1,721,036 research outputs found
Adaptive Wavelet Neural Network for Terrestrial Laser Scanner-Based Crack Detection
Get PDFObjective, accurate, and fast assessment of civil infrastructure conditions is critical to timely assess safety risks. Current practices rely on visual observations and manual interpretation of reports and sketches prepared by inspectors in the field, which are labor intensive, subject to personal judgment and experience, and prone to error. Terrestrial laser scanners (TLS) are promising for automatically identifying structural condition indicators, as they are capable of providing coverage for large areas with accuracy at long ranges. Major challenges in using this technology are in storing significant amount of data and extracting appropriate features enabling condition assessment. This paper proposes a novel adaptive wavelet neural network (WNN)-based approach to compress data into a combination of low- and high-resolution surfaces, and automatically detect concrete cracks and other forms of damage. The adaptive WNN is designed to sequentially self-organize and self-adapt in order to construct an optimized representation. The architecture of the WNN is based on a single-layer neural network consisting of Mexican hat wavelet functions. The strategy is to first construct a low-resolution representation of the point cloud, then detect and localize anomalies, and finally construct a high-resolution representation around these anomalies to enhance their characterization. The approach was verified on four cracked concrete specimens. The experimental results show that the proposed approach was capable of fitting the point cloud, and of detecting and fitting the crack. The results demonstrated data compression of 99.4%, 72.2%, 92.4% and 78.9% for the four specimens when using low resolution fit for crack detection. For specimens 1, 2 and 3, 97.1%, 42.5% and 63.9% compression of data were obtained for crack localization, which is a significant improvement over previous TLS based crack detection and measurement approaches. Using the proposed method for crack detection would enable automatic and remote assessment of structural conditions. This would, in turn, result in reducing costs associated with infrastructure management, and improving the overall quality of our infrastructure by enhancing maintenance operations.This is a manuscript of an article published as Turkan, Yelda, Jonathan Hong, Simon Laflamme, and Nisha Puri. "Adaptive wavelet neural network for terrestrial laser scanner-based crack detection." Automation in Construction 94 (2018): 191-202. doi: 10.1016/j.autcon.2018.06.017. Posted with permission.</p
Recommended from our members
Progress Monitoring and Quality Assessment/Quality Control of Construction Projects Using Lidar and BIM
Get PDFThe construction industry is a key contributor to the Gross Domestic Product (GDP) of many countries around the world and is valued at more than $10 trillion globally. Schedule, cost and quality are the main performance measures of construction projects. The primary goal for project stakeholders in the construction industry is to ensure that a project is delivered on time and on budget, while meeting the project specific quality standards. However, cost and schedule overruns, and rework have become the costly standard for most construction projects. In particular, transportation construction projects are very sensitive to cost and schedule overruns due to the magnitude of risk and uncertainty involved. The inaccuracies, inconsistencies, and delays associated with manual collection of project progress data further contribute to the inefficient tracking of resources, activities, and cost, consequently causing issues to be overlooked and leaving them unresolved. Another major issue in the construction industry is related to the assessment of the quality of work in a timely fashion in order to avoid rework. Focusing on measuring the quality of concrete slabs, several concrete surface waviness assessment methods have been developed to overcome the disadvantages of one assessment method over the other. Floor surface waviness assessment over multiple
one-dimensional (1D)-survey lines may not accurately reflect the actual condition or waviness of an entire floor. Thus, it can be concluded that the current practices for performing project quality control and progress tracking are prone to errors, labor-intensive, and time-consuming, and there is a need to develop novel, technology supplemented methodologies to improve current project quality control and progress tracking practices.
This dissertation proposes two technology-supplemented frameworks for project progress tracking and dimensional quality control, and is comprised of three manuscripts. The first manuscript presents a framework that uses mobile lidar data and four dimensional- (4D-) design models for tracking the progress of bridge construction projects. The framework is capable of determining the completion of individual bridge elements in an accurate and efficient manner, and the progress information is reported as Percentage of Completion (POC). The second manuscript presents a framework that enables assessment of a concrete surface in two-dimensional (2D) domain using the synergy between Terrestrial Laser Scanning (TLS) and Continuous Wavelet Transform (CWT). 2D CWT analysis provides information not only about the periods of the surface undulations, but also the location of such undulations. The third manuscript presents a sensitivity analysis of the impact of various TLS point cloud scanning resolutions on surface waviness results. Furthermore, the surface waviness results obtained using TLS and Unmanned Aerial Vehicles (UAV)-based laser scanning are compared and analyzed
Bride Structural Inspections using Bridge Information Modeling (BrIM) and Unmanned Aerial Vehicles (UAVs)
No full texthttps://doi.org/10.7910/DVN/6PKXMCBridge inspection is a critical task needed to monitor bridge quality and serviceability. In the U.S., 40 percent of bridges are more than 50 years old, while most bridges are typically designed for a lifespan of 50 years. Of the 614,387 bridges across the U.S., 9.1 percent are considered structurally deficient. These statistics reported in the literature emphasize the urgent need for more frequent and comprehensive bridge inspections. However, the current manual inspection routine is expensive, time-consuming, hazardous, and subjective. Moreover, current Bridge Management Systems (BMS) may not coordinate management of all four phases of the bridge life cycle. Also, dispersion of inspection data drastically reduces the effectiveness of these systems. Therefore, there is a need to find cost-efficient and productive ways to inspect and manage our bridges.
