Article
Chemistry, Analytical
Elham Eslami, Hae-Bum Yun
Summary: The paper introduces an attention-based multi-scale convolutional neural network (A+MCNN) that improves the automated classification of pavement distress in road surface images by encoding contextual information and employing a mid-fusion approach with an attention module. A+MCNN outperforms other deep classifiers by 1 to 26% in terms of the F-score, showing its effectiveness in recognizing different types of distress and non-distress objects on roads.
Article
Construction & Building Technology
R. A. Pietersen, M. S. Beauregard, H. H. Einstein
Summary: This paper presents a method for partially automated airfield pavement condition assessment using drone mounted imaging technology, which shows strong agreement with manual inspection results. This indicates that automation of pavement evaluation is achievable using drone-captured images and machine learning.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Computer Science, Hardware & Architecture
Swadesh Jana, Asif Iqbal Middya, Sarbani Roy
Summary: This paper attempts to classify road surface images using transfer learning on pre-trained convolution neural network models. Among all the deep CNN models, SEResNet-50, Xception, and DenseNet-121 achieve the best performance in terms of the evaluation metrics. The effectiveness of the deep CNN models is also evaluated on benchmark datasets.
MOBILE NETWORKS & APPLICATIONS
(2023)
Review
Construction & Building Technology
Abdulnaser M. Al-Sabaeei, Mena I. Souliman, Ajayshankar Jagadeesh
Summary: Smartphones have the potential to be used for efficient and cost-effective pavement condition monitoring (PCM), but further research and development are needed. The challenge lies in ensuring the accuracy of the collected data.
CONSTRUCTION AND BUILDING MATERIALS
(2024)
Article
Computer Science, Information Systems
Jing Zheng, Ziren Gao, Jingsong Ma, Jie Shen, Kang Zhang
Summary: The study demonstrates the importance of road network selection in cartographic generalization. It introduces the use of graph convolutional networks (GCNs) for automatic road network selection, showing that the graph attention networks (GAT) provide better results compared to other models. Additionally, different deep architectures can effectively improve the selection effect of models, with JK-Nets demonstrating higher accuracy in the selection process.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Chemistry, Analytical
Dapeng Dong, Zili Li
Summary: This study used smartphones to collect road surface condition information, achieving an accuracy of 84% in defect detection through machine learning algorithms, demonstrating the potential of crowdsourced data in road maintenance.
Article
Engineering, Civil
Mida Cui, Gang Wu, Ji Dang, Zhiqiang Chen, Minghua Zhou
Summary: This paper develops a dataset with engineering-meaningful condition labels and benchmarks the performance of computer vision methods and convolutional neural networks (CNNs) for automatic elastomeric-bearing condition assessment. Different CNN architectures and transfer learning techniques are evaluated, and the authors conclude that CNN models with fully fine-tuned transfer learning techniques show promising performance for real-world applications.
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2022)
Article
Remote Sensing
Stefano Puliti, Rasmus Astrup
Summary: The assessment of forest abiotic damages, such as snow breakage, is crucial for compensating forest owners. Traditional field surveys are time-consuming and biased, but the use of unmanned aerial vehicles (UAVs) and computer vision techniques has provided a more efficient and objective method. This study proposed an object detection method based on the YOLO CNN architecture to automatically identify and classify trees according to snow damage. The model performed well across different conditions and seasons, with high precision and recall for detecting snow damaged trees.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Review
Chemistry, Analytical
Eshta Ranyal, Ayan Sadhu, Kamal Jain
Summary: This paper provides an exhaustive literature review of road condition monitoring (RCM) technologies published from 2017 to 2022. It discusses the methodologies, contributions, limitations, and the role of smart sensors and data acquisition platforms in RCM systems. The paper also highlights the challenges in developing AI technologies and suggests potential areas for further exploration.
Article
Engineering, Electrical & Electronic
Tamilarasi Rajamani, Prabu Sevugan, Sathyaraj Ragupathi
Summary: Hyperspectral imagery provides detailed spectral information through numerous spectral bands, which poses a challenge for traditional methods due to the curse of dimensionality. In this study, a convolutional neural network (CNN) based technique is proposed for automated building footprint extraction and road detection from hyperspectral imagery. The CNN is used to classify spectral features, achieving a classification accuracy of 97%.
