Dual Convolutional Neural Network Research Articles

Gaussian Aquila optimizer based dual convolutional neural networks for identification and grading of osteoarthritis using knee joint images

Degenerative musculoskeletal disease known as Osteoarthritis (OA) causes serious pain and abnormalities for humans and on detecting at an early stage, timely treatment shall be initiated to the patients at the earliest to overcome this pain. In this research study, X-ray images are captured from the humans and the proposed Gaussian Aquila Optimizer based Dual Convolutional Neural Networks is employed for detecting and classifying the osteoarthritis patients. The new Gaussian Aquila Optimizer (GAO) is devised to include Gaussian mutation at the exploitation stage of Aquila optimizer, which results in attaining the best global optimal value. Novel Dual Convolutional Neural Network (DCNN) is devised to balance the convolutional layers in each convolutional model and the weight and bias parameters of the new DCNN model are optimized using the developed GAO. The novelty of the proposed work lies in evolving a new optimizer, Gaussian Aquila Optimizer for parameter optimization of the devised DCNN model and the new DCNN model is structured to minimize the computational burden incurred in spite of it possessing dual layers but with minimal number of layers. The knee dataset comprises of total 2283 knee images, out of which 1267 are normal knee images and 1016 are the osteoarthritis images with an image of 512 × 512-pixel width and height respectively. The proposed novel GAO-DCNN system attains the classification results of 98.25% of sensitivity, 98.93% of specificity and 98.77% of classification accuracy for abnormal knee case–knee joint images. Experimental simulation results carried out confirms the superiority of the developed hybrid GAO-DCNN over the existing deep learning neural models form previous literature studies.

A dual nonsubsampled contourlet network for synthesis images and infrared thermal images denoising

The most direct way to find the electrical switchgear fault is to use infrared thermal imaging technology for temperature measurement. However, infrared thermal imaging images are usually polluted by noise, and there are problems such as low contrast and blurred edges. To solve these problems, this article proposes a dual convolutional neural network model based on nonsubsampled contourlet transform (NSCT). First, the overall structure of the model is made wider by combining the two networks. Compared with the deeper convolutional neural network, the dual convolutional neural network (CNN) improves the denoising performance without increasing the computational cost too much. Secondly, the model uses NSCT and inverse NSCT to obtain more texture information and avoid the gridding effect. It achieves a good balance between noise reduction performance and detail retention. A large number of simulation experiments show that the model has the ability to deal with synthetic noise and real noise, which has high practical value.

Dual-convolutional neural network-enhanced strain estimation method for optical coherence elastography.

Strain estimation is vital in phase-sensitive optical coherence elastography (PhS-OCE). In this Letter, we introduce a novel, to the best of our knowledge, method to improve strain estimation by using a dual-convolutional neural network (Dual-CNN). This approach requires two sets of PhS-OCE systems: a high-resolution system for high-quality training data and a cost-effective standard-resolution system for practical measurements. During training, high-resolution strain results acquired from the former system and the pre-existing strain estimation CNN serve as label data, while the narrowed light source-acquired standard-resolution phase results act as input data. By training a new network with this data, high-quality strain results can be estimated from standard-resolution PhS-OCE phase results. Comparison experiments show that the proposed Dual-CNN can preserve the strain quality even when the light source bandwidth is reduced by over 80%.

Microseismic Signal Reconstruction From Strong Complex Noise Using Low-Rank Structure Extraction and Dual Convolutional Neural Networks.

Microseismic signal reconstruction from complex nonrandom noise is challenging, especially when the signal is disrupted or completely covered by strong field noise. Various methods often assume that signals are laterally coherent or the noise is predictable. In this article, we propose a dual convolutional neural network preceded by a low-rank structure extraction module to reconstruct signals hidden by strong complex field noise. Preconditioning by low-rank structure extraction is the first step in removing high-energy regular noise. The module is followed by two convolutional neural networks with different complexity to achieve better signal reconstruction and noise removal. In addition to the combination of synthetic and field microseismic data, natural images are also used in the training due to their correlation, complexity, and completeness, which contributes to increasing the generalization of the networks. The results from synthetic and real datasets demonstrate superior signal recovery, which cannot be achieved by using solely deep learning, low-rank structure extraction, or curvelet thresholding. Algorithmic generalization is demonstrated using independently acquired array data excluded during training.

