Convolutional Neural Network-based Method Research Articles

A deep convolutional neural network-based wavelength selection method for spectral characteristics of rice blast disease

Characteristic wavelength selection is a research hotspot in hyperspectral data processing and a key to improving the accuracy of identifying the degree of rice blast infection. This study combines deep learning and visualization techniques to create a wavelength selection method for spectral features of rice blast. A deep convolutional neural (DCNN) structure was designed by combining the convolutional block attention module (CBAM) with residual network (ResNet) to learn different classes of disease features. And the guided grade-weighted heatmap (Guided-GradHM) of the last layer of convolution was obtained using the guided gradient-weighted class activation mapping (Guided-GradCAM) method. Then the spectral characteristic wavelengths were selected based on the average Guided-GradHM of different disease levels. Finally, statistical analysis (JM distance, within-class scatter) and comparative modeling analysis were used to verify the method's validity in this study. The results show that the characteristic wavelengths selected by the Guided-GradCAM method based on the ResNet-CBAM network structure have good inter-class separability and intra-class aggregation, with JM distance greater than 1.9 and within-class scatter less than 0.4. Meanwhile, the random forest (RF) and support vector machine (SVM) models constructed from the spectral characteristic wavelengths selected by the Guided-GradCAM method achieved the best disease level classification accuracy, with overall accuracy (OA) and Kappa of 97.21% and 96.55%, 96.51%, and 95.69%, respectively. Overall, this research method can more accurately select the spectral characteristic wavelengths of different disease levels of rice blast and can provide a more effective method for accurate identification and timely control of the disease.

Multi-path Convolutional Neural Network to Identify Tumorous Sub-classes for Breast Tissue from Histopathological Images

Malignancy is one of the leading causes of death. It is on the rise in the developed and low-income countries with survival rates of less than 40%. However, early diagnosis may increase survival chances. Histopathology images acquired from the biopsy are a popular method for cancer diagnosis. In this work, we propose a deep convolutional neural network-based method that helps classify breast cancer tumor subtypes from histopathology images. The model is trained on the BreakHis dataset but is also tested on images from other datasets. The model is trained to recognized eight different tumor subtypes, and also to perform binary classification (malignant/non-malignant). The CNN model combines an encoder–decoder architecture and a parallel feed-forward network with attention mechanism. The proposed model provides state-of-the-art scores. Comparing with the other models, the accuracy of the proposed model is higher at different magnification and patient levels. The implementation is available at github.com/rangan2510/Residual\(\_\)Unet

Convolutional neural network-based automatic cervical vertebral maturation classification method.

This study aimed to develop a fully automated artificial intelligence-aided cervical vertebral maturation (CVM) classification method based on convolutional neural networks (CNNs) to provide an auxiliary diagnosis for orthodontists. This study consisted of cephalometric images from patients aged between 5 and 18 years. After grouping them into six cervical stages (CSs) by orthodontists, a data set was constructed for analyzing CVM using CNNs. The data set was divided into training, validation, and test sets in the ratio of 70, 15, and 15%. Four CNN models namely, VGG16, GoogLeNet, DenseNet161, and ResNet152 were selected as the candidate models. After training and validation, the models were evaluated to determine which of them is most suitable for CVM analysis. Heat maps were analyzed for a deeper understanding of what the CNNs had learned. The final classification accuracy ranking was ResNet152>DenseNet161>GoogLeNet>VGG16, as evaluated on the test set. ResNet152 proved to be the best model among the four models for CVM classification with a weighted κ of 0.826, an average AUC of 0.933 and total accuracy of 67.06%. The F1 score rank for each subgroup was: CS6>CS1>CS4>CS5>CS3>CS2. The area of the third (C3) and fourth (C4) cervical vertebrae were activated when CNNs were assessing the images. CNN models proved to be a convenient, fast and reliable method for CVM analysis. CNN models have the potential to provide automatic auxiliary diagnostic tools in the future.

