Search

Copyright of Shipin Kexue/ Food Science is the property of Food Science Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Considering insufficient sample numbers in the practical detection of soluble solid content (SSC) in cherry tomato, we proposed a deep convolutional generation adversarial network (DCGAN) model to expand spectral data and SSC label data, and established a one-dimensional convolutional neural network regression (1D-CNNR) model to improve the prediction accuracy and generalization capability of the DCGAN model. For comparison, a partial least squares regression (PLSR) model and a support vector regression (SVR) model were established. The original dataset of 80 samples, the DCGAN extended dataset of 1 000 samples and the combined dataset of 1 080 samples were separately used for modeling and prediction with 1D-CNNR, SVR and PLSR. To further verify the generalization capability of the models, a new batch of 40 cherry tomato samples was used as a new test set. The results showed that the 1D-CNNR model based on the calibration set separated from the combined dataset was the optimal regression model for SSC detection. The prediction accuracy of the model for the test set from the combined dataset was the highest, with correlation coefficient of prediction (rp) of 0.980 7, and root mean square error of prediction (RMSEp) of 0.192 9. The prediction accuracy of the 1D-CNNR model for the new test set of 40 samples was also the highest, with rp of 0.963 8 and RMSEp of 0.224 5. This study provides a new idea for the accurate determination of the SSC in cherry tomato.

Generative Adversarial Networks (GANs) are highly effective for generating realistic images, yet their training can be unstable due to challenges such as mode collapse and oscillatory convergence. In this paper, we propose a novel hybrid optimization method that integrates Genetic Algorithms (GAs) to improve the training process of Deep Convolutional GANs (DCGANs). Specifically, GAs are used to evolve the discriminator's weights, complementing the gradient-based learning typically employed in GANs. The proposed GAGAN model is trained on the CelebA dataset, using 2000 images, to generate 128 × 128 images, with the generator learning to produce realistic faces from random latent vectors. The discriminator, which classifies images as real or fake, is optimized not only through standard backpropagation, but also through a GA framework that evolves its weights via crossover, mutation, and selection processes. This hybrid method aims to enhance convergence stability and boost image quality by balancing local search from gradient-based methods with the global search capabilities of GAs. Experiments show that the proposed approach reduces generator loss and improves image fidelity, demonstrating that evolutionary algorithms can effectively complement deep learning techniques. This work opens new avenues for optimizing GAN training and enhancing performance in generative models. [ABSTRACT FROM AUTHOR]

Abstract Background In recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications. Results To mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index. Conclusion The results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA . Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/ .

Cracks in tunnel lining surfaces directly threaten structural integrity; therefore, regular inspection of cracks is essential. Lightweight convolutional neural networks (LCNNs) have recently offered a promising alternative to conventional manual inspection. However, the effectiveness of LCNNs is still adversely affected by the lack of sufficient crack images, which limits the potential detection performance. In this paper, transfer learning was used to optimize deep convolutional generative adversarial networks (DCGANs) for crack image synthesis to significantly improve the accuracy of LCNNs. In addition, an improved LCNN model named ShuffleNetV2-1.0-SE was proposed, incorporating the squeeze–excitation (SE) attention mechanism into ShuffleNetV2-1.0 and realizing highly accurate classification results while maintaining lightness. The results show that the DCGAN-based data enhancement method can significantly improve the classification accuracy of ShuffleNetV2-1.0-SE for tunnel lining cracks. ShuffleNetV2-1.0-SE achieves an accuracy of 98.14% on the enhanced dataset, which is superior to multiple advanced LCNN models. [ABSTRACT FROM AUTHOR]

Background: In recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications. Results: To mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index. Conclusion: The results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA. Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/. [ABSTRACT FROM AUTHOR]

This research paper introduces a novel approach for the classification of dementia disease using Rotation Forests based on Deep Convolutional Generative Adversarial Networks (DCGAN). Dementia is a significant cognitive disorder prevalent among the elderly population, demanding accurate and early diagnosis for effective intervention. Traditional methods often rely on manual feature extraction and shallow learning, which may lack the ability to capture intricate patterns in complex medical data. In this study, we propose a fusion of Rotation Forests, a robust ensemble learning technique, with DCGAN, a deep learning model recognized for its feature extraction capabilities. The Rotation Forests enhance the diversity of the base classifiers, while DCGAN learns meaningful features from raw medical imaging data. We validate the proposed approach on a comprehensive dataset and compare its performance against existing methods. The experimental results demonstrate the effectiveness of the Rotation Forests based on DCGAN approach in accurately classifying dementia diseases, showcasing its potential as a valuable tool in medical diagnosis. [ABSTRACT FROM AUTHOR]