High Precision Raman Distributed Fiber Sensing Using Residual Composite Dual-Convolutional Neural Network

High Precision Raman Distributed Fiber Sensing Using Residual Composite Dual-Convolutional Neural Network

A Dual Convolutional Neural Network with Attention Mechanism for Thermal Infrared Image Enhancement

In industrial applications, thermal infrared images, which are commonly used, often suffer from issues such as low contrast and blurred details. Traditional image enhancement algorithms are limited in their effectiveness in improving the visual quality of thermal infrared images due to the specific nature of the application. Therefore, we propose a dual Convolutional Neural Network (CNN) combined with an attention mechanism to address the challenges of enhancing low-quality thermal infrared images and improving their visual quality. Firstly, we employ two parallel sub-networks to extract both global and local features. In one sub-network, we utilize a sparse mechanism incorporating dilated convolutions, while the other sub-network employs Feature Attention (FA) blocks based on channel attention and pixel attention. This architecture significantly enhances the feature extraction capability. The use of attention mechanisms allows the network to filter out irrelevant background information, enabling more flexible feature extraction. Finally, through a simple yet effective fusion block, we thoroughly integrate the extracted features to achieve an optimal fusion strategy, ensuring the highest quality enhancement of the final image. Extensive experiments on benchmark datasets and real images demonstrate that our proposed method outperforms other state-of-the-art models in terms of objective evaluation metrics and subjective assessments. The generated images also exhibit superior visual quality.

Dual convolutional neural network for aberration pre-correction and image quality enhancement in integral imaging display.

This paper proposes a method that utilizes a dual neural network model to address the challenges posed by aberration in the integral imaging microlens array (MLA) and the degradation of 3D image quality. The approach involves a cascaded dual convolutional neural network (CNN) model designed to handle aberration pre-correction and image quality restoration tasks. By training these models end-to-end, the MLA aberration is corrected effectively and the image quality of integral imaging is enhanced. The feasibility of the proposed method is validated through simulations and optical experiments, using an optimized, high-quality pre-corrected element image array (EIA) as the image source for 3D display. The proposed method achieves high-quality integral imaging 3D display by alleviating the contradiction between MLA aberration and 3D image resolution reduction caused by system noise without introducing additional complexity to the display system.

Intelligent recognition and identification of fracture types and parameters for borehole images based on developed convolutional neural networks and post-processing

Borehole imaging is one of the main methods for fracture observation in the rock formations, but there is still a lack of identification systems for deriving fracture parameters from borehole images. Additionally, previous research were limited to sinusoidal fractures. In this study, an intelligent system is developed for multiple types of qualitative fracture identification in a quick and robust manner using convolution neural networks and post-processing. Initially, borehole imaging was carried out in six coal mines to develop a borehole image database that includes a wide variety of rock types and fractures. Afterward, the acquired borehole images of fractures were categorized into three types, such as sinusoidal fractures, vertical fractures and broken areas. In this connection, dual convolutional neural networks were developed to recognize fracture type pixels. Meanwhile, the calculation models associated with corresponding fracture parameters were established to quantitatively describe the fracture characteristics. Eventually, the post-processing programs were developed to identify the geometric parameters for each fracture type. The results indicate that the developed dual convolutional neural networks has the capability to detect fracture pixels with a recognition accuracy of 77.1% for each sinusoidal and vertical fracture pixels, and recognication accuracy of 72.9% for broken area pixels. The post-processing program was developed based on Hough transform and a thinning algorithm, that enables it to the the average recognition rate of 88.71% with an average false alarm rate of 16.67% for all three types of fractures.

Dual CNN cross-teaching semi-supervised segmentation network with multi-kernels and global contrastive loss in ACDC.

