Data Augmentation Using Contour Image for Convolutional Neural Network

With the development of artificial intelligence-related technologies such as deep learning,various organizations,including the government,are making various efforts to generate and manage big data for use in artificial intelligence.However,it is difficult to acquire big data due to various social problems and restrictions such as personal information leakage.There are many problems in introducing technology in fields that do not have enough training data necessary to apply deep learning technology.Therefore,this study proposes a mixed contour data augmentation technique,which is a data augmentation technique using contour images,to solve a problem caused by a lack of data.ResNet,a famous convolutional neural network(CNN)architecture,and CIFAR-10,a benchmark data set,are used for experimental performance evaluation to prove the superiority of the proposed method.And to prove that high performance improvement can be achieved even with a small training dataset,the ratio of the training dataset was divided into 70%,50%,and 30%for comparative analysis.As a result of applying the mixed contour data augmentation technique,it was possible to achieve a classification accuracy improvement of up to 4.64%and high accuracy even with a small amount of data set.In addition,it is expected that the mixed contour data augmentation technique can be applied in various fields by proving the excellence of the proposed data augmentation technique using benchmark datasets.

Effect of Data Augmentation of Renal Lesion Image by Nine-layer Convolutional Neural Network in Kidney CT

Artificial Intelligence(AI)becomes one hotspot in the field of the medical images analysis and provides rather promising solution.Although some research has been explored in smart diagnosis for the common diseases of urinary system,some problems remain unsolved completely A nine-layer Convolutional Neural Network(CNN)is proposed in this paper to classify the renal Computed Tomography(CT)images.Four group of comparative experiments prove the structure of this CNN is optimal and can achieve good performance with average accuracy about 92.07±1.67%.Although our renal CT data is not very large,we do augment the training data by affine,translating,rotating and scaling geometric transformation and gamma,noise transformation in color space.Experimental results validate the Data Augmentation(DA)on training data can improve the performance of our proposed CNN compared to without DA with the average accuracy about 0.85%.This proposed algorithm gives a promising solution to help clinical doctors automatically recognize the abnormal images faster than manual judgment and more accurately than previous methods.

Sparse Seismic Data Reconstruction Based on a Convolutional Neural Network Algorithm

At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achieving uniform and intensive acquisition,which makes complete seismic data collection impossible.Therefore,data reconstruction is required in the processing link to ensure imaging accuracy.Deep learning,as a new field in rapid development,presents clear advantages in feature extraction and modeling.In this study,the convolutional neural network deep learning algorithm is applied to seismic data reconstruction.Based on the convolutional neural network algorithm and combined with the characteristics of seismic data acquisition,two training strategies of supervised and unsupervised learning are designed to reconstruct sparse acquisition seismic records.First,a supervised learning strategy is proposed for labeled data,wherein the complete seismic data are segmented as the input of the training set and are randomly sampled before each training,thereby increasing the number of samples and the richness of features.Second,an unsupervised learning strategy based on large samples is proposed for unlabeled data,and the rolling segmentation method is used to update(pseudo)labels and training parameters in the training process.Through the reconstruction test of simulated and actual data,the deep learning algorithm based on a convolutional neural network shows better reconstruction quality and higher accuracy than compressed sensing based on Curvelet transform.

A multiscale adaptive framework based on convolutional neural network:Application to fluid catalytic cracking product yield prediction

Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production indicators.While the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical processes.In light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale information.First,the industrial data from the Fluid Catalytic Cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature subset.Then,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale data.Finally,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final output.Msrt Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as examples.In conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series models.Furthermore,its robustness and transferability underscore its promising potential for broader applications.