JOURNAL OF ELECTRONIC IMAGING
(2023)
Article
Multidisciplinary Sciences
Meshkat Botshekan, Erfan Asaadi, Jake Roxon, Franz-Josef Ulm, Mazdak Tootkaboni, Arghavan Louhghalam
Summary: This study develops a framework that combines vehicle dynamics, random vibration theory, and two-layer inverse analysis to estimate road roughness using in-cabin recordings of a vehicle's vertical acceleration measured by a smartphone. The framework links the frequency spectrum of the vehicle's vertical acceleration to the road roughness power spectral density for quantitative characterization of roughness-induced energy dissipation. The framework's critical crowdsourcing features and transferability were examined and its utility in identifying vehicle classes on roadway networks through big data analytics was demonstrated.
PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2021)
Article
Computer Science, Interdisciplinary Applications
Guangwei Yang, Kelvin C. P. Wang, Joshua Qiang Li, Yue Fei, Yang Liu, Kamyar C. Mahboub, Allen A. Zhang
Summary: This study presents a CNN-based PvmtTPNet to automatically recognize pavement types with high levels of consistency, accuracy, and speed. By training and testing on a large dataset of pavement images, the network achieved excellent performance in identifying different pavement types.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2021)
Article
Computer Science, Information Systems
Burak Ekim, Elif Sertel, M. Erdem Kabadayi
Summary: Historical maps are scanned from various sources and automatic geographical feature extraction is conducted using deep learning to derive valuable spatial information. By digitizing and labeling different road types, the study achieved remarkable results with an overall accuracy of 98.73%.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Computer Science, Artificial Intelligence
Wajdi Elhamzi, Wadhah Ayadi, Mohamed Atri
Summary: This article introduces a new brain tumor segmentation method based on deep learning, which uses Convolutional Neural Networks to automatically and accurately segment MRI images. The method shows good performance in the tests, with high segmentation accuracy for different tumor regions.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Remote Sensing
Erik Rua, Anton Nunez-Seoane, Pedro Arias, Joaquin Martinez-Sanchez
Summary: The transport infrastructure plays a crucial role in the economic development and quality of life improvement in a country. This article focuses on the rockfall hazard on roads and proposes a methodology to estimate the invaded road area in case of a rockfall. The methodology combines LiDAR point cloud analysis and RockGIS software to remotely identify and assess the danger levels of road slopes.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Article
Environmental Sciences
Vijendra Singh Bramhe, Sanjay Kumar Ghosh, Pradeep Kumar Garg
GEOCARTO INTERNATIONAL
(2020)
Article
Environmental Sciences
Veerendra Yadav, Sanjay Kumar Ghosh
Summary: This study assessed the land use and land cover changes in Chennai using temporal Landsat data and various analytical methods to study the impact of urbanization. The results showed a growing trend in the urban area of Chennai, with the prediction model indicating that vegetation and barren land will continue to be converted into urban land in the coming decades.
GEOCARTO INTERNATIONAL
(2021)
Article
Environmental Sciences
Rashmi Saini, Sanjay Kumar Ghosh
Summary: This study successfully identified major crops in the Roorkee, India using Sentinel-2A data, with Xgboost showing the best performance for crop mapping and support vector machine (SVM) performing the worst. Major crops, such as wheat and sugarcane, were accurately classified with high accuracy rates.
GEOCARTO INTERNATIONAL
(2021)
Article
Environmental Sciences
Atul Kant Piyoosh, Sanjay Kumar Ghosh
Summary: A new spectral index NRUI(ms) has been proposed for assessing LULC changes in Dehradun, India using Landsat satellite data. The NRUI(ms) showed better separability compared to other indices for the fallow-urban class pair. Significant LULC changes were observed during the period 1991-2019, with unprecedented urban growth and conversion of vegetated areas into non-vegetated areas.
GEOCARTO INTERNATIONAL
(2022)
Article
Multidisciplinary Sciences
Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Yoshihide Sekimoto
Summary: The RDD2020 dataset includes road images from India, Japan, and the Czech Republic, totaling 26,336, capturing 4 types of road damage, aiming to develop deep learning methods to automatically detect and classify road damage, which can be used for developing low-cost methods for monitoring road pavement conditions.
Article
Instruments & Instrumentation
Surendra Singh Choudhary, S. K. Ghosh
Summary: This study utilizes satellite images to accurately extract and calculate surface water area. It compares the accuracy of different water indices and uses a semi-automatic method to obtain optimum threshold values and classify water indices. The results show that NDWI provides the best surface water area outputs.