Cracks in tunnel lining surfaces directly threaten structural integrity; therefore, regular inspection of cracks is essential. Lightweight convolutional neural networks (LCNNs) have recently offered a promising alternative to conventional manual inspection. However, the effectiveness of LCNNs is still adversely affected by the lack of sufficient crack images, which limits the potential detection performance. In this paper, transfer learning was used to optimize deep convolutional generative adversarial networks (DCGANs) for crack image synthesis to significantly improve the accuracy of LCNNs. In addition, an improved LCNN model named ShuffleNetV2-1.0-SE was proposed, incorporating the squeeze–excitation (SE) attention mechanism into ShuffleNetV2-1.0 and realizing highly accurate classification results while maintaining lightness. The results show that the DCGAN-based data enhancement method can significantly improve the classification accuracy of ShuffleNetV2-1.0-SE for tunnel lining cracks. ShuffleNetV2-1.0-SE achieves an accuracy of 98.14% on the enhanced dataset, which is superior to multiple advanced LCNN models.

Diffusion models, variational autoencoders, and generative adversarial networks (GANs) are three common types of generative artificial intelligence models for image generation. Among these, GANs are the most frequently used for medical image generation and are often employed for data augmentation in various studies. However, due to the adversarial nature of GANs, where the generator and discriminator compete against each other, the training process can sometimes end with the model unable to generate meaningful images or even producing noise. This phenomenon is rarely discussed in the literature, and no studies have proposed solutions to address this issue. Such outcomes can introduce significant bias when GANs are used for data augmentation in medical image training. Moreover, GANs often require substantial computational power and storage, adding to the challenges. In this study, we used deep convolutional GANs for chest X-ray generation, and three typical training outcomes were found. Two scenarios generated meaningful medical images and one failed to produce usable images. By analyzing the loss history during training, we observed that the regression line of the overall losses tends to diverge slowly. After excluding outlier losses, we found that the slope of the regression line within the stable loss segment indicates the optimal point to terminate training, ensuring the generation of meaningful medical images., Competing Interests: Human subjects: All authors have confirmed that this study did not involve human participants or tissue. Animal subjects: All authors have confirmed that this study did not involve animal subjects or tissue. Conflicts of interest: In compliance with the ICMJE uniform disclosure form, all authors declare the following: Payment/services info: All authors have declared that no financial support was received from any organization for the submitted work. Financial relationships: All authors have declared that they have no financial relationships at present or within the previous three years with any organizations that might have an interest in the submitted work. Other relationships: All authors have declared that there are no other relationships or activities that could appear to have influenced the submitted work., (Copyright © 2025, Chen et al.)

Rotating machinery plays an important role in industrial systems, and faults in the machinery may damage the system health. A novel image-based diagnosis method using improved deep convolutional generative adversarial networks (DCGAN) is proposed for the feature recognition and fault classification of rotating machinery. First, vibration signal data from the rotating machinery is transformed into time–frequency feature 2-D image data by a continuous wavelet transform and used for fault classification with the neural network method. The adaptive deep convolution neural network (ADCNN) is then combined with the generative adversarial networks (GANs) to improve the performance of the feature self-learning ability from input data. Compared with different fault diagnosis methods, the proposed method has better performance for image feature classification in rotating machinery. [ABSTRACT FROM AUTHOR]

How to reconstruct a credible three-dimensional (3D) geological model from very limited survey data, e.g. boreholes, outcrop, and two-dimensional (2D) images, is challenging in the field of 3D geological modeling. Against the limitations of the huge computational consumption and complex parameterization of geostatistics-based stochastic simulation methods, we propose an automatic reconstruction method of 3D geological models based on deep convolutional generative adversarial network (DCGAN). In this work, 2D geological sections are used as conditioning data to generate 3D geological models automatically. Various realizations can be reproduced under a same DCGAN model established through deep network training. A U-Net structure is used to enhance the fitting effect of the DCGAN model. In addition, joint loss functions are exploited to increase the similarity between 3D realizations and reference models. Three synthetic datasets were used to verify the capability of the method presented in this paper. Experimental results show that the proposed 3D automatic reconstruction method based on DCGAN can capture the features, trends and spatial patterns of geological structures well. The output models obey the used conditioning data. The complex heterogeneous structures are reconstructed more accurately and quickly by using the proposed method. [ABSTRACT FROM AUTHOR]

