, accurately characterizing the shadow fading (SF) behavior in UAV communications remains a challenge. Traditional SF correlation models rely on spatial distance and neglect the UAV's 3D orientation and elevation angle. Yet even slight variations in pitch angle (5 to 10 degrees) can significantly affect the signal strength observed by a UAV. In this study, we investigate the impact of UAV pitch and elevation geometry on SF and propose an elevation- and tilt-aware spatial correlation model. We use a real-world fixed-altitude UAV measurement dataset collected in a rural environment at 3.32 GHz with a 125 kHz bandwidth. Results show that a 10-degree tilt-angle separation and a 20-degree elevation-angle separation can reduce the SF correlation by up to 15% and 40%, respectively. In addition, integrating the proposed correlation model into the ordinary Kriging (OK) framework for signal strength prediction yields an approximate 1.5 dB improvement in median RMSE relative to the traditional correlation model that ignores UAV orientation and elevation.

eess.SP↗

arXiv2026

Less Is More? Selective Visual Attention to High-Importance Regions for Multimodal Radiology Summarization

Automated radiology report summarization aims to distill verbose findings into concise clinical impressions, but existing multimodal models often struggle with visual noise and fail to meaningfully improve over strong text-only baselines in the FINDINGS $\to$ IMPRESSION transformation. We challenge two prevailing assumptions: (1) that more visual input is always better, and (2) that multimodal models add limited value when findings already contain rich image-derived detail. Through controlled ablations on MIMIC-CXR benchmark, we show that selectively focusing on pathology-relevant visual patches rather than full images yields substantially better performance. We introduce ViTAS, Visual-Text Attention Summarizer, a multi-stage pipeline that combines ensemble-guided MedSAM2 lung segmentation, bidirectional cross-attention for multi-view fusion, Shapley-guided adaptive patch clustering, and hierarchical visual tokenization feeding a ViT. ViTAS achieves SOTA results with 29.25% BLEU-4 and 69.83% ROUGE-L, improved factual alignment in qualitative analysis, and the highest expert-rated human evaluation scores. Our findings demonstrate that less but more relevant visual input is not only sufficient but superior for multimodal radiology summarization.

cs.CV↗

arXiv2026

Curated Wireless Datasets for Aerial Network Research

This Review consolidates publicly available aerial wireless measurement datasets collected using AERPAW. We organize signal-level, power-level, and KPI-level datasets under a unified taxonomy, harmonize metadata, and provide verified access with reproducible post-processing scripts. The curated catalog supports propagation modeling, machine learning, localization, and system-level evaluation for 5G-Advanced and emerging 6G aerial networks.

cs.NI↗

arXiv2026

Platform-Aware Channel Knowledge Mapping via Mutual Antenna Pattern Learning in 3D Wireless Links

This letter proposes a platform-aware framework to characterize wireless links by empirically modeling the `near-platform' scattering and reflections induced by the hardware mounting structures of both endpoints. We model the link characteristics as a novel mutual antenna pattern: a joint function of the angle of arrival (AoA) and angle of departure (AoD). We demonstrate that while individual platform-aware patterns are mathematically unidentifiable from power measurements, the coupled mutual pattern can be effectively estimated in a least-squares sense. Our framework is evaluated using noisy measurement data, revealing that as few as 10 measurements per joint-angular bin are sufficient. The proposed methodology is validated through cross-validation of experimental subsets, demonstrating that the learned mutual radiation pattern reduces path loss estimation errors by up to 10 dB compared to traditional models using isolated anechoic chamber antenna gains.

eess.SP↗

arXiv2026

3D Spectrum Awareness for Radio Dynamic Zones Using Kriging and Matrix Completion

Radio Dynamic Zones (RDZs) are geographically defined areas specifically allocated for testing new wireless technologies. It is essential to safeguard the regular spectrum users outside the zones from the interference caused by the deployed equipment within this zone. Previous works have utilized sparse reference signal received power (RSRP) measurements collected by unmanned aerial vehicles (UAVs) to construct a dense 3D radio map through ordinary Kriging. In this work, we illustrate that matrix completion can outperform ordinary Kriging. We partitioned a 2D area of interest into small square grids where each grid corresponds to a single entry of a matrix. The matrix completion algorithm learns the global structure of the radio environment map by leveraging the low-rank property of propagation maps. Additionally, we illustrate that the simple Kriging and trans-Gaussian Kriging yield better results when the density of known measurements is lower. Earlier works of RSRP prediction involved a training dataset at a single altitude. In this work, we also show that performance can be improved by utilizing a combined dataset from multiple altitudes.