SENSING AND IMAGING
(2022)
Article
Environmental Sciences
Sumit Kumar, Sanjay Kumar Ghosh, Brijendra Pateriya
Summary: The vegetation fire patterns and burning trends in the Indo-Gangetic Region have shifted from forest and shrubland to cropland. Fire counts have increased by 2.6 times over the past 20 years, and there has been a shift in the burning season.
GEOCARTO INTERNATIONAL
(2022)
Article
Meteorology & Atmospheric Sciences
Surendra Singh Choudhary, S. K. Ghosh
Summary: The uncertainty of climatic variations presents a challenge for human adaptation. Despite technological developments for predicting and forecasting climate behavior, uncertainty of atmospheric and geoprocesses hinders efforts in dealing with disasters. It is crucial to understand future atmospheric uncertainty and predict climatic variations for analysis and decision-making. This study focuses on developing a model trained with rainfall and temperature data to support climatic predictions and adaptation to adverse situations.
THEORETICAL AND APPLIED CLIMATOLOGY
(2023)
Article
Environmental Sciences
Surendra Singh Choudhary, S. K. Ghosh
Summary: The Long Short Term Memory model of Deep Learning is applied to predict reservoir outflow using rainfall, rainfall intensity, runoff rate, temperature, surface water area, and reservoir outflow. This study analyzes the effect of parameter settings on model performance and identifies the main factors influencing reservoir outflow prediction. The proposed model can accurately and efficiently predict multiple parameters.
MODELING EARTH SYSTEMS AND ENVIRONMENT
(2023)
Proceedings Paper
Engineering, Aerospace
D. S. Vohra, P. K. Garg, S. K. Ghosh
Summary: Drones are used for various activities and require long flying time, which depends on the LiPo batteries used. This paper will discuss how to choose the right LiPo battery pack for drones, the working principle of LiPo batteries, different forms/configurations and cell sizes, maintenance, and alternatives such as charging stations, charging drones while in flight, and the use of solar voltaic cells.
PROCEEDINGS OF UASG 2021: WINGS 4 SUSTAINABILITY
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Deeksha Arya, Sanjay Kumar Ghosh, Durga Toshniwal
Summary: The doctoral work discussed in this summary applies Artificial Intelligence (AI) for social good, aiming to achieve low-cost and faster monitoring of road conditions across different nations for safer roads. Furthermore, the study provides recommendations for utilizing road image data and Deep Learning models from one country to detect road damage in other countries.
THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, Hiroshi Omata, Takehiro Kashiyama, Yoshihide Sekimoto
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2020)
Article
Construction & Building Technology
Jia Liang, Qipeng Zhang, Xingyu Gu
Summary: A lightweight PCSNet-based segmentation model is developed to address the issues of insufficient performance in feature extraction and boundary loss information. The introduction of generalized Dice loss improves prediction performance, and the visualization of class activation mapping enhances model interpretability.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Gilsu Jeong, Minhyuk Jung, Seongeun Park, Moonseo Park, Changbum Ryan Ahn
Summary: This study introduces a contextual audio-visual approach to recognize multi-equipment activities in tunnel construction sites, improving monitoring effectiveness. Tested against real-world operation data, the model achieved remarkable results, emphasizing the potential of contextual multimodal models in enhancing operational efficiency in complex construction sites.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Jin Wang, Zhigao Zeng, Pradip Kumar Sharma, Osama Alfarraj, Amr Tolba, Jianming Zhang, Lei Wang
Summary: This study presents a dual-path network for pavement crack segmentation, combining Convolutional Neural Network (CNN) and transformer. A lightweight CNN encoder is used for local feature extraction, while a novel transformer encoder integrates high-low frequency attention mechanism and efficient feedforward network for global feature extraction. Additionally, a complementary fusion module is introduced to aggregate intermediate features extracted from both encoders. Evaluation on three datasets confirms the superior performance of the proposed network.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Pierre Gilibert, Romain Mesnil, Olivier Baverel
Summary: This paper introduces a flexible method for crafting 2D assemblies adaptable to various geometric assumptions in the realm of sustainable construction. By utilizing digital fabrication technologies and optimization approaches, precise control over demountable buildings can be achieved, improving mechanical performance and sustainability.
