See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/339272663

Deep Learning Models for Bridge Deck Evaluation Using Impact Echo

Preprint · February 2020

CITATIONS READS
0 1,020

2 authors, including:

Sattar Dorafshan
University of North Dakota
50 PUBLICATIONS 1,474 CITATIONS

SEE PROFILE

All content following this page was uploaded by Sattar Dorafshan on 18 February 2020.

The user has requested enhancement of the downloaded file.

 1

Deep Learning Models for Bridge Deck Evaluation Using Impact

Echo

Sattar Dorafshan1*, Ph.D.

Hoda Azari2, Ph.D.

1*
Corresponding Author, Assistant Professor, Department of Civil Engineering,

University of North Dakota, Grand Forks, ND 58202, [email protected]

2
Nondestructive Evaluation Program and Laboratory Manager, Federal Highway

Administration, Turner-Fairbank Highway Research Center, McLean, VA 22101,

[email protected]

Abstract

One of the challenges in using non-destructive evaluation methods (NDE) for bridge

evaluation is their dependency on experienced users to perform the tests and interpret the results.

Impact echo (IE) is a common NDE method to detect subsurface defects in concrete bridge

decks. The conventional approach for analyzing the IE data (peak frequency method) requires

user expertise and user-defined parameters that could hinder broad field implementation. In this

paper, the feasibility of using deep learning for autonomous subsurface defect detection has been

studied to introduce automation in IE data analysis. A set of eight lab-made reinforced concrete

bridge specimens with known subsurface defects were made at the Federal Highway

Administration (FHWA) Advanced Sensing Technology (FAST) NDE laboratory. A total

number of 2016 of IE data was collected from these specimens. A one-dimensional (1D)

convolutional neural network (CNN), and a 1D recurrent neural network using bidirectional
 2

long-short term memory units, were developed and applied on the IE data. In addition, two-

dimensional (2D) CNNs with AlexNet, GoogleNet, and ResNet architectures were applied on the

2D representatives of the IE data, i.e., spectrograms. The proposed 1D CNN achieved an overall

accuracy of 0.88 by classifying 0.70 of the defects and 0.95 of the sound regions correctly. The

accuracy varied between 0.80-0.86 for the rest of the models. The 1D CNN was considerably

faster to train compared to the other investigated models. The deep learning models were also

used to generate a defect map for each specimen that matched or exceeded the quality of the

defect maps generated by the peak frequency method.

Keywords: Deep learning, Impact Echo, Bridge Decks, Convolutional Neural Networks,

Nondestructive Evaluation Methods, Bridge Inspection.

Introduction

Bridge inspection has been included in the Code of Federal Regulations for more than

half a century [1]. Conventional visual inspections [1-2] are time-consuming and dependent on

the inspector’s skills and experience [3-6]. Considering only one type of infrastructure (bridges)

and one bridge element (decks), bridge decks cover almost 4 billion square meters of the US

transportation grid [7], which is equivalent to an area larger than the City of Detroit in the United

States. Bridge decks are subjected to the same biannual inspections as other parts of bridges.

Bridge decks become start exhibiting more defects as they become older, making visual

inspections even more burdensome. Bridge inspectors use nondestructive evaluation (NDE)

techniques for comprehensive bridge deck evaluation as these methods provide essential

information about the material properties and presence of subsurface defects.

 3

Recent demands to introduce automation in infrastructure construction, inspection, and

planning have led to implementing artificial intelligence (AI) for bridge evaluation. One can

define a set of features in inspection data and employ AI to create statistical classifiers using

supervised learning to detect bridge defects, i.e., machine learning. However, defining the feature

still requires an expert’s opinion. It is possible to obtain both features and classifiers using

unsupervised learning and through training on annotated inspection datasets to further reduce the

role of experts in the classification process, i.e., deep learning. An artificial neural network

(ANN) is a computational system that learns to perform tasks without being tuned by task-

specific criteria, either through machine or deep learning.

Researchers have used machine learning techniques for semi-autonomous surface defect

detection from visual images to reduce the cost and time associated with the current manned

practice, and to minimize the role of humans for interpreting the inspection data [8-10]. The

application of machine learning for bridge condition evaluations has been mostly focused on

surface defects in visual images of bridge decks [11-20]. Deep learning frameworks has been

leveraged for characterization of acoustic emission signals in metallic plates [21-22]. Deep

learning architecture has been shown to be superior to humans in terms of recognizing an object

or a pattern in visual images [23-25]. Deep learning models (DLMs) also have been used in past

studies to detect surface defects in bridges and other structures [9, 25-30].

A variety of NDE methods can be used to detect different subsurface defects in bridge

decks [35-36], The methods include sonic and ultrasonic methods [37-41], ground penetration

radar [43-47], electrical resistivity [48-49], and impact echo (IE) [50-52]. Researchers have used

machine learning to detect subsurface defects through NDE data [57-61]. In particular,

researchers have developed classifiers and predication models using signal processing to classify
 4

IE processed data [62-65]; however, these classifiers still require manual feature selection in the

IE signals which limits their applications in the field. DLMs have not been designed for or

implemented on IE data. DLMs are superior to statistical classifiers, i.e., unsupervised learning

methods, because they depend on considerably fewer user-defined parameters [9,25]. The

dependency on human expertise could be reduced by combining two or more NDE methods

using homogenous and heterogeneous data fusion techniques in concrete [66] and steel [67]

structures. However, extracting and combining the proper features from these sources can be

challenging without having inspector’s or expert’s input.

The authors hypnotize that DLMs can be used for robust and unbiased IE data analysis as

one of the essential steps toward introducing automation to bridge evaluation. The scopes of this

study include the followings.

• Forming a fully annotated dataset made of raw IE signal and its transformation;

• Developing and training DLMs capable of separating defected and intact concrete

using this dataset;

• Identifying the most efficient DLMs for IE data analysis;

• Comparing DLMs to conventional method for IE data analysis;

• Validating trained DLMs on diverse IE data to mimic field tests.

Background

Impact Echo (IE)

IE instruments became commercially available in the late 1990s. American Society of

Testing Material (ASTM) adopted this technology in 1998 to be formally used for thickness

measurements of plate-shaped concrete structures [68]. A typical IE instrument includes an

 5

impact source, a nearby receiver, and a data acquisition system, as shown in Figure 1. The

impact source generates seismic waves through and on the inspected region. When the waves hit

the bottom of the medium, i.e., backwall, or a subsurface irregularity, they are reflected. These

reflections, i.e., echoes, then travel back to the surface where their amplitudes are recorded by

the receiver [36]. The travel time of the echoes could indicate the location of the reflectors, and

whether a reflection is associated with a backwall reflection or a subsurface defect. Therefore,

the IE test can be used to determine the thickness of the deck if applied on a sound region, or to

detect subsurface defects if applied on a defected region [35].