In recent years, researchers designed several artificial intelligence solutions for healthcare applications, which usually evolved into functional solutions for clinical practice. Furthermore, deep learning (DL) methods are well-suited to process the broad amounts of data acquired by wearable devices, smartphones, and other sensors employed in different medical domains. Conceived to serve the role of diagnostic tool and surgical guidance, hyperspectral images emerged as a non-contact, non-ionizing, and label-free technology. However, the lack of large datasets to efficiently train the models limits DL applications in the medical field. Hence, its usage with hyperspectral images is still at an early stage. We propose a deep convolutional generative adversarial network to generate synthetic hyperspectral images of epidermal lesions, targeting skin cancer diagnosis, and overcome small-sized datasets challenges to train DL architectures. Experimental results show the effectiveness of the proposed framework, capable of generating synthetic data to train DL classifiers. [ABSTRACT FROM AUTHOR]

This paper proposes a novel chaotic block image encryption algorithm based on deep convolutional generative adversarial networks (DCGANs), quaternions, an improved Feistel network, and an overall scrambling and diffusion mechanism. First, a new hyperchaotic system is introduced and combined with DCGANs to generate a random sequence with better randomness and complexity as a key stream. This sequence is then combined with a quaternion and an improved Feistel network encryption of a colour plaintext image by utilizing the key block matrix to ultimately achieve overall scrambling and diffusion of the cipher image. Finally, the security of this algorithm is quantitatively and qualitatively analysed. The simulation results show that the proposed hyperchaotic system has a large key space and good random characteristics and that the new algorithm yields adequate security and can resist brute-force attacks and chosen-plaintext attacks. Therefore, this approach provides a new way to achieve secure transmission and protection of image information.

Mechanical design is one of the essential disciplines in engineering applications, while inspirations of design ideas highly depend on the ability and prior knowledge of engineers or designers. With the rapid development of machine learning (ML) techniques, artificial intelligence (AI)‐based design methods are promising tools for the design of advanced engineering systems. So far, there have been some studies of 2D patterns and structural designs based on ML techniques. However, a particular challenge remains in allowing complex 3D mechanical designs using ML techniques. Herein, a novel and experience‐free method to equip ML models with 3D design capabilities by combining a convolutional neuron network (CNN) with a deep convolutional generative adversarial network (DCGAN) is developed. The model directly receives 2D image‐based training data that define the complex 3D structures of a specific machine part. After the training process, an infinite number of new 3D designs can be generated by the proposed model, with their geometric and mechanical properties being accurately predicted at the same time. Moreover, the generated new designs can be fed back to expand the original input datasets for further ML model training and updating. [ABSTRACT FROM AUTHOR]

To understand the material paradigm, data‐driven material design necessitates both microstructural input and output in the form of visual images. Therefore, generative adversarial networks (GAN)‐based deep convolutional GAN, cycle‐consistent GAN, and super‐resolution GAN techniques are used to generate, translate, and improve the quality of microstructural images in this study. The reconstructed virtual microstructural images are realistic and indistinguishable from the real ones. Furthermore, using GAN techniques to reconstruct microstructural image suggests promising ways to design desired microstructures using parameterized descriptors and image augmentation, which are expected to advance data‐driven materials research. [ABSTRACT FROM AUTHOR]

Mechanical design is one of the essential disciplines in engineering applications, while inspirations of design ideas highly depend on the ability and prior knowledge of engineers or designers. With the rapid development of machine learning (ML) techniques, artificial intelligence (AI)‐based design methods are promising tools for the design of advanced engineering systems. So far, there have been some studies of 2D patterns and structural designs based on ML techniques. However, a particular challenge remains in allowing complex 3D mechanical designs using ML techniques. Herein, a novel and experience‐free method to equip ML models with 3D design capabilities by combining a convolutional neuron network (CNN) with a deep convolutional generative adversarial network (DCGAN) is developed. The model directly receives 2D image‐based training data that define the complex 3D structures of a specific machine part. After the training process, an infinite number of new 3D designs can be generated by the proposed model, with their geometric and mechanical properties being accurately predicted at the same time. Moreover, the generated new designs can be fed back to expand the original input datasets for further ML model training and updating.