SOCIAL DISTANCE DETECTION

COVID-19 is an illness caused by the SARSCoV-2 virus. The majority of COVID-19 patients will have low to normal symptoms and will recover without requiring extra care. Otherwise, some patients will become extremely sick and require medical support. A Deep Learning model is made to track people and measure the distance between them. To prevent the transmission of the infection, making people maintain the minimum distance is the key objective. We apply YOLOv3 and other convolutional neural network-based methods, as well as a distance measurement method, to recognise individuals. This Deep Learning model can determine whether members of a large group maintain their distance from one another. If they maintain a 6 feet distance, it will be indicated in green; if not, it will be highlighted in red. This can help identify social disparities and lessen the spread of COVID-19

Optimized convolutional neural network-based comprehensive early diagnosis method for multiple eye disease recognition

The multilabel classification method (MCM) is an active and effective research area in image analysis for the detection of various diseases. MCM provides insights and assistance to ophthalmologists in the detection of eye disease at an early stage. We propose comprehensive age-related eye disease detection at an early stage using retinal fundus images that were taken from the online public dataset. The flower pollination optimization algorithm was used for the optimization of the hyperparameters of the deep convolutional neural network (DCNN), which increased the speed and accuracy of the network. Initially, training was performed using the public datasets. The overall improvement in training accuracy (7.5%) was achieved using the optimized method compared with the nonoptimized method. Then, the output of the DCNN was applied to a multiclass support vector machine for the classification of eye diseases. The performance of the proposed method was compared with that of the other optimization techniques with the help of the standard performance measures, namely accuracy, specificity, sensitivity, precision, and F1-score. Upon comparing the performance of the proposed method with that of the nonoptimized DCNN in terms of performance measures, it had an improvement in the detection accuracy of 9.62% for AMD, 3.57% for glaucoma, 6.59% for normal, 7.71% for DR, and 11.75% for cataract. The obtained results show the effectiveness of the proposed method.

Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes

Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high segmentation accuracy. However, they usually adopt the feature alignment modules with the same network configuration in the decoder and thus ignore the different roles of stages of the decoder during feature aggregation, leading to a complex decoder structure. Such a manner greatly affects the inference speed. In this paper, we present a novel Stage-aware Feature Alignment Network (SFANet) based on the encoder-decoder structure for real-time semantic segmentation of street scenes. Specifically, a Stage-aware Feature Alignment module (SFA) is proposed to align and aggregate two adjacent levels of feature maps effectively. In the SFA, by taking into account the unique role of each stage in the decoder, a novel stage-aware Feature Enhancement Block (FEB) is designed to enhance spatial details and contextual information of feature maps from the encoder. In this way, we are able to address the misalignment problem with a very simple and efficient multi-branch decoder structure. Moreover, an auxiliary training strategy is developed to explicitly alleviate the multi-scale object problem without bringing additional computational costs during the inference phase. Experimental results show that the proposed SFANet exhibits a good balance between accuracy and speed for real-time semantic segmentation of street scenes. In particular, based on ResNet-18, SFANet respectively obtains 78.1% and 74.7% mean of class-wise Intersection-over-Union (mIoU) at inference speeds of 37 FPS and 96 FPS on the challenging Cityscapes and CamVid test datasets by using only a single GTX 1080Ti GPU.

An Improved Convolutional Neural Network-Based Scene Image Recognition Method.

To solve the problems existing in the research of scene recognition, this paper studies a new convolutional neural network target detection model to achieve a better balance between the accuracy and speed of high-speed scene image recognition. First, aiming at the problem that the image is easy to be disturbed by impurities and poor quality in fine-grained image recognition, a preprocessing method based on the Canny edge detection is designed and the Canny operator is introduced to process the gray image. Second, the L2 regularization algorithm is used to optimize the basic network framework of the convolutional neural network, enhance the stability of the model in a complex environment, improve the generalization ability of the model, and improve the recognition accuracy of the algorithm to a certain extent. Finally, by collecting the campus environment datasets under different environmental conditions, the location recognition experiment and heat map visualization experiment are carried out. Experiments show that compared with the basic convolution neural network algorithm, the algorithm has better recognition performance and good generalization ability. The research of this study realizes the effective combination of multiframe convolution neural network and batch normalization algorithm and has a good practical effect on scene image recognition.