Receiver
Impact Source

(a) (b)
Figure 1. (a) IE impact source and receiver, (b) data acquisition system.

The Peak Frequency Method

The following relationship exists between the travel time of echoes in seconds (t), the

echo’s velocity in concrete in meter per second (𝐶𝐶𝑝𝑝 ), and the traveled distance in meter (d):

𝑑𝑑
𝑡𝑡 = (1)
𝐶𝐶𝑝𝑝
If the echoes all correspond to the backwall reflection, then the travelled distance would

roughly be equal to 2𝑇𝑇, where T is the thickness of the deck. Performing Fourier transform on IE

signals, one can establish a relationship between the deck thickness and the frequency associated

with it, 𝑓𝑓𝐼𝐼𝐼𝐼, as follows:

 6

𝐶𝐶𝑝𝑝
𝑇𝑇 = 𝛽𝛽 (2)
2𝑓𝑓𝐼𝐼𝐼𝐼
where β is a correction factor influenced by the material properties of the propagation

medium.

In theory, a distinctive peak in the frequency response, close to the thickness frequency

( 𝑓𝑓𝐼𝐼𝐼𝐼 ), indicates sound concrete. The presence of defects could be manifested in the spectra in

two distinct peaks, a single peak at higher frequencies than the 𝑓𝑓𝐼𝐼𝐼𝐼 , or a low-frequency response

of the flexural mode [36]. However, these patterns are not always present in the frequency

response. Figure 2a and b show the IE signals associated with a sound and a defected (shallow

delamination) concrete region of reinforced concrete specimen constructed at the Federal

Highway Administration (FHWA) Advanced Sensing Technology (FAST) NDE laboratory. The

frequency responses exhibit a single peak, Figure 2c and d. Without knowing the value of the

thickness frequency or past engagement with the IE data, it is difficult to recognize the difference

between the two responses. In addition, the shape of the frequency responses in these figures did

not exactly follow the theoretical description of a defected concrete region.

0.50 0.50

0.30 0.30
Voltage

0.10
Voltage

0.10

-0.10 -0.10

-0.30 -0.30

-0.50
-0.50
0.000 0.005 0.010
0.000 0.005 0.010
Time (s) Time (s)

(a) (b)
 7

1.00 1.00

0.80 0.80

Normalized Amp.
Normalized Amp

0.60 0.60

0.40 0.40

0.20 0.20

0.00 0.00
1,000 11,000 21,000 1,000 11,000 21,000
Frequency (Hz) Frequency (Hz)
(c) (d)
1.00 1.00

0.80 0.80
Normalized Amp.

Normalized Amp
0.60 0.60

0.40 0.40

0.20 0.20

0.00 0.00
1,000 11,000 21,000 1,000 11,000 21,000
Frequnecy (Hz) Frequency (Hz)
(e) (f)
Figure 2. IE signals (a) sound (b) defected (shallow delamination), frequency response without processing (c) sound,
(d) defected, and frequency response with processing (e) sound, (f) defected concrete

Figure 2e and f show the frequency responses after a Blackman Harris filter was applied

[69]. As seen, it is after the filtering that the frequency responses started to match with the

theoretical interpretations. Note that the IE tests in Figure 2 were performed in a controlled

environment. IE signals and their frequency responses, collected in practice, tend to be noisier

than the laboratory data which makes them more difficult to classify with the peak frequency

method. Therefore, practitioners and inspectors demand for alternatives that could produce

consistent results. Unlike the peak frequency method that heavily relies on user-defined

parameters and expertise, DLMs could potentially analyze raw IE data in an autonomous manner

which could lead to a broader implementation of this technique in bridge inspection and

evaluation.
 8

Experimental Program

Deck Specimens

Eight reinforced concrete specimens, 3.0 m long, 1.0 m wide, and 0.2 m thick, were

constructed at the FAST NDE Laboratory to have four types of artificial defects: shallow

delamination (above the specimens’ top rebar level), deep delamination (above the specimens’

bottom rebar level), honeycombing, and voids, as seen in Figure 3.

Figure 3. Details of the specimens with artificial defects.

Initially, the specimens were made to study the effectiveness of NDE methods on

specimens with different types of overlay systems [35]. The specimens were constructed by

normal-weight concrete mix with a water-to-cement ratio of 0.37 and a 28-day compressive

strength of 27.6 MPa, with two mats of uncoated steel reinforcement with no. 5 rebar (15.8 mm

diameter) spaced 203 mm in both longitudinal and transverse directions. The specimens were

inspected using several NDE methods including IE before and after placing the overlays. In this

study, the IE data of specimens without overlays was investigated. All defects were 0.30 m long

along the length of the specimens, and 0.20 m wide along the width of the specimens. A
 9

transverse crack was also artificially made in the middle of all specimens. Details about the

defects, their materials, and specimen construction can be found in [70].

Annotated IE Dataset

The specimens were marked with a marker to create a grid system on their surface with

100 mm spacing (longitudinally and transversely). The IE tests were performed on the grid

points using a custom-made IE device, an accelerometer (receiver), and steel spheres (11mm in

diameter) on spring rods (impact source), as shown in Figure 1. The sampling frequency was 200

kHz for 10 ms of IE data acquisition at any point of the gird. Each IE signal consisted of 2000

points (shown in Figure 2a and b) and was saved by a name that represented the location of the

receiver on the grid. No IE tests were conducted on and within 100 mm of the transverse crack.

Table 1 shows the classification of the IE test signals into sound and defected concrete,

along with their quantities. In this table, class 0 is assigned to sound concrete and class 1 is

assigned to the defected regions.

Table 1. Classification and number of IE tests.

Type Quantity Class
Sound 1504 0
Defected 256 1
Boundary 256 1
Total 2016

Investigated Deep Learning Methods

Recurrent neural network (RNN) is a type of DLM that has been used for classification of

time-variant signals. Hidden layer(s) in a RNN include the neurons that have a memory to

preserve the information about the previous time step [71]. In this study, a bidirectional long

short-term memory (biLSTM) network was developed and implemented on the IE signals. A

biLSTM network is a combination of two LSTM networks, one works on the signal in a normal

order, the other works on the signal in a reverse order [72].

 10

Convolutional neural networks (CNNs) are another type of DLMs that have been widely

and successfully used for image classification in different disciplines, including defect detection

in civil infrastructure [27-34]. CNNs are commonly used on 2D input data, i.e., images; however,

it is possible to construct CNNs for 1D data as well [73-74]. In addition to the biLSTM model, a

1D CNN was developed to classify the IE signals directly.

