Article
Chemistry, Analytical
Daegyun Choi, William Bell, Donghoon Kim, Jichul Kim
Summary: Structural cracks are crucial in assessing the health of aging structures. This study proposes a framework for detecting and locating cracks using image data from a UAV and a deep learning model, showcasing an effective way to identify cracks and their positions.
Article
Chemistry, Analytical
Chendong Zhu, Junqing Zhu, Tianxiang Bu, Xiaofei Gao
Summary: This research aims to integrate UAVs and AI to establish a UAV-based road construction safety monitoring platform. The study proposes flight and photography schemes based on the UAV platform for information collection, and utilizes deep learning algorithms to automatically detect and track safety factors. A road construction dataset with 3594 images is established. The results show that the UAV-based monitoring platform can help managers with security inspection and recording images.
Article
Agronomy
Shanxin Zhang, Hao Feng, Shaoyu Han, Zhengkai Shi, Haoran Xu, Yang Liu, Haikuan Feng, Chengquan Zhou, Jibo Yue
Summary: Soybean breeders need different varieties for planting at different latitudes, and timely monitoring of soybean breeding line maturity is crucial for soybean harvesting management. A new convolutional neural network (CNN) called DS-SoybeanNet is designed to improve the performance of unmanned aerial vehicle (UAV)-based soybean maturity monitoring. DS-SoybeanNet can extract and utilize both shallow and deep image features.
Article
Ecology
Farian S. Ishengoma, Idris A. Rai, Said Rutabayiro Ngoga
Summary: This study proposes a hybrid convolutional neural network model that combines UAV technology and VGG16 with InceptionV3 models for accelerated detection of fall armyworm-infested maize leaves. Comparisons show that the proposed hybrid model outperforms four existing CNN models in terms of accuracy and training time.
ECOLOGICAL INFORMATICS
(2022)
Article
Geochemistry & Geophysics
Yueming Sun, Zhenfeng Shao, Gui Cheng, Xiao Huang, Zhongyuan Wang
Summary: The study proposes a lightweight and efficient dual contextual parsing network (EDCPNet) to address the challenges of conducting urban traffic information extraction using UAV images. The network surpasses competing methods in car and road extraction from UAV images, demonstrating superior performance and adaptability in complex urban scenes.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Multidisciplinary Sciences
Wenxiao Xu, Shengguang Chu, Shanshan Yang
Summary: This paper proposes a double branch fusion network based on UAV inspection images to improve the detection accuracy of vital components and defects in transmission lines. The network consists of a combination of a convolutional neural network (CNN) and a Transformer network, which extract local and global information respectively. To solve the semantic differences and feature aliasing problem, the paper introduces multiscale convolution and pooling modules. The network also includes a residual-like convolution module and performs feature fusion in multiple regions to enhance the multi-scale adaptability.
ADVANCED THEORY AND SIMULATIONS
(2023)
Article
Automation & Control Systems
Yuanda Wang, Wenzhang Liu, Jian Liu, Changyin Sun
Summary: This paper investigates the visual navigation and control of a cooperative USV-UAV system for marine search and rescue. A deep learning-based visual detection architecture is developed to extract positional information from UAV images, improving accuracy and efficiency. A reinforcement learning-based USV control strategy is proposed, which can learn a motion control policy with enhanced disturbance rejection ability. Simulation results show stable and accurate position estimation and satisfactory control ability under wave disturbances.
Article
Environmental Sciences
Peng Yang, Kamran Esmaeili, Sebastian Goodfellow, Juan Carlos Ordonez Calderon
Summary: Geological pit wall mapping in surface mining is important for improving geological certainty and operational planning. This study explores the use of drone-acquired RGB images for pit wall mapping. While the results are promising for simple geological settings, they deviate from human-labelled ground truth maps in more complex conditions, highlighting the need for further algorithm optimization for robustness.
Article
Chemistry, Multidisciplinary
Jiri Maslan, Ludek Cicmanec
Summary: This study explores the automatic detection and evaluation of distress on an airport pavement using unmanned aerial vehicle imagery and artificial intelligence. The YOLOv2 object detector is used for crack detection and the obtained features are processed for position determination and dimension measurement. The study successfully verifies the system on the experimental section of the runway, demonstrating the efficiency and impressive results of unmanned aerial vehicle imagery combined with artificial intelligence.
APPLIED SCIENCES-BASEL
(2023)
Article
Environmental Sciences
Yuyun Pan, Nengzhi Zhu, Lu Ding, Xiuhua Li, Hui-Hwang Goh, Chao Han, Muqing Zhang
Summary: This study proposes a method based on improved Faster RCNN for automatically detecting and counting sugarcane seedlings using aerial photography. The proposed method outperforms other commonly used detection models and a seedlings de-duplication algorithm is further proposed to eliminate counting errors.
Article
Environmental Sciences
Lele Wei, Yusen Luo, Lizhang Xu, Qian Zhang, Qibing Cai, Mingjun Shen
Summary: In this paper, UAV and YOLOv4 deep neural network were used to detect mature rice ears and generate rice density prescription maps. The study showed that the CNN model had excellent robustness and accuracy in detecting rice in different health states.
