Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Deep Convolutional Neural Networks
share announcement

Deep Convolutional Neural Networks

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (20 March 2023) | Viewed by 54895

Special Issue Editor

Dr. Ha Young Kim

E-Mail Website
Guest Editor
Graduate School of Information, Yonsei University, Seoul 03722, Korea
Interests: deep learning in real-time applications; automated machine learning; explainable deep learning; multi-modality fusion

Special Issue Information

Dear Colleagues,

Recently, deep learning algorithms have come to prominence owing to their excellent performance among machine learning algorithms. Particularly, such algorithms provide human-level performance in tasks such as face recognition based on deep convolutional neural networks, and they are being actively researched in computer vision fields such as image classification, object detection, instance segmentation, video classification, and gesture recognition. Furthermore, the areas of application of deep convolutional neural networks are expanding to the industries in most fields, such as medical, construction, agriculture, and manufacturing.

Convolutional neural networks can learn local and spatial relationships through filters, maintain local information, and learn patterns in a translation-invariant manner through weight sharing. Additionally, for high-dimensional data such as images, the number of parameters in these networks is much smaller than that in basic deep feedforward neural networks, which is advantageous in terms of overfitting prevention and the number of required data. Moreover, edge and texture features are learned in the low layers, partial patterns in the middle layers, and abstract and high-level features in the high layers. In other words, the convolutional neural network learns patterns hierarchically.

Owing to the aforementioned advantages, studies based on convolutional neural networks are being actively conducted not only in the field of computer vision using images but also in natural language processing using text and speech data and in prediction studies using high-dimensional time-series data. Therefore, the main focus of this Special Issue is on new methodologies based on deep convolutional neural networks applied to various industries such as medical, construction, manufacturing, and agriculture. Furthermore, this issue includes novel architecture studies of deep convolutional neural networks for various data types such as text, time series, and images. Additionally, methodologies that can compact and speed up deep convolutional neural networks for on-device applications are covered.

Dr. Ha Young Kim
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Deep convolutional neural networks in industry applications
  • Deep convolutional neural networks in real-time applications
  • Deep convolutional neural networks for multivariate time-series prediction
  • Deep convolutional neural networks for natural language processing
  • Fast deep convolutional neural network
  • Deep convolutional neural networks for prediction, detection, segmentation, and generation

Published Papers (22 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

21 pages, 2870 KiB  
Article
Multi-Defect Identification of Concrete Piles Based on Low Strain Integrity Test and Two-Channel Convolutional Neural Network
by Chuan-Sheng Wu, Man Ge, Ling-Ling Qi, De-Bing Zhuo, Jian-Qiang Zhang, Tian-Qi Hao and Yang-Xia Peng
Appl. Sci. 2023, 13(6), 3530; https://0-doi-org.brum.beds.ac.uk/10.3390/app13063530 - 09 Mar 2023
Cited by 1 | Viewed by 1359
Abstract
Defects in different positions and degrees in pile foundations will affect the building structure’s safety and the foundation’s bearing capacity. The efficiency and accuracy of using traditional methods to identify multi-defect types of pile foundations are very low, so finding suitable methods to [...] Read more.
Defects in different positions and degrees in pile foundations will affect the building structure’s safety and the foundation’s bearing capacity. The efficiency and accuracy of using traditional methods to identify multi-defect types of pile foundations are very low, so finding suitable methods to improve their related indicators for pile foundation safety and engineering applications is necessary. In this paper, under the condition of secondary development of finite element software ABAQUS to obtain the time-domain signal database of six kinds of multi-defect pile foundations, a multi-defect type identification method of pile foundations based on two-channel convolutional neural network (TC-CNN) and low-strain pile integrity test (LSPIT) is proposed. Firstly, simulated time-domain signals of the dynamic measurements that match the experimental results performed wavelet packet denoising. Secondly, the 1D time-domain signals before and after denoising and the corresponding 2D wavelet time–frequency maps are inputs to retain more data information and prevent overfitting. Finally, TC-CNN achieved the multi-defect type identification of concrete piles. Compared with the single-channel convolutional neural network, this method can effectively fuse 1D and 2D features, extract more potential features, and make the classification accuracy reach 99.17%. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

13 pages, 8826 KiB  
Article
Free-Breathing and Ungated Cardiac MRI Reconstruction Using a Deep Kernel Representation
by Qing Zou, Abdul Haseeb Ahmed, Sanja Dzelebdzic and Tarique Hussain
Appl. Sci. 2023, 13(4), 2281; https://0-doi-org.brum.beds.ac.uk/10.3390/app13042281 - 10 Feb 2023
Cited by 1 | Viewed by 1462
Abstract
Free-breathing and ungated cardiac MRI is a challenging problem due to the cardiac motion and respiration motion, which are not tracked. In this work, we propose an unsupervised deep kernel method for reconstructing real-time free-breathing and ungated cardiac MRI from highly undersampled k-t [...] Read more.
Free-breathing and ungated cardiac MRI is a challenging problem due to the cardiac motion and respiration motion, which are not tracked. In this work, we propose an unsupervised deep kernel method for reconstructing real-time free-breathing and ungated cardiac MRI from highly undersampled k-t space measurements. We propose implementing the feature map and kernel function in the kernel method using CNNs. The parameters of the CNNs are learned from specific-subject data directly. Comparisons with state-of-the-art kernel methods show improved performance of the proposed deep kernel method. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

