Dual-channel Convolutional Neural Network Research Articles

Fault diagnosis of rolling bearings under varying speeds based on gray level co-occurrence matrix and DCCNN

Rolling bearings are widely used in various industries, including rail transit, aerospace, and wind power generation, playing a critical role. However, bearing failures can lead to serious consequences, impacting equipment operation and even causing safety accidents. Hence, the diagnosis of bearing faults is of utmost importance. However, the variable speed conditions experienced during bearing operation pose significant challenges to fault diagnosis. To overcome the limitations of traditional methods in diagnosing bearing faults under variable speed conditions, this paper proposes a fault diagnosis method based on the gray-level co-occurrence matrix (GLCM) and Dual Channel Convolutional Neural Network (DCCNN). The method introduces a two-dimensional grayscale matrix construction (2D-GMC) technique to extract grayscale texture features for fault diagnosis. Additionally, an unconventional kernel design method, based on grayscale image contrast, is proposed to reduce the complexity associated with traditional square kernels. A new DCCNN architecture is developed accordingly. Furthermore, the transfer learning concept is utilized to train the proposed DCCNN model using fault signals at specific rotational speeds. The method intercepts the variable speed into multi-speed short-time series, then constructs gray image under different speed to realize the rapid fault diagnosis of bearings under variable speed conditions.

Hierarchically Gated Recurrent Neural Network optimized with Tasmanian Devil Optimization for Piano Playing Based on Virtual Reality Technology

Playing the piano is a beautiful and extremely technical art form in addition to an elegant performance art. The player's ability to execute with elegance and technicality which requires years of practice will be crucial. The success of a piano concert ultimately rests not only on the performing abilities of the pianist but also on the pianist's mental and psychological makeup. This manuscript presents a Hierarchically Gated Recurrent Neural Network (HGRNN) optimized with the Tasmanian Devil Optimization (TDO) for predicting the real time instruction for playing piano based on virtual reality (PPVR-HGRNN-TDO). Initially, the data is collected from MIDI dataset. Afterward, the data is fed to a Multi-domain collaborative Filter (MDCF) based preprocessing process. Then the preprocessed data’s are fed to Scaling-Basis Chirplet Transform (SBCT) for extracting features such as tone quality and loudness variations. The extracted features are fed to HGRNN to classify the piano playing performance such as good, normal and poor. The weight parameters of HGRNN are optimized using TDO. The proposed PPVR-HGRNN-TDO is implemented in python, effectiveness assessed by several performance metrics such as accuracy, precision, specificity, sensitivity, F1-score and ROC. The gained results of the proposed PPVR-HGRNN-TDO method attains higher accuracy 20.46%, 23.54%, 35.58%, higher precision 33.56%, 21.72%, 33.97% and higher sensitivity 32.54%, 22.76%, 36.97%. The proposed method shows better results in all existing systems like Dual Channel Convolutional Neural Network (DCCNN),Convolutional Neural Network (CNN), and Back Propagation Neural Network with Genetic Algorithm (BPNN-GA). From the result it is concludes that the proposed PPVR-HGRNN-TDO method based accuracy is higher than the existing methods.

Automatic and real-time tissue sensing for autonomous intestinal anastomosis using hybrid MLP-DC-CNN classifier-based optical coherence tomography.