Article
Agronomy
Ryoya Tanabe, Tsutomu Matsui, Takashi S. T. Tanaka
Summary: An inexpensive and precise crop yield prediction technology is required for small-scale fields in Asian countries. The effectiveness of convolutional neural networks (CNNs) for crop yield prediction was verified using UAV-based multispectral imagery. The results showed that the CNN model of the heading stage had the lowest RMSE among the four growth stages and outperformed the best linear regression model. These findings suggest that CNN has the potential to improve accuracy, and the heading stage is a suitable data acquisition time for winter wheat.
FIELD CROPS RESEARCH
(2023)
Article
Chemistry, Analytical
Szu-Yueh Yang, Hsin-Che Jan, Chun-Yu Chen, Ming-Shyan Wang
Summary: This paper proposes a warehouse management system based on an unmanned aerial vehicle (UAV) that scans QR codes on packages. The UAV consists of a quadcopter drone and various sensors and components. By employing convolutional neural networks (CNNs), the system accurately identifies the placement angle of the package. Optimizations are applied to improve system performance, and image processing techniques are used when the package is not placed correctly. Experimental results demonstrate a high recognition rate for QR code reading.
Article
Forestry
Yan Zhou, Wenping Liu, Haojie Bi, Riqiang Chen, Shixiang Zong, Youqing Luo
Summary: This study proposes a deep learning-based multi-band image fusion method for detecting infected pine trees and determining different infection stages. Experimental results show that the method can accurately detect infected pine trees, especially those in the early stage, and improve the early warning ability of Pine Wilt Disease (PWD).
Article
Computer Science, Information Systems
Fei Jiang, Feifei Yu, Canyi Du, Yicong Kuang, Zhaoqian Wu, Kang Ding, Guolin He
Summary: In this study, a novel dual attention convolutional neural network based on multisensory frequency features is proposed for UAV rotor fault diagnosis. The method analyzes time and frequency features in different health states and uses a dual attention mechanism to improve fault diagnosis accuracy. Experimental results demonstrate the superiority of the proposed method, with higher fault diagnosis accuracy for frequency features.
Article
Engineering, Industrial
Mengqi Yuan, Zhongfu Li, Xiaodong Li, Xiaowei Luo, Xianfei Yin, Jin Cai
Summary: This study proposes a multifaceted model for explaining practitioners' adoption behavior of prefabricated construction (PC) technology. The findings indicate that relative advantage, corporate social responsibility, market demand, regulatory support, and trading partner support are important factors influencing the adoption of PC technology.
ENGINEERING CONSTRUCTION AND ARCHITECTURAL MANAGEMENT
(2023)
Review
Construction & Building Technology
Yuexiong Ding, Jie Ma, Xiaowei Luo
Summary: This article reviews the application of Natural Language Processing (NLP) in the construction industry and highlights the issue of data isolation. It suggests that more interdisciplinary research is needed for future development.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Green & Sustainable Science & Technology
Mengqi Yuan, Zhongfu Li, Xiaodong Li, Long Li, Shengxi Zhang, Xiaowei Luo
Summary: This research, based on evolutionary game theory, explores the behavioral strategies and stable strategies of three stakeholders in the PRB industry, including the government, real estate developers, and homebuyers. The study found that the government plays a leadership role in the initial stage, gradually decreasing its intervention in the PRB market as the industry matures.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Construction & Building Technology
Guangchong Chen, Jiayu Chen, Yuchun Tang, Qiming Li, Xiaowei Luo
Summary: This study systematically identified effective collaborative behaviors in BIM-enabled construction projects (BECPs) through interviews with 34 BECPs. The findings revealed that adaptation to customized BIM use, integrated coordination, integrated communication, shared responsibility to reduce conflicts, and flexibility to support the team were effective collaborative behaviors. Additionally, a theoretical model was established to describe how these behaviors combined for effective BIM use.
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT
(2022)
Article
Environmental Sciences
M. Sadeghi, A. Mahmoudi, X. Deng, X. Luo
Summary: The synergy between blockchain technology and circular economy can achieve sustainable development in terms of economy, environment, and society. Prioritized requirements for implementing blockchain in the construction supply chain were determined using the Fuzzy Ordinal Priority Approach (Fuzzy OPA). The results emphasize the importance of developing circular economy attributes, considering intra-organizational factors, and meeting technological requirements and collaboration infrastructure.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
(2023)
Article
Green & Sustainable Science & Technology
Muyang Liu, Xiaowei Luo, Wei-Zhen Lu
Summary: This study explores the general public's perceptions of environmental, social, and governance (ESG) in China using a social media analytics framework. The results reveal regional and industry-specific disparities in ESG-conscious users. The topics discussed on Sina Weibo include ESG investment, ESG disclosure, ESG rating, and ESG notion and practice. The study also identifies positive, neutral, and negative sentiments towards ESG, highlighting issues such as greenwashing, lack of ESG knowledge, inconsistent ratings, and transparency in rating methods. The findings provide valuable insights for policymakers and corporations to understand public needs and improve ESG communication and policies.