Efficient self-attention mechanism and structural distilling model for Alzheimer’s disease diagnosis

Structural magnetic resonance imaging (sMRI) is commonly used for the identification of Alzheimer’s disease because of its keen insight into atrophy-induced changes in brain structure. Current mainstream convolutional neural network-based deep learning methods ignore the long-term dependencies between voxels; thus, it is challenging to learn the global features of sMRI data. In this study, an advanced deep learning architecture called Brain Informer (BraInf) was developed based on an efficient self-attention mechanism. The proposed model integrates representation learning, feature distilling, and classifier modeling into a unified framework. First, the proposed model uses a multihead ProbSparse self-attention block for representation learning. This self-attention mechanism selects the first ⌊lnN⌋ elements that can represent the overall features from the perspective of probability sparsity, which significantly reduces computational cost. Subsequently, a structural distilling block is proposed that applies the concept of patch merging to the distilling operation. The block reduces the size of the three-dimensional tensor and further lowers the memory cost while preserving the original data as much as possible. Thus, there was a significant improvement in the space complexity. Finally, the feature vector was projected into the classification target space for disease prediction. The effectiveness of the proposed model was validated using the Alzheimer’s Disease Neuroimaging Initiative dataset. The model achieved 97.97% and 91.89% accuracy on Alzheimer’s disease and mild cognitive impairment classification tasks, respectively. The experimental results also demonstrate that the proposed framework outperforms several state-of-the-art methods.

WSRD-Net: A Convolutional Neural Network-Based Arbitrary-Oriented Wheat Stripe Rust Detection Method.

Wheat stripe rusts are responsible for the major reduction in production and economic losses in the wheat industry. Thus, accurate detection of wheat stripe rust is critical to improving wheat quality and the agricultural economy. At present, the results of existing wheat stripe rust detection methods based on convolutional neural network (CNN) are not satisfactory due to the arbitrary orientation of wheat stripe rust, with a large aspect ratio. To address these problems, a WSRD-Net method based on CNN for detecting wheat stripe rust is developed in this study. The model is a refined single-stage rotation detector based on the RetinaNet, by adding the feature refinement module (FRM) into the rotation RetinaNet network to solve the problem of feature misalignment of wheat stripe rust with a large aspect ratio. Furthermore, we have built an oriented annotation dataset of in-field wheat stripe rust images, called the wheat stripe rust dataset 2021 (WSRD2021). The performance of WSRD-Net is compared to that of the state-of-the-art oriented object detection models, and results show that WSRD-Net can obtain 60.8% AP and 73.8% Recall on the wheat stripe rust dataset, higher than the other four oriented object detection models. Furthermore, through the comparison with horizontal object detection models, it is found that WSRD-Net outperforms horizontal object detection models on localization for corresponding disease areas.

Application of Convolutional Neural Network-Based Detection Methods in Fresh Fruit Production: A Comprehensive Review.

As one of the representative algorithms of deep learning, a convolutional neural network (CNN) with the advantage of local perception and parameter sharing has been rapidly developed. CNN-based detection technology has been widely used in computer vision, natural language processing, and other fields. Fresh fruit production is an important socioeconomic activity, where CNN-based deep learning detection technology has been successfully applied to its important links. To the best of our knowledge, this review is the first on the whole production process of fresh fruit. We first introduced the network architecture and implementation principle of CNN and described the training process of a CNN-based deep learning model in detail. A large number of articles were investigated, which have made breakthroughs in response to challenges using CNN-based deep learning detection technology in important links of fresh fruit production including fruit flower detection, fruit detection, fruit harvesting, and fruit grading. Object detection based on CNN deep learning was elaborated from data acquisition to model training, and different detection methods based on CNN deep learning were compared in each link of the fresh fruit production. The investigation results of this review show that improved CNN deep learning models can give full play to detection potential by combining with the characteristics of each link of fruit production. The investigation results also imply that CNN-based detection may penetrate the challenges created by environmental issues, new area exploration, and multiple task execution of fresh fruit production in the future.