To cover other possible analysis methods, the authors also investigated 2D CNNs on 2D

representatives of the IE data. In this paper, short-time Fourier transform (STFT) [74] was used

to generate spectrograms, as seen in Figure 4. In the spectrograms, the horizontal axis represents

time and the vertical axis represents frequency. The spectrograms provide the opportunity for

implementing famous CNN architectures, commonly used in the realm of visual images, for IE

classification. Note that the spectrograms were generated using all the existing frequencies (0-

200 kHz), without removing the unwanted frequencies.

(a) (b)
Figure 4. Data 2D representatives of IE signals with the horizontal axis represents time and the vertical axis
represents frequency: (a) sound concrete, (b) defected concrete (with shallow delamination).

1D Deep Learning

The biLSTM network architecture is shown in Figure 5 (the number of neurons in the

middle layer is schematic). The network consisted of an input layer to read the IE data, a hidden

layer (biLSTM layer with 200 neurons, a fully connected layer, and a softmax layer), and an

output (classification) layer to label the IE data. The number of neurons was selected empirically

and the network architecture was inspired by [75]. The fully connected layer connects the
 11

parameters from the past layers together in way that the softmax layer can assign a probability to

each class. The classification layer assigns a label to the data, 0 or 1, according to the highest

probabilities.

Figure 5. Architecture of the biLSTM network

Figure 6 shows the architecture of the proposed 1D CNN. This network is a combination

conventional layers in deep learning literature including convolution, batch normalization, and

rectified linear (CBR layers); max pooling (MP layers); fully connected, rectified linear unit, and

dropout (FRD layers), and softmax layer. The size and number of convolution kernels for each

CBR layer are shown Figure 6. In CBR, a batch normalization is applied to the result of the

convolution operation on the input from the previous layer (i.e., activation maps). The batch

normalization layer increases the speed of training by normalizing the activation maps. The

rectified linear unit (ReLU) is an activation function that adds non-linearity to the normalized

activation maps. If a value in the normalized activation map is negative, the ReLU would assign

0 to it; but it would not change a positive value. The MP layer analyzes sets of neighboring

locations in each activation map and represents them by their maximum value to reduce the size

of the input and avoid overfitting. In the FRD layers, dropout layers toss out responses smaller

than specific threshold values.

 12

Figure 6. Schematic. Architecture of the 1D CNN.

2D Deep Learning

Three world renown CNN architectures were trained and applied on the IE spectrograms:

AlexNet [76], GoogleNet [77], and ResNet [77]. Each has won the image classification

competition (2012, 2014, and 2016, respectively) [78]. For brevity, the details of these networks

are not discussed in detail here, given most of layers were already defined before. Figure 7 shows

the AlexNet schematic architecture.

Figure 7. AlexNet Schematic Architecture.

Figure 8 depicts a schematic architecture of GoogleNet. The significant contribution of

this architecture to the realm of CNNs was the introduction and application of an “inception”

layer. The inception layer consisted of a combination of convolution and max pooling kernels

with a configuration shown in Figure 8. With an inception layer, a concatenation filter is applied
 13

to make the output of the inception layer compatible with the rest of network. The AP in the

GoogleNet architecture stands for average pooling and works similar to the MP layer except it

takes average values instead of maximum values.

Figure 8. GoogleNet schematic architecture.

Finally, the ResNet architecture is shown in Figure 9. ResNet introduced residual

connections (a combination of convolution and max pooling) between the convolution kernels to

short-circuit the model for faster optimization.

 14

Figure 9. ResNet schematic architecture.

Training and Testing Parameters

The annotated IE dataset was split into a training and a testing dataset. The IE data of one

specimen was used as testing dataset, while the rest were used as the training dataset for each

DLM. By rotating the order, eight training and testing dataset were formed which then used to

train eight networks using every investigated DLM. Table 2 shows the size and labels of the

training and testing datasets.

Table 2. IE training and testing dataset.

Dataset Class Label Quantity
Sound 0 1764
Training
Defected 1 448
Sound 0 188
Testing
Defected 1 64

The biLSTM and the 1D CNN were fully trained (FT) using the training datasets. For the

2D CNNs, a method called transfer learning (TL) was also used. In this mode, parameters

obtained from trained networks on large image datasets, i.e., ImageNet [79], are squeezed into

the architecture of the new models before being trained on a new dataset, i.e., the IE data.
 15

Therefore, only the end layers (with respect to the input layer) are altered during the training.

The weights in the first layers consist of generic feature extractors which potentially are effective

on any image while the weights in the end layers are updated through re-training to match the

new dataset [30]. TL is very effective when training deep architectures on small datasets.

Therefore, AlexNet-based model was trained in both FT and TL manners while GoogleNet-

based and ResNet-based models were only TL trained. The layers used for re-training in the TL

mode for each DLM was different which are shown in Figure 7, Figure 8, and Figure 9 by

dashed circles.

All computations were performed on a desktop with a 64-bit operating system, 32 GB

memory, Intel® Core™ i7 CPU, and two GeForce GTX 1080 Ti graphics processing units

(GPU). MATLAB 2019a was used to program the DLMs. Before training began, several training

parameters, i.e., hyperparameters, were determined for each model. These parameters and their

values (shown in Table 3) were chosen empirically to optimize the training process. In Table 3,

solver refers to the type of algorithm used to optimize the model during the training. The purpose

of an optimizer is to solve the gradient descent of the model in order to minimize the model’s

error. An adaptive moment estimation (ADAM) optimizer was selected for the biLSTM model

while the stochastic gradient descent with momentum (SGDM) was chosen for the rest. The

optimizers were selected based on their past successful implementations on each type of ANN.

There are other parameters that should be determined empirically before the training

begins. Mini batch size is the size of the segments of the training data used to calculate the loss

and error of the models. Iteration is when the models go through a forward and backward

processing for a batch of data while one epoch is when all training data is processed once over

the training dataset. Learning rate is the tolerance of parameters to optimize the gradient descent
 16

and minimize the loss. The number of retrained layers in each network is also shown in the table

(only applicable to transfer learning).

Table 3. Training parameters for each investigated network.