Anastomosis is a common and critical part of reconstructive procedures within gastrointestinal, urologic, and gynecologic surgery. The use of autonomous surgical robots such as the smart tissue autonomous robot (STAR) system demonstrates an improved efficiency and consistency of the laparoscopic small bowel anastomosis over the current da Vinci surgical system. However, the STAR workflow requires auxiliary manual monitoring during the suturing procedure to avoid missed or wrong stitches. To eliminate this monitoring task from the operators, we integrated an optical coherence tomography (OCT) fiber sensor with the suture tool and developed an automatic tissue classification algorithm for detecting missed or wrong stitches in real time. The classification results were updated and sent to the control loop of STAR robot in real time. The suture tool was guided to approach the object by a dual-camera system. If the tissue inside the tool jaw was inconsistent with the desired suture pattern, a warning message would be generated. The proposed hybrid multilayer perceptron dual-channel convolutional neural network (MLP-DC-CNN) classification platform can automatically classify eight different abdominal tissue types that require different suture strategies for anastomosis. In MLP, numerous handcrafted features (∼1955) were utilized including optical properties and morphological features of one-dimensional (1D) OCT A-line signals. In DC-CNN, intensity-based features and depth-resolved tissues' attenuation coefficients were fully exploited. A decision fusion technique was applied to leverage the information collected from both classifiers to further increase the accuracy. The algorithm was evaluated on 69,773 testing A-line data. The results showed that our model can classify the 1D OCT signals of small bowels in real time with an accuracy of 90.06%, a precision of 88.34%, and a sensitivity of 87.29%, respectively. The refresh rate of the displayed A-line signals was set as 300 Hz, the maximum sensing depth of the fiber was 3.6 mm, and the running time of the image processing algorithm was ∼1.56 s for 1,024 A-lines. The proposed fully automated tissue sensing model outperformed the single classifier of CNN, MLP, or SVM with optimized architectures, showing the complementarity of different feature sets and network architectures in classifying intestinal OCT A-line signals. It can potentially reduce the manual involvement of robotic laparoscopic surgery, which is a crucial step towards a fully autonomous STAR system.

A Refined Wind Power Forecasting Method with High Temporal Resolution Based on Light Convolutional Neural Network Architecture

With a large proportion of wind farms connected to the power grid, it brings more pressure on the stable operation of power systems in shorter time scales. Efficient and accurate scheduling, operation control and decision making require high time resolution power forecasting algorithms with higher accuracy and real-time performance. In this paper, we innovatively propose a high temporal resolution wind power forecasting method based on a light convolutional architecture—DC_LCNN. The method starts from the source data and novelly designs the dual-channel data input mode to provide different combinations of feature data for the model, thus improving the upper limit of the learning ability of the whole model. The dual-channel convolutional neural network (CNN) structure extracts different spatial and temporal constraints of the input features. The light global maximum pooling method replaces the flat operation combined with the fully connected (FC) forecasting method in the traditional CNN, extracts the most significant features of the global method, and directly performs data downscaling at the same time, which significantly improves the forecasting accuracy and efficiency of the model. In this paper, the experiments are carried out on the 1 s resolution data of the actual wind field, and the single-step forecasting task with 1 s ahead of time and the multi-step forecasting task with 1~10 s ahead of time are executed, respectively. Comparing the experimental results with the classical deep learning models in the current field, the proposed model shows absolute accuracy advantages on both forecasting tasks. This also shows that the light architecture design based on simple deep learning models is also a good solution in performing high time resolution wind power forecasting tasks.

Mudslide susceptibility assessment based on a two-channel residual network

In response to the challenges posed by rugged terrain in Yunnan, hindering large-scale mudslide screening efforts, this article introduces a dual-channel Convolutional Neural Network (CNN) constructed using elevation data from historical mudslide-prone valleys (Digital Elevation Model, DEM) and remote sensing imagery. The network is designed to facilitate the comprehensive assessment of potential mudslide hazards in gullies, serving as a crucial tool for early mudslide disaster warning. The model initially employs an enhanced residual structure to extract fundamental features from both types of data. Subsequently, it leverages the SE module and deep separable structure to emphasize the importance of relevant features and expedite model convergence. Finally, the model classifies the gullies under evaluation based on their similarity to gullies where mudslides have previously occurred. Experimental results demonstrate the model’s robust performance in assessing mudflow-prone gullies, achieving an impressive precision rate of up to 81.10% and a recall rate of 82.76%. When applied to evaluate the potential hazard of mudslide gullies across the entirety of Nujiang Prefecture, the model predicts that 87.80% of the mudslide locations are at an extremely high risk. These findings underscore the viability of utilizing image-based gully feature analysis for assessing the hazard levels of mudslide-prone gullies.

