arXiv subjects

Tanzima Hashem

Publications and source records attributed to Tanzima Hashem.

14 recordsLinked to original sources

arXiv2026

ECG-LENS: Lead-Aware Clinical Context Enriched ECG Report Generation and Evaluation

Electrocardiography (ECG) is one of the most widely used non-invasive tools for diagnosing cardiovascular disease, but transforming multi-lead ECG recordings into reliable clinical reports remains challenging. Automating ECG report generation could reduce clinicians' interpretive workload, improve diagnostic efficiency, and expand access to cardiac assessment in underserved communities. Unlike image-based report-generation tasks, ECG interpretation requires the analysis of subtle temporal morphologies, followed by coherent diagnostic reasoning expressed in dense clinical terminology. Existing systems predominantly focus on classification, while current report-generation methods often produce outputs that remain inadequate for practical clinical use. To address these challenges, we propose ECG-LENS, an end-to-end ECG report-generation framework that jointly integrates multi-lead signal modeling, diagnosis-aware representations, and clinically grounded text generation. ECG-LENS combines lead-wise encoders that preserve localized waveform morphology with a global encoder that captures inter-lead dependencies. To guide report generation, we fuse signal representations with clinically enriched textual prompts that condition a GPT-2 decoder. We further introduce an ECG-specific report-preprocessing strategy that helps the model focus on clinically meaningful findings. Finally, because lexical metrics may under- or overestimate report quality, we propose F1-ECGBERT, a BERT-based, ECG-specific metric that measures agreement between diagnostic labels extracted from generated and reference reports. In-domain experiments on PTB-XL and cross-domain evaluation on MIMIC-IV-ECG show that ECG-LENS consistently outperforms state-of-the-art methods, with absolute gains of 4.0%, 6.3%, and 11.5% in METEOR, ROUGE-L, and F1-ECGBERT, respectively, over the strongest baselines.

cs.AI↗

arXiv2025

WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment

LLM-based agents often operate in a greedy, step-by-step manner, selecting actions solely based on the current observation without considering long-term consequences or alternative paths. This lack of foresight is particularly problematic in web environments, which are only partially observable-limited to browser-visible content (e.g., DOM and UI elements)-where a single misstep often requires complex and brittle navigation to undo. Without an explicit backtracking mechanism, agents struggle to correct errors or systematically explore alternative paths. Tree-search methods provide a principled framework for such structured exploration, but existing approaches lack mechanisms for safe backtracking, making them prone to unintended side effects. They also assume that all actions are reversible, ignoring the presence of irreversible actions-limitations that reduce their effectiveness in realistic web tasks. To address these challenges, we introduce WebOperator, a tree-search framework that enables reliable backtracking and strategic exploration. Our method incorporates a best-first search strategy that ranks actions by both reward estimates and safety considerations, along with a robust backtracking mechanism that verifies the feasibility of previously visited paths before replaying them, preventing unintended side effects. To further guide exploration, WebOperator generates action candidates from multiple, varied reasoning contexts to ensure diverse and robust exploration, and subsequently curates a high-quality action set by filtering out invalid actions pre-execution and merging semantically equivalent ones. Experimental results on WebArena and WebVoyager demonstrate the effectiveness of WebOperator. On WebArena, WebOperator achieves a state-of-the-art 54.6% success rate with gpt-4o, underscoring the critical advantage of integrating strategic foresight with safe execution.

cs.AI↗

arXiv2025

AttMetNet: Attention-Enhanced Deep Neural Network for Methane Plume Detection in Sentinel-2 Satellite Imagery

Methane is a powerful greenhouse gas that contributes significantly to global warming. Accurate detection of methane emissions is the key to taking timely action and minimizing their impact on climate change. We present AttMetNet, a novel attention-enhanced deep learning framework for methane plume detection with Sentinel-2 satellite imagery. The major challenge in developing a methane detection model is to accurately identify methane plumes from Sentinel-2's B11 and B12 bands while suppressing false positives caused by background variability and diverse land cover types. Traditional detection methods typically depend on the differences or ratios between these bands when comparing the scenes with and without plumes. However, these methods often require verification by a domain expert because they generate numerous false positives. Recent deep learning methods make some improvements using CNN-based architectures, but lack mechanisms to prioritize methane-specific features. AttMetNet introduces a methane-aware architecture that fuses the Normalized Difference Methane Index (NDMI) with an attention-enhanced U-Net. By jointly exploiting NDMI's plume-sensitive cues and attention-driven feature selection, AttMetNet selectively amplifies methane absorption features while suppressing background noise. This integration establishes a first-of-its-kind architecture tailored for robust methane plume detection in real satellite imagery. Additionally, we employ focal loss to address the severe class imbalance arising from both limited positive plume samples and sparse plume pixels within imagery. Furthermore, AttMetNet is trained on the real methane plume dataset, making it more robust to practical scenarios. Extensive experiments show that AttMetNet surpasses recent methods in methane plume detection with a lower false positive rate, better precision recall balance, and higher IoU.