Network Mode Solver Mini Batch Size Max Epochs Learning Rate Retrained Layers
biLSTM FT ADAM 20 95 1e-3 NA
1D CNN FT SGDM 50 40 1e-3 NA
AlexNet CNN FT SGDM 50 40 1e-3 NA
AlexNet CNN TL SGDM 50 40 1e-4 3
GoogleNet CNN TL SGDM 50 60 1e-4 4
ResNet CNN TL SGDM 50 25 1e-4 4

Results and Discussion

The performance of a DLM was evaluated using binary classification metrics (equations

3 through 6). The DLMs labeled an input signal or an image as the class that had the highest a

probability among the sound and defected classes. When a model labeled a defected input

correctly, it was a true positive (TP) whereas false negative (FN) was when the model labeled it

as sound. When the model labeled a sound input correctly, it was a true negative (TN) whereas

false positive (FP) was when the model labeled it as defected. The true positive rate (TPR), true

negative rate (TNR), accuracy (ACC), and F1 score were used to evaluate and compare the

results of each model per the following equations:

𝑇𝑇𝑇𝑇
𝑇𝑇𝑇𝑇𝑇𝑇 = � � (3)
𝑇𝑇𝑇𝑇 + 𝐹𝐹𝐹𝐹
𝑇𝑇𝑇𝑇
𝑇𝑇𝑇𝑇𝑇𝑇 = � � (4)
𝑇𝑇𝑇𝑇 + 𝐹𝐹𝐹𝐹
𝑇𝑇𝑇𝑇 + 𝑇𝑇𝑇𝑇
𝐴𝐴𝐴𝐴𝐴𝐴 = � � (5)
𝑇𝑇𝑇𝑇 + 𝐹𝐹𝐹𝐹 + 𝑇𝑇𝑇𝑇 + 𝐹𝐹𝐹𝐹
2𝑇𝑇𝑇𝑇
𝐹𝐹1 = � � (6)
2𝑇𝑇𝑇𝑇 + 𝐹𝐹𝐹𝐹 + 𝐹𝐹𝐹𝐹
Training Results

The results of training on each specimen are shown in Figure 10. The legends of these

plots represent the specimen id that was used for testing. For instance, a training process labeled
 17

as S1 is when the DLMs are trained on specimens S2 through S8. All models reached an

accuracy of 95 percent or higher at the last iteration of their training.

100 100

75 75
Accuracy (%)

Accurcy (%)
S1 S1
50 S2 50 S2
S3 S3
S4 S4
25 S5 25 S5
S6 S6
S7 S7
S8 S8
0 0
0 2000 4000 6000 8000 0 400 800 1200
Iteration Iteration
(a) (b)
100 100

75 75
Accuracy (%)
Accurcy (%)

S1 S1
50 S2 50 S2
S3 S3
S4 S4
25 S5 25 S5
S6 S6
S7 S7
S8 S8
0 0
0 400 800 1200 0 400 800 1200
Iteration Iteration
(c) (d)
100 100

75 75
Accuracy (%)

Accuracy (%)

S1 S1
50 S2 50 S2
S3 S3
S4 S4
25 S5 25 S5
S6 S6
S7 S7
S8 S8
0 0
0 400 800 1200 0 400 800
Iteration Iteration
(e) (f)
Figure 10. Results of training using different deep leaning models: (a) biLSTM, (b) 1D CNN, (c) AlexNet fully
trained, (d) AlexNet (transfer learning), (e) GoogleNet (transfer learning), (f) ResNet (transfer learning)

Each model required a different amount of time to finish one round of iteration based on

its architectures. The 2D models were more time-consuming than the 1D models since less

calculations are required to analyze an image, i.e., spectrograms, than a signal. As the models got
 18

deeper they required more time to finish one iteration with ResNet spending 1.21 s, GoogleNet

spending 0.57 s, and AlexNet (TL) spending 0.28 s. The AlexNet FT required 0.36 s per iteration

since more parameters had to be determined compared to TL. With 0.11 s per iteration, the

biLSTM model required twice the time 1D CNN spent on one iteration, i.e., only 0.05 s, which

makes both methods considerably faster than the 2D CNNs. As seen in Figure 10a the biLSTM

model required more iterations than convolutional networks to reach a desirable accuracy (e.g.,

95%) at the end of the training. Taking this fact into consideration, the proposed 1D CNN was

the fastest DLMs by a substantial margin.

Testing Results

After the training was completed, DLMs were used to classify the IE data in the testing

dataset. The testing data is not used during the training of the model. The results are shown in

Figure 11, and Table 4 shows the mean, coefficient of variation (COV), maximum, and

minimum values of the performance metrics (equations 3 through 6) for each DLM. The results

are promising and relatively consistent (low COV values). Looking at the results, 1D CNN

produced the best average TPR, 0.70, with the lowest COV, 0.14. The ResNet model resulted in

the lowest TPR values with only 0.53 on average. The 1D CNN model also produced the highest

TNR and ACC on average with 0.95 and 0.88 respectively, which were consistent for all

specimens (COV of 0.04). The biLSTM model produced the lowest average TNR and ACC

values of 0.87 and 0.80, respectively. In terms of F1 scores, the 1D CNN was also the winner

among the investigated models with 0.75; the ResNet and biLSTM models shared the low of

0.61. Comparing the 2D DLMs, AleNet FT had the best overall performance by achieving a TPR

of 0.70, TNR of 0.92, ACC of 0.86, and F1 score of 0.72. Results indicate that the shallower

CNNs was, the more successful it performed on the binary annotated IE dataset. In addition, the
 19

1D models were more accurate than the 2D models since they were applied directly on the

signal, not the 2D approximation. One challenge of the using 2D representations is that all

frequencies were included. Considering the conventional IE analysis, peak frequency described

in section 2.2., the four mentioned patterns exhibit themselves in specific range of frequencies

[80]. Unlike visual images, the vertical and horizontal axis in spectrograms represent time and

frequency, which limits the 2D CNNs spatial invariance for feature detection. In addition, the

pixels in the visual images often belong to an object whereas there are no objects in the

spectrograms. The challenges of using DLMs on the 2D spectrograms of signals have been

previously discussed in [81-82]. The TPR values were consistently higher than TNR values. As

shown in Table 3, the number of training data classified as 0, i.e., sound, was almost four times

larger than the testing dataset which would justify high TNRs. However, unlike other

applications of deep learning, this imbalance is benign since it matches the reality of in-service

bridges. The second reason was due to the variability of the defected regions compared to the

sound concrete. The defects had four sources: shallow delamination, voids, honeycombing, and

deep delamination, as shown in Figure 3. This difference was likely manifested in some of

features extracted by the DLMs from the IE signals and consequently the spectrograms within

the same class, i.e., 1. One solution is to designate a class for each defect type if enough data for

each class were available.

The performance of the 2D CNNs seems to be counterintuitive at first since the deeper

networks resulted in poorer performance. The performance of these models does not always

follow their performance on ImageNet [83-84]. In addition, deeper networks, e.g., GoogleNet

and ResNet, do not necessarily perform better than shallower networks, e.g., AlexNet, for binary

classifications [27]. For better implementation of 2D CNNs, more labeled spectrograms are
 20

required. Note that spectrograms could be generated with differently, using other transforms such

as wavelet, that could potentially alter the performance of the 2D CNNs.

1.00

0.75

0.50

0.25

0.00

TPR TNR ACC F1

(a)
1.00

0.75

0.50

0.25

0.00
ResNet

ResNet

ResNet

ResNet

ResNet

ResNet

ResNet

ResNet

ResNet
AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet

AlexNetFT
AlexNetTL
GoogleNet
TPR TNR ACC F1

(b)
Figure 11. Testing metrics for the investigated DLMs: (a) using IE signals, (b) using IE spectrograms.

