arXiv subjects

Mohammed Hadi

Publications and source records attributed to Mohammed Hadi.

3 recordsLinked to original sources

arXiv2026

PulseBench-Tab: A Multilingual Benchmark for Table Extraction with Graph-Based Evaluation

We introduce PulseBench-Tab, an open multilingual benchmark for evaluating table extraction from document images. The benchmark comprises 1,820 human-annotated tables spanning 9 languages and 4 scripts (Latin, CJK, Arabic, Cyrillic), drawn from 380 real-world source documents including financial filings, government reports, and regulatory disclosures. Tables range from 2 to 1,183 cells, with 48.1% containing merged or spanning cells. Alongside the dataset, we propose T-LAG (Table Logical Adjacency Graph), a novel evaluation metric that models tables as directed graphs over cell adjacencies and computes structural and content fidelity in a single score via optimal bipartite matching. We evaluate 9 commercial and open-source table extraction systems across the benchmark and report per-language breakdowns. The full dataset, scoring code, and all provider outputs are publicly available.

cs.IR↗

arXiv2026

Measuring Braking Behavior Using Vehicle Tracking and Camera-to-Satellite Homography Rectification

This paper presents an open-source software application for analyzing traffic camera footage, focusing on vehicle behavior and braking events at signalized urban highways. The core innovation is a robust ground-plane homography estimation that links fixed traffic camera views to satellite orthoimagery. This process rectifies the camera's oblique perspective, ensuring that pixel distances accurately represent real-world distances. This enables the acquisition of features such as vehicle trajectory, speed, deceleration, and braking severity without the need for camera calibration. The pipeline employs the MAGSAC++ estimator to build the homography, converting YOLO11 object detections into a rectified top-down coordinate system. All detection and trajectory data are stored in a ClickHouse database for subsequent analysis. A real-world case study at two signalized intersections in Key West, Florida, showcased the system's capabilities. Across two days of daytime footage, braking activity at the higher-volume intersection peaked around 4 PM at approximately 57.5 events per hour, while the second intersection peaked around 10 AM at roughly 15.5 events per hour. The spatial analysis revealed that most braking events initiated upstream, with mild and moderate braking mostly occurring 30 to 45+ meters away from the stop bar and severe braking distributed throughout, but particularly concentrated in lanes with higher interaction and merging activity. The findings highlight the significant potential of this centralized safety information system to support connected vehicles, facilitating proactive traffic management, crash mitigation, and data-driven roadway design and safety analysis.

cs.SE↗

arXiv2019

Using Machine Learning and Big Data Analytics to Prioritize Outpatients in HetNets

In this paper, we introduce machine learning approaches that are used to prioritize outpatients (OP) according to their current health state, resulting in self-optimizing heterogeneous networks (HetNet) that intelligently adapt according to users' needs. We use a naïve Bayesian classifier to analyze data acquired from OPs' medical records, alongside data from medical Internet of Things (IoT) sensors that provide the current state of the OP. We use this machine learning algorithm to calculate the likelihood of a life-threatening medical condition, in this case an imminent stroke. An OP is assigned high-powered resource blocks (RBs) according to the seriousness of their current health state, enabling them to remain connected and send their critical data to the designated medical facility with minimal delay. Using a mixed integer linear programming formulation (MILP), we present two approaches to optimizing the uplink side of a HetNet in terms of user-RB assignment: a Weighted Sum Rate Maximization (WSRMax) approach and a Proportional Fairness (PF) approach. Using these approaches, we illustrate the utility of the proposed system in terms of providing reliable connectivity to medical IoT sensors, enabling the OPs to maintain the quality and speed of their connection. Moreover, we demonstrate how system response can change according to alterations in the OPs' medical conditions.

cs.CY↗