17 pages, 3524 KiB  
Article
Deep Machine Learning-Based Water Level Prediction Model for Colombo Flood Detention Area
by Madhawa Herath, Tharaka Jayathilaka, Yukinobu Hoshino and Upaka Rathnayake
Appl. Sci. 2023, 13(4), 2194; https://0-doi-org.brum.beds.ac.uk/10.3390/app13042194 - 08 Feb 2023
Cited by 7 | Viewed by 3042
Abstract
Machine learning has already been proven as a powerful state-of-the-art technique for many non-linear applications, including environmental changes and climate predictions. Wetlands are among some of the most challenging and complex ecosystems for water level predictions. Wetland water level prediction is vital, as [...] Read more.
Machine learning has already been proven as a powerful state-of-the-art technique for many non-linear applications, including environmental changes and climate predictions. Wetlands are among some of the most challenging and complex ecosystems for water level predictions. Wetland water level prediction is vital, as wetlands have their own permissible water levels. Exceeding these water levels can cause flooding and other severe environmental damage. On the other hand, the biodiversity of the wetlands is threatened by the sudden fluctuation of water levels. Hence, early prediction of water levels benefits in mitigating most of such environmental damage. However, monitoring and predicting the water levels in wetlands worldwide have been limited owing to various constraints. This study presents the first-ever application of deep machine-learning techniques (deep neural networks) to predict the water level in an urban wetland in Sri Lanka located in its capital. Moreover, for the first time in water level prediction, it investigates two types of relationships: the traditional relationship between water levels and environmental factors, including temperature, humidity, wind speed, and evaporation, and the temporal relationship between daily water levels. Two types of low load artificial neural networks (ANNs) were developed and employed to analyze two relationships which are feed forward neural networks (FFNN) and long short-term memory (LSTM) neural networks, to conduct the comparison on an unbiased common ground. The LSTM has outperformed FFNN and confirmed that the temporal relationship is much more robust in predicting wetland water levels than the traditional relationship. Further, the study identified interesting relationships between prediction accuracy, data volume, ANN type, and degree of information extraction embedded in wetland data. The LSTM neural networks (NN) has achieved substantial performance, including R2 of 0.8786, mean squared error (MSE) of 0.0004, and mean absolute error (MAE) of 0.0155 compared to existing studies. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

29 pages, 9792 KiB  
Article
Predicting the Porosity in Selective Laser Melting Parts Using Hybrid Regression Convolutional Neural Network
by Nawaf Mohammad H. Alamri, Michael Packianather and Samuel Bigot
Appl. Sci. 2022, 12(24), 12571; https://0-doi-org.brum.beds.ac.uk/10.3390/app122412571 - 08 Dec 2022
Cited by 5 | Viewed by 1319
Abstract
Assessing the porosity in Selective Laser Melting (SLM) parts is a challenging issue, and the drawback of using the existing gray value analysis method to assess the porosity is the difficulty and subjectivity in selecting a uniform grayscale threshold to convert a single [...] Read more.
Assessing the porosity in Selective Laser Melting (SLM) parts is a challenging issue, and the drawback of using the existing gray value analysis method to assess the porosity is the difficulty and subjectivity in selecting a uniform grayscale threshold to convert a single slice to binary image to highlight the porosity. This paper proposes a new approach based on the use of a Regression Convolutional Neural Network (RCNN) algorithm to predict the percent of porosity in CT scans of finished SLM parts, without the need for subjective difficult thresholding determination to convert a single slice to a binary image. In order to test the algorithm, as the training of the RCNN would require a large amount of experimental data, this paper proposed a new efficient approach of creating artificial porosity images mimicking the real CT scan slices of the finished SLM part with a similarity index of 0.9976. Applying RCNN improved porosity prediction accuracy from 68.60% for image binarization method to 75.50% using the RCNN. The algorithm was then further developed by optimizing its parameters using Bees Algorithm (BA), which is known to mimic the behavior of honeybees, and the hybrid Bees Regression Convolutional Neural Network (BA-RCNN) produced better prediction accuracy with a value of 85.33%. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