AUTOMATION IN CONSTRUCTION
(2024)
Review
Construction & Building Technology
Jorge Loy-Benitez, Myung Kyu Song, Yo-Hyun Choi, Je-Kyum Lee, Sean Seungwon Lee
Summary: This paper discusses the advancement of tunnel boring machines (TBM) through the application of artificial intelligence. It highlights the significance of AI-based management subsystems for automatic TBM operations and presents recent contributions in this field. The paper evaluates modeling, monitoring, and control subsystems and suggests research paths for integrating existing management subsystems into TBM automation.
AUTOMATION IN CONSTRUCTION
(2024)
Review
Construction & Building Technology
Alireza Shamshiri, Kyeong Rok Ryu, June Young Park
Summary: This paper reviews the application of text mining and natural language processing in the construction field, highlighting the need for automation and minimizing manual tasks. The study identifies potential research opportunities in strengthening overlooked construction aspects, coupling diverse data formats, and leveraging pre-trained language models and reinforcement learning.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Zhengyi Chen, Hao Wang, Keyu Chen, Changhao Song, Xiao Zhang, Boyu Wang, Jack C. P. Cheng
Summary: This study proposes an improved coverage path planning system that leverages building information modeling and robotic configurations to optimize coverage performance in indoor environments. Experimental validation shows the effectiveness and applicability of the system. Future research will focus on further enhancing coverage ratio and optimizing computation time.
AUTOMATION IN CONSTRUCTION
(2024)
Review
Construction & Building Technology
Yonglin Fu, Junjie Chen, Weisheng Lu
Summary: This study presents a review of human-robot collaboration (HRC) in modular construction manufacturing (MCM), focusing on tasks, human roles, and interaction levels. The review found that HRC solutions are applicable to various MCM tasks, with a primary focus on timber component production. It also revealed the diverse collaborative roles humans can play and the varying levels of interaction with robots.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Qiong Liu, Shengbo Cheng, Chang Sun, Kailun Chen, Wengui Li, Vivian W. Y. Tam
Summary: This paper presents an approach to enhance the path-following capability of concrete printing by integrating steel cables into the printed mortar strips, and validates the feasibility and effectiveness of this approach through experiments.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Honghu Chu, Lu Deng, Huaqing Yuan, Lizhi Long, Jingjing Guo
Summary: The study proposes a method called Cascade CATransUNet for high-resolution crack image segmentation. This method combines the coordinate attention mechanism and self-cascaded design to accurately segment cracks. Through a customized feature extraction architecture and an optimized boundary loss function, the proposed method achieves impressive segmentation performance on HR images and demonstrates its practicality in UAV crack detection tasks.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Daniel Lamas, Andres Justo, Mario Soilan, Belen Riveiro
Summary: This paper introduces a new method for creating synthetic point clouds of truss bridges and demonstrates the effectiveness of a deep learning approach for semantic and instance segmentation of these point clouds. The proposed methodology has significant implications for the development of automated inspection and monitoring systems for truss bridges.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Kahyun Jeon, Ghang Lee, Seongmin Yang, Yonghan Kim, Seungah Suh
Summary: This study proposes two enhanced unsupervised text classification methods for domain-specific non-English text. The results of the tests show that these methods achieve excellent performance on Korean building defect complaints, outperforming state-of-the-art zero-shot and few-shot text classification methods, with minimal data preparation effort and computing resources.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Yoonhwa Jung, Julia Hockenmaier, Mani Golparvar-Fard
Summary: This study introduces a transformer-based natural language processing model, UNIfORMATBRIDGE, that automatically labels activities in a project schedule with Uniformat classification. Experimental results show that the model performs well in matching unstructured schedule data to Uniformat classifications. Additionally, the study highlights the importance of this method in developing new techniques.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
De-Graft Joe Opoku, Srinath Perera, Robert Osei-Kyei, Maria Rashidi, Keivan Bamdad, Tosin Famakinwa
Summary: This paper introduces a digital twin technology combining Building Information Modelling and the Internet of Things for the construction industry, aiming to optimize building conditions. The technology is implemented in a university library, successfully achieving real-time data capture and visual representation of internal conditions.
AUTOMATION IN CONSTRUCTION
(2024)
Article
Construction & Building Technology
Zaolin Pan, Yantao Yu
Summary: The construction industry faces safety and workforce shortages globally, and worker-robot collaboration is seen as a solution. However, robots face challenges in recognizing worker intentions in construction. This study tackles these challenges by proposing a fusion method and investigating the best granularity for recognizing worker intentions. The results show that the proposed method can recognize multi-granular worker intentions effectively, contributing to seamless worker-robot collaboration in construction.
AUTOMATION IN CONSTRUCTION
(2024)