End-to-End 2D Convolutional Neural Network Architecture for Lung Nodule Identification and Abnormal Detection in Cloud

The extent of the peril associated with cancer can be perceivedfrom the lack of treatment, ineffective early diagnosis techniques, and mostimportantly its fatality rate. Globally, cancer is the second leading cause ofdeath and among over a hundred types of cancer;lung cancer is the secondmost common type of cancer as well as the leading cause of cancer-relateddeaths. Anyhow, an accurate lung cancer diagnosis in a timely manner canelevate the likelihood of survival by a noticeable margin and medical imagingis a prevalent manner of cancer diagnosis since it is easily accessible to peoplearound the globe. Nonetheless, this is not eminently efficacious consideringhuman inspection of medical images can yield a high false positive rate. Ineffectiveand inefficient diagnosis is a crucial reason for such a high mortalityrate for this malady. However, the conspicuous advancements in deep learningand artificial intelligence have stimulated the development of exceedinglyprecise diagnosis systems. The development and performance of these systemsrely prominently on the data that is used to train these systems. A standardproblem witnessed in publicly available medical image datasets is the severeimbalance of data between different classes. This grave imbalance of data canmake a deep learning model biased towards the dominant class and unableto generalize. This study aims to present an end-to-end convolutional neuralnetwork that can accurately differentiate lung nodules from non-nodules andreduce the false positive rate to a bare minimum. To tackle the problem ofdata imbalance, we oversampled the data by transforming available images inthe minority class. The average false positive rate in the proposed method isa mere 1.5 percent. However, the average false negative rate is 31.76 percent.The proposed neural network has 68.66 percent sensitivity and 98.42 percentspecificity.

Human and Machine Vision Based Indian Race Classification Using Modified-Convolutional Neural Network

The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.

Image Augmentation-Based Food Recognition with Convolutional Neural Networks

Image retrieval for food ingredients is important work,tremendously tiring,uninteresting,and expensive.Computer vision systems have extraordinary advancements in image retrieval with CNNs skills.But it is not feasible for small-size food datasets using convolutional neural networks directly.In this study,a novel image retrieval approach is presented for small and medium-scale food datasets,which both augments images utilizing image transformation techniques to enlarge the size of datasets,and promotes the average accuracy of food recognition with state-of-the-art deep learning technologies.First,typical image transformation techniques are used to augment food images.Then transfer learning technology based on deep learning is applied to extract image features.Finally,a food recognition algorithm is leveraged on extracted deepfeature vectors.The presented image-retrieval architecture is analyzed based on a smallscale food dataset which is composed of forty-one categories of food ingredients and one hundred pictures for each category.Extensive experimental results demonstrate the advantages of image-augmentation architecture for small and medium datasets using deep learning.The novel approach combines image augmentation,ResNet feature vectors,and SMO classification,and shows its superiority for food detection of small/medium-scale datasets with comprehensive experiments.

Extended Forgery Detection Framework for COVID-19 Medical Data Using Convolutional Neural Network

Medical data tampering has become one of the main challenges in the field of secure-aware medical data processing.Forgery of normal patients’medical data to present them as COVID-19 patients is an illegitimate action that has been carried out in different ways recently.Therefore,the integrity of these data can be questionable.Forgery detection is a method of detecting an anomaly in manipulated forged data.An appropriate number of features are needed to identify an anomaly as either forged or non-forged data in order to find distortion or tampering in the original data.Convolutional neural networks(CNNs)have contributed a major breakthrough in this type of detection.There has been much interest from both the clinicians and the AI community in the possibility of widespread usage of artificial neural networks for quick diagnosis using medical data for early COVID-19 patient screening.The purpose of this paper is to detect forgery in COVID-19 medical data by using CNN in the error level analysis(ELA)by verifying the noise pattern in the data.The proposed improved ELA method is evaluated using a type of data splicing forgery and sigmoid and ReLU phenomenon schemes.The proposed method is verified by manipulating COVID-19 data using different types of forgeries and then applying the proposed CNN model to the data to detect the data tampering.The results show that the accuracy of the proposed CNN model on the test COVID-19 data is approximately 92%.