Seismic Landslide Susceptibility Assessment Using Newmark Displacement Based on a Dual-Channel Convolutional Neural Network

Landslide susceptibility assessment (LSA) is an essential tool for landslide hazard warning. The selection of earthquake-related factors is pivotal for seismic LSA. In this study, Newmark displacement (Dn) is employed as the earthquake-related factor, providing a detailed representation of seismic characteristics. On the algorithmic side, a dual-channel convolutional neural network (CNN) model is built, and the last classification layer is replaced with two machine learning (ML) models to facilitate the extraction of deeper features related to landslide development. This research focuses on Beichuan County in Sichuan Province, China. Fifteen landslide predisposing factors, including hydrological, geomorphic, geological, vegetation cover, anthropogenic, and earthquake-related features, were extensively collected. The results demonstrate some specific issues. Dn outperforms conventional earthquake-related factors such as peak ground acceleration (PGA) and Arias intensity (Ia) in capturing seismic influence on landslide development. Under the same conditions, the OA improved by 5.55% and AUC improved by 0.055 compared to the PGA; the OA improved by 3.2% and AUC improved by 0.0327 compared to the Ia. The improved CNN outperforms ML models. Under the same conditions, the OA improved by 4.69% and AUC improved by 0.0467 compared to RF; the OA improved by 4.47% and AUC improved by 0.0447 compared to SVM. Additionally, historical landslides validate the reasonableness of the landslide susceptibility maps. The proposed method exhibits a high rate of overlap with the historical landslide inventory. The proportion of historical landslides in the very high and high susceptibility zones exceeds 87%. The method not only enhances accuracy but also produces a more fine-grained susceptibility map, providing a reliable basis for early warning of seismic landslides.

Research on Fault Detection for Microservices Based on Log Information and Social Network Mechanism Using BiLSTM-DCNN Model

The microservice architecture breaks through the traditional cluster architecture mode based on virtual machines and uses containers as carriers to interact through lightweight communication mechanisms to reduce system coupling and provide more flexible system service support. With the expansion of the system scale, a large number of system logs with complex structures and chaotic relationships are generated. How to accurately analyze the system logs and make efficient fault prediction is particularly important for building a safe and reliable system. By studying neural network technology, this paper proposes an Attention-Based Bidirectional Long Short-Term Memory Network (Bi-LSTM). Combined with the dual channel convolutional neural network model (DCNN), it uses the attention mechanism to explore the differences between dimensional features, realizes multi-dimensional feature fusion, and establishes a BiLSTM-DCNN deep learning model that integrates the attention mechanism. From the perspective of social network analysis, a data preprocessing method is proposed to process fault redundant data and improve the accuracy of fault prediction under Microservices. Compare BiLSTM-DCNN with the mainstream system log analysis machine learning models SVM, CNN and Bi-LSTM, and explore the advantages of BiLSTM-DCNN in processing microservice system log text. The model is applied to simulation data and HDFS data set for experimental comparison, which proves the good generalization ability and universality of BiLSTM-DCNN.

Design and research of music teaching system based on virtual reality system in the context of education informatization.

Virtual Reality (VR) technology uses computers to simulate the real world comprehensively. VR has been widely used in college teaching and has a huge application prospect. To better apply computer-aided instruction technology in music teaching, a music teaching system based on VR technology is proposed. First, a virtual piano is developed using the HTC Vive kit and the Leap Motion sensor fixed on the helmet as the hardware platform, and using Unity3D, related SteamVR plug-ins, and Leap Motion plug-ins as software platforms. Then, a gesture recognition algorithm is proposed and implemented. Specifically, the Dual Channel Convolutional Neural Network (DCCNN) is adopted to collect the user's gesture command data. The dual-size convolution kernel is applied to extract the feature information in the image and the gesture command in the video, and then the DCCNN recognizes it. After the spatial and temporal information is extracted, Red-Green-Blue (RGB) color pattern images and optical flow images are input into the DCCNN. The prediction results are merged to obtain the final recognition result. The experimental results reveal that the recognition accuracy of DCCNN for the Curwen gesture is as high as 96%, and the recognition accuracy varies with different convolution kernels. By comparison, it is found that the recognition effect of DCCNN is affected by the size of the convolution kernel. Combining convolution kernels of size 5×5 and 7×7 can improve the recognition accuracy to 98%. The research results of this study can be used for music teaching piano and other VR products, with extensive popularization and application value.