eess.SP↗

arXiv2026

Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker Diarization

Bengali (Bangla) remains under-resourced in long-form speech technology despite its wide use. We present Bengali-Loop, two community benchmarks to address this gap: (1) a long-form ASR corpus of 191 recordings (158.6 hours, 792k words) from 11 YouTube channels, collected via a reproducible subtitle-extraction pipeline and human-in-the-loop transcript verification; and (2) a speaker diarization corpus of 24 recordings (22 hours, 5,744 annotated segments) with fully manual speaker-turn labels in CSV format. Both benchmarks target realistic multi-speaker, long-duration content (e.g., Bangla drama/natok). We establish baselines (Tugstugi: 34.07% WER; pyannote.audio: 40.08% DER) and provide standardized evaluation protocols (WER/CER, DER), annotation rules, and data formats to support reproducible benchmarking and future model development for Bangla long-form ASR and diarization.

cs.SD↗

arXiv2025

CLARA: A Developer's Companion for Code Comprehension and Analysis

Code comprehension and analysis of open-source project codebases is a task frequently performed by developers and researchers. However, existing tools that practitioners use for assistance with such tasks often require prior project setup, lack context-awareness, and involve significant manual effort. To address this, we present CLARA, a browser extension that utilizes a state-of-the-art inference model to assist developers and researchers in: (i) comprehending code files and code fragments, (ii) code refactoring, and (iii) code quality attribute detection. We qualitatively evaluated CLARA's inference model using existing datasets and methodology, and performed a comprehensive user study with 10 developers and academic researchers to assess its usability and usefulness. The results show that CLARA is useful, accurate, and practical in code comprehension and analysis tasks. CLARA is an open-source tool available at https://github.com/SaadNoor555/CLARA_tool_demo. A video showing the full capabilities of CLARA can be found at https://youtu.be/VDKVXvIH41Q?si=qBFsmS_Y4m_9x3YH.

cs.SE↗

arXiv2025

SpectraSentinel: LightWeight Dual-Stream Real-Time Drone Detection, Tracking and Payload Identification

The proliferation of drones in civilian airspace has raised urgent security concerns, necessitating robust real-time surveillance systems. In response to the 2025 VIP Cup challenge tasks - drone detection, tracking, and payload identification - we propose a dual-stream drone monitoring framework. Our approach deploys independent You Only Look Once v11-nano (YOLOv11n) object detectors on parallel infrared (thermal) and visible (RGB) data streams, deliberately avoiding early fusion. This separation allows each model to be specifically optimized for the distinct characteristics of its input modality, addressing the unique challenges posed by small aerial objects in diverse environmental conditions. We customize data preprocessing and augmentation strategies per domain - such as limiting color jitter for IR imagery - and fine-tune training hyperparameters to enhance detection performance under conditions of heavy noise, low light, and motion blur. The resulting lightweight YOLOv11n models demonstrate high accuracy in distinguishing drones from birds and in classifying payload types, all while maintaining real-time performance. This report details the rationale for a dual-modality design, the specialized training pipelines, and the architectural optimizations that collectively enable efficient and accurate drone surveillance across RGB and IR channels.

cs.CV↗

arXiv2025

Individualized Deepfake Detection Exploiting Traces Due to Double Neural-Network Operations

In today's digital landscape, journalists urgently require tools to verify the authenticity of facial images and videos depicting specific public figures before incorporating them into news stories. Existing deepfake detectors are not optimized for this detection task when an image is associated with a specific and identifiable individual. This study focuses on the deepfake detection of facial images of individual public figures. We propose to condition the proposed detector on the identity of an identified individual, given the advantages revealed by our theory-driven simulations. While most detectors in the literature rely on perceptible or imperceptible artifacts present in deepfake facial images, we demonstrate that the detection performance can be improved by exploiting the idempotency property of neural networks. In our approach, the training process involves double neural-network operations where we pass an authentic image through a deepfake simulating network twice. Experimental results show that the proposed method improves the area under the curve (AUC) from 0.92 to 0.94 and reduces its standard deviation by 17%. To address the need for evaluating detection performance for individual public figures, we curated and publicly released a dataset of ~32k images featuring 45 public figures, as existing deepfake datasets do not meet this criterion.

eess.IV↗

arXiv2025

UAV-Assisted Coverage Hole Detection Using Reinforcement Learning in Urban Cellular Networks