Bamboo culm has been widely used in engineering for its high strength, lightweight, and low cost. Its outermost epidermis is a smooth and dense layer that contains cellulose, silica particles, and stomata and acts as a water and mechanical barrier. Recent experimental studies have shown that the layer has a higher mechanical strength than other inside regions. Still, the mechanism is unclear, especially for how the low silica concentration (<10%) can effectively reinforce the layer and prevent the inner fibers from splitting. Here, theoretical analysis is combined with experimental imaging and 3D printing to investigate the effect of the distribution of silica particles on composite mechanics. The anisotropic partial distribution function of silica particles in bamboo skin yields higher toughness (>10%) than randomly distributed particles. A generative artificial intelligence (AI) model inspired by bamboo epidermis is developed to generate particle-reinforced composites. Besides the visual similarity, it is found that the samples by the generative model show failure processes and fracture toughness identical to the actual bamboo epidermis. This work reveals the micromechanics of the bamboo epidermis. It illustrates that generative AI can help design bio-inspired composites of a complex structure that cannot be uniformly represented by a simple building block or optimized around local boundaries. It expands the design space of particle-reinforced composites for enhanced toughness modulus, offering advantages in industries where mechanical reliability is critical., (© 2024 The Author(s). Advanced Materials published by Wiley‐VCH GmbH.)

With the evolution of deep learning technologies, computer vision-related tasks achieved tremendous success in the biomedical domain. For supervised deep learning training, we need a large number of labeled datasets. The task of achieving a large number of label dataset is a challenging. The availability of data makes it difficult to achieve and enhance an automated disease diagnosis model's performance. To synthesize data and improve the disease diagnosis model's accuracy, we proposed a novel approach for the generation of images for three different stages of Alzheimer's disease using deep convolutional generative adversarial networks. The proposed model out-perform in synthesis of brain positron emission tomography images for all three stages of Alzheimer disease. The three-stage of Alzheimer's disease is normal control, mild cognitive impairment, and Alzheimer's disease. The model performance is measured using a classification model that achieved an accuracy of 72% against synthetic images. We also experimented with quantitative measures, that is, peak signal-to-noise (PSNR) and structural similarity index measure (SSIM). We achieved average PSNR score values of 82 for AD, 72 for CN, and 73 for MCI and SSIM average score values of 25.6 for AD, 22.6 for CN, and 22.8 for MCI. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Image colorization technique is used to colorize the gray-level image or single-channel image, which is a very significant and challenging task in image processing, especially the colorization of remote sensing images. This paper proposes a new method for coloring remote sensing images based on deep convolution generation adversarial network. The adopted generator model is a symmetrical structure using the principle of auto-encoder, and a multi-scale convolutional module is specially designed to introduce into the generator model. Thus, the proposed generator can enable the whole model to retain more image features in the process of up-sampling and down-sampling. Meanwhile, the discriminator uses residual neural network 18 that can compete with the generator, so that the generator and discriminator can effectively optimize each other. In the proposed method, the color space transformation technique is first utilized to convert remote sensing images from RGB to YUV. Then, the Y channel (a gray-level image) is used as the input of the neural network model to predict UV channels. Finally, the predicted UV channels are concatenated with the original Y channel as a whole YUV that is then transformed into RGB space to get the final color image. Experiments are conducted to test the performance of different image colorization methods, and the results show that the proposed method has good performance in both visual quality and objective indexes on the colorization of remote sensing image. [ABSTRACT FROM AUTHOR]

DC arc faults, especially series arcing, can occur in photovoltaic (PV) systems and pose a challenging detection and protection problem. Machine learning-based methods are increasingly being used for fault diagnosis applications. However, the performance of such detection algorithms will degrade because of variations between the source domain data used during the development and the target domain data encountered in operation of the field. Furthermore, the fault's data in the target domain for model training are usually not available. In this paper, domain adaptation combined with deep convolutional generative adversarial network (DA-DCGAN)-based methodology is proposed, where DA-DCGAN first learns an intelligent normal-to-arcing transformation from the source-domain data. Then by generating dummy arcing data with the learned transformation using the normal data from the target domain and employing domain adaptation, a robust and reliable fault diagnosis scheme can be achieved for the target domain. The PV loop current is framed and arranged into a 2D matrix as input for cross-domain DC series arc fault diagnosis. The system is validated offline using pre-recorded PV loop current data from a real 1.5-kW grid-connected rooftop PV system. Also, the proposed method is implemented in an embedded system and tested in real-time according to UL-1699B standard. The experimental results clearly demonstrate benefits of DA-DCGAN and confirm the effectiveness of the proposed methodology for practical PV applications.