Table 4. Summary of metrics for the investigated DLMs.

Metrics
Model TPR TNR ACC F1
(Mean, COV, Max, Min) (Mean, COV, Max, Min) (Mean, COV, Max, Min) (Mean, COV, Max, Min)
biLSTM 0.61 0.18 0.77 0.48 0.87 0.06 0.93 0.83 0.80 0.05 0.88 0.76 0.61 0.14 0.76 0.53
1D CNN 0.70 0.14 0.81 0.48 0.95 0.04 1.00 0.85 0.88 0.04 0.92 0.83 0.75 0.08 0.83 0.65
AlexNet
0.70 0.17 0.89 0.50 0.92 0.06 0.97 0.81 0.86 0.03 0.89 0.83 0.72 0.07 0.76 0.60
(FT)
AlexNet
0.67 0.26 0.83 0.27 0.90 0.08 1.00 0.77 0.86 0.05 0.89 0.76 0.67 0.18 0.80 0.42
(TL)
GoogleNet 0.64 0.19 0.83 0.41 0.91 0.05 0.98 0.87 0.84 0.02 0.87 0.81 0.66 0.09 0.75 0.55
ResNet 0.53 0.19 0.63 0.36 0.94 0.05 0.99 0.89 0.83 0.02 0.87 0.81 0.61 0.09 0.70 0.52
 21

To investigate sources of false reports, the misclassified IE data are shown in Table 5.

Almost all the mutual false negatives between the investigated DLMs were associated with the

IE data on the boundary. Higher false negatives in some models (S6 compared to S3-S5) while

models were trained on relatively similar datasets indicates that this inconsistency has external

sources. It is possible that the IE instrument was not properly positioned during the data

collection or defect construction and placement.

Table 5. Source of false negatives reports by DLMs.

Specimen No FNs Type (Quantity)
S1 8 Boundary (8)
S2 6 Boundary (6)
S3 2 Boundary (2)
S4 1 Boundary (1)
S5 3 Boundary (2)
S6 16 Boundary (13)
S7 8 Boundary (8)
S8 6 Boundary (6)
Comparison

In this section, the 1D CNN, as the best performing DLM, was compared to other

methods for IE data analysis in two subsections. In subsection one, a set of defect maps for

studied specimens were generated and compared using the proposed 1D CNN and the peak

frequency method. In subsection two, TPR, TNR, ACC, and F1 were computed and compared

using the proposed 1D CNN, and two a machine learning approaches using support vector

machine (SVM) and wavelet decomposition coupled with extreme learning method (ELM).

5.3.1 Conventional Method

Defect maps were used to compare the investigated DLMs to the peak frequency method.

A defect map shows the relationship between the spatial location of subsurface defects to a

certain property of the inspected deck obtained through a particular NDE method [35,48,52].

This property is the frequency associated with highest amplitude, e.g., vertical axis of the

spectrums shown in Figure 2. Using these frequencies, one can generate contour plots to present
 22

the defect maps. A similar approach was taken to create contour plots using the DLMs by

plotting the probability assigned to the defected class which essentially the probability of defect

presence. Figure 12 shows the defect maps generated by the peak frequency method and the best

performing DLM, 1D CNN, for all specimens (S1 through S8).

S1 (CONVENTIONAL)
S1 (1D CNN)
S2 (CONVENTIONAL)
S2 (1D CNN)
S4 (1D CNN) S4 (CONVENTIONAL) S3 (1D CNN) S3 (CONVENTIONAL)
23
S6 (1D CNN) S6 (CONVENTIONAL) S5 (1D CNN) S5 (CONVENTIONAL)
24
 25

S7(CONVENTIONAL)
S7 (1D CNN)
S8 (CONVENTIONAL)
S8 (1D CNN)

Figure 12. Defect maps generated by frequency analysis and 1D CNN.

Shallow delamination was detected easier by both approaches which was expected [35].

The proposed 1D DLM had difficulties when used on S6 and S8 as expected due to possible

construction or data acquisition errors. The 1D CNN provided a precise prediction of defects
 26

locations for all four defects type in all the specimens. In addition, the 1D CNNs produced a

better distinction between the sound and the defected concrete through a more tangible contrast

change in the defect maps compared to the frequency method. The results show not only that

deep learning is a feasible solution for IE data analysis but it was more robust in generating

defect maps than the conventional frequency analysis.

5.3.2 Comparison to Machine Learning Models

Metrics
Model TPR TNR ACC F1
(Mean, COV, Max, Min) (Mean, COV, Max, Min) (Mean, COV, Max, Min) (Mean, COV, Max, Min)
1D CNN
0.70 0.14 0.81 0.48 0.95 0.04 1.00 0.85 0.88 0.04 0.92 0.83 0.75 0.08 0.83 0.65
(proposed)
SVM []
ELM

Analysis of a New IE Dataset

The DLMs were successfully implemented for bridge evaluation in the previous section.

However, testing datasets were similar to training datasets in terms of defects, geometry, and

material properties. Even though there exist IE filed dataset in some public repositories, such as

FHWA InfoBridge [7], they are not validated with the ground truth. Therefore, the investigated

DLMs could not be validated on such datasets. To mimic the field investigation, the models were

used on a set of IE data acquired using a different IE device on a different bridge specimen. The

bridge specimen was built in the Center for Transportation Infrastructure Systems at the

University of Texas at El Paso, as shown in Figure 13 [85]. The 0.22 m thick specimen was

inspected by applying an IE device on 126 grid points with a sampling frequency of 400 kHz for

5 ms of data acquisition.
 27

Figure 13. Schematic plan of the validation bridge specimen with delamination.

First, the IE data of the specimen were analyzed using the peak frequency analysis which

resulted in a defect map shown in Figure 14a. The user tailored frequency method detected most

of the defected areas. Then the proposed 1D DLM was used to evaluate the new specimen

(Figure 14b). The 1D CNN model trained on all 8 specimens using the same training parameters

as before. The 1D CNN detected most of the defected area of the specimen; however, it reported

several false positives. Since not a single IE data of the new specimen was used during the

training, the new dataset was and the models were unfamiliar with respect to each other. Yet, the

1D CNN was able to detect most of the damaged areas. This shows the possibly of using these

models for bridge evaluations using IE in the field. With a larger and more diverse annotated

dataset it is likely to acquire substantially more accurate defect maps than the one shown in

Figure 14b.

(a)
 28

(b)

Figure 14. Defect maps of the validation specimen using (a) frequency method, (b) 1D CNN.

Conclusion

The feasibility of using deep learning models (DLMs) to classify impact echo (IE) data

on bridge decks to localize subsurface defects has been investigated in this paper for the first

time. Eight lab-made bridge specimens with four types of defects were constructed at the Federal

Highway Administration (FHWA) Advanced Sensing Technology (FAST) NDE laboratory.

