INFRASTRUCTURE SENSOR-ENABLED VEHICLE DA T A GENERA TION USING MUL TI-SENSOR FUSION FOR PROACTIVE SAFETY APPLICA TIONS A T WORK ZONE Suhala Rabab Saba Department of Civil, Construction & Environmental Engineering, The University of Alabama Smart Communities and Innovation Building (SCIB), 28 Kirkbride Lane, Tuscaloosa, AL 35487-0288 Email: ssaba@crimson.ua.edu Saba, Khan, Ahmad, Cao, Rahman, Zhao, Huynh, and Ozguven 3 ABSTRACT Infrastructure-based sensing and real-time trajectory generation hold significant promise for improving safety in high-risk roadway segments like work zones, yet practical deployments are hindered by perspective distortion, complex geometry, occlusions, and costs. This study tackles these barriers by (i) integrating roadside camera and LiDAR sensors into a cosimulation environment to develop a scalable, cost-effective vehicle detection and localization framework, and (ii) employing a Kalman Filter-based late fusion strategy to enhance trajectory consistency and accuracy. In simulation, the fusion algorithm reduced longitudinal error by up to 70% compared to individual sensors while preserving lateral accuracy within 1-3 meters. Field validation in an active work zone, using LiDAR, a radar-camera rig, and RTK-GPS as ground truth, demonstrated that the fused trajectories closely match real vehicle paths, even when single-sensor data are intermittent or degraded. These results confirm that KF based sensor fusion can reliably compensate for individual sensor limitations, providing precise and robust vehicle tracking capabilities. Our approach thus offers a practical pathway to deploy infrastructure-enabled multi-sensor systems for proactive safety measures in complex traffic environments. Keywords: work zone, fusion, lidar, camera, localization, safety Saba, Khan, Ahmad, Cao, Rahman, Zhao, Huynh, and Ozguven 4 INTRODUCTION Work zone crashes do not necessarily impact only the vehicles and people directly involved; instead, they have cascading effects that cause operational delays for passing vehicles and project completion delays for work zone contractors. The Federal Motor Carrier Safety Administration (FMCSA) report indicates that commercial motor vehicles (CMVs) are involved in one-third of work zone fatal crashes, although they represent only 5% of all vehicular traffic (1). In addition, speed is a contributing factor in 26% of all fatal work zone crashes (2). According to Jiao (2022) (3), 13% of CMV drivers are fatigued when they are involved in crashes.

When you purchase through links in our articles, we may earn a small commission. AMD's AI plans have only just begun. If you've been wondering when the "AI" branding spigot might be turned down a notch, AMD's answer is that it won't be anytime soon. At an AMD breakfast at IFA 2025 this week, Jack Huynh, senior vice president and general manager of AMD's Computing and Graphics Group, said that AMD will continue to promote its AI capabilities as much as it can. Huynh also shrugged off a report that AMD -- and everyone else, really -- is being obliterated by Nvidia's dominance in the desktop GPU market.

Proactive safety systems aim to mitigate risks by anticipating potential conflicts between vehicles and enabling early intervention to prevent work zone-related crashes. This study presents an infrastructure-enabled proactive work zone safety warning system that leverages a Digital Twin environment, integrating real-time multi-sensor data, detailed High-Definition (HD) maps, and a historical prediction attention mechanism-based trajectory prediction model. Using a co-simulation environment that combines Simulation of Urban MObility (SUMO) and CAR Learning to Act (CARLA) simulators, along with Lanelet2 HD maps and the Historical Prediction Network (HPNet) model, we demonstrate effective trajectory prediction and early warning generation for vehicle interactions in freeway work zones. To evaluate the accuracy of predicted trajectories, we use two standard metrics: Joint Average Displacement Error (ADE) and Joint Final Displacement Error (FDE). Specifically, the infrastructure-enabled HPNet model demonstrates superior performance on the work-zone datasets generated from the co-simulation environment, achieving a minimum Joint FDE of 0.3228 meters and a minimum Joint ADE of 0.1327 meters, lower than the benchmarks on the Argoverse (minJointFDE: 1.0986 m, minJointADE: 0.7612 m) and Interaction (minJointFDE: 0.8231 m, minJointADE: 0.2548 m) datasets. In addition, our proactive safety warning generation application, utilizing vehicle bounding boxes and probabilistic conflict modeling, demonstrates its capability to issue alerts for potential vehicle conflicts.

Ensuring transparency in AI decision-making requires interpretable explanations, particularly at the instance level. Counterfactual explanations are a powerful tool for this purpose, but existing techniques frequently depend on synthetic examples, introducing biases from unrealistic assumptions, flawed models, or skewed data. Many methods also assume full dataset availability, an impractical constraint in real-time environments where data flows continuously. In contrast, streaming explanations offer adaptive, real-time insights without requiring persistent storage of the entire dataset. This work introduces a scalable, model-free approach to selecting diverse and relevant counterfactual examples directly from observed data. Our algorithm operates efficiently in streaming settings, maintaining $O(\log k)$ update complexity per item while ensuring high-quality counterfactual selection. Empirical evaluations on both real-world and synthetic datasets demonstrate superior performance over baseline methods, with robust behavior even under adversarial conditions.