Duplicate Bug Report Detection Using an Attention-Based Neural Language Model

<i>Context:</i> Users and developers use bug tracking systems to report errors that occur during the development and testing of software. The manual identification of duplicates is a tedious task especially with software that have large bug repositories. In this context, their automatic detection becomes a necessary task that can help prevent frequently fixing the same bug. <i>Objective:</i> In this article, we propose <i>BERT-MLP</i>, a novel pretrained language model using bidirectional encoder representations from ransformers (BERT) for duplicate bug report detection (DBRD) with the aim of improving the detection rate compared to existing works. <i>Method:</i> Our approach considers only unstructured data. These are fed into the BERT model in order to learn the contextual relationships between words. The output is fed into a multilayer perceptron (MLP) classifier, representing our base DBRD. <i>Results:</i> Our approach was evaluated on three projects: Mozilla Firefox, Eclipse Platform, and Thunderbird. It achieved an accuracy of 92.11, 94.08, and 89.03&#x0025;, respectively, for Mozilla, Eclipse, and Thunderbird. A comparison with a dual-channel convolutional neural network (DC-CNN) model and other pretrained models, including RoBERTa and Sentence-Bert has been conducted. Results showed that <i>BERT-MLP</i> outperformed, the second best performing models (DC-CNN and Sentence-BERT) by 12&#x0025; in accuracy for Eclipse and 9&#x0025; for both Mozilla and Thunderbird, respectively.

Synergy of Sentinel-1 and Sentinel-2 Imagery for Crop Classification Based on DC-CNN

Over the years, remote sensing technology has become an important means to obtain accurate agricultural production information, such as crop type distribution, due to its advantages of large coverage and a short observation period. Nowadays, the cooperative use of multi-source remote sensing imagery has become a new development trend in the field of crop classification. In this paper, the polarimetric components of Sentinel-1 (S-1) decomposed by a new model-based decomposition method adapted to dual-polarized SAR data were introduced into crop classification for the first time. Furthermore, a Dual-Channel Convolutional Neural Network (DC-CNN) with feature extraction, feature fusion, and encoder-decoder modules for crop classification based on S-1 and Sentinel-2 (S-2) was constructed. The two branches can learn from each other by sharing parameters so as to effectively integrate the features extracted from multi-source data and obtain a high-precision crop classification map. In the proposed method, firstly, the backscattering components (VV, VH) and polarimetric components (volume scattering, remaining scattering) were obtained from S-1, and the multispectral feature was extracted from S-2. Four candidate combinations of multi-source features were formed with the above features. Following that, the optimal one was found on a trial. Next, the characteristics of optimal combinations were input into the corresponding network branches. In the feature extraction module, the features with strong collaboration ability in multi-source data were learned by parameter sharing, and they were deeply fused in the feature fusion module and encoder-decoder module to obtain more accurate classification results. The experimental results showed that the polarimetric components, which increased the difference between crop categories and reduced the misclassification rate, played an important role in crop classification. Among the four candidate feature combinations, the combination of S-1 and S-2 features had a higher classification accuracy than using a single data source, and the classification accuracy was the highest when two polarimetric components were utilized simultaneously. On the basis of the optimal combination of features, the effectiveness of the proposed method was verified. The classification accuracy of DC-CNN reached 98.40%, with Kappa scoring 0.98 and Macro-F1 scoring 0.98, compared to 2D-CNN (OA reached 94.87%, Kappa scored 0.92, and Macro-F1 scored 0.95), FCN (OA reached 96.27%, Kappa scored 0.94, and Macro-F1 scored 0.96), and SegNet (OA reached 96.90%, Kappa scored 0.95, and Macro-F1 scored 0.97). The results of this study demonstrated that the proposed method had significant potential for crop classification.

