Streamlined bridge inspection system utilizing unmanned aerial vehicles (UAVs) and machine learning

Perry, Brandon J.; Guo, Yanlin; Atadero, Rebecca A.; Lindt, John W. van de

doi:10.1016/j.measurement.2020.108048

Cited by 95 publications

(50 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, especially when it comes to processing complicated tasks, we can see that humans collaborate to select the ML methods regarding the type and characteristics of the data set. For example, Perry et al [ 85 ] presented an efficient bridge inspection system implementing Unmanned Aerial Vehicles (UAVs), computer vision techniques and three clustering approaches with human–AI interaction in model selection. In their paper, to segment different parts of a bridge in its 3D point cloud model, three clustering methods were used that each one was suitable for the special shapes of the bridge elements (data samples).…”

Section: Resultsmentioning

confidence: 99%

“…So, a high level of expertise is not needed for this kind of ML applications. For example, in Perry et al [ 85 ], humans or users who were in the loop should have basic knowledge in the related field. In Feder et al [ 25 ], the ability to identify demographic traits was enough for a human to be in the loop.…”

Section: Resultsmentioning

confidence: 99%

“…Depending on ML applications, humans interact with ML methods at specific times. For example, In Perry et al [ 85 ], we can see that human interacted only twice with the ML method. At the first time, human selected the initial point of a clustering method and in the second time, the human was responsible for model selection.…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

Maadi

Khorshidi

Aickelin

2021

IJERPH

View full text Add to dashboard Cite

Objective: To provide a human–Artificial Intelligence (AI) interaction review for Machine Learning (ML) applications to inform how to best combine both human domain expertise and computational power of ML methods. The review focuses on the medical field, as the medical ML application literature highlights a special necessity of medical experts collaborating with ML approaches. Methods: A scoping literature review is performed on Scopus and Google Scholar using the terms “human in the loop”, “human in the loop machine learning”, and “interactive machine learning”. Peer-reviewed papers published from 2015 to 2020 are included in our review. Results: We design four questions to investigate and describe human–AI interaction in ML applications. These questions are “Why should humans be in the loop?”, “Where does human–AI interaction occur in the ML processes?”, “Who are the humans in the loop?”, and “How do humans interact with ML in Human-In-the-Loop ML (HILML)?”. To answer the first question, we describe three main reasons regarding the importance of human involvement in ML applications. To address the second question, human–AI interaction is investigated in three main algorithmic stages: 1. data producing and pre-processing; 2. ML modelling; and 3. ML evaluation and refinement. The importance of the expertise level of the humans in human–AI interaction is described to answer the third question. The number of human interactions in HILML is grouped into three categories to address the fourth question. We conclude the paper by offering a discussion on open opportunities for future research in HILML.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

Maadi

Khorshidi

Aickelin

2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…Furinghetti et al have discussed cloud computing techniques for data acquisition to detect the damage in structure to be recorded and this approach has been discussed in both software and hardware perspective, which refined at EUCENTRE foundation in Italy [81]. Perry et al demonstrated a new approach by collecting the images of bridge quality, the severity of the damage, expansion of damage, and a spot of the damage has been monitored using the Unmanned Aerial Vehicles (UAVs) method that is a more convenient approach to access the health of the bridge [82].…”

Section: Et Al Presented a Case Study By Applying The Shm Technique In Sydney Harbormentioning

confidence: 99%

[Retracted] Development of Smart Sensing Technology Approaches in Structural Health Monitoring of Bridge Structures

Sivasuriyan

Vijayan

LeemaRose³

et al. 2021

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

In recent years, immense development in Structural Health Monitoring (SHM) of bridges helps address the life span and reliability of bridge structure at contrasting phases of their service life. This article provides a detailed understanding of bridge monitoring, and it focuses on sensors utilized and all kinds of damage detection (strain, displacement, acceleration, and temperature) according to bridge nature (scour, suspender failure, disconnection of bolt and cables, etc.) and environmental degradation under static and dynamic loading. This paper presents information about various methods, approaches, case studies, advanced technologies, real-time experiments, stimulated models, data acquisition, and predictive analysis. Future scope and research also discussed the implementation of SHM in bridges. The main aim of this research is to assist researchers in better understanding the monitoring mechanism in bridges.

show abstract

“…Lydon et al (2018) achieved high accuracy in measuring the displacement of a laboratory beam using a Nikon D180 (approximate cost £2500) as well as a modified GoPro (approximate cost £500) camera. Unmanned aerial vehicles are emerging hardware used in VBM to collect visual information of damages in structures (Perry et al, 2020). Moreover, promising accuracy of response measurement has been recorded by researchers using readily available advances in the in-built camera of smartphones (Kromanis et al, 2019b;Orak and Ozturk, 2018).…”

Section: Hardware Adaptabilitymentioning

confidence: 99%

Proceedings of the Joint International Resilience Conference, JIRC2020

Hölscher¹

2020

Proceedings of the Joint International Resilience Conference, JIRC2020

View full text Add to dashboard Cite

co-organized by the 4TU.Centre for Resilience Engineering and the Future Resilient Systems Program FRS at the Singapore ETH Center SEC, took place in November 2020. The conference brought -for the first time -together two communities that were before organized separately. Conference as a meeting placeThe 4TU.RE conferences and community focus on improving resilience of coupled socio-technicalenvironmental (STE) systems. Accordingly, resilience engineering knowledge and expertise are combined with principles of adaptation, both of which are learning and tipping points characteristic for the socioecological systems. FRS Singapore had organized two conferences on resilience preceding the current joint event.

show abstract

Streamlined bridge inspection system utilizing unmanned aerial vehicles (UAVs) and machine learning

Cited by 95 publications

References 35 publications

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

[Retracted] Development of Smart Sensing Technology Approaches in Structural Health Monitoring of Bridge Structures

Proceedings of the Joint International Resilience Conference, JIRC2020

Contact Info

Product

Resources

About