cs.CV↗

arXiv2025

MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration

Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and fall short on geospatial tasks that require spatial reasoning, multi-hop planning, and real-time map interaction. To address these challenges, we introduce MapAgent, a hierarchical multi-agent plug-and-play framework with customized toolsets and agentic scaffolds for map-integrated geospatial reasoning. Unlike existing flat agent-based approaches that treat tools uniformly-often overwhelming the LLM when handling similar but subtly different geospatial APIs-MapAgent decouples planning from execution. A high-level planner decomposes complex queries into subgoals, which are routed to specialized modules. For tool-heavy modules-such as map-based services-we then design a dedicated map-tool agent that efficiently orchestrates related APIs adaptively in parallel to effectively fetch geospatial data relevant for the query, while simpler modules (e.g., solution generation or answer extraction) operate without additional agent overhead. This hierarchical design reduces cognitive load, improves tool selection accuracy, and enables precise coordination across similar APIs. We evaluate MapAgent on four diverse geospatial benchmarks-MapEval-Textual, MapEval-API, MapEval-Visual, and MapQA-and demonstrate substantial gains over state-of-the-art tool-augmented and agentic baselines. We open-source our framwork at https://github.com/Hasebul/MapAgent.

cs.AI↗

arXiv2025

Efficient Computation of Trip-based Group Nearest Neighbor Queries (Full Version)

In recent years, organizing group meetups for entertainment or other necessities has gained significant importance, especially given the busy nature of daily schedules. People often combine multiple activities, such as dropping kids off at school, commuting to work, and grocery shopping, while seeking opportunities to meet others. To address this need, we propose a novel query type, the Trip-based Group Nearest Neighbor (T-GNN) query, which identifies the optimal meetup Point of Interest (POI) that aligns with users' existing trips. An individual trip consists of a sequence of locations, allowing users the flexibility to detour to the meetup POI at any location within the sequence, known as a detour location. Given a set of trips for the users, the query identifies the optimal meetup POI (e.g., restaurants or movie theaters) and detour locations from each user's trip that minimize the total trip overhead distance. The trip overhead distance refers to the additional distance a user must travel to visit the meetup POI before returning to the next location in their trip. The sum of these overhead distances for all users constitutes the total trip overhead distance. The computation time for processing T-GNN queries increases with the number of POIs. To address this, we introduce three techniques to prune the POIs that cannot contribute to the optimal solution, and thus refine the search space. We also develop an efficient approach for processing T-GNN queries in real-time. Extensive experiments validate the performance of the proposed algorithm.

cs.DB↗

arXiv2025

Lightning Prediction under Uncertainty: DeepLight with Hazy Loss

Lightning, a common feature of severe meteorological conditions, poses significant risks, from direct human injuries to substantial economic losses. These risks are further exacerbated by climate change. Early and accurate prediction of lightning would enable preventive measures to safeguard people, protect property, and minimize economic losses. In this paper, we present DeepLight, a novel deep learning architecture for predicting lightning occurrences. Existing prediction models face several critical limitations: i) they often struggle to capture the dynamic spatial context and the inherent randomness of lightning events, including whether lightning occurs and its variability in location and timing even under similar meteorological conditions; ii) they underutilize key observational data, such as radar reflectivity and cloud properties; and iii) they rely heavily on Numerical Weather Prediction (NWP) systems, which are both computationally expensive and highly sensitive to parameter settings. To overcome these challenges, DeepLight leverages multi-source meteorological data, including radar reflectivity, cloud properties, and historical lightning occurrences through a dual-encoder architecture. By employing multi-branch convolution techniques, it dynamically captures spatial correlations across varying extents. Furthermore, its novel Hazy Loss function explicitly addresses the spatio-temporal uncertainty of lightning by penalizing deviations based on proximity to true events, enabling the model to better learn patterns amidst randomness. Extensive experiments show that DeepLight improves the Equitable Threat Score (ETS) by 18\%--30\% over state-of-the-art methods, establishing it as a robust solution for lightning prediction.