A Terahertz Fast Imaging Method for Debonding Defects of Thermal Barrier Coatings Based on Dual-Channel Convolutional Neural Network

To tackle the inefficiency of terahertz (THz)-based C-scan defect detection for thermal barrier coatings (TBCs), a dual-channel convolutional neural network–based THz fast imaging method is proposed. In this paper, the finite-difference time-domain (FDTD) method is used to prepare the training set. In the numerical simulation, the actual C-scan step is simulated by grid division of different sizes. The large step THz image is preliminarily reconstructed by bicubic interpolation, and then the deep and shallow features in the image are extracted by the dual-channel convolution neural network and the image under small step is reconstructed by different weight refusion, so as to improve the detection efficiency by reducing the number of C-scan points. Gaussian white noise with different distributions is employed when simulating the real test image. The experimental results show that compared with bicubic, ICBI, SRCNN, and ResNet, the dual-channel convolutional neural network improves PSNR (peak signal-to-noise ratio) by 2.85, 2.81, 2.25, and 1.54, and improves by 0.019, 0.014, 0.014, and 0.009 on SSIM (structural similarity).

Research on the mechanical fault diagnosis method based on sound signal and IEMD-DDCNN

PurposeThe purpose of this paper is to provide a shorter time cost, high-accuracy fault diagnosis method for water pumps. Water pumps are widely used in industrial equipment and their fault diagnosis is gaining increasing attention. Considering the time-consuming empirical mode decomposition (EMD) method and the more efficient classification provided by the convolutional neural network (CNN) method, a novel classification method based on incomplete empirical mode decomposition (IEMD) and dual-input dual-channel convolutional neural network (DDCNN) composite data is proposed and applied to the fault diagnosis of water pumps.Design/methodology/approachThis paper proposes a data preprocessing method using IEMD combined with mel-frequency cepstrum coefficient (MFCC) and a neural network model of DDCNN. First, the sound signal is decomposed by IEMD to get numerous intrinsic mode functions (IMFs) and a residual (RES). Several IMFs and one RES are then extracted by MFCC features. Ultimately, the obtained features are split into two channels (IMFs one channel; RES one channel) and input into DDCNN.FindingsThe Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection (MIMII dataset) is used to verify the practicability of the method. Experimental results show that decomposition into an IMF is optimal when taking into account the real-time and accuracy of the diagnosis. Compared with EMD, 51.52% of data preprocessing time, 67.25% of network training time and 63.7% of test time are saved and also improve accuracy.Research limitations/implicationsThis method can achieve higher accuracy in fault diagnosis with a shorter time cost. Therefore, the fault diagnosis of equipment based on the sound signal in the factory has certain feasibility and research importance.Originality/valueThis method provides a feasible method for mechanical fault diagnosis based on sound signals in industrial applications.

A hybrid classification method with dual-channel CNN and KELM for hyperspectral remote sensing images

ABSTRACT In this paper, a hybrid classification method based on dual-channel convolutional neural network (DC-CNN) and kernel extreme learning machine (KELM), namely PLDC-KELM, is proposed to improve the spatial-spectral feature extraction ability and hyperspectral remote sensing image (HRSI) classification accuracy. In the proposed PLDC-KELM, principal component analysis (PCA) is employed to reduce the dimensionality of original HRSI, and local binary pattern (LBP) is utilized to extract spatial features from the data after dimensionality reduction, and the one-dimensional convolutional neural network (1D-CNN) model is constructed to extract deep spatial features from the dimensionality-reduced spatial features. The secure connection layers of two 1D-CNN models are connected to fuse deep spectral and spatial features. Finally, the fused features are input into KELM in order to realize an HRSI classification method. Indian Pines data, Pavia University data, and Salinas data are used to prove the effectiveness of the PLDC-KELM. The experimental results show that the PLDC-KELM method can achieve classification accuracy of 99.95%, 99.98%, and 99.97%, respectively. It is an effective method for hyperspectral remote sensing image classification.

Sea Surface Target Detection Using Global False Alarm Controllable Adaptive Boosting Based on Correlation Features