The cross-teaching based on Convolutional Neural Network (CNN) and Transformer has been successful in semi-supervised learning; however, the information interaction between local and global relations ignores the semantic features of the medium scale, and at the same time, the information in the process of feature coding is not fully utilized. To solve these problems, we proposed a new semi-supervised segmentation network. Based on the principle of complementary modeling information of different kernel convolutions, we design a dual CNN cross-supervised network with different kernel sizes under cross-teaching. We introduce global feature contrastive learning and generate contrast samples with the help of dual CNN architecture to make efficient use of coding features. We conducted plenty of experiments on the Automated Cardiac Diagnosis Challenge (ACDC) dataset to evaluate our approach. Our method achieves an average Dice Similarity Coefficient (DSC) of 87.2% and Hausdorff distance ([Formula: see text]) of 6.1 mm on 10% labeled data, which is significantly improved compared with many current popular models. Supervised learning is performed on the labeled data, and dual CNN cross-teaching supervised learning is performed on the unlabeled data. All data would be mapped by the two CNNs to generate features, which are used for contrastive learning to optimize the parameters.

Dual convolutional neural network for crowd counting

Dual convolutional neural network for crowd counting

A novel interval dual convolutional neural network method for interval-valued stock price prediction

Accurate interval-valued stock price prediction is challenging and of great interest to investors and for-profit organizations. In this study, by considering individual stock information and relevant stock information simultaneously, we propose a novel interval dual convolutional neural network (Dual-CNNI) model based method to predict interval-valued stock prices. First, the individual and relevant stock information are collected and transformed into images. Then, the Dual-CNNI model is proposed to predict interval-valued stock prices. Specifically, two convolutional neural network (CNN) models with different structures are constructed to respectively extract individual stock features and relevant stock features, and then an interval multilayer perceptron (MLPI) model is used for final interval-valued stock price prediction. Finally, extensive experiments are conducted based on six randomly selected stocks, with comparison to several popular machine learning model based methods and interval-valued time series (ITS) prediction methods. The experimental results indicate that the proposed Dual-CNNI based method has superior predictive ability.

Pose recognition of dancing images using fuzzy deep learning technique in an IoT environment

AbstractWith the development of smart technologies (e.g., Internet of Things (IoT), Artificial Intelligence (AI), and Big Data), people have start using them for various purposes. The real‐time IoT devices generate an enormous amount of video and imaging data, leading to the concept of complex data structure. And people face major challenges in mining and extraction of useful features and information from such data. How to efficiently analyse and process video data to obtain valuable information has become a key research topic. The traditional manual annotation methods are unable to meet the current demand for the growing number of videos. Therefore, a more convenient method for processing video data needs to be developed. The research objective of this paper is dance videos, and the goal is to realize automatic recognition of dance movements. In this paper, a Dual Convolutional Neural Network Algorithm (DCNNA) is proposed for the automatic recognition of different dance movements in live and remote videos. DCNNA can extract video information more comprehensively and efficiently. It can simultaneously extract the light flow features corresponding to the action changes and the information contained in each frame of the video. Therefore, the dance movements can be more accurately identified. In the experiments, the performance of DCNNA is evaluated based on dance videos and compared with Inception V3 and 3D‐CNN. All the experiments illustrate the superior performance of the proposed DCNN algorithm. From the experimental results, it is quite obvious that the F1 score of the proposed DCNNA is 11% and 6% higher than that of the Inception V3 and 3D‐CNN, respectively.

Enhanced Dual Convolutional Neural Network Model Using Explainable Artificial Intelligence of Fault Prioritization for Industrial 4.0.