Application of Convolutional Neural Network-Based Hierarchical Teaching Method in College English Teaching and Examination Reform

Along with the pace of educational reform in colleges and universities, a variety of new types of teaching and research approaches stand out in each subject taught in colleges and universities. For example, in college English lectures, given the practice of individualized tiered teaching, the development of relevant teaching models for students at different levels has become a new type of teaching and research developed year by year. Based on the English classroom program, teachers should make cognizance of the tiered teaching model when teaching. This paper discusses the tiered teaching method of English teaching and carries out teaching from strategies such as paying attention to students’ tiered teaching, doing well in lecture tiered teaching, developing homework tiered teaching, and paying attention to evaluation tiered teaching. In addition, the assessment system of college English courses lags behind the development of college English teaching reform and cannot play a guiding role in teaching. In response to the above-mentioned views and problems, this paper proposes a convolutional neural network-based algorithm that provides different learning styles for different students in the stratified teaching method of college English, making capable students understand what they learn in class, improving the teaching quality of high school English courses, and, at the same time, establishing a standardized and scientific course with high reliability and validity that meets the actual situation of applied technical college students. At the same time, a standardized and scientific course assessment system with high reliability and validity has been established to meet the actual needs of applied technical college students.

A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition.

Human action recognition is an important field in computer vision that has attracted remarkable attention from researchers. This survey aims to provide a comprehensive overview of recent human action recognition approaches based on deep learning using RGB video data. Our work divides recent deep learning-based methods into five different categories to provide a comprehensive overview for researchers who are interested in this field of computer vision. Moreover, a pure-transformer architecture (convolution-free) has outperformed its convolutional counterparts in many fields of computer vision recently. Our work also provides recent convolution-free-based methods which replaced convolution networks with the transformer networks that achieved state-of-the-art results on many human action recognition datasets. Firstly, we discuss proposed methods based on a 2D convolutional neural network. Then, methods based on a recurrent neural network which is used to capture motion information are discussed. 3D convolutional neural network-based methods are used in many recent approaches to capture both spatial and temporal information in videos. However, with long action videos, multistream approaches with different streams to encode different features are reviewed. We also compare the performance of recently proposed methods on four popular benchmark datasets. We review 26 benchmark datasets for human action recognition. Some potential research directions are discussed to conclude this survey.

A DC Series Arc Fault Detection Method Based on a Lightweight Convolutional Neural Network Used in Photovoltaic System

Although photovoltaic (PV) systems play an essential role in distributed generation systems, they also suffer from serious safety concerns due to DC series arc faults. This paper proposes a lightweight convolutional neural network-based method for detecting DC series arc fault in PV systems to solve this issue. An experimental platform according to UL1699B is built, and current data ranging from 3 A to 25 A is collected. Moreover, test conditions, including PV inverter startup and irradiance mutation, are also considered to evaluate the robustness of the proposed method. Before fault detection, the current data is preprocessed with power spectrum estimation. The lightweight convolutional neural network has a lower computational burden for its fewer parameters, which can be ready for embedded microprocessor-based edge applications. Compared to similar lightweight convolutional network models such as Efficientnet-B0, B2, and B3, the Efficientnet-B1 model shows the highest accuracy of 96.16% for arc fault detection. Furthermore, an attention mechanism is combined with the Efficientnet-B1 to make the algorithm more focused on arc features, which can help the algorithm reduce unnecessary computation. The test results show that the detection accuracy of the proposed method can be up to 98.81% under all test conditions, which is higher than that of general networks.