In the complex marine environment, traditional detectors based on the classifiers cannot guarantee the global false alarm control. In this paper, we propose a detector based on dual channel convolutional neural network (DC-CNN) and global false alarm controllable adaptive boosting tree (GFAC-A), which is shortened as DC-CNN-GFAC-A. DC-CNN focuses on the correlation features of radar echoes in time domain and frequency domain, better use multi-dimensional features and show a better feature extraction ability. Through the application of GFAC-A, the false alarm rate is introduced into the algorithm combining decision tree and AdaBoost to achieve the high-performance detection of global false alarm controllable for high-dimensional features. It is heuristics. The combination of DC-CNN and GFAC-A solves the disadvantage that current classifiers cannot meet the conditions of good performance and low false alarm. First, the connectivity information is obtained by using the frequency domain amplitude characteristics of radar echo data, and the recursive information is obtained by using the nonlinear recursive time series characteristics. And the dual-channel datasets of targets and clutter are built. Then, DC-CNN is built to extract and fuse high-dimensional features to obtain feature vectors of targets and clutter. Besides, the performance comparison of different neural network model combinations is carried out. Finally, compared with the traditional threshold-controllable classifiers, the proposed GFAC-A classifier achieves the high detection performance under the global controlled false alarm. The results show that DC-CNN-GFAC-A can achieve 96.491% detection accuracy when the false alarm rate is 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-3</sup> , which is superior to other detections.

Sternum age estimation with dual channel fusion CNN model

Although age determination by radiographs of the hand and wrist before the age of 18 is an area where there is a lot of radiological knowledge and many studies are carried out, studies on age determination for adults are limited. Studies on adult age determination through sternum multidetector computed tomography (MDCT) images using artificial intelligence algorithms are much fewer. The reason for the very few studies on adult age determination is that most of the changes observed in the human skeleton with age are outside the limits of what can be perceived by the human eye. In this context, with the dual-channel Convolutional Neural Network (CNN) we developed, we were able to predict the age groups defined as 20-35, 35-50, 51-65, and over 65 with 73% accuracy over sternum MDCT images. Our study shows that fusion modeling with dual-channel convolutional neural networks and using more than one image from the same patient is more successful. Fusion models will make adult age determination, which is often a problem in forensic medicine, more accurate.

A Dual-Channel Deep Learning Approach for Lung Cavity Estimation From Hyperpolarized Gas and Proton MRI.

Hyperpolarized gas MRI can quantify regional lung ventilation via biomarkers, including the ventilation defect percentage (VDP). VDP is computed from segmentations derived from spatially co-registered functional hyperpolarized gas and structural proton (1 H)-MRI. Although acquired at similar lung inflation levels, they are frequently misaligned, requiring a lung cavity estimation (LCE). Recently, single-channel, mono-modal deep learning (DL)-based methods have shown promise for pulmonary image segmentation problems. Multichannel, multimodal approaches may outperform single-channel alternatives. We hypothesized that a DL-based dual-channel approach, leveraging both 1 H-MRI and Xenon-129-MRI (129 Xe-MRI), can generate LCEs more accurately than single-channel alternatives. Retrospective. A total of 480 corresponding 1 H-MRI and 129 Xe-MRI scans from 26 healthy participants (median age [range]: 11 [8-71]; 50% females) and 289 patients with pulmonary pathologies (median age [range]: 47 [6-83]; 51% females) were split into training (422 scans [88%]; 257 participants [82%]) and testing (58 scans [12%]; 58 participants [18%]) sets. 1.5-T, three-dimensional (3D) spoiled gradient-recalled 1 H-MRI and 3D steady-state free-precession 129 Xe-MRI. We developed a multimodal DL approach, integrating 129 Xe-MRI and 1 H-MRI, in a dual-channel convolutional neural network. We compared this approach to single-channel alternatives using manually edited LCEs as a benchmark. We further assessed a fully automatic DL-based framework to calculate VDPs and compared it to manually generated VDPs. Friedman tests with post hoc Bonferroni correction for multiple comparisons compared single-channel and dual-channel DL approaches using Dice similarity coefficient (DSC), average boundary Hausdorff distance (average HD), and relative error (XOR) metrics. Bland-Altman analysis and paired t-tests compared manual and DL-generated VDPs. A P value < 0.05 was considered statistically significant. The dual-channel approach significantly outperformed single-channel approaches, achieving a median (range) DSC, average HD, and XOR of 0.967 (0.867-0.978), 1.68 mm (37.0-0.778), and 0.066 (0.246-0.045), respectively. DL-generated VDPs were statistically indistinguishable from manually generated VDPs (P= 0.710). Our dual-channel approach generated LCEs, which could be integrated with ventilated lung segmentations to produce biomarkers such as the VDP without manual intervention. 4. Stage 1.