Deployment of cellular networks in urban areas requires addressing various challenges. For example, high-rise buildings with varying geometrical shapes and heights contribute to signal attenuation, reflection, diffraction, and scattering effects. This creates a high possibility of coverage holes (CHs) within the proximity of the buildings. Detecting these CHs is critical for network operators to ensure quality of service, as customers in these areas may experience weak or no signal reception. To address this challenge, we propose an approach using an autonomous vehicle, such as an unmanned aerial vehicle (UAV), to detect CHs, for minimizing drive test efforts and reducing human labor. The UAV leverages reinforcement learning (RL) to find CHs using stored local building maps, its current location, and measured signal strengths. As the UAV moves, it dynamically updates its knowledge of the signal environment and its direction to a nearby CH while avoiding collisions with buildings. We created a wide range of testing scenarios using building maps from OpenStreetMap and signal strength data generated by NVIDIA Sionna raytracing simulations. The results show that the RL-based approach outperforms non-machine learning, geometry-based methods in detecting CHs in urban areas. Additionally, even with a limited number of UAV measurements, the method achieves performance close to theoretical upper bounds that assume complete knowledge of all signal strengths.

eess.SP↗

arXiv2023

Bengali Document Layout Analysis with Detectron2

Document digitization is vital for preserving historical records, efficient document management, and advancing OCR (Optical Character Recognition) research. Document Layout Analysis (DLA) involves segmenting documents into meaningful units like text boxes, paragraphs, images, and tables. Challenges arise when dealing with diverse layouts, historical documents, and unique scripts like Bengali, hindered by the lack of comprehensive Bengali DLA datasets. We improved the accuracy of the DLA model for Bengali documents by utilizing advanced Mask R-CNN models available in the Detectron2 library. Our evaluation involved three variants: Mask R-CNN R-50, R-101, and X-101, both with and without pretrained weights from PubLayNet, on the BaDLAD dataset, which contains human-annotated Bengali documents in four categories: text boxes, paragraphs, images, and tables. Results show the effectiveness of these models in accurately segmenting Bengali documents. We discuss speed-accuracy tradeoffs and underscore the significance of pretrained weights. Our findings expand the applicability of Mask R-CNN in document layout analysis, efficient document management, and OCR research while suggesting future avenues for fine-tuning and data augmentation.

cs.CV↗

arXiv2022

Contact-Free Simultaneous Sensing of Human Heart Rate and Canine Breathing Rate for Animal Assisted Interactions

Animal Assisted Interventions (AAIs) involve pleasant interactions between humans and animals and can potentially benefit both types of participants. Research in this field may help to uncover universal insights about cross-species bonding, dynamic affect detection, and the influence of environmental factors on dyadic interactions. However, experiments evaluating these outcomes are limited to methodologies that are qualitative, subjective, and cumbersome due to the ergonomic challenges related to attaching sensors to the body. Current approaches in AAIs also face challenges when translating beyond controlled clinical environments or research contexts. These also often neglect the measurements from the animal throughout the interaction. Here, we present our preliminary effort toward a contact-free approach to facilitate AAI assessment via the physiological sensing of humans and canines using consumer-grade cameras. This initial effort focuses on verifying the technological feasibility of remotely sensing the heart rate signal of the human subject and the breathing rate signal of the dog subject while they are interacting. Small amounts of motion such as patting and involuntary body shaking or movement can be tolerated with our custom designed vision-based algorithms. The experimental results show that the physiological measurements obtained by our algorithms were consistent with those provided by the standard reference devices. With further validation and expansion to other physiological parameters, the presented approach offers great promise for many scenarios from the AAI research space to veterinary, surgical, and clinical applications.

eess.SP↗

arXiv2017

Earth matter effect on atmospheric neutrino oscillation in (3+3) model

In a recent combined analysis of short baseline neutrino oscillation data by Conrad et al it is shown that (3+3) neutrino model, defined by three active and three sterile neutrinos, results in an overall goodness of $67\%$ and a compatibility of $90\%$ among all data sets - to be compared to the compatibility of $0.043\% $ and $13\% $ for a (3+1) and a (3+2) model, respectively. Aside from the fact that (3+3) model still finds inconsistencies with MiniBooNE appearance data sets, its high quality overall compatibility and goodness of fit led us to study the atmospheric neutrinos in this model which travel distances of thousands of kilometers through earth. We show that in this mixing scheme matter resonance effect inside earth enhances the small vacuum oscillations into near-maximal transitions and at high energies these maximal transitions occur in the TeV range, whereas at low energies those can occur in the few GeV region. We also calculate the zenith angle distributions of $ν_μ^{CC}$(charged current) events in the 10 - 100 GeV energy range in DeepCore sub-array of the IceCube Neutrino Observatory and comment on the possibility of probing active neutrino mass hierarchy and six neutrino scenario.

hep-ph↗