Importance of Adaptive Photometric Augmentation for Different Convolutional Neural Network

Existing segmentation and augmentation techniques on convolutional neural network(CNN)has produced remarkable progress in object detection.However,the nominal accuracy and performance might be downturned with the photometric variation of images that are directly ignored in the training process,along with the context of the individual CNN algorithm.In this paper,we investigate the effect of a photometric variation like brightness and sharpness on different CNN.We observe that random augmentation of images weakens the performance unless the augmentation combines the weak limits of photometric variation.Our approach has been justified by the experimental result obtained from the PASCAL VOC 2007 dataset,with object detection CNN algorithms such as YOLOv3(You Only Look Once),Faster R-CNN(Region-based CNN),and SSD(Single Shot Multibox Detector).Each CNN model shows performance loss for varying sharpness and brightness,ranging between−80%to 80%.It was further shown that compared to random augmentation,the augmented dataset with weak photometric changes delivered high performance,but the photometric augmentation range differs for each model.Concurrently,we discuss some research questions that benefit the direction of the study.The results prove the importance of adaptive augmentation for individual CNN model,subjecting towards the robustness of object detection.

Multiple Data Augmentation Strategy for Enhancing the Performance of YOLOv7 Object Detection Algorithm

The object detection technique depends on various methods for duplicating the dataset without adding more images.Data augmentation is a popularmethod that assists deep neural networks in achieving better generalization performance and can be seen as a type of implicit regularization.Thismethod is recommended in the casewhere the amount of high-quality data is limited,and gaining new examples is costly and time-consuming.In this paper,we trained YOLOv7 with a dataset that is part of the Open Images dataset that has 8,600 images with four classes(Car,Bus,Motorcycle,and Person).We used five different data augmentations techniques for duplicates and improvement of our dataset.The performance of the object detection algorithm was compared when using the proposed augmented dataset with a combination of two and three types of data augmentation with the result of the original data.The evaluation result for the augmented data gives a promising result for every object,and every kind of data augmentation gives a different improvement.The mAP@.5 of all classes was 76%,and F1-score was 74%.The proposed method increased the mAP@.5 value by+13%and F1-score by+10%for all objects.

Optimized Convolutional Neural Network Models for Skin Lesion Classification

Skin cancer is one of themost severe diseases,andmedical imaging is among themain tools for cancer diagnosis.The images provide information on the evolutionary stage,size,and location of tumor lesions.This paper focuses on the classification of skin lesion images considering a framework of four experiments to analyze the classification performance of Convolutional Neural Networks(CNNs)in distinguishing different skin lesions.The CNNs are based on transfer learning,taking advantage of ImageNet weights.Accordingly,in each experiment,different workflow stages are tested,including data augmentation and fine-tuning optimization.Three CNN models based on DenseNet-201,Inception-ResNet-V2,and Inception-V3 are proposed and compared using the HAM10000 dataset.The results obtained by the three models demonstrate accuracies of 98%,97%,and 96%,respectively.Finally,the best model is tested on the ISIC 2019 dataset showing an accuracy of 93%.The proposed methodology using CNN represents a helpful tool to accurately diagnose skin cancer disease.

Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network

With the rapid development of mechanical equipment, the mechanical health monitoring field has entered the era of big data. However, the method of manual feature extraction has the disadvantages of low efficiency and poor accuracy, when handling big data. In this study, the research object was the asynchronous motor in the drivetrain diagnostics simulator system. The vibration signals of different fault motors were collected. The raw signal was pretreated using short time Fourier transform （STFT） to obtain the corresponding time-frequency map. Then, the feature of the time-frequency map was adap- tively extracted by using a convolutional neural network （CNN）. The effects of the pretreatment method, and the hyper parameters of network diagnostic accuracy, were investigated experimentally. The experimental results showed that the influence of the preprocessing method is small, and that the batch-size is the main factor affecting accuracy and training efficiency. By investigating feature visualization, it was shown that, in the case of big data, the extracted CNN features can represent complex mapping relationships between signal and health status, and can also overcome the prior knowledge and engineering experience requirement for feature extraction, which is used by tra- ditional diagnosis methods. This paper proposes a new method, based on STFT and CNN, which can complete motor fault diagnosis tasks more intelligently and accurately.