Due to the complex and time-varying network environments, traditional methods are difficult to extract accurate features of intrusion behavior from the high-dimensional data samples and process the high-volume of these data efficiently. Even worse, the network intrusion samples are submerged into a large number of normal data packets, which leads to insufficient samples for model training; therefore it is accompanied by high false detection rates. To address the challenge of unbalanced positive and negative learning samples, we propose using deep convolutional generative adversarial networks (DCGAN), which allows features to be extracted directly from the rawdata, and then generates new training-sets by learning from the rawdata. Given the fact that the attack samples are usually intra-dependent time sequence data, we apply long short-term memory (LSTM) to automatically learn the features of network intrusion behaviors. However, it is hard to parallelize the learning/training of the LSTM network, since the LSTM algorithm depends on the result of the previous moment. To remove such dependency and enable intrusion detection in real time, we propose a simple recurrent unit based (SRU)-based model. The proposed model was verified by extensive experiments on the benchmark datasets KDD'99 and NSL-KDD, which effectively identifies normal and abnormal network activities. It achieves 99.73% accuracy on the KDD'99 dataset and 99.62% on the NSL-KDD dataset.

Detecting anomalies in time series is a vital technique in a wide variety of industrial application in which sensors monitor expensive machinery. The complexity of this task increases when heterogeneous sensors provide information of different attributes, scales and characteristics from the same machine. Actually, the challenges of anomaly detection for industrial time series are to design effective pre-processing, feature extraction and overcome the lack of abnormal samples. Recent deep learning models have shown prominent abilities on raw multivariate time series, alleviating these previous works. In this work, a novel framework named multi-time scale deep convolutional generative adversarial network (MTS-DCGAN) is proposed to deal with anomaly detection of industrial time series. Firstly, multivariate time series are transformed into the multi-channel signature matrices via sliding window based cross-correlation computation, and therein forgetting mechanism is introduced to effectively avoid false alarms due to excessive influence of old sequences. Then the framework conducts an unsupervised adversarial training of multi-channel signature matrices and capture their hidden features via deep convolution structure. Besides, a novel threshold setting strategy is proposed to optimize anomaly detection performance under imbalance of normal and abnormal data. Finally, the proposed framework is assessed against the experiments on four datasets. Within this study, experimental results show our framework outperforms the comparison algorithms in terms of model performance and robustness, providing an effective anomaly detection method for industrial multivariate time series. [ABSTRACT FROM AUTHOR]

Tuberculosis (TB) is a contagious bacterial airborne disease, and is one of the top 10 causes of death worldwide. According to the World Health Organisation, around 1.8 billion people are infected with TB and 1.6 million deaths were reported in 2018. More importantly, 95% of cases and deaths were from developing countries. Yet, TB is a completely curable disease through early diagnosis. To achieve this goal one of the key requirements is efficient utilisation of existing diagnostic technologies, among which chest X-ray is the first line of diagnostic tool used for screening for active TB. The presented deep learning pipeline consists of three different modern deep learning architectures, to generate, segment, and classify lung X-rays. Apart from this, image preprocessing, image augmentation, genetic algorithm based hyper parameter tuning, and model ensembling were used to improve the diagnostic process. We were able to achieve classification accuracy of 97.1% (Youden's index-0.941, sensitivity of 97.9%, specificity of 96.2%) which is a considerable improvement compared to the existing work in the literature. In our work, we present a highly accurate, automated TB screening system using chest X-rays, which would be helpful especially for low income countries with low access to qualified medical professionals. [ABSTRACT FROM AUTHOR]

The aggravation of left ventricular diastolic dysfunction (LVDD) could lead to ventricular remodeling, wall stiffness, reduced compliance, and progression to heart failure with a preserved ejection fraction. A non-invasive method based on convolutional neural networks (CNN) and heart sounds (HS) is presented for the early diagnosis of LVDD in this paper. A deep convolutional generative adversarial networks (DCGAN) model-based data augmentation (DA) method was proposed to expand a HS database of LVDD for model training. Firstly, the preprocessing of HS signals was performed using the improved wavelet denoising method. Secondly, the logistic regression based hidden semi-Markov model was utilized to segment HS signals, which were subsequently converted into spectrograms for DA using the short-time Fourier transform (STFT). Finally, the proposed method was compared with VGG-16, VGG-19, ResNet-18, ResNet-50, DenseNet-121, and AlexNet in terms of performance for LVDD diagnosis. The result shows that the proposed method has a reasonable performance with an accuracy of 0.987, a sensitivity of 0.986, and a specificity of 0.988, which proves the effectiveness of HS analysis for the early diagnosis of LVDD and demonstrates that the DCGAN-based DA method could effectively augment HS data.