Parallel interactive delayed attention network for pansharpening

ABSTRACT As deep learning has gained wide attention in computer vision tasks, researchers have also started to explore the application of deep learning in panchromatic sharpening. In recent years, various convolutional neural network-based methods for panchromatic sharpening have been proposed, and these methods have achieved good results. However, shallower networks are unable to learn complex mapping relationships. Networks that are too deep are prone to overfitting, which leads to the degradation of the fusion effect. Moreover, since the convolutional operations are concentrated in local regions, it is difficult to obtain the association information with other regions even in deep networks. Therefore, more accurate feature selection and representation with limited network depth is needed. In this paper, a parallel interactive delayed attention network for panchromatic sharpening (PIDAN) is proposed. The network consists of multiple resolution subnetworks with parallel inputs to improve the representation of high-resolution feature maps by multiscale low-resolution features of the same depth and similar level. In addition, we propose a delayed channel attention module. This module obtains correlations between low-frequency and high-frequency information through adaptive learning, making the network more flexible in processing different types of information. The depth feature reweighting restriction combined with the residual unit can further avoid the overfitting representation of features as the network deepens. Experimental results on Gaofen-2 and WorldView-2 datasets show that the proposed method is competitive in both quality assessment and visual perception.

A Convolutional Neural Network-Based Recognition Method of Gear Performance Degradation Mode

Abstract In an increasingly intelligent modern society, whether in industrial production activities or daily life, mechanical transmission equipment is more and more widely used. Once a failure occurs, it will not only cause the stagnation of industrial production, bring huge economic losses and environmental pollution, but may also cause casualties. Therefore, it is particularly important to identify and monitor the performance degradation of mechanical equipment. Based on the convolutional neural network (CNN), a stacking incremental deformable residual block network recognition model is proposed. This method converts the one-dimensional signal recognition problem into an image recognition problem. The average pooling layer replaces the fully connected layer, and the large-size convolution kernel is replaced with a small-size convolution kernel. With the recognition of the gear performance degradation modes, the experiment proves that the multi-channel recognition model has a better recognition effect.

Automatic construction of filter tree by genetic programming for ultrasound guidance image segmentation

Segmentation of ultrasound guidance images (UGIs) is a critical step in ultrasound-guided high intensity focused ultrasound (HIFU) therapy. However, the low signal-to-noise ratio characteristic of UGIs makes it difficult to acquire enough annotations. This paper proposes a novel genetic programming-based approach to achieve automatic construction of an image filter tree (IFT) for UGI segmentation since genetic programming has a natural advantage in training on small datasets. In the new approach, a set of predefined functions are adapted with better anti-noise performance to deal with noise interference. Moreover, a position-determined function is designed for incorporating preoperative information in each IFT to form a closed-loop system thereby facilitating the segmentation process. The optimal IFT evolved by genetic programming, along with a preprocessing step and a postprocessing step, constructs the pipeline for the segmentation of UGIs. The quantitative evaluation of the segmentation results shows the mean true positive rate, the mean false positive rate, the mean intersection over union, the mean norm Hausdorff distance and the mean norm maximum average distance are found to be 94.86%, 6.72%, 89.14%, 3.20% and 0.83%, respectively, outperforming the popular convolutional neural network-based segmentation methods. The segmentation results reveal that the evolved IFT can achieve accurate segmentation of UGIs and indicate that the proposed approach can be a promising option for medical image segmentation when there are only a few training samples available.

Teaching machines to optimizing machining parameters: using independent fuzzy logic controller and image data

Optimization of machining parameters like cutting speed, feed, and depth of cut is one of the extensively studied fields in the past two decades. While researchers agree optimization of these parameters is essential, there is no conscience as to what the objective of the optimization should be. The studies consider production cost, production time, surface finish, among others, as the objective of parameter optimization, but there are very few studies that consider the manufacturer prescribed tool life as the criteria for parament optimization. Among the methods that do consider tool life as an optimization objective, very few are closed-loop systems and these systems are facing challenges to generalizing when the application changes or the machining material changes or the tool geometry changes. Considering this, a novel image feedback using a convolution neural network-based method combined with principles of fuzzy logic is used to optimize machining parameters. Since the system is based on online feedback from the images of the inserts, it can be used for different materials, and the system is invariant to the different tool geometries and grades as the decisions are based on the wear mechanisms detected. The hybrid system is validated through experimentation for the turning application, but the methodology can be easily adapted for other machining applications.