Convolutional Neural Network-based Leakage Detection of Crude Oil Transmission Pipes

Due to the rapid development in the petroleum industry,the leakage detection of crude oil transmission pipes has become an increasingly crucial issue.At present,oil plants at home and abroad mostly use manual inspection method for detection.This traditional method is not only inefficient but also labor-intensive.The present paper proposes a novel convolutional neural network(CNN)architecture for automatic leakage level assessment of crude oil transmission pipes.An experimental setup is developed,where a visible camera and a thermal imaging camera are used to collect image data and analyze various leakage conditions.Specifically,images are collected from various pipes with no leaking and different leaking states.Apart from images from existing pipelines,images are collected from the experimental setup with different types of joints to simulate leakage conditions in the real world.The main contributions of the present paper are,developing a convolutional neural network to classify the information in red-green-blue(RGB)and thermal images,development of the experimental setup,conducting leakage experiments,and analyzing the data using the developed approach.By successfully combining the two types of images,the proposed method is able to achieve a higher classification accuracy,compared to other methods that use RGB images or thermal images alone.Especially,compared with the method that uses thermal images only,the accuracy increases from about 91%to over 96%.

Convolutional neural networks for time series classification

Time series classification is an important task in time series data mining, and has attracted great interests and tremendous efforts during last decades. However, it remains a challenging problem due to the nature of time series data: high dimensionality, large in data size and updating continuously. The deep learning techniques are explored to improve the performance of traditional feature-based approaches. Specifically, a novel convolutional neural network (CNN) framework is proposed for time series classification. Different from other feature-based classification approaches, CNN can discover and extract the suitable internal structure to generate deep features of the input time series automatically by using convolution and pooling operations. Two groups of experiments are conducted on simulated data sets and eight groups of experiments are conducted on real-world data sets from different application domains. The final experimental results show that the proposed method outperforms state-of-the-art methods for time series classification in terms of the classification accuracy and noise tolerance. © 1990-2011 Beijing Institute of Aerospace Information.

Automatic modulation recognition of radiation source signals based on two-dimensional data matrix and improved residual neural network

Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.

An Urban Road Risk Assessment Framework Based on Convolutional Neural Networks

In contemporary cities,road collapse is one of the most common disasters.This study proposed a framework for assessing the risk of urban road collapse.The framework first established a risk indicator system that combined environmental and anthropogenic factors,such as soil type,pipeline,and construction,as well as other indicators.Second,an oversampling technique was used to create the dataset.The framework then constructed and trained a convolutional neural network(CNN)-based model for risk assessment.The experimental results show that the CNN model(accuracy:0.97,average recall:0.91)outperformed other models.The indicator contribution analysis revealed that the distance between the road and the construction site(contribution:0.132)and the size of the construction(contribution:0.144)are the most significant factors contributing to road collapse.According to the natural breaks,a road collapse risk map of Foshan City,Guangdong Province,was created,and the risk level was divided into five categories.Nearly 3%of the roads in the study area are at very high risk,and 6%are at high risk levels,with the high risk roads concentrated in the east and southeast.The risk map produced by this study can be utilized by local authorities and policymakers to help maintain road safety.

Fault diagnosis of axial piston pumps with multi-sensor data and convolutional neural network

Axial piston pumps have wide applications in hydraulic systems for power transmission.Their condition monitoring and fault diagnosis are essential in ensuring the safety and reliability of the entire hydraulic system.Vibration and discharge pressure signals are two common signals used for the fault diagnosis of axial piston pumps because of their sensitivity to pump health conditions.However,most of the previous fault diagnosis methods only used vibration or pressure signal,and literatures related to multi-sensor data fusion for the pump fault diagnosis are limited.This paper presents an end-to-end multi-sensor data fusion method for the fault diagnosis of axial piston pumps.The vibration and pressure signals under different pump health conditions are fused into RGB images and then recognized by a convolutional neural network.Experiments were performed on an axial piston pump to confirm the effectiveness of the proposed method.Results show that the proposed multi-sensor data fusion method greatly improves the fault diagnosis of axial piston pumps in terms of accuracy and robustness and has better diagnostic performance than other existing diagnosis methods.