Artificial intelligence (AI) systems are increasingly used in corporate security measures to predict the status of assets and suggest appropriate procedures. These programs are also designed to reduce repair time. One way to create an efficient system is to integrate physical repair agents with a computerized management system to develop an intelligent system. To address this, there is a need for a new technique to assist operators in interacting with a predictive system using natural language. The system also uses double neural network convolutional models to analyze device data. For fault prioritization, a technique utilizing fuzzy logic is presented. This strategy ranks the flaws based on the harm or expense they produce. However, the method's success relies on ongoing improvement in spoken language comprehension through language modification and query processing. To carry out this technique, a conversation-driven design is necessary. This type of learning relies on actual experiences with the assistants to provide efficient learning data for language and interaction models. These models can be trained to have more natural conversations. To improve accuracy, academics should construct and maintain publicly usable training sets to update word vectors. We proposed the model dataset (DS) with the Adam (AD) optimizer, Ridge Regression (RR) and Feature Mapping (FP). Our proposed algorithm has been coined with an appropriate acronym DSADRRFP. The same proposed approach aims to leverage each component's benefits to enhance the predictive model's overall performance and precision. This ensures the model is up-to-date and accurate. In conclusion, an AI system integrated with physical repair agents is a useful tool in corporate security measures. However, it needs to be refined to extract data from the operating system and to interact with users in a natural language. The system also needs to be constantly updated to improve accuracy.

CNN-CNN: Dual Convolutional Neural Network Approach for Feature Selection and Attack Detection on Internet of Things Networks.

The Internet of Things (IoT) has brought significant advancements that have connected our world more closely than ever before. However, the growing number of connected devices has also increased the vulnerability of IoT networks to several types of attacks. In this paper, we present an approach for detecting attacks on IoT networks using a combination of two convolutional neural networks (CNN-CNN). The first CNN model is leveraged to select the significant features that contribute to IoT attack detection from the raw data on network traffic. The second CNN utilizes the features identified by the first CNN to build a robust detection model that accurately detects IoT attacks. The proposed approach is evaluated using the BoT IoT 2020 dataset. The results reveal that the proposed approach achieves 98.04% detection accuracy, 98.09% precision, 99.85% recall, 98.96% recall, and a 1.93% false positive rate (FPR). Furthermore, the proposed approach is compared with other deep learning algorithms and feature selection methods; the results show that it outperforms these algorithms.

Dual Deep CNN for Tumor Brain Classification.

Brain tumor (BT) is a serious issue and potentially deadly disease that receives much attention. However, early detection and identification of tumor type and location are crucial for effective treatment and saving lives. Manual diagnoses are time-consuming and depend on radiologist experts; the increasing number of new cases of brain tumors makes it difficult to process massive and large amounts of data rapidly, as time is a critical factor in patients' lives. Hence, artificial intelligence (AI) is vital for understanding disease and its various types. Several studies proposed different techniques for BT detection and classification. These studies are on machine learning (ML) and deep learning (DL). The ML-based method requires handcrafted or automatic feature extraction algorithms; however, DL becomes superior in self-learning and robust in classification and recognition tasks. This research focuses on classifying three types of tumors using MRI imaging: meningioma, glioma, and pituitary tumors. The proposed DCTN model depends on dual convolutional neural networks with VGG-16 architecture concatenated with custom CNN (convolutional neural networks) architecture. After conducting approximately 22 experiments with different architectures and models, our model reached 100% accuracy during training and 99% during testing. The proposed methodology obtained the highest possible improvement over existing research studies. The solution provides a revolution for healthcare providers that can be used as a different disease classification in the future and save human lives.

Dual Convolutional Neural Network Classifier with Pyramid Attention Network for Image-Based Kinship Verification

A family is the smallest entity that formed the world with specific characteristics. The characteristics of a family are that the member can/may share some similar DNA and leads to similar physical appearances, including similar facial features. This paper proposed a dual convolutional neural network (CNN) with a pyramid attention network for image-based kinship verification problems. The dual CNN classifier is formed by paralleling the FaceNet CNN architecture followed by family-aware features extraction network and three final fully-connected layers. A channel-wise pyramid attention network is added after the last convolutional layers of FaceNet CNN architecture. The family-aware features extraction network is used to learn family-aware features using the SphereFace loss function. The final features used to classify the kin/non-kin pair are joint aggregation features between the pyramid attention features and family-aware features. At the end of the fully connected layer, a softmax loss layer is attached to learn kinship verification via binary classification problems. To analyze the performance of our proposed classifier, we performed experiments heavily on the Family in The Wild (FIW) kinship verification dataset. The FIW kinship verification dataset is the largest dataset for kinship verification currently available. Experiments of the FIW dataset show that our proposed classifier can achieve the highest average accuracy of 68.05% on a single classifier scenario and 68.73% on an ensemble classifier scenario which is comparable with other state-of-the-art methods. 

