http://yetl.yabesh.ir/yetl1/handle/yetl/19002 Sat, 04 Apr 2026 02:35:54 GMT 2026-04-04T02:35:54Z http://localhost:80/yetl1/bitstream/id/184292/ http://yetl.yabesh.ir/yetl1/handle/yetl/19002 http://yetl.yabesh.ir/yetl1/handle/yetl/4309282 HangCon: Benchmark Data Set for Enhanced Detection of Hanging Objects in Construction Sites Gilsu Jeong; Seongeun Park; Joonseok Lee; Moonseo Park; Changbum R. Ahn Lifting operations on construction sites pose significant safety risks due to the potential hazard of falling objects. Effective monitoring of hanging objects is crucial for preventing accidents and ensuring worker safety. However, detecting hanging objects presents unique challenges for existing models, including the invariance in object shapes regardless of their hanging status, complex backgrounds that obscure ropes, and the diversity of hanging objects in terms of size, shape, and texture. To address these challenges, this study introduces HangCon (Hanging Objects in Construction Sites), a novel data set specifically designed for detecting “hanging objects”—loads suspended by tower cranes. HangCon contains 101,381 images, split between 50,842 images of hanging objects and 50,539 images of nonhanging objects, providing detailed annotations and diverse scenes. To evaluate HangCon’s effectiveness, this study conducted experiments using 10 benchmark models. The results highlighted the challenges in detecting hanging objects, with the best mAP at 71.63% for hanging objects alone, improving to 76.01% with unified annotations of objects and ropes. These findings highlight the complexity of detecting hanging objects and emphasize the necessity to implement advanced techniques such as semantic segmentation, depth estimation, and improved rope line detection. HangCon serves as a crucial resource for developing and refining detection models tailored to construction environments, significantly contributing to improved safety and operational efficiency on construction sites. By offering a comprehensive and well-annotated collection of images, HangCon facilitates the training and benchmarking of object detection models specifically for construction environments. Wed, 01 Jan 2025 00:00:00 GMT http://yetl.yabesh.ir/yetl1/handle/yetl/4309282 2025-01-01T00:00:00Z http://yetl.yabesh.ir/yetl1/handle/yetl/4309281 Multimodal Data Fusion and Deep Learning for Occupant-Centric Indoor Environmental Quality Classification Min Jae Lee; Ruichuan Zhang Amidst the growing recognition of the impact of indoor environmental conditions on buildings and occupant comfort, health, and well-being, there has been an increasing focus on the assessment and modeling of indoor environmental quality (IEQ). Despite considerable advancements, existing IEQ modeling methodologies often prioritize and limit to singular comfort metrics, potentially neglecting the comprehensive factors associated with occupant comfort and health. There is a need for more inclusive and occupant-centric IEQ assessment models that cover a broader spectrum of environmental parameters and occupant needs. Such models require integrating diverse environmental and occupant data, facing challenges in leveraging data across various modalities and time scales as well as understanding the temporal patterns, relationships, and trends. This paper proposes a novel framework for classifying IEQ conditions based on occupant self-reported comfort and health levels to address these challenges. The proposed framework leverages a multimodal data-fusion approach with Transformer-based models, aiming to accurately predict indoor comfort and health levels by integrating diverse data sources, including multidimensional IEQ data and multimodal occupant feedback. The framework was evaluated in classifying IEQ conditions of selected public indoor spaces and achieved 97% and 96% accuracy in comfort and health-based classifications, outperforming several baselines. Wed, 01 Jan 2025 00:00:00 GMT http://yetl.yabesh.ir/yetl1/handle/yetl/4309281 2025-01-01T00:00:00Z http://yetl.yabesh.ir/yetl1/handle/yetl/4309280 Adaptive Information Filtering Method Based on Sensitivity Analysis for Bayesian Updating Mai Cao; Quanwang Li; Xiong Xiao Bayesian updating is a powerful tool for updating engineering models with observed information. As a result of structural health monitoring sensors or platforms, up-to-date information reflecting characteristics of structures and infrastructure systems is available. However, there is usually a large amount of data collected from monitoring technologies in practical engineering, which means the associated computational cost for Bayesian updating will be considerably challenging. The lack of knowledge of observed information makes it impossible to select valuable information for updating. To overcome these limitations, this paper proposes an adaptive information filtering (AIF) method based on sensitivity analysis for Bayesian updating. Specifically, observed information is classified by means of sensitivity analysis and the information valuable to the updating target is filtered out. Moreover, the dispersion of the posterior distribution is adopted as the metric for quantifying updating effectiveness. One linear algebraic example and one case study of chloride-induced concrete corrosion considering carbonation are investigated to demonstrate the computational performance of the proposed method. Wed, 01 Jan 2025 00:00:00 GMT http://yetl.yabesh.ir/yetl1/handle/yetl/4309280 2025-01-01T00:00:00Z http://yetl.yabesh.ir/yetl1/handle/yetl/4309279 Graph Neural Network–Based Spatiotemporal Structural Response Modeling in Buildings Fangyu Liu; Yongjia Xu; Junlin Li; Linbing Wang Modeling structural responses is vital in building structural health monitoring. This study proposed the graph network–based structure simulator (GNSS), a method employing graph neural networks, for spatiotemporal structural response modeling in buildings. GNSS considered both the spatial positions and connections of structural components and the temporal correlations of time-series structural data. The entire 6-story building was represented as a graph, with nodes representing mass and edges representing columns and beams. These nodes and edges captured time-series data about structural information, responses, and ground motion. GNSS included three components: encoder, processor, and decoder. Four GNSS model variations were explored (GNSS-NE, GNSS-N2E, GNSS-NUEU, and GNSS-Full), each investigating different feature integrations and graph network architectures. To assess GNSS’s predictive performance for structural responses (displacement and acceleration) under varying test conditions, three case studies were conducted: One-Step, Rollout, and Rollout&Calibration. Among the four model variations, GNSS-NE demonstrated superior performance in predicting both displacement and acceleration across all three case studies, except for displacement prediction in the Rollout scenario. Overall, GNSS models performed best in the One-Step case study, followed by Rollout&Calibration, with the lowest performance observed in the Rollout case study. These results highlight the significant potential of GNSS for extensive application in structural response modeling by effectively integrating spatial and temporal information. Wed, 01 Jan 2025 00:00:00 GMT http://yetl.yabesh.ir/yetl1/handle/yetl/4309279 2025-01-01T00:00:00Z