15 pages, 990 KiB  
Article
Research on Generalized Hybrid Probability Convolutional Neural Network
by Wenyi Zhou, Hongguang Fan, Jihong Zhu, Hui Wen and Ying Xie
Appl. Sci. 2022, 12(21), 11301; https://0-doi-org.brum.beds.ac.uk/10.3390/app122111301 - 07 Nov 2022
Cited by 1 | Viewed by 1178
Abstract
This paper first studies the generalization ability of the convolutional layer as a feature mapper (CFM) for extracting image features and the classification ability of the multilayer perception (MLP) in a CNN. Then, a novel generalized hybrid probability convolutional neural network (GHP-CNN) is [...] Read more.
This paper first studies the generalization ability of the convolutional layer as a feature mapper (CFM) for extracting image features and the classification ability of the multilayer perception (MLP) in a CNN. Then, a novel generalized hybrid probability convolutional neural network (GHP-CNN) is proposed to solve abstract feature classification with an unknown distribution form. To measure the generalization ability of the CFM, a new index is defined and the positive correlation between it and the CFM is researched. Generally, a fully trained CFM can extract features that are beneficial to classification, regardless of whether the data participate in training the CFM. In the CNN, the fully connected layer in the MLP is not always optimal, and the extracted abstract feature has an unknown distribution. Thus, an improved classifier called the structure-optimized probabilistic neural network (SOPNN) is used for abstract feature classification in the GHP-CNN. In the SOPNN, the separability information is not lost in the normalization process, and the final classification surface is close to the optimal classification surface under the Bayesian criterion. The proposed GHP-CNN utilizes the generalization ability of the CFM and the classification ability of the SOPNN. Experiments show that the proposed network has better classification ability than the existing hybrid neural networks. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

13 pages, 1372 KiB  
Article
Application of Neural Networks for Water Meter Body Assembly Process Optimization
by Marcin Suszyński, Artur Meller, Katarzyna Peta, Marek Trączyński, Marcin Butlewski and Frantisek Klimenda
Appl. Sci. 2022, 12(21), 11160; https://0-doi-org.brum.beds.ac.uk/10.3390/app122111160 - 03 Nov 2022
Cited by 1 | Viewed by 1201
Abstract
The proposed model of the neural network (NN) describes the optimization task of the water meter body assembly process, based on 18 selected production parameters. The aim of this network was to obtain a certain value of radial runout after the assembly. The [...] Read more.
The proposed model of the neural network (NN) describes the optimization task of the water meter body assembly process, based on 18 selected production parameters. The aim of this network was to obtain a certain value of radial runout after the assembly. The tolerance field for this parameter is 0.2 mm. The repeatability of this value is difficult to achieve during production. To find the most effective networks, 1000 of their models were made (using various training methods). Ten NN with lowest errors of the output value prediction were chosen for further analysis. During model validation the best network achieved the efficiency of 93%, and the sum of squared residuals (SSR) was 0.007. The example of the prediction of the value of radial runout of machine parts presented in this paper confirms the adopted statement about the usefulness of the presented method for industrial conditions and is based on the analysis of hundreds of thousands of parametric and descriptive data on the process flow collected to create an effective network model. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

21 pages, 8594 KiB  
Article
A Multi-Scale Contextual Information Enhancement Network for Crack Segmentation
by Lili Zhang, Yang Liao, Gaoxu Wang, Jun Chen and Huibin Wang
Appl. Sci. 2022, 12(21), 11135; https://0-doi-org.brum.beds.ac.uk/10.3390/app122111135 - 02 Nov 2022
Cited by 4 | Viewed by 1584
Abstract
In recent years, convolutional neural-network-based crack segmentation methods have performed excellently. However, existing crack segmentation methods still suffer from background noise interference, such as dirt patches and pitting, as well as the imprecise segmentation of fine-grained spatial structures. This is mainly due to [...] Read more.
In recent years, convolutional neural-network-based crack segmentation methods have performed excellently. However, existing crack segmentation methods still suffer from background noise interference, such as dirt patches and pitting, as well as the imprecise segmentation of fine-grained spatial structures. This is mainly due to the fact that convolutional neural networks dilute low-level spatial information in the process of extracting deep semantic features, and the network cannot obtain accurate context awareness because of the limitation of the actual receptive field size. To address these problems, an encoder–decoder crack segmentation network based on multi-scale contextual information enhancement is proposed. First, a new architecture of skip connection is proposed, enabling the network to obtain refined crack segmentation results; then, a contextual feature enhancement module is designed to make the network more effective at distinguishing between cracks and background noise; finally, the deformable convolution is introduced into the encoder network to further enhance its ability to extract the diverse morphological features of cracks by adaptively adjusting the sampling area and the receptive field size. Experiments show that the proposed method is effective in crack segmentation and outperforms mainstream segmentation networks such as DeepLab V3+ and UNet++. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