A novel gated dual convolutional neural network model with autoregressive method and attention mechanism for probabilistic load forecasting

A novel gated dual convolutional neural network model with autoregressive method and attention mechanism for probabilistic load forecasting

Glioma brain tumor detection using dual convolutional neural networks and histogram density segmentation algorithm

In this work, Glioma brain tumor images are detected from the healthy brain images using Edge preserving image fusion and dual-deep learning Convolutional Neural Network (CNN) method. The first CNN module is used to extract the internal features from the brain image and the second CNN module is used for the feature classification process in this work. In case of training, the brain tumor images and the healthy brain images from the BraTS-IXI dataset are fused using edge preserving method and the fused images are data augmented for increasing the image counts for classification process. Then, the data augmented images are classified by the proposed CNN classifier (to be functioned in training) to produce the Trained Vector (TV). In case of testing process, the source brain images are fused with edge preserving method and the fused image is data augmented and further these data augmented images are classified (to be functioned in classification) into either Glioma or healthy brain image. Then, Histogram-Density Segmentation Algorithm (HDSA) is proposed to segment the tumor regions in the classified Glioma images.

GeoDualCNN: Geometry-Supporting Dual Convolutional Neural Network for Noisy Point Clouds.

We propose a geometry-supporting dual convolutional neural network (GeoDualCNN) for both point cloud normal estimation and denoising. GeoDualCNN fuses the geometry domain knowledge that the underlying surface of a noisy point cloud is piecewisely smooth with the fact that a point normal is properly defined only when local surface smoothness is guaranteed. Centered around this insight, we define the homogeneous neighborhood (HoNe) which stays clear of surface discontinuities, and associate each HoNe with a point whose geometry and normal orientation is mostly consistent with that of HoNe. Thus, we not only obtain initial estimates of the point normals by performing PCA on HoNes, but also for the first time optimize these initial point normals by learning the mapping from two proposed geometric descriptors to the ground-truth point normals. GeoDualCNN consists of two parallel branches that remove noise using the first geometric descriptor (a homogeneous height map, which encodes the point-position information), while preserving surface features using the second geometric descriptor (a homogeneous normal map, which encodes the point-normal information). Such geometry-supporting network architectures enable our model to leverage previous geometry expertise and to benefit from training data. Experiments with noisy point clouds show that GeoDualCNN outperforms the state-of-the-art methods in terms of both noise-robustness and feature preservation.

An application of deep dual convolutional neural network for enhanced medical image denoising.

This work investigates the medical image denoising (MID) application of the dual denoising network (DudeNet) model for chest X-ray (CXR). The DudeNet model comprises four components: a feature extraction block with a sparse mechanism, an enhancement block, a compression block, and a reconstruction block. The developed model uses residual learning to boost denoising performance and batch normalization to accelerate the training process. The name proposed for this model is dual convolutional medical image-enhanced denoising network (DCMIEDNet). The peak signal-to-noise ratio (PSNR) and structure similarity index measurement (SSIM) are used to assess the MID performance for five different additive white Gaussian noise (AWGN) levels of σ = 15, 25, 40, 50, and 60 in CXR images. Presented investigations revealed that the PSNR and SSIM offered by DCMIEDNet are better than several popular state-of-the-art models such as block matching and 3D filtering, denoising convolutional neural network, and feature-guided denoising convolutional neural network. In addition, it is also superior to the recently reported MID models like deep convolutional neural network with residual learning, real-valued medical image denoising network, and complex-valued medical image denoising network. Therefore, based on the presented experiments, it is concluded that applying the DudeNet methodology for DCMIEDNet promises to be quite helpful for physicians.