The increasing concern over pesticide residues on Hami melon is due to the unregulated use of pesticides, which poses a potential food safety hazard. Thus, it is urgent to propose a method for the rapid and nondestructive detection of pesticide residues on the Hami melon. This study used short-wave infrared hyperspectral imaging (SWIR-HSI) to identify pesticide residues on the Hami melon. The data augmentation method based on improved deep convolutional generative adversarial networks (DCGAN) was proposed to expand Hami melon's spectral data with different pesticide residues. To determine the optimal training epoch, the 1-nearest neighbor (1-NN) classifier was used to evaluate the quality of the generated spectra. The effectiveness of the improved DCGAN was verified by three commonly used classifiers, including the decision tree (DT), random forest (RF), and support vector machine (SVM). The results showed that the performance of all three classifiers was improved to varying degrees by the improved DCGAN. The DT, RF, and SVM accuracy was improved by 13.13%, 7.50%, and 11.25%, respectively. Moreover, the SVM model achieved the highest accuracy of 93.13%. These findings indicated that the combination of SWIR-HSI and the improved DCGAN-based data augmentation method has good promise for detecting pesticide residues on Hami melon. • The DCGAN was improved by introducing the double branch structure. • The improved DCGAN was proposed to extend the SWIR-HSI spectra. • The 1-NN classifier was introduced to evaluate the generated spectral data. • The accuracy of the classifiers was improved by the generated spectral data. [ABSTRACT FROM AUTHOR]

Urinary bladder cancer is one of the most common urinary tract cancers. Standard diagnosis procedure can be invasive and time-consuming. For these reasons, procedure called optical biopsy is introduced. This procedure allows in-vivo evaluation of bladder mucosa without the need for biopsy. Although less invasive and faster, accuracy is often lower. For this reason, machine learning (ML) algorithms are used to increase its accuracy. The issue with ML algorithms is their sensitivity to the amount of input data. In medicine, collection can be time-consuming due to a potentially low number of patients. For these reasons, data augmentation is performed, usually through a series of geometric variations of original images. While such images improve classification performance, the number of new data points and the insight they provide is limited. These issues are a motivation for the application of novel augmentation methods. Authors demonstrate the use of Deep Convolutional Generative Adversarial Networks (DCGAN) for the generation of images. Augmented datasets used for training of commonly used Convolutional Neural Network-based (CNN) architectures (AlexNet and VGG-16) show a significcan performance increase for AlexNet, where AUCmicro reaches values up to 0.99. Average and median results of networks used in grid-search increases. These results point towards the conclusion that GAN-based augmentation has decreased the networks sensitivity to hyperparemeter change.

Aiming at live fish identification in aquaculture, a practical and efficient semi-supervised learning model, based on modified deep convolutional generative adversarial networks (DCGANs), was proposed in this study. Benefiting from the modified DCGANs structure, the presented model can be trained effectively using relatively few labeled training samples. In consideration of the complex poses of fish and the low resolution of sampling images in aquaculture, spatial pyramid pooling and some improved techniques specifically for the presented model were used to make the model more robust. Finally, in tests with two preprocessed and challenging datasets (with 5%, 10%, and 15% labeled training data in the fish recognition ground-truth dataset and 25%, 50%, and 75% labeled training data in the Croatian fish dataset), the feasibility and reliability of the presented model for live fish identification were proved with respective accuracies of 80.52%, 81.66%, and 83.07% for the ground-truth dataset and 65.13%, 78.72%, and 82.95% for the Croatian fish dataset. [ABSTRACT FROM AUTHOR]