cs.LG↗

arXiv2024

Deep Learning Based Crime Prediction Models: Experiments and Analysis

Crime prediction is a widely studied research problem due to its importance in ensuring safety of city dwellers. Starting from statistical and classical machine learning based crime prediction methods, in recent years researchers have focused on exploiting deep learning based models for crime prediction. Deep learning based crime prediction models use complex architectures to capture the latent features in the crime data, and outperform the statistical and classical machine learning based crime prediction methods. However, there is a significant research gap in existing research on the applicability of different models in different real-life scenarios as no longitudinal study exists comparing all these approaches in a unified setting. In this paper, we conduct a comprehensive experimental evaluation of all major state-of-the-art deep learning based crime prediction models. Our evaluation provides several key insights on the pros and cons of these models, which enables us to select the most suitable models for different application scenarios. Based on the findings, we further recommend certain design practices that should be taken into account while building future deep learning based crime prediction models.

cs.LG↗

arXiv2023

Enabling Spatial Digital Twins: Technologies, Challenges, and Future Research Directions

A Digital Twin (DT) is a virtual replica of a physical object or system, created to monitor, analyze, and optimize its behavior and characteristics. A Spatial Digital Twin (SDT) is a specific type of digital twin that emphasizes the geospatial aspects of the physical entity, incorporating precise location and dimensional attributes for a comprehensive understanding within its spatial environment. The current body of research on SDTs primarily concentrates on analyzing their potential impact and opportunities within various application domains. As building an SDT is a complex process and requires a variety of spatial computing technologies, it is not straightforward for practitioners and researchers of this multi-disciplinary domain to grasp the underlying details of enabling technologies of the SDT. In this paper, we are the first to systematically analyze different spatial technologies relevant to building an SDT in layered approach (starting from data acquisition to visualization). More specifically, we present the key components of SDTs into four layers of technologies: (i) data acquisition; (ii) spatial database management \& big data analytics systems; (iii) GIS middleware software, maps \& APIs; and (iv) key functional components such as visualizing, querying, mining, simulation and prediction. Moreover, we discuss how modern technologies such as AI/ML, blockchains, and cloud computing can be effectively utilized in enabling and enhancing SDTs. Finally, we identify a number of research challenges and opportunities in SDTs. This work serves as an important resource for SDT researchers and practitioners as it explicitly distinguishes SDTs from traditional DTs, identifies unique applications, outlines the essential technological components of SDTs, and presents a vision for their future development along with the challenges that lie ahead.

cs.CY↗

arXiv2021

A Crowd-enabled Solution for Privacy-Preserving and Personalized Safe Route Planning for Fixed or Flexible Destinations (Full Version)

Ensuring travelers' safety on roads has become a research challenge in recent years. We introduce a novel safe route planning problem and develop an efficient solution to ensure the travelers' safety on roads. Though few research attempts have been made in this regard, all of them assume that people share their sensitive travel experiences with a centralized entity for finding the safest routes, which is not ideal in practice for privacy reasons. Furthermore, existing works formulate safe route planning in ways that do not meet a traveler's need for safe travel on roads. Our approach finds the safest routes within a user-specified distance threshold based on the personalized travel experience of the knowledgeable crowd without involving any centralized computation. We develop a privacy-preserving model to quantify the travel experience of a user into personalized safety scores. Our algorithms for finding the safest route further enhance user privacy by minimizing the exposure of personalized safety scores with others. Our safe route planner can find the safest routes for individuals and groups by considering both a fixed and a set of flexible destination locations. Extensive experiments using real datasets show that our approach finds the safest route in seconds. Compared to the direct algorithm, our iterative algorithm requires 47% less exposure of personalized safety scores.

cs.DB↗

arXiv2021

Safest Nearby Neighbor Queries in Road Networks (Full Version)

Traditional route planning and k nearest neighbors queries only consider distance or travel time and ignore road safety altogether. However, many travellers prefer to avoid risky or unpleasant road conditions such as roads with high crime rates (e.g., robberies, kidnapping, riots etc.) and bumpy roads. To facilitate safe travel, we introduce a novel query for road networks called the k safest nearby neighbors (kSNN) query. Given a query location $v_l$, a distance constraint $d_c$ and a point of interest $p_i$, we define the safest path from $v_l$ to $p_i$ as the path with the highest path safety score among all the paths from $v_l$ to $p_i$ with length less than $d_c$. The path safety score is computed considering the road safety of each road segment on the path. Given a query location $v_l$, a distance constraint $d_c$ and a set of POIs P, a kSNN query returns k POIs with the k highest path safety scores in P along with their respective safest paths from the query location. We develop two novel indexing structures called Ct-tree and a safety score based Voronoi diagram (SNVD). We propose two efficient query processing algorithms each exploiting one of the proposed indexes to effectively refine the search space using the properties of the index. Our extensive experimental study on real datasets demonstrates that our solution is on average an order of magnitude faster than the baselines.