JOURNAL OF CLEANER PRODUCTION
(2023)
Review
Construction & Building Technology
Jinpeng Wang, Shang Zhang, Peter Fenn, Xiaowei Luo, Yan Liu, Lilin Zhao
Summary: By conducting a critical literature review, this study examines the adoption of Building Information Modeling (BIM) to enhance effective dispute management in the construction industry. The findings identify common causes of disputes and primary benefits of BIM application, and propose a conceptual framework illustrating the mechanism of adopting BIM in dispute management.
JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT
(2023)
Article
Engineering, Environmental
Muhammad Shafique, Arslan Akbar, Muhammad Rafiq, Anam Azam, Xiaowei Luo
Summary: The global market for battery electric vehicles (BEVs) is continuously increasing, resulting in higher demand for Li-ion batteries (LIBs). This study analyses the global distribution of end-of-life (EOL) lithium nickel manganese cobalt (NMC) oxide batteries from BEVs and predicts the flow of NMC battery materials worldwide. The study also estimates the economic value of recovered materials, highlighting the importance of setting up large-scale recycling infrastructures.
WASTE MANAGEMENT & RESEARCH
(2023)
Article
Engineering, Electrical & Electronic
Zhuang Zheng, Shengwei Wang, Wenzhuo Li, Xiaowei Luo
Summary: This paper proposes a novel voltage control strategy that regulates the on/off states of AC clusters to address voltage issues caused by high PV penetrations. The strategy includes temperature priority-based on/off control, real-time optimal demand response resources dispatch, distributed sensing of ACs, and flexibility capacity estimation. The strategy is validated to be effective and scalable, and is incorporated into a hierarchical control framework for smart grid voltage control.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Engineering, Industrial
Lili Gao, Xiaowei Luo, Weimin Yang, Na Zhang, Xiaopeng Deng
Summary: This paper explores the influence of social support on the repatriation intention of expatriates in the international construction industry in the post-COVID-19 era. It also examines the mediation effect of team climate and individual resilience in this relationship. The findings suggest that social support enhances the team climate of construction expatriates, thus reducing their repatriation intention. This study contributes to the literature on expatriate management by establishing the link between social support and repatriation intention.
ENGINEERING CONSTRUCTION AND ARCHITECTURAL MANAGEMENT
(2023)
Review
Construction & Building Technology
Ming Zhang, Rui Xu, Haitao Wu, Jia Pan, Xiaowei Luo
Summary: The rapid development of robotic technology enables human-robot collaboration (HRC) in the construction industry. HRC systems combining robot intelligence and human skills can enhance productivity and safety. However, research on the status, challenges, and emerging trends of HRC in construction is limited. This systematic review of 110 relevant articles provides insights into HRC, including quantitative analysis of robot types, construction activities, and interaction roles, and identifies significant research themes in adaptive robot programming, human-robot interaction interface, and safety issues.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Engineering, Industrial
Yanliang Niu, Huimin Li, Xiaowei Luo, Xiaopeng Deng
Summary: This study aims to determine various combinations of three coopetition constructs (coopetition relationship, coopetition capability and coopetition strategy) that lead to high-performance in international joint ventures for high-speed rail projects. The results show that there are six coopetition configurations that lead to common benefits and seven configurations that lead to private benefits. The optimal coopetition strategies also vary in different contexts.
ENGINEERING CONSTRUCTION AND ARCHITECTURAL MANAGEMENT
(2023)
Article
Construction & Building Technology
Qi Li, Jiayu Chen, Xiaowei Luo
Summary: This study focuses on the vertical wind conditions as a main external factor that limits the energy assessment of high-rise buildings in urban areas. Traditional tools for energy assessment of buildings use a universal vertical wind profile estimation, without taking into account the unique wind speed in each direction induced by the various shapes and configurations of buildings in cities. To address this limitation, the study developed an omnidirectional urban vertical wind speed estimation method using direction-dependent building morphologies and machine learning algorithms.
ENERGY AND BUILDINGS
(2024)
Article
Green & Sustainable Science & Technology
Jing Cheng, Xiaowei Luo
Summary: This paper investigates the urban function renewal in Shenzhen, China using a complex network method. The study identifies the dominant urban functions in each district based on points of interest and location quotient, and analyzes the interdependence of these functions. The results show that hotels and life services are crucial for the planning and development in Shenzhen, and districts with higher economic levels face greater difficulty in urban function renewal.
Proceedings Paper
Computer Science, Artificial Intelligence
Shijie Lin, Yinqiang Zhang, Lei Yu, Bin Zhou, Xiaowei Luo, Jia Pan
Summary: Focus control is crucial for cameras, but event cameras lack effective autofocus methods. To address this, researchers have developed a novel event-based autofocus framework using event rate and event-based golden search to achieve accurate focus adjustments.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)