To solve the problems associated with a small sample size during intelligent road detection, a virtual image set generation method for asphalt pavement cracks is proposed based on improved deep convolutional generative adversarial networks (DCGANs). First, a small set of sample crack images is collected and used as the basic image set to perform filtering, gamma transformation, and other processes, whereby crack feature recognition is enhanced. Second, a variational autoencoder (VAE) is used to encode real crack images. The latent variable values obtained from the VAE are provided as input to the DCGAN model generator, and the model hyperparameters are optimized. Subsequently, the adaptive moment estimation (Adam) optimizer is used to reoptimize the model and thereby improve the model convergence speed and generalization ability. The proposed method has the advantages of both VAE and DCGAN. Finally, a pavement crack classification detection model based on faster region convolutional neural network (Faster R-CNN) is used to evaluate the reliability of the generated crack images. The results show that the augmented dataset of the proposed method with the detection model has an average precision of 90.32%, which is higher than that of the conventional method evaluated using the same test dataset. The proposed method generates virtual crack images that are moderately identical to real ones, thereby solving the problem of insufficient image datasets of cracks in specific road sections. The method also provides data assurance for the intelligentization of pavement crack detection and the reduction of pavement maintenance costs. [ABSTRACT FROM AUTHOR]

Simple Summary: One of the main challenges in the application of Machine Learning in medicine is data collection. Either due to ethical concerns or lack of patients, data may be scarce. In this paper Deep Convolutional Generative Adversarial Networks (DCGAN) have been applied for the purpose of data augmentation. Images of bladder mucosa are used in order to generate new images using DCGANs. Then, combination of original and generated images are used to train AlexNet and VGG16 architectures. The results show improvements in AUC score in some cases, or equal scores with apparent lowering of standard deviation across data folds during cross-validation; indicating networks trained with the addition of generated data have a lower sensitivity across the hyperparameter range. Urinary bladder cancer is one of the most common urinary tract cancers. Standard diagnosis procedure can be invasive and time-consuming. For these reasons, procedure called optical biopsy is introduced. This procedure allows in-vivo evaluation of bladder mucosa without the need for biopsy. Although less invasive and faster, accuracy is often lower. For this reason, machine learning (ML) algorithms are used to increase its accuracy. The issue with ML algorithms is their sensitivity to the amount of input data. In medicine, collection can be time-consuming due to a potentially low number of patients. For these reasons, data augmentation is performed, usually through a series of geometric variations of original images. While such images improve classification performance, the number of new data points and the insight they provide is limited. These issues are a motivation for the application of novel augmentation methods. Authors demonstrate the use of Deep Convolutional Generative Adversarial Networks (DCGAN) for the generation of images. Augmented datasets used for training of commonly used Convolutional Neural Network-based (CNN) architectures (AlexNet and VGG-16) show a significcan performance increase for AlexNet, where AUCmicro reaches values up to 0.99. Average and median results of networks used in grid-search increases. These results point towards the conclusion that GAN-based augmentation has decreased the networks sensitivity to hyperparemeter change. [ABSTRACT FROM AUTHOR]

• A self-defined threshold can be automatically created based on DCGAN model. • It can be utilized to identify the anomalous condition of wind turbine bearings. • A sample discrepancy analysis is employed to evaluate the fault severity. • The proposed method is demonstrated to be reliable with less human intervention. Long-term reliable health condition monitoring (HCM) of a wind turbine is an essential method to avoid catastrophic failure results. Existing unsupervised learning methods, such as auto-encoder (AE) and de-noising auto-encoder (DAE) models, are utilized to the condition monitoring of wind turbines. The critical bottleneck of these models for monitoring is to determine a threshold for identifying different health conditions. Unfortunately, the threshold is usually set up with different kinds of calculation methods or even based on experience. Therefore, the uncertainty of the threshold will inevitably influence the accuracy of the monitoring process and may lead to misdiagnoses. To overcome this limitation, this research introduces a threshold self-setting HCM scheme, based on deep convolutional generative adversarial networks (DCGAN) and employed for defining a self-setting threshold to monitor wind turbine generator bearings. A threshold for HCM can be automatically created through the output of the G network in the DCGAN model, and the challenging problem of setting up a threshold can be solved. Besides, the use of Nash Equilibrium for training enables this scheme to become self-defined evaluators with a high level of consistency, without any human intervention and can be treated as a self-defined threshold, and it is a model self-tuning process. Furthermore, a sample discrepancy analysis based on the output of the G network is utilized so that a quantitative indicator of the fault severity in wind turbine generator bearings are provided. By tracking a real wind turbine dataset from the LU NAN wind farm in China, the effectiveness of the proposed scheme is verified. [ABSTRACT FROM AUTHOR]