15 pages, 5923 KiB  
Article
A DC Arc Fault Detection Method Based on AR Model for Photovoltaic Systems
by Yao Wang, Xiang Li, Yunsheng Ban, Xiaochen Ma, Chenguang Hao, Jiawang Zhou and Huimao Cai
Appl. Sci. 2022, 12(20), 10379; https://0-doi-org.brum.beds.ac.uk/10.3390/app122010379 - 14 Oct 2022
Cited by 2 | Viewed by 2493
Abstract
DC arc faults are dangerous to photovoltaic (PV) systems and can cause serious electric fire hazards and property damage. Because the PV inverter works in a high−frequency pulse width modulation (PWM) control mode, the arc fault detection is prone to nuisance tripping due [...] Read more.
DC arc faults are dangerous to photovoltaic (PV) systems and can cause serious electric fire hazards and property damage. Because the PV inverter works in a high−frequency pulse width modulation (PWM) control mode, the arc fault detection is prone to nuisance tripping due to PV inverter noises. An arc fault detection method based on the autoregressive (AR) model is proposed. A test platform collects the database of this research according to the UL1699B standard, in which three different types of PV inverters are taken into consideration to make it more generalized. The arc current can be considered a nonstationary random signal while the noise of the PV inverter is not. According to the difference in randomness features between an arc and the noise, a detection method based on the AR model is proposed. The Burg algorithm is used to determine model coefficients, while the Akaike Information Criterion (AIC) is applied to explore the best order of the proposed model. The correlation coefficient difference of the model coefficients plays a role as a criterion to identify if there is an arc fault. Moreover, a prototype circuit based on the TMS320F28033 MCU is built for algorithm verification. Test results show that the proposed algorithm can identify an arc fault without a false positive under different PV inverter conditions. The fault clearing time is between 60 ms to 80 ms, which can meet the requirement of 200 ms specified by the standard. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

19 pages, 6539 KiB  
Article
Energy Ratio Variation-Based Structural Damage Detection Using Convolutional Neural Network
by Chuan-Sheng Wu, Yang-Xia Peng, De-Bing Zhuo, Jian-Qiang Zhang, Wei Ren and Zhen-Yang Feng
Appl. Sci. 2022, 12(20), 10220; https://0-doi-org.brum.beds.ac.uk/10.3390/app122010220 - 11 Oct 2022
Cited by 4 | Viewed by 1370
Abstract
In the field of structural health monitoring (SHM), with the mature development of artificial intelligence, deep learning-based structural damage identification techniques have attracted wide attention. In this paper, the convolutional neural network (CNN) is used to extract the damage feature of simple supported [...] Read more.
In the field of structural health monitoring (SHM), with the mature development of artificial intelligence, deep learning-based structural damage identification techniques have attracted wide attention. In this paper, the convolutional neural network (CNN) is used to extract the damage feature of simple supported steel beams. Firstly, the transient dynamic analysis of the steel beam is carried out by finite element software, and the acceleration response signals under different damage scenarios are obtained. Then, the acceleration response signal is decomposed by wavelet packet decomposition (WPD) to extract the wavelet packet band energy ratio variation (ERV) index as the training sample of CNN. Subsequently, the vibration experiment of a simple supported steel beam was carried out, and the results were compared with the numerical simulation results. The characteristic indexes were obtained by making corresponding changes to the vibration signal, and then, the experimental data were input into the CNN to predict the effect of damage detection. The results show that the method can successfully detect the intact structure, single damage, and multiple damages with an accuracy of 95.14% under impact load, and the performance is better than that of support vector machine (SVM), with good robustness. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

10 pages, 1150 KiB  
Communication
Global–Local Self-Attention Based Transformer for Speaker Verification
by Fei Xie, Dalong Zhang and Chengming Liu
Appl. Sci. 2022, 12(19), 10154; https://0-doi-org.brum.beds.ac.uk/10.3390/app121910154 - 10 Oct 2022
Cited by 3 | Viewed by 1757
Abstract
Transformer models are now widely used for speech processing tasks due to their powerful sequence modeling capabilities. Previous work determined an efficient way to model speaker embeddings using the Transformer model by combining transformers with convolutional networks. However, traditional global self-attention mechanisms lack [...] Read more.
Transformer models are now widely used for speech processing tasks due to their powerful sequence modeling capabilities. Previous work determined an efficient way to model speaker embeddings using the Transformer model by combining transformers with convolutional networks. However, traditional global self-attention mechanisms lack the ability to capture local information. To alleviate these problems, we proposed a novel global–local self-attention mechanism. Instead of using local or global multi-head attention alone, this method performs local and global attention in parallel in two parallel groups to enhance local modeling and reduce computational cost. To better handle local location information, we introduced locally enhanced location encoding in the speaker verification task. The experimental results of the VoxCeleb1 test set and the VoxCeleb2 dev set demonstrated the improved effect of our proposed global–local self-attention mechanism. Compared with the Transformer-based Robust Embedding Extractor Baseline System, the proposed speaker Transformer network exhibited better performance in the speaker verification task. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