cs.DB↗

arXiv2020

AIST: An Interpretable Attention-based Deep Learning Model for Crime Prediction

Accuracy and interpretability are two essential properties for a crime prediction model. Because of the adverse effects that the crimes can have on human life, economy and safety, we need a model that can predict future occurrence of crime as accurately as possible so that early steps can be taken to avoid the crime. On the other hand, an interpretable model reveals the reason behind a model's prediction, ensures its transparency and allows us to plan the crime prevention steps accordingly. The key challenge in developing the model is to capture the non-linear spatial dependency and temporal patterns of a specific crime category while keeping the underlying structure of the model interpretable. In this paper, we develop AIST, an Attention-based Interpretable Spatio Temporal Network for crime prediction. AIST models the dynamic spatio-temporal correlations for a crime category based on past crime occurrences, external features (e.g., traffic flow and point of interest (POI) information) and recurring trends of crime. Extensive experiments show the superiority of our model in terms of both accuracy and interpretability using real datasets.

cs.LG↗

arXiv2015

Impact of Imbalance Usage of Social Networking Sites on Families

With the proliferation of social networking sites (SNSs) such as Facebook and Google+, investigating the impact of SNSs on our lives has become an important research area in recent years. Though SNS usage plays a key role in connecting people with friends and families from distant places, SNSs also bring concern for families. We focus on imbalance SNS usage, i.e., an individual remains busy in using SNSs when her family member is expecting to spend time with her. More specifically, we investigate the cause and pattern of imbalance SNS usage and how the emotion of family members may become affected, if they use SNSs in an imbalanced way in a regular manner. This paper is the first attempt to identify the relationship between an individual's imbalance SNS usage and the emotion of her family member in the context of a developing country.

cs.HC↗

arXiv2012

Shared Execution of Path Queries on Road Networks

The advancement of mobile technologies and the proliferation of map-based applications have enabled a user to access a wide variety of services that range from information queries to navigation systems. Due to the popularity of map-based applications among the users, the service provider often requires to answer a large number of simultaneous queries. Thus, processing queries efficiently on spatial networks (i.e., road networks) have become an important research area in recent years. In this paper, we focus on path queries that find the shortest path between a source and a destination of the user. In particular, we address the problem of finding the shortest paths for a large number of simultaneous path queries in road networks. Traditional systems that consider one query at a time are not suitable for many applications due to high computational and service costs. These systems cannot guarantee required response time in high load conditions. We propose an efficient group based approach that provides a practical solution with reduced cost. The key concept for our approach is to group queries that share a common travel path and then compute the shortest path for the group. Experimental results show that our approach is on an average ten times faster than the traditional approach in return of sacrificing the accuracy by 0.5% in the worst case, which is acceptable for most of the users.

cs.DB↗

arXiv2011

Privacy Preserving Moving KNN Queries

We present a novel approach that protects trajectory privacy of users who access location-based services through a moving k nearest neighbor (MkNN) query. An MkNN query continuously returns the k nearest data objects for a moving user (query point). Simply updating a user's imprecise location such as a region instead of the exact position to a location-based service provider (LSP) cannot ensure privacy of the user for an MkNN query: continuous disclosure of regions enables the LSP to follow a user's trajectory. We identify the problem of trajectory privacy that arises from the overlap of consecutive regions while requesting an MkNN query and provide the first solution to this problem. Our approach allows a user to specify the confidence level that represents a bound of how much more the user may need to travel than the actual kth nearest data object. By hiding a user's required confidence level and the required number of nearest data objects from an LSP, we develop a technique to prevent the LSP from tracking the user's trajectory for MkNN queries. We propose an efficient algorithm for the LSP to find k nearest data objects for a region with a user's specified confidence level, which is an essential component to evaluate an MkNN query in a privacy preserving manner; this algorithm is at least two times faster than the state-of-the-art algorithm. Extensive experimental studies validate the effectiveness of our trajectory privacy protection technique and the efficiency of our algorithm.

cs.DB↗