These specimens were inspected using IE. Six DLMs were trained on the data from seven

specimens and then were used to classify the IE data on the remaining specimen. A bidirectional

long short-term memory (biLSTM) and a one-dimensional convolutional neural network (1D

CNN) were developed and applied directly on the IE signals. In addition, the IE signals were

converted into 2D representation, i.e., color images, through the short-time Fourier transform to

use pre-trained 2D CNNs with AlexNet, GoogleNet, and ResNet architectures. The proposed 1D

CNN outperformed other investigations by detecting 0.70 of the defects on average. This model

also had the lowest false positive average (0.05), highest accuracy (0.88), and highest F1 score

(0.75). The proposed 1D CNN was also considerably faster during the training compared to the

other DLMs. The defect maps generated by 1D CNN matched or exceeded the ones generated by

the peak frequency method by providing a more accurate localization of the defects. The

proposed 1D CNN was applied on a validation specimen with different dimensions to mimic the
 29

field testing. The model was able detect most of the defected areas although it reported more

false positives than the conventional peak frequency method due to lack of diversity in the

training dataset.

AUTHOR CONTRIBUTIONS

Sattar Dorafshan: Conceptualization, Methodology, Software, Validation, Formal

analysis, Investigation, Writing - Original Draft, Writing - Review & Editing, and Visualization.

Hoda Azari: Conceptualization, Resources, Validation, Supervision, Project administration, and

Writing - Review & Editing.

Acknowledgment

This research was sponsored by the Federal Highway Administration (FHWA). The

contents do not necessarily reflect the official views or policies of the FHWA. This research was

performed while the first author held a National Research Council (NRC) Research

Associateship award administrated by the National Academies of Sciences, Engineering, and

Medicine fellowships office and their support is greatly acknowledged.

References

[1] Hearn, G. (2007). Bridge inspection practices, A Synthesis of Highway Practice (Vol. 375).

Transportation Research Board. Washington, DC, https://doi.org/10.17226/14127

[2] Ryan, T. W., Hartle, R. A., Mann, J. E., & Danovich, L. J. (2012). Bridge inspector’s

reference manual. Report No. FHWA NHI, 03-001, U.S. Department of Transportation,

Washington, DC.

[3] Graybeal, B. A., Phares, B. M., Rolander, D. D., Moore, M., & Washer, G. (2002). Visual

inspection of highway bridges. Journal of nondestructive evaluation, 21(3), 67-83.

 30

[4] Dorafshan, S., & Maguire, M. (2018). Bridge inspection: human performance, unmanned

aerial systems and automation. Journal of Civil Structural Health Monitoring, 8(3), 443-476.

[5] Washer, G.; Hammed, M.; Brown, H.; Connor, R.; Jensen, P.; Fogg, J.; Salazar, J.; Leshko,

B.; Koonce, J.; Karper, C. Guidelines to Improve the Quality of Element-Level Bridge

Inspection Data; No. NCHRP Project 12-104; 2018, Washington DC, USA.

[6] Dorafshan, S., Maguire, M., Hoffer, N. V., & Coopmans, C. (2017, June). Challenges in

bridge inspection using small unmanned aerial systems: Results and lessons learned. In 2017

International Conference on Unmanned Aircraft Systems (ICUAS) (pp. 1722-1730). IEEE.

[7] FHWA (Federal Highway Administration). InfoBridge. https://infobridge.fhwa.dot.gov/Data

(accessed on 27 June 2019).

[8] Lattanzi, D., & Miller, G. (2017). Review of robotic infrastructure inspection

systems. Journal of Infrastructure Systems, 23(3), 04017004.

[9] Dorafshan, S., Thomas, R. J., & Maguire, M. (2018). Comparison of deep convolutional

neural networks and edge detectors for image-based crack detection in

concrete. Construction and Building Materials, 186, 1031-1045.

[10] Gibb, S., La, H. M., Le, T., Nguyen, L., Schmid, R., & Pham, H. (2018). Nondestructive

evaluation sensor fusion with autonomous robotic system for civil infrastructure

inspection. Journal of Field Robotics, 35(6), 988-1004.

[11] Dorafshan, S., Thomas, R. J., & Maguire, M. (2019). Benchmarking Image Processing

Algorithms for Unmanned Aerial System-Assisted Crack Detection in Concrete

Structures. Infrastructures, 4(2), 19.

 31

[12] Kim, H., Ahn, E., Cho, S., Shin, M., & Sim, S. H. (2017). Comparative analysis of image

binarization methods for crack identification in concrete structures. Cement and Concrete

Research, 99, 53-61.

[13] Farhidzadeh, A., Ebrahimkhanlou, A., & Salamone, S. (2014, March). A vision-based

technique for damage assessment of reinforced concrete structures. In Health Monitoring of

Structural and Biological Systems 2014 (Vol. 9064, p. 90642H). International Society for

Optics and Photonics.

[14] Dorafshan, S., & Maguire, M. (2017, June). Autonomous detection of concrete cracks on

bridge decks and fatigue cracks on steel members. In Digital Imaging 2017 (pp. 33-44).

[15] Luo, Q., Ge, B., & Tian, Q. (2019). A fast adaptive crack detection algorithm based on a

double-edge extraction operator of FSM. Construction and Building Materials, 204, 244-254.

[16] Koch, C., Georgieva, K., Kasireddy, V., Akinci, B., & Fieguth, P. (2015). A review on

computer vision based defect detection and condition assessment of concrete and asphalt

civil infrastructure. Advanced Engineering Informatics, 29(2), 196-210.

[17] Dorafshan, S., Maguire, M., & Chang, M. (2017, March). Comparing automated image-

based crack detection techniques in the spatial and frequency domains. In 26th ASNT

Research Symposium (pp. 34-42).

[18] Omar, T., & Nehdi, M. L. (2017). Remote sensing of concrete bridge decks using

unmanned aerial vehicle infrared thermography. Automation in Construction, 83, 360-371.

[19] Dorafshan, S.; Maguire, M.; Qi, X. Automatic Surface Crack Detection in Concrete

Structures Using OTSU Thresholding and Morphological Operations; Paper 1234; Civil and

Environmental Engineering Faculty Publications Logan UT: 2016. Available online:

https://digitalcommons.usu.edu/cee_facpub/1234 (accessed on 30 January 2019).

 32

[20] Dixit, A., & Wagatsuma, H. (2018, October). Comparison of Effectiveness of Dual Tree

Complex Wavelet Transform and Anisotropic Diffusion in MCA for Concrete Crack

Detection. In 2018 IEEE International Conference on Systems, Man, and Cybernetics

(SMC) (pp. 2681-2686). IEEE.

