A novel unsupervised deep learning model for global and local health condition assessment of structures

646

338

Research on damage detection of road surfaces using image processing techniques has been actively conducted. This study makes three contributions to address road damage detection issues. First, to the best of our knowledge, for the first time, a large‐scale road damage data set is prepared, comprising 9,053 road damage images captured using a smartphone installed on a car, with 15,435 instances of road surface damage included in these road images. Next, we used state‐of‐the‐art object detection methods using convolutional neural networks to train the damage detection model with our data set, and compared the accuracy and runtime speed on both, using a GPU server and a smartphone. Finally, we demonstrate that the type of damage can be classified into eight types with high accuracy by applying the proposed object detection method. The road damage data set, our experimental results, and the developed smartphone application used in this study are publicly available (https://github.com/sekilab/RoadDamageDetector/).

Section: Related Workmentioning

confidence: 99%

Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images

Maeda

Sekimoto

Seto

et al. 2018

646

338

“…ML and data science has shown great potential for predicting, designing, and discovering materials (Ley & Bordas, ). In civil engineering and construction, ML has been extensively used in a variety of applications such as structural heal monitoring (Gao & Mosalam, ; Rafiei & Adeli, , ; Xue & Li, ), reliability analysis (Dai & Cao, ; Grande, Castillo, Mora, & Lo, ; Nabian & Meidani, ), transportation (Dharia & Adeli, ; García‐Ródenas, López‐García, & Sánchez‐Rico, ; Yu, Wang, Shan, & Yao, ; Zhang & Ge, ), and prediction and estimation (Adeli & Wu, ; Chou & Pham, ; Rafiei, Khushefati, Demirboga, & Adeli, ; Zhao & Ren, ). In concrete‐related studies, DeRousseau, Kasprzyk, and Srubar () recently reviewed the application of ML to optimize mixture design of concrete.…”

Section: Introductionmentioning

confidence: 99%

Deep neural network with high‐order neuron for the prediction of foamed concrete strength

Nguyen

Kashani

Ngo

et al. 2018

214

The article presents a deep neural network model for the prediction of the compressive strength of foamed concrete. A new, high‐order neuron was developed for the deep neural network model to improve the performance of the model. Moreover, the cross‐entropy cost function and rectified linear unit activation function were employed to enhance the performance of the model. The present model was then applied to predict the compressive strength of foamed concrete through a given data set, and the obtained results were compared with other machine learning methods including conventional artificial neural network (C‐ANN) and second‐order artificial neural network (SO‐ANN). To further validate the proposed model, a new data set from the laboratory and a given data set of high‐performance concrete were used to obtain a higher degree of confidence in the prediction. It is shown that the proposed model obtained a better prediction, compared to other methods. In contrast to C‐ANN and SO‐ANN, the proposed model can genuinely improve its performance when training a deep neural network model with multiple hidden layers. A sensitivity analysis was conducted to investigate the effects of the input variables on the compressive strength. The results indicated that the compressive strength of foamed concrete is greatly affected by density, followed by the water‐to‐cement and sand‐to‐cement ratios. By providing a reliable prediction tool, the proposed model can aid researchers and engineers in mixture design optimization of foamed concrete.

“…Machine learning nonparametric modeling (Adeli & Hung, 1994;Marsland, 2011;Reich & Barai, 1999) has attracted increasing attention in various engineering disciplines Rafiei & Adeli, 2018;Rafiei, Khushefati, Demirboga, & Adeli, 2017;Xue & Li, 2018;Yang et al, 2018;Zhang et al, 2019). It provides a powerful toolkit to establish spatial model based on the unstructured data (Kanevski, Timonin, & Pozdnukhov, 2009;Karpatne, Ebert-Uphoff, Ravela, Babaie, & Kumar, 2018).…”

Section: Introductionmentioning

confidence: 99%

Broad learning for nonparametric spatial modeling with application to seismic attenuation

Kuok

Yuen

2019

Spatial modeling is a core element in geographical information science. It incorporates geographic information to construct the relationship for interpreting the behavior of spatial phenomena. In this paper, a broad learning framework for nonparametric spatial modeling is presented. Broad learning overcomes the obstacle of expensive computational consumption in deep learning and provides a powerful computationally efficient alternative. In contrast to the deep learning architecture that is configured with stacks of hierarchical layers, broad learning networks are established in a flat manner that can be flexibly reconfigured with the inherited information from the trained network. To develop the broad learning network, a simple prototype network is established as the initial trial and it is modified incrementally to enhance its data fitting capacity. Consequently, complex relationship of unstructured spatial data can be modeled efficiently. To demonstrate the efficacy and applicability of the broad learning framework, we will present a simulated example and a real application using the strong ground motion records on the 2008 great Wenchuan earthquake.