9 pages, 563 KiB  
Communication
Graph Convolutional Networks with POS Gate for Aspect-Based Sentiment Analysis
by Dahye Kim, YoungJin Kim and Young-Seob Jeong
Appl. Sci. 2022, 12(19), 10134; https://0-doi-org.brum.beds.ac.uk/10.3390/app121910134 - 09 Oct 2022
Cited by 6 | Viewed by 1544
Abstract
We make daily comments on online platforms (e.g., social networks), and such natural language texts often contain sentiment (e.g., positive and negative) for certain aspects (e.g., food and service). If we can automatically extract the aspect-based sentiment from the texts, then it will [...] Read more.
We make daily comments on online platforms (e.g., social networks), and such natural language texts often contain sentiment (e.g., positive and negative) for certain aspects (e.g., food and service). If we can automatically extract the aspect-based sentiment from the texts, then it will help many services or products to overcome their limitations of particular aspects. There have been studies of aspect sentiment classification (ASC) that finds sentiment towards particular aspects. Recent studies mostly adopt deep-learning models or graph neural networks as these techniques are capable of capturing linguistic patterns that contributed to performance improvement in various natural language processing tasks. In this paper, for the ASC task, we propose a new hybrid architecture of graph convolutional network (GCN) and recurrent neural network. We design a gate mechanism that jointly models word embeddings and syntactic representation of sentences. By experimental results on five datasets, we show that the proposed model outperforms other recent models and also verify that the gate mechanism contributes to the performance improvement. The overall F1 scores that we achieved is 66.64∼76.80%. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

15 pages, 773 KiB  
Article
Deep Neural Network Model for Evaluating and Achieving the Sustainable Development Goal 16
by Ananya Misra, Emmanuel Okewu, Sanjay Misra and Luis Fernández-Sanz
Appl. Sci. 2022, 12(18), 9256; https://0-doi-org.brum.beds.ac.uk/10.3390/app12189256 - 15 Sep 2022
Cited by 2 | Viewed by 1667
Abstract
The decision-making process for attaining Sustainable Development Goals (SDGs) can be enhanced through the use of predictive modelling. The application of predictive tools like deep neural networks (DNN) empowers stakeholders with quality information and promotes open data policy for curbing corruption. The anti-corruption [...] Read more.
The decision-making process for attaining Sustainable Development Goals (SDGs) can be enhanced through the use of predictive modelling. The application of predictive tools like deep neural networks (DNN) empowers stakeholders with quality information and promotes open data policy for curbing corruption. The anti-corruption drive is a cardinal component of SDG 16 which is aimed at strengthening state institutions and promoting social justice for the attainment of all 17 SDGs. This study examined the implementation of the SDGs in Nigeria and modelled the 2017 national corruption survey data using a DNN. We experimentally tested the efficacy of DNN optimizers using a standard image dataset from the Modified National Institute of Standards and Technology (MNIST). The outcomes validated our claims that predictive analytics could enhance decision-making through high-level accuracies as posted by the optimizers: Adam 98.2%; Adadelta 98.4%; SGD 94.9%; RMSProp 98.1%; Adagrad 98.1%. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

23 pages, 5904 KiB  
Article
Reconstruction of Motion Images from Single Two-Dimensional Motion-Blurred Computed Tomographic Image of Aortic Valves Using In Silico Deep Learning: Proof of Concept
by Yawu Long, Ichiro Sakuma and Naoki Tomii
Appl. Sci. 2022, 12(18), 9044; https://0-doi-org.brum.beds.ac.uk/10.3390/app12189044 - 08 Sep 2022
Viewed by 1322
Abstract
The visualization of motion is important in the diagnosis and treatment of aortic valve disease. It is difficult to perform using computed tomography (CT) because of motion blur. Existing research focuses on suppressing or removing motion blur. The purpose of this study is [...] Read more.
The visualization of motion is important in the diagnosis and treatment of aortic valve disease. It is difficult to perform using computed tomography (CT) because of motion blur. Existing research focuses on suppressing or removing motion blur. The purpose of this study is to prove the feasibility of inferring motion images using motion information from a motion-blurred CT image. An in silico learning method is proposed, to infer 60 motion images from a two-dimensional (2D) motion-blurred CT image, to verify the concept. A dataset of motion-blurred CT images and motion images was generated using motion and CT simulators to train a deep neural network. The trained model was evaluated using two image similarity evaluation metrics, a structural similarity index measure (0.97 ± 0.01), and a peak signal-to-noise ratio (36.0 ± 1.3 dB), as well as three motion feature evaluation metrics, maximum opening distance error between endpoints (0.7 ± 0.6 mm), maximum-swept area velocity error between adjacent images (393.3 ± 423.3 mm2/s), and opening time error (5.5 ± 5.5 ms). According to the results, the trained model can successfully infer 60 motion images from a motion-blurred CT image. This study demonstrates the feasibility of inferring motion images from a motion-blurred CT image under simulated conditions. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