[21] Ebrahimkhanlou, A., Dubuc, B., & Salamone, S. (2019). A generalizable deep learning

framework for localizing and characterizing acoustic emission sources in riveted metallic

panels. Mechanical Systems and Signal Processing, 130, 248-272.

[22] Ebrahimkhanlou, A., Dubuc, B., & Salamone, S. (2019, April). A deep learning-based

framework for two-step localization and characterization of acoustic emission sources in

metallic panels using only one sensor. In Health Monitoring of Structural and Biological

Systems XIII (Vol. 10972, p. 1097209). International Society for Optics and Photonics.

[23] He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing

human-level performance on imagenet classification. In Proceedings of the IEEE

international conference on computer vision (pp. 1026-1034).

[24] Dodge, S., & Karam, L. (2017, July). A study and comparison of human and deep

learning recognition performance under visual distortions. In 2017 26th international

conference on computer communication and networks (ICCCN) (pp. 1-7). IEEE.

[25] Dorafshan, S., Thomas, R. J., & Maguire, M. (2018). SDNET2018: An annotated image

dataset for non-contact concrete crack detection using deep convolutional neural

networks. Data in brief, 21, 1664-1668.

[26] Dung, C. V. (2019). Autonomous concrete crack detection using deep fully convolutional

neural network. Automation in Construction, 99, 52-58.

 33

[27] Doulamis, A., Doulamis, N., Protopapadakis, E., & Voulodimos, A. (2018, October).

Combined convolutional neural networks and fuzzy spectral clustering for real time crack

detection in tunnels. In 2018 25th IEEE International Conference on Image Processing

(ICIP) (pp. 4153-4157). IEEE.

[28] Dorafshan, S., Thomas, R. J., Coopmans, C., & Maguire, M. (2018, June). Deep learning

neural networks for sUAS-assisted structural inspections: Feasibility and application. In 2018

International Conference on Unmanned Aircraft Systems (ICUAS) (pp. 874-882). IEEE.

[29] Atha, D. J., & Jahanshahi, M. R. (2018). Evaluation of deep learning approaches based

on convolutional neural networks for corrosion detection. Structural Health

Monitoring, 17(5), 1110-1128.

[30] Cha, Y. J., Choi, W., Suh, G., Mahmoudkhani, S., & Büyüköztürk, O. (2018).

Autonomous structural visual inspection using region‐based deep learning for detecting

multiple damage types. Computer‐Aided Civil and Infrastructure Engineering, 33(9), 731-

747.

[31] Azari, H., Lin, S., & Meng, D. (2019). Nondestructive Corrosion Evaluation of

Reinforced Concrete Bridge Decks with Overlays: An Experimental Study. Journal of

Testing and Evaluation, 48(1).

[32] FHWA (2015). Nondestructive Evaluation (NDE) Web Manual, Version 1.0. FAST NDE

Program, Federal Highway Administration Research and Technology. Available online:

https://fhwaapps.fhwa.dot.gov/ndep/. (accessed on 05 May 2019).

[33] Popovics, J. S., Roesler, J. R., Bittner, J., Amirkhanian, A. N., Brand, A. S., Gupta, P., &

Flowers, K. (2017). Ultrasonic imaging for concrete infrastructure condition assessment and

quality assurance. Illinois Center for Transportation/Illinois Department of Transportation.

 34

[34] Jalinoos, F., Tran, K. T., Nguyen, T. D., & Agrawal, A. K. (2017). Evaluation of Bridge

Abutments and Bounded Wall Type Structures with Ultraseismic Waveform

Tomography. Journal of Bridge Engineering, 22(12), 04017104.

[35] Lin, S., Shams, S., Choi, H., & Azari, H. (2018). Ultrasonic imaging of multi-layer

concrete structures. NDT & E International, 98, 101-109.

[36] Nguyen, T. D., Tran, K. T., & Gucunski, N. (2016). Detection of bridge-deck

delamination using full ultrasonic waveform tomography. Journal of Infrastructure

Systems, 23(2), 04016027.

[37] Azari, H., Meng, D., Choi, H., Shams, S., & Lin, S. (2019). Estimation of Wave Velocity

for Ultrasonic Imaging of Concrete Structures Based on Dispersion Analysis. Journal of

Testing and Evaluation, 48(2).

[38] Yehia, S., Abudayyeh, O., Nabulsi, S., & Abdelqader, I. (2007). Detection of common

defects in concrete bridge decks using nondestructive evaluation techniques. Journal of

Bridge Engineering, 12(2), 215-225.

[39] Dinh, K., Zayed, T., Romero, F., & Tarussov, A. (2014). Method for analyzing time-

series GPR data of concrete bridge decks. Journal of Bridge Engineering, 20(6), 04014086.

[40] Ma, X., Liu, H., Wang, M. L., & Birken, R. (2018). Automatic detection of steel rebar in

bridge decks from ground penetrating radar data. Journal of Applied Geophysics, 158, 93-

102.

[41] Dinh, K., Gucunski, N., Kim, J., & Duong, T. H. (2017). Method for attenuation

assessment of GPR data from concrete bridge decks. NDT & E International, 92, 50-58.
 35

[42] Dinh, K., Gucunski, N., & Duong, T. H. (2018). An algorithm for automatic localization

and detection of rebars from GPR data of concrete bridge decks. Automation in

Construction, 89, 292-298.

[43] Romero, F. A., Barnes, C. L., Azari, H., Nazarian, S., & Rascoe, C. D. (2019). Validation

of benefits of automated depth correction method: improving accuracy of ground-penetrating

radar deck deterioration maps. Transportation Research Record, 2522(1), 100-109.

[44] Gucunski, N., Romero, F., Kruschwitz, S., Feldmann, R., Abu-Hawash, A., & Dunn, M.

(2010). Multiple complementary nondestructive evaluation technologies for condition

assessment of concrete bridge decks. Transportation Research Record, 2201(1), 34-44.

[45] La, H. M., Lim, R. S., Basily, B. B., Gucunski, N., Yi, J., Maher, A., ... & Parvardeh, H.

(2013). Mechatronic systems design for an autonomous robotic system for high-efficiency

bridge deck inspection and evaluation. IEEE/ASME Transactions on Mechatronics, 18(6),

1655-1664.

[46] Tawhed, W. F., & Gassman, S. L. (2002). Damage assessment of concrete bridge decks

using impact-echo method. Materials Journal, 99(3), 273-281.

[47] Kee, S. H., Oh, T., Popovics, J. S., Arndt, R. W., & Zhu, J. (2011). Nondestructive bridge

deck testing with air-coupled impact-echo and infrared thermography. Journal of Bridge

Engineering, 17(6), 928-939.

[48] Gucunski, N., Kee, S., La, H., Basily, B., & Maher, A. (2015). Delamination and

concrete quality assessment of concrete bridge decks using a fully autonomous RABIT

platform. Structural Monitoring and Maintenance, 2(1), 19-34.