The objective of this study was to develop a novel framework for performing bridge inspections and management. The framework implements Bridge Information Modeling (BrIM) and unmanned aerial system (UAS) technologies to solve the problems with current manual bridge inspection and management practices. The proposed framework was implemented with data collected from an existing bridge located in Eugene, Oregon. Different types of defects were identified from the digital images captured by the UAS, and cracks were detected automatically by applying computer vision algorithms to those images. The identified defects were assigned to individual BrIM elements. BrIM was used as the central database to store the 3D bridge model and all inspection data. The framework also enables bridge inspectors and decision makers to access the most up-to-date inspection data simultaneously by taking advantage of cloud computing technology. The proposed framework will (1) provide a systematic approach for collecting and accurately documenting structural condition assessment data, (2) reduce the number of site visits and eliminates potential errors resulting from data transcription, and (3) enable a more efficient, more cost-effective, and safer bridge inspection process.Pacific Northwest Transportation Consortium
US Department of Transportation
Oregon State Universit
Automated Construction Progress Tracking using 3D Sensing Technologies
Get PDFAccurate and frequent construction progress tracking provides critical input data for project systems such as cost and schedule control as well as billing. Unfortunately, conventional progress tracking is labor intensive, sometimes subject to negotiation, and often driven by arcane rules. Attempts to improve progress tracking have recently focused mainly on automation, using technologies such as 3D imaging, Global Positioning System (GPS), Ultra Wide Band (UWB) indoor locating, hand-held computers, voice recognition, wireless networks, and other technologies in various combinations.
Three dimensional (3D) imaging technologies, such as 3D laser scanners (LADARs) and photogrammetry have shown great potential for saving time and cost for recording project 3D status and thus to support some categories of progress tracking. Although laser scanners in particular and 3D imaging in general are being investigated and used in multiple applications in the construction industry, their full potential has not yet been achieved. The reason may be that commercial software packages are still too complicated and time consuming for processing scanned data. Methods have however been developed for the automated, efficient and effective recognition of project 3D BIM objects in site laser scans.
This thesis presents a novel system that combines 3D object recognition technology with schedule information into a combined 4D object based construction progress tracking system. The performance of the system is investigated on a comprehensive field database acquired during the construction of a steel reinforced concrete structure, Engineering V Building at the University of Waterloo. It demonstrates a degree of accuracy that meets or exceeds typical manual performance. However, the earned value tracking is the most commonly used method in the industry. That is why the object based automated progress tracking system is further explored, and combined with earned value theory into an earned value based automated progress tracking system. Nevertheless, both of these systems are focused on permanent structure objects only, not secondary or temporary. In the last part of the thesis, several approaches are proposed for concrete construction secondary and temporary object tracking.
It is concluded that accurate tracking of structural building project progress is possible by combining a-priori 4D project models with 3D object recognition using the algorithms developed and presented in this thesis
3D Bridge Information Model & UAV captured bridge images in Eugene, OR
No full textUAV Data Collection Dates: December-1-2017; December-7-2017; May 11, 2018
This data will remain relevant for 4 years, it includes bridge condition data and its 3D model (structural). Bridge condition will change rapidly so those images showing cracks and spalling on the bridge will no longer be relevant
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Recommended from our members
Multiagent Learning via Dynamic Skill Selection
Get PDFMultiagent coordination has many real-world applications such as self-driving cars, inventory management, search and rescue, package delivery, traffic management, warehouse management, and transportation. These tasks are generally character-ized by a global team objective that is often temporally sparse - realized only upon completing an episode. The sparsity of the shared team objective often makes it an inadequate learning signal to learn effective strategies. Moreover, this reward signal does not capture the marginal contribution of each agent towards the global objective. This leads to the problem of structural credit assignment in multia-gent systems. Furthermore, due to a lack of accurate understanding of desired task behaviors, it is often challenging to manually design agent-specific rewards to improved coordination.
While learning these undefined local objectives is very critical for a successful coordination, it is extremely challenging due to these two core challenges. Firstly, due to interaction among agents in an environment, the complexity of the problem may rise exponentially with the number of agents, and their behavioral sophisti-cation. An agent perceives the environment as non-stationary, due to all learn-ing concurrently. This leads to an agent perceiving the coordination objective as extremely noisy. Secondly, the goal information required to learn coordination behavior is distributed among agents. This makes it difficult for agents to learn undefined desired behaviors that optimizes a team objective.
The key contribution of this work is to address the credit assignment problem in multiagent coordination using several semantically meaningful local rewards. We argue that real-world multiagent coordination tasks can be decomposed into several meaningful skills. Further, we introduce MADyS, a framework that can optimize a global reward by learning to dynamically select the most optimal skill from semantically meaningful skills, characterized by their local rewards, without requiring any form of reward shaping. Here, each local reward describes a basic skill and is designed based on domain knowledge. MADyS combines gradient-based optimization to maximize dense local rewards and gradient-free optimization to maximize the sparse team-based reward. Each local reward is used to train a local policy learner using policy gradient (PG) - and an evolutionary algorithm (EA) that searches in a population of policies to maximize the global objective by picking the most optimal local reward at each time step of an episode. While these two processes occur concurrently, the experiences collected by the EA population are stored in a replay buffer and utilized by the PG based local rewards optimizer for better sample efficiency.
Our experimental results show that MADyS outperforms several baselines. We also visualize the complex coordination behaviors by studying the temporal distri-bution shifts of the selected local rewards. By visualizing these shifts throughout an episode, we gain insight into how agents learn to (i) decompose a complex task into various sub-tasks, (ii) dynamically configure sub-teams, and (iii) assign the selected sub-tasks to the sub-teams to optimize as a team on the global objective
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