12 pages, 2357 KiB  
Article
Real-Time Face Mask Detection to Ensure COVID-19 Precautionary Measures in the Developing Countries
by Haleem Farman, Taimoor Khan, Zahid Khan, Shabana Habib, Muhammad Islam and Adel Ammar
Appl. Sci. 2022, 12(8), 3879; https://0-doi-org.brum.beds.ac.uk/10.3390/app12083879 - 12 Apr 2022
Cited by 12 | Viewed by 3145
Abstract
Recently, the rapid transmission of Coronavirus 2019 (COVID-19) is causing a significant health crisis worldwide. The World Health Organization (WHO) issued several guidelines for protection against the spreading of COVID-19. According to the WHO, the most effective preventive measure against COVID-19 is wearing [...] Read more.
Recently, the rapid transmission of Coronavirus 2019 (COVID-19) is causing a significant health crisis worldwide. The World Health Organization (WHO) issued several guidelines for protection against the spreading of COVID-19. According to the WHO, the most effective preventive measure against COVID-19 is wearing a mask in public and crowded areas. It is quite difficult to manually monitor and determine people with masks and no masks. In this paper, different deep learning architectures were used for better results evaluations. After extensive experimentation, we selected a custom model having the best performance to identify whether people wear a face mask or not and allowing an easy deployment on a small device such as a Jetson Nano. The experimental evaluation is performed on the custom dataset that is developed from the website (See data collection section) after applying different masks on those images. The proposed model in comparison with other methods produced higher accuracy (99% for training accuracy and 99% for validation accuracy). Moreover, the proposed method can be deployed on resource-constrained devices. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

13 pages, 1565 KiB  
Article
Risk Factor Recognition for Automatic Safety Management in Construction Sites Using Fast Deep Convolutional Neural Networks
by Jeongeun Park, Hyunjae Lee and Ha Young Kim
Appl. Sci. 2022, 12(2), 694; https://0-doi-org.brum.beds.ac.uk/10.3390/app12020694 - 11 Jan 2022
Cited by 9 | Viewed by 2412
Abstract
Many industrial accidents occur at construction sites. Several countries are instating safety management measures to reduce industrial accidents at construction sites. However, there are few technical measures relevant to this task, and there are safety blind spots related to differences in human resources’ [...] Read more.
Many industrial accidents occur at construction sites. Several countries are instating safety management measures to reduce industrial accidents at construction sites. However, there are few technical measures relevant to this task, and there are safety blind spots related to differences in human resources’ capabilities. We propose a deep convolutional neural network that automatically recognizes possible material and human risk factors in the field regardless of individual management capabilities. The most suitable learning method and model for this study’s task and environment were experimentally identified, and visualization was performed to increase the interpretability of the model’s prediction results. The fine-tuned Safety-MobileNet model showed a high performance of 99.79% (30 ms), demonstrating its high potential to be applied in actual construction sites. In addition, via visualization, the cause of the model’s confusion of classes could be found in a dataset that the model did not predict correctly, and insights for result analysis could be presented. The material and human risk factor recognition model presented in this study can contribute to solving various practical problems, such as the absence of accident prevention systems, the limitations of human resources for safety management, and the difficulties in applying safety management systems to small construction companies. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

23 pages, 41642 KiB  
Article
An Experimental Study on State Representation Extraction for Vision-Based Deep Reinforcement Learning
by Junkai Ren, Yujun Zeng, Sihang Zhou and Yichuan Zhang
Appl. Sci. 2021, 11(21), 10337; https://0-doi-org.brum.beds.ac.uk/10.3390/app112110337 - 03 Nov 2021
Cited by 2 | Viewed by 1910
Abstract
Scaling end-to-end learning to control robots with vision inputs is a challenging problem in the field of deep reinforcement learning (DRL). While achieving remarkable success in complex sequential tasks, vision-based DRL remains extremely data-inefficient, especially when dealing with high-dimensional pixels inputs. Many recent [...] Read more.
Scaling end-to-end learning to control robots with vision inputs is a challenging problem in the field of deep reinforcement learning (DRL). While achieving remarkable success in complex sequential tasks, vision-based DRL remains extremely data-inefficient, especially when dealing with high-dimensional pixels inputs. Many recent studies have tried to leverage state representation learning (SRL) to break through such a barrier. Some of them could even help the agent learn from pixels as efficiently as from states. Reproducing existing work, accurately judging the improvements offered by novel methods, and applying these approaches to new tasks are vital for sustaining this progress. However, the demands of these three aspects are seldom straightforward. Without significant criteria and tighter standardization of experimental reporting, it is difficult to determine whether improvements over the previous methods are meaningful. For this reason, we conducted ablation studies on hyperparameters, embedding network architecture, embedded dimension, regularization methods, sample quality and SRL methods to compare and analyze their effects on representation learning and reinforcement learning systematically. Three evaluation metrics are summarized, including five baseline algorithms (including both value-based and policy-based methods) and eight tasks are adopted to avoid the particularity of each experiment setting. We highlight the variability in reported methods and suggest guidelines to make future results in SRL more reproducible and stable based on a wide number of experimental analyses. We aim to spur discussion about how to assure continued progress in the field by minimizing wasted effort stemming from results that are non-reproducible and easily misinterpreted. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Graphical abstract

