Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review

B Chen, Z Zhang, N Langrené, S Zhu - arXiv preprint arXiv:2310.14735, 2023 - arxiv.org
This paper delves into the pivotal role of prompt engineering in unleashing the capabilities
of Large Language Models (LLMs). Prompt engineering is the process of structuring input …

Surface defect detection of civil structures using images: Review from data perspective

J Guo, P Liu, B Xiao, L Deng, Q Wang - Automation in Construction, 2024 - Elsevier
As civil structures age and deteriorate, it becomes crucial to conduct structural health
monitoring (SHM) to ensure safety and timely maintenance. Surface defect detection plays a …

Semantic understanding and prompt engineering for large-scale traffic data imputation

K Zhang, F Zhou, L Wu, N Xie, Z He - Information Fusion, 2024 - Elsevier
Abstract Intelligent Transportation Systems (ITS) face the formidable challenge of large-
scale missing data, particularly in the imputation of traffic data. Existing studies have mainly …

Improving visual question answering for bridge inspection by pre‐training with external data of image–text pairs

T Kunlamai, T Yamane, M Suganuma… - … ‐Aided Civil and …, 2024 - Wiley Online Library
This paper explores the application of visual question answering (VQA) in bridge inspection
using recent advancements in multimodal artificial intelligence (AI) systems. VQA involves …

Vision‐based fatigue crack automatic perception and geometric updating of finite element model for welded joint in steel structures

T Gao, Z Yuanzhou, B Ji, Z Xie - Computer‐Aided Civil and …, 2024 - Wiley Online Library
Digital twin requires establishing a self‐updated model to simulate the structural damage
perceived onsite. Despite the great success in damage identification and quantification, the …

Unsupervised Vision‐Based Structural Anomaly Detection and Localization with Reverse Knowledge Distillation

X Lei, M Sun, R Zhao, H Wu, Z Zhou… - Structural Control and …, 2024 - Wiley Online Library
Most of vision‐based methods for structural damage detection rely on supervised learning,
requiring a substantial number of labeled images for model training, which is labor‐intensive …

Automated building damage assessment and large‐scale mapping by integrating satellite imagery, GIS, and deep learning

AM Braik, M Koliou - Computer‐Aided Civil and Infrastructure …, 2024 - Wiley Online Library
Efficient and accurate building damage assessment is crucial for effective emergency
response and resource allocation following natural hazards. However, traditional methods …

Prompt Engineering: a methodology for optimizing interactions with AI-Language Models in the field of engineering

JD Velásquez-Henao, CJ Franco-Cardona… - Dyna, 2023 - revistas.unal.edu.co
ChatGPT is a versatile conversational Artificial Intelligence model that responds to user input
prompts, with applications in academia and various sectors. However, crafting effective …

A novel integration strategy for uncertain knowledge in group decision-making with artificial opinions: A DSFIT-SOA-DEMATEL approach

L Sheng, Z Gu, F Chang - Expert Systems with Applications, 2024 - Elsevier
The inherent knowledge limitations possessed by human experts often yield suboptimal
accuracy in linguistic decisions within traditional Decision Making Experimentation and …

Monocular 3D object detection for construction scene analysis

J Shen, L Jiao, C Zhang, K Peng - Computer‐Aided Civil and …, 2024 - Wiley Online Library
Abstract Three‐dimensional (3D) object detection, that is, localizing and classifying all
critical objects in a 3D space, is essential for downstream construction scene analysis tasks …