A convolutional neural network-based COVID-19 detection method using chest CT images.

BackgroundHigh-throughput population screening for the novel coronavirus disease (COVID-19) is critical to controlling disease transmission. Convolutional neural networks (CNNs) are a cutting-edge technology in the field of computer vision and may prove more effective than humans in medical diagnosis based on computed tomography (CT) images. Chest CT images can show pulmonary abnormalities in patients with COVID-19.MethodsIn this study, CT image preprocessing are firstly performed using fuzzy c-means (FCM) algorithm to extracted the region of the pulmonary parenchyma. Through multiscale transformation, the preprocessed image is subjected to multi scale transformation and RGB (red, green, blue) space construction. After then, the performances of GoogLeNet and ResNet, as the most advanced CNN architectures, were compared in COVID-19 detection. In addition, transfer learning (TL) was employed to solve overfitting problems caused by limited CT samples. Finally, the performance of the models were evaluated and compared using the accuracy, recall rate, and F1 score.ResultsOur results showed that the ResNet-50 method based on TL (ResNet-50-TL) obtained the highest diagnostic accuracy, with a rate of 82.7% and a recall rate of 79.1% for COVID-19. These results showed that applying deep learning technology to COVID-19 screening based on chest CT images is a very promising approach. This study inspired us to work towards developing an automatic diagnostic system that can quickly and accurately screen large numbers of people with COVID-19.ConclusionsWe tested a deep learning algorithm to accurately detect COVID-19 and differentiate between healthy control samples, COVID-19 samples, and common pneumonia samples. We found that TL can significantly increase accuracy when the sample size is limited.

Super Resolution for Noisy Images Using Convolutional Neural Networks

The images in high resolution contain more useful information than the images in low resolution. Thus, high-resolution digital images are preferred over low-resolution images. Image super-resolution is one of the principal techniques for generating high-resolution images. The major advantages of super-resolution methods are that they are economical, independent of the image capture devices, and can be statically used. In this paper, a single-image super-resolution network model based on convolutional neural networks is proposed by combining conventional autoencoder and residual neural network approaches. A convolutional neural network-based dictionary method is used to train low-resolution input images for high-resolution images. In addition, a linear refined unit thresholds the convolutional neural network output to provide a better low-resolution image dictionary. Autoencoders aid in the removal of noise from images and the enhancement of their quality. Secondly, the residual neural network model processes it further to create a high-resolution image. The experimental results demonstrate the outstanding performance of our proposed method compared to other traditional methods. The proposed method produces clearer and more detailed high-resolution images, as they are important in real-life applications. Moreover, it has the advantage of combining convolutional neural network-based dictionary learning, autoencoder image enhancement, and noise removal. Furthermore, residual neural network training with improved preprocessing creates an efficient and versatile single-image super-resolution network.

Nonlocal Feature Selection Encoder–Decoder Network for Accurate InSAR Phase Filtering

Accurate interferometric phase filtering is an essential step in InSAR data processing. The existing deep learning-based phase-filtering methods were developed based on local neighboring pixels and only use local phase information. The idea of nonlocal processing has been proven to be very effective for improving the accuracy of interferometric phase filtering. In this paper, we propose a deep convolutional neural network-based nonlocal InSAR filtering method via a nonlocal phase filtering network (NL-PFNet) based on the encoder–decoder structure and nonlocal feature selection strategy. Thanks to the powerful phase feature extraction ability of the encoder–decoder structure and the utilization of nonlocal phase information, NL-PFNet can predict an accurately filtered interferometric phase after training using a large number of interferometric phase images with different noise levels. Experiments on both simulated and real InSAR data show that the proposed method significantly outperforms three traditional well-established methods and another deep learning-based method. Compared with the InSAR-BM3D filter and another deep learning-based method, the mean square error of the proposed method is 25% and 11% lower when processing simulated data, respectively, and when processing the real Sentinel-1 interferometric phase, the no-reference evaluation metric Q of the proposed method is 25% and 9% higher, respectively. In addition, the running time of the proposed method is tens of times less than that of the traditional filtering methods.