19 pages, 4403 KiB  
Article
A CNN-Based Advertisement Recommendation through Real-Time User Face Recognition
by Gihwi Kim, Ilyoung Choi, Qinglong Li and Jaekyeong Kim
Appl. Sci. 2021, 11(20), 9705; https://0-doi-org.brum.beds.ac.uk/10.3390/app11209705 - 18 Oct 2021
Cited by 13 | Viewed by 3206
Abstract
The advertising market’s use of smartphones and kiosks for non-face-to-face ordering is growing. An advertising video recommender system is needed that continuously shows advertising videos that match a user’s taste and displays other advertising videos quickly for unwanted advertisements. However, it is difficult [...] Read more.
The advertising market’s use of smartphones and kiosks for non-face-to-face ordering is growing. An advertising video recommender system is needed that continuously shows advertising videos that match a user’s taste and displays other advertising videos quickly for unwanted advertisements. However, it is difficult to make a recommender system to identify users’ dynamic preferences in real time. In this study, we propose an advertising video recommendation procedure based on computer vision and deep learning, which uses changes in users’ facial expressions captured at every moment. Facial expressions represent a user’s emotions toward advertisements. We can utilize facial expressions to find a user’s dynamic preferences. For such a purpose, a CNN-based prediction model was developed to predict ratings, and a SIFT algorithm-based similarity model was developed to search for users with similar preferences in real time. To evaluate the proposed recommendation procedure, we experimented with food advertising videos. The experimental results show that the proposed procedure is superior to benchmark systems such as a random recommendation, an average rating approach, and a typical collaborative filtering approach in recommending advertising videos to both existing users and new users. From these results, we conclude that facial expressions are a critical factor for advertising video recommendations and are helpful in properly addressing the new user problem in existing recommender systems. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

16 pages, 5810 KiB  
Article
Prediction of Beck Depression Inventory Score in EEG: Application of Deep-Asymmetry Method
by Min Kang, Seokhwan Kang and Youngho Lee
Appl. Sci. 2021, 11(19), 9218; https://0-doi-org.brum.beds.ac.uk/10.3390/app11199218 - 03 Oct 2021
Cited by 1 | Viewed by 2473
Abstract
There is ongoing research on using electroencephalography (EEG) to predict depression. In particular, the deep learning method in which brain waves are used as inputs of a convolutional neural network (CNN) is being widely researched and has shown remarkable performance. We built a [...] Read more.
There is ongoing research on using electroencephalography (EEG) to predict depression. In particular, the deep learning method in which brain waves are used as inputs of a convolutional neural network (CNN) is being widely researched and has shown remarkable performance. We built a regression model to predict the severity score (Beck Depression Inventory [BDI]) of depressed patients as an extension of the deep-asymmetry method, which has shown promising performance in depression classification. Predicting the severity of depression is very important because the treatment and coping methods are different for each severity level. We imaged brain waves using the deep-asymmetry method, used them to train a two-dimensional CNN-based deep learning model, and achieved satisfactory performance. The EEG image-based CNN approach will make an important contribution to creating a highly interpretable model for predicting depression in the future. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

18 pages, 12014 KiB  
Article
Copper Strip Surface Defect Detection Model Based on Deep Convolutional Neural Network
by Yanghuan Xu, Dongcheng Wang, Bowei Duan, Huaxin Yu and Hongmin Liu
Appl. Sci. 2021, 11(19), 8945; https://0-doi-org.brum.beds.ac.uk/10.3390/app11198945 - 25 Sep 2021
Cited by 6 | Viewed by 2648
Abstract
Surface defect automatic detection has great significance for copper strip production. The traditional machine vision for surface defect automatic detection of copper strip needs artificial feature design, which has a long cycle, and poor ability of versatility and robustness. However, deep learning can [...] Read more.
Surface defect automatic detection has great significance for copper strip production. The traditional machine vision for surface defect automatic detection of copper strip needs artificial feature design, which has a long cycle, and poor ability of versatility and robustness. However, deep learning can effectively solve these problems. Therefore, based on the deep convolution neural network and the transfer learning strategy, an intelligent recognition model of surface defects of copper strip is established in this paper. Firstly, the defects were classified in accordance with the mechanism and morphology, and the surface defect dataset of copper strip was established by comprehensively adopting image acquisition and image augmentation. Then, a two-class discrimination model was established to achieve the accurate discrimination of perfect and defect images. On this basis, four CNN models were adopted for the recognition of defect images. Among these models, the EfficientNet model through transfer learning strategy had the best comprehensive performance with a recognition accuracy rate of 93.05%. Finally, the interpretability and deficiency of the model were analysed by the class activation map and confusion matrix, which point toward the direction of further optimization for future research. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