High-dimensional aerodynamic data modeling using a machine learning method based on a convolutional neural network

Modeling high-dimensional aerodynamic data presents a significant challenge in aero-loads prediction, aerodynamic shape optimization, flight control, and simulation. This article develops a machine learning approach based on a convolutional neural network (CNN) to address this problem. A CNN can implicitly distill features underlying the data. The number of parameters to be trained can be significantly reduced because of its local connectivity and parameter-sharing properties, which is favorable for solving high-dimensional problems in which the training cost can be prohibitive. A hypersonic wing similar to the Sanger aerospace plane carrier wing is employed as the test case to demonstrate the CNN-based modeling method. First, the wing is parameterized by the free-form deformation method, and 109 variables incorporating flight status and aerodynamic shape variables are defined as model input. Second, more than 7000 sample points generated by the Latin hypercube sampling method are evaluated by performing computational fluid dynamics simulations using a Reynolds-averaged Navier-Stokes flow solver to obtain an aerodynamic database, and a CNN model is built based on the observed data. Finally, the well-trained CNN model considering both flight status and shape variables is applied to aerodynamic shape optimization to demonstrate its capability to achieve fast optimization at multiple flight statuses.

Slope stability analysis based on big data and convolutional neural network

The Limit Equilibrium Method(LEM)is commonly used in traditional slope stability analyses,but it is time-consuming and complicated.Due to its complexity and nonlinearity involved in the evaluation process,it cannot provide a quick stability estimation when facing a large number of slopes.In this case,the convolutional neural network(CNN)provides a better alternative.A CNN model can process data quickly and complete a large amount of data analysis in a specific situation,while it needs a large number of training samples.It is difficult to get enough slope data samples in practical engineering.This study proposes a slope database generation method based on the LEM.Samples were amplified from 40 typical slopes,and a sample database consisting of 20000 slope samples was established.The sample database for slopes covered a wide range of slope geometries and soil layers’physical and mechanical properties.The CNN trained with this sample database was then applied to the stability prediction of 15 real slopes to test the accuracy of the CNN model.The results show that the slope stability prediction method based on the CNN does not need complex calculation but only needs to provide the slope coordinate information and physical and mechanical parameters of the soil layers,and it can quickly obtain the safety factor and stability state of the slopes.Moreover,the prediction accuracy of the CNN trained by the sample database for slope stability analysis reaches more than 99%,and the comparisons with the BP neural network show that the CNN has significant superiority in slope stability evaluation.Therefore,the CNN can predict the safety factor of real slopes.In particular,the combination of typical actual slopes and generated slope data provides enough training and testing samples for the CNN,which improves the prediction speed and practicability of the CNN-based evaluation method in engineering practice.

Multi-dimension and multi-modal rolling mill vibration prediction model based on multi-level network fusion

Mill vibration is a common problem in rolling production,which directly affects the thickness accuracy of the strip and may even lead to strip fracture accidents in serious cases.The existing vibration prediction models do not consider the features contained in the data,resulting in limited improvement of model accuracy.To address these challenges,this paper proposes a multi-dimensional multi-modal cold rolling vibration time series prediction model(MDMMVPM)based on the deep fusion of multi-level networks.In the model,the long-term and short-term modal features of multi-dimensional data are considered,and the appropriate prediction algorithms are selected for different data features.Based on the established prediction model,the effects of tension and rolling force on mill vibration are analyzed.Taking the 5th stand of a cold mill in a steel mill as the research object,the innovative model is applied to predict the mill vibration for the first time.The experimental results show that the correlation coefficient(R^(2))of the model proposed in this paper is 92.5%,and the root-mean-square error(RMSE)is 0.0011,which significantly improves the modeling accuracy compared with the existing models.The proposed model is also suitable for the hot rolling process,which provides a new method for the prediction of strip rolling vibration.