 36

[49] Choi, H., Shams, S., & Azari, H. (2018). Frequency Wave Number–Domain Analysis of

Air-Coupled Impact-Echo Tests in Concrete Slab. Journal of Infrastructure Systems, 24(3),

04018015.

[50] Choi, H., & Azari, H. (2017). Guided wave analysis of air-coupled impact-echo in

concrete slab. Computers and Concrete, 20(3), 257-262.

[51] Azari, H., Nazarian, S., & Yuan, D. (2014). Assessing sensitivity of impact echo and

ultrasonic surface waves methods for nondestructive evaluation of concrete

structures. Construction and Building Materials, 71, 384-391.

[52] Besaw, L. E., & Stimac, P. J. (2015, May). Deep convolutional neural networks for

classifying GPR B-scans. In Detection and Sensing of Mines, Explosive Objects, and

Obscured Targets XX (Vol. 9454, p. 945413). International Society for Optics and Photonics.

[53] Kim, N., Kim, K., An, Y. K., Lee, H. J., & Lee, J. J. (2018). Deep learning-based

underground object detection for urban road pavement. International Journal of Pavement

Engineering, 1-13.

[54] Kaur, P., Dana, K. J., Romero, F. A., & Gucunski, N. (2016). Automated GPR rebar

analysis for robotic bridge deck evaluation. IEEE transactions on cybernetics, 46(10), 2265-

2276.

[55] Wiwatrojanagul, P., Sahamitmongkol, R., Tangtermsirikul, S., & Khamsemanan, N.

(2017). A new method to determine locations of rebars and estimate cover thickness of RC

structures using GPR data. Construction and Building Materials, 140, 257-273.

[56] Epp, T., Svecova, D., & Cha, Y. J. (2018). Semi-Automated Air-Coupled Impact-Echo

Method for Large-Scale Parkade Structure. Sensors, 18(4), 1018.

 37

[57] Xu, J., Ren, Q., & Shen, Z. (2018). Analysis method of impact echo based on variational

mode decomposition. Journal of Vibroengineering, 20(7).

[58] Li, B., Cao, J., Xiao, J., Zhang, X., & Wang, H. (2014, June). Robotic impact-echo non-

destructive evaluation based on fft and svm. In Proceeding of the 11th World Congress on

Intelligent Control and Automation (pp. 2854-2859). IEEE.

[59] Igual, J., Salazar, A., Safont, G., & Vergara, L. (2015). Semi-supervised Bayesian

classification of materials with impact-echo signals. Sensors, 15(5), 11528-11550.

[60] Amini, K., Cetin, K., Ceylan,H., Taylor, P., (2018). Development of prediction models

for mechanical properties and durability of concrete using combined nondestructive tests.

Journal of Materials in Civil Engineering, 31(2). 04018378

[61] Völker, C., & Shokouhi, P. (2015). Multi sensor data fusion approach for automatic

honeycomb detection in concrete. NDT & E International, 71, 54-60.

[62] Xiao, X., Gao, B., yun Tian, G., & qing Wang, K. (2019). Fusion model of inductive

thermography and ultrasound for nondestructive testing. Infrared Physics & Technology,

101, 162-170.

[63] Zhang, J. K., Yan, W., & Cui, D. M. (2016). Concrete condition assessment using

impact-echo method and extreme learning machines. Sensors, 16(4), 447.

[64] ASTM C 1383. (2004). Test method for measuring the P-wave speed and the thickness of

concrete plates using the Impact-Echo method, ASTM Standards. vol. 04.02. ASTM: West

Conshohocken, PA.

[65] Medina, R., & Garrido, M. (2007). Improving impact-echo method by using cross-

spectral density. Journal of sound and vibration, 304(3-5), 769-778.

 38

[66] Lin, S., Meng, D., Choi, H., Shams, S., & Azari, H. (2018). Laboratory assessment of

nine methods for nondestructive evaluation of concrete bridge decks with

overlays. Construction and Building Materials, 188, 966-982.

[67] Elman, J. L. (1990). Finding structure in time. Cognitive science, 14(2), 179-211.

[68] Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE

Transactions on Signal Processing, 45(11), 2673-2681.

[69] Abdeljaber, O., Avci, O., Kiranyaz, M. S., Boashash, B., Sodano, H., & Inman, D. J.

(2018). 1-D CNNs for structural damage detection: verification on a structural health

monitoring benchmark data. Neurocomputing, 275, 1308-1317.

[70] Zhang, Y., Miyamori, Y., Mikami, S., & Saito, T. (2019). Vibration‐based structural state

identification by a 1‐dimensional convolutional neural network. Computer‐Aided Civil and

Infrastructure Engineering.

[71] Carino, N. J., Sansalone, M., & Hsu, N. N. (1986). Flaw detection in concrete by

frequency spectrum analysis of impact-echo waveforms. International advances in

nondestructive testing, 12, 117-146.

[72] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep

convolutional neural networks. In Advances in neural information processing systems (pp.

1097-1105).

[73] Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A.

(2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer

vision and pattern recognition (pp. 1-9).

 39

[74] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image

recognition. In Proceedings of the IEEE conference on computer vision and pattern

recognition (pp. 770-778).

[75] Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009, June). Imagenet: A

large-scale hierarchical image database. In 2009 IEEE conference on computer vision and

pattern recognition (pp. 248-255). IEEE.

[76] Abdel-Hamid, O., Deng, L., & Yu, D. (2013, August). Exploring convolutional neural

network structures and optimization techniques for speech recognition. In Interspeech (Vol.

2013, pp. 1173-5).

[77] Wyse, L. (2017, May). Audio Spectrogram Representations for Processing with

Convolutional Neural Networks. In Proceedings of the First International Conference on

Deep Learning and Music, Anchorage, US, May, 2017., pp. 37-41(pp. 37-41).

[78] Chorowski, J., Weiss, R. J., Saurous, R. A., & Bengio, S. (2018, April). On using

backpropagation for speech texture generation and voice conversion. In 2018 IEEE

International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2256-

2260). IEEE.

[79] Pritt, M., & Chern, G. (2017, October). Satellite Image Classification with Deep

Learning. In 2017 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) (pp. 1-7).

IEEE.

[80] Wu, R. T., Singla, A., Jahanshahi, M. R., Bertino, E., Ko, B. J., & Verma, D. (2019).

Pruning deep convolutional neural networks for efficient edge computing in condition

assessment of infrastructures. Computer‐Aided Civil and Infrastructure Engineering..

 40

[81] Azari, H., Yuan, D., Nazarian, S., & Gucunski, N. (2012). Sonic methods to detect

delamination in concrete bridge decks: Impact of testing configuration and data analysis

approach. Transportation Research Record, 2292(1), 113-124.

View publication stats