20 pages, 13188 KiB  
Article
A Hybrid CNN-Based Review Helpfulness Filtering Model for Improving E-Commerce Recommendation Service
by Qinglong Li, Xinzhe Li, Byunghyun Lee and Jaekyeong Kim
Appl. Sci. 2021, 11(18), 8613; https://0-doi-org.brum.beds.ac.uk/10.3390/app11188613 - 16 Sep 2021
Cited by 17 | Viewed by 3388
Abstract
As the e-commerce market grows worldwide, personalized recommendation services have become essential to users’ personalized items or services. They can decrease the cost of user information exploration and have a positive impact on corporate sales growth. Recently, many studies have been actively conducted [...] Read more.
As the e-commerce market grows worldwide, personalized recommendation services have become essential to users’ personalized items or services. They can decrease the cost of user information exploration and have a positive impact on corporate sales growth. Recently, many studies have been actively conducted using reviews written by users to address traditional recommender system research problems. However, reviews can include content that is not conducive to purchasing decisions, such as advertising, false reviews, or fake reviews. Using such reviews to provide recommendation services can lower the recommendation performance as well as a trust in the company. This study proposes a novel review of the helpfulness-based recommendation methodology (RHRM) framework to support users’ purchasing decisions in personalized recommendation services. The core of our framework is a review semantics extractor and a user/item recommendation generator. The review semantics extractor learns reviews representations in a convolutional neural network and bidirectional long short-term memory hybrid neural network for review helpfulness classification. The user/item recommendation generator models the user’s preference on items based on their past interactions. Here, past interactions indicate only records in which the user-written reviews of items are helpful. Since many reviews do not have helpfulness scores, we first propose a helpfulness classification model to reflect the review helpfulness that significantly impacts users’ purchasing decisions in personalized recommendation services. The helpfulness classification model is trained about limited reviews utilizing helpfulness scores. Several experiments with the Amazon dataset show that if review helpfulness information is used in the recommender system, performance such as the accuracy of personalized recommendation service can be further improved, thereby enhancing user satisfaction and further increasing trust in the company. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

26 pages, 3786 KiB  
Article
Predicting Success of Outbound Telemarketing in Insurance Policy Loans Using an Explainable Multiple-Filter Convolutional Neural Network
by Jinmo Gu, Jinhyuk Na, Jeongeun Park and Hayoung Kim
Appl. Sci. 2021, 11(15), 7147; https://0-doi-org.brum.beds.ac.uk/10.3390/app11157147 - 02 Aug 2021
Cited by 3 | Viewed by 3407
Abstract
Outbound telemarketing is an efficient direct marketing method wherein telemarketers solicit potential customers by phone to purchase or subscribe to products or services. However, those who are not interested in the information or offers provided by outbound telemarketing generally experience such interactions negatively [...] Read more.
Outbound telemarketing is an efficient direct marketing method wherein telemarketers solicit potential customers by phone to purchase or subscribe to products or services. However, those who are not interested in the information or offers provided by outbound telemarketing generally experience such interactions negatively because they perceive telemarketing as spam. In this study, therefore, we investigate the use of deep learning models to predict the success of outbound telemarketing for insurance policy loans. We propose an explainable multiple-filter convolutional neural network model called XmCNN that can alleviate overfitting and extract various high-level features using hundreds of input variables. To enable the practical application of the proposed method, we also examine ensemble models to further improve its performance. We experimentally demonstrate that the proposed XmCNN significantly outperformed conventional deep neural network models and machine learning models. Furthermore, a deep learning ensemble model constructed using the XmCNN architecture achieved the lowest false positive rate (4.92%) and the highest F1-score (87.47%). We identified important variables influencing insurance policy loan prediction through the proposed model, suggesting that these factors should be considered in practice. The proposed method may increase the efficiency of outbound telemarketing and reduce the spam problems caused by calling non-potential customers. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

23 pages, 13973 KiB  
Article
Real-Time AI-Based Informational Decision-Making Support System Utilizing Dynamic Text Sources
by Azharul Islam and KyungHi Chang
Appl. Sci. 2021, 11(13), 6237; https://0-doi-org.brum.beds.ac.uk/10.3390/app11136237 - 05 Jul 2021
Cited by 6 | Viewed by 5628
Abstract
Unstructured data from the internet constitute large sources of information, which need to be formatted in a user-friendly way. This research develops a model that classifies unstructured data from data mining into labeled data, and builds an informational and decision-making support system (DMSS). [...] Read more.
Unstructured data from the internet constitute large sources of information, which need to be formatted in a user-friendly way. This research develops a model that classifies unstructured data from data mining into labeled data, and builds an informational and decision-making support system (DMSS). We often have assortments of information collected by mining data from various sources, where the key challenge is to extract valuable information. We observe substantial classification accuracy enhancement for our datasets with both machine learning and deep learning algorithms. The highest classification accuracy (99% in training, 96% in testing) was achieved from a Covid corpus which is processed by using a long short-term memory (LSTM). Furthermore, we conducted tests on large datasets relevant to the Disaster corpus, with an LSTM classification accuracy of 98%. In addition, random forest (RF), a machine learning algorithm, provides a reasonable 84% accuracy. This research’s main objective is to increase the application’s robustness by integrating intelligence into the developed DMSS, which provides insight into the user’s intent, despite dealing with a noisy dataset. Our designed model selects the random forest and stochastic gradient descent (SGD) algorithms’ F1 score, where the RF method outperforms by improving accuracy by 2% (to 83% from 81%) compared with a conventional method. Full article
(This article belongs to the Special Issue Deep Convolutional Neural Networks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-22
Back to TopTop