Recommender systems rely on Collaborative Filtering (CF) to predict user preferences by leveraging patterns in historical user-item interactions. While traditional CF methods primarily focus on learning compact vector embeddings for users and items, graph neural network (GNN)-based approaches have emerged as a powerful alternative, utilizing the structure of user-item interaction graphs to enhance recommendation accuracy. However, existing GNN-based models, such as LightGCN and UltraGCN, often struggle with two major limitations: an inability to fully account for heterophilic interactions, where users engage with diverse item categories, and the over-smoothing problem in multi-layer GNNs, which hinders their ability to model complex, high-order relationships. To address these gaps, we introduce WaveHDNN, an innovative wavelet-enhanced hypergraph diffusion framework. WaveHDNN integrates a Heterophily-aware Collaborative Encoder, designed to capture user-item interactions across diverse categories, with a Multi-scale Group-wise Structure Encoder, which leverages wavelet transforms to effectively model localized graph structures. Additionally, cross-view contrastive learning is employed to maintain robust and consistent representations. Experiments on benchmark datasets validate the efficacy of WaveHDNN, demonstrating its superior ability to capture both heterophilic and localized structural information, leading to improved recommendation performance.

In today's fast-evolving business landscape, having insight into the technology stacks that organizations use is crucial for forging partnerships, uncovering market openings, and informing strategic choices. However, conventional technology mapping, which typically hinges on keyword searches, struggles with the sheer scale and variety of data available, often failing to capture nascent technologies. To overcome these hurdles, we present STARS (Semantic Technology and Retrieval System), a novel framework that harnesses Large Language Models (LLMs) and Sentence-BERT to pinpoint relevant technologies within unstructured content, build comprehensive company profiles, and rank each firm's technologies according to their operational importance. By integrating entity extraction with Chain-of-Thought prompting and employing semantic ranking, STARS provides a precise method for mapping corporate technology portfolios. Experimental results show that STARS markedly boosts retrieval accuracy, offering a versatile and high-performance solution for cross-industry technology mapping.

For months, internet rumor mills have claimed that AMD's next-generation Radeon RX 8000 graphics cards would cede the high-end market to Nvidia's GeForce lineup, after the GeForce RTX 4090 stomped all over the competition this time around. Now, AMD's senior VP and general manager of the computing and graphics group, Jack Huynh, all but confirmed it when he responded to Tom's Hardware's question about whether Radeon will compete with Nvidia at the "top of the stack": "My number one priority right now is to build scale, to get us to 40 to 50 percent of the market faster. Do I want to go after 10 percent of the TAM [Total Addressable Market] or 80 percent? I'm an 80 percent kind of guy because I don't want AMD to be the company that only people who can afford Porsches and Ferraris can buy. We want to build gaming systems for millions of users. Yes, we will have great, great, great products. But we tried that strategy [King of the Hill] -- it hasn't really grown. ATI has tried this King of the Hill strategy, and the market share has kind of been… the market share. I want to build the best products at the right system price point. So, think about price point-wise; we'll have leadership."

Former Obama-Biden fundraiser Allison Huynh joins'Jesse Watters Primetime' to discuss her'divorce' from the Democratic Party and why she is auctioning off her million-dollar Obama'Hope' poster. An ex-Obama fundraiser who helped raise millions in donations for his campaign announced that she is "divorcing" the Democratic Party and plans to vote for Trump in the upcoming election. "Like any divorce, there's not just one thing, there's a series of things that led up to it," Allison Huynh said on "Jesse Watters Primetime" Wednesday. Huynh, who created Willow Garage, a company that created robotics and AI systems which were later sold to Google, along with her then-husband Google programmer Scott Hassan, helped raise millions of dollars for the Obama campaign in 2008 by hosting elaborate " 50,000- and 100,000-per-plate dinners," for Silicon Valley giants, the New York Post reported. Allison Huynh attends FORMS Opening Reception Presented by Gagosian and Jeffrey Deitch at Miami Design District on December 5, 2023, in Miami, Florida.

Alternative data vendor QuantCube has created a slew of environmental intelligence products using satellite data sourced from the European Space Agency combined with other alternative data sources. As well as creating four environmental and social economic indicator services, the Paris-based company has also incorporated the new information into its benchmarking and analytical overlays. The offerings are the fruit of a two-year collaboration with the European Space Agency (ESA) and the French Space Agency (CNES), which gave the company access to its Earth observation data through its business application programme. Using data beamed from the Copernicus programme's Sentinel satellites, QuantCube is providing its clients with four environmental indicators at macro-level: The data is processed by artificial intelligence software after being harvested from orbiting technology that can take detailed images down to 30 square centimetres on the Earth's surface. Satellite technology can also identify concentrations of greenhouse gases and pollutants, including carbon dioxide (CO2), nitrogen dioxide (NO2) and sulphur dioxide (SO2).

When Tam Mai Huynh found out in 2016 that the source of his nagging cough was lung cancer, it came as a shock. A recently retired Army Special Forces veteran and married father of two young children, Huynh never had smoked. Nor did he have a family history of cancer. Nevertheless, the disease had spread to Huynh's spine, lymph nodes, and brain. He began chemotherapy, driving two hours every two to three weeks from his home to the U.S. Department of Veterans Affairs (VA) hospital in Durham, North Carolina.