Dual-Channel Convolutional Network-Based Fault Cause Identification for Active Distribution System Using Realistic Waveform Measurements

Accurate and rapid identification of distribution system fault causes is essential for power system reliability enhancement. Manual fault cause identification requires extensive human resources that leads to extended power outage time. To this end, this paper proposes a dual-channel convolutional neural network (DC-CNN)-based method for distribution system fault cause identification using realistic data from waveform measurement units. The fault mechanism and waveform characteristics of different fault causes are investigated by analyzing large amounts of field waveform data. The short-time Fourier transform (STFT) is advocated to extract the frequency-domain features, which are used together with the time-domain data for constructing the time-frequency feature images. This leads to improved feature extraction via the proposed DC-CNN-enabled multimodal information fusion. A fully connected layer with a maxout unit (FCM layer) is constructed to enhance the mapping ability of high-level features and improve classification accuracy. Extensive test results using field data demonstrate the superiority of the proposed method over other methods.

Hyperspectral imaging coupled with Dual-channel convolutional neural network for early detection of apple valsa canker

Assessing the status of apple tree for orchard precision management is critical. However, apple valsa canker severely restricts apple production and quality in China, especially symptomless branches skin at the pathogen early infection stage increases the difficulty for rapid and high throughput disease detection in orchards. Hyperspectral imaging (HSI) is a promising sensing technique widely implemented for plant disease detection. While exploring efficient methods for HSI analysis remains challenging due to the high dimensionality, information redundancy, and noise interference. This study aims to establish a dual-channel convolutional neural network (DC-CNN) model (integration of 3D-CNN and 1D-CNN) based on spectral and spatial information for detecting apple branches infected by apple valsa canker at an early stage. DC-CNN models were established based on different spectral pre-processing algorithms. The gradient-weighted class activation mapping (Grad-CAM) algorithm with constructed saliency maps and gradient histograms were used to explain the classification mechanism of the models visually. The results demonstrated that the DC-CNN model based on the images and spectra after multiple scattering correction (MSC) pretreatment had the best performance, with an accuracy of 98% for early detection of apple valsa canker. This study confirmed the feasibility of HSI coupled with DC-CNN in the early detection of apple valsa canker. Furthermore, the visual explanation helped improve the DC-CNN model’s explanatory and availability.

Prediction on EMS of UAV's Data Link Based on SSA-Optimized Dual-Channel CNN

In this article, a novel method is presented for electromagnetic interference (EMI) perception and electromagnetic susceptibility (EMS) assessment of an unmanned aerial vehicle (UAV) against interference. A large number of in-phase and quadrature data of the UAV's data link and their corresponding critical EMI signal were collected by the equivalent injection test method. After visualization and preprocessing of the in-phase and quadrature data, the obtained time–frequency spectrum and the data-link state parameter histogram were joined to further preprocess as the input of the model. A dual-channel convolutional neural network optimized by a sparrow search algorithm (SSA-DCNN) was proposed to predict the EMS of the data link of the UAV. The proposed method can not only avoid manual extraction of data features but also improve the intelligence level of EMI perception and safety evaluation on UAVs. The performance of the dual-channel convolutional neural network is compared with that of the SSA-DCNN method under different optimization algorithms. The results show that the SSA-DCNN model can significantly enhance the convergence speed and prediction accuracy of the training process compared with the dual-channel convolutional neural network. Besides, among the optimization algorithms, the stochastic gradient descent with momentum applied to the SSA-DCNN model shows a better performance.

Sliding window and dual-channel CNN (SWDC-CNN): A novel method for synchronous prediction of coal and electricity consumption in cement calcination process

As a representative of the process industry, the cement industry consumes a large amount of coal and electricity resources. This is mainly due to the irrational energy scheduling caused by the rough production and independent statistics of each energy consumption indicator within the cement industry. The synchronous accurate prediction of energy consumption can provide a more resultful scheme for the production control process and energy scheduling. However, due to the time delay, variables coupling, and uncertainty of production, it is difficult to synchronously forecast multiple indicators. In this paper, a data-driven prediction method combining Sliding Window and Dual-Channel Convolutional Neural Network (SWDC-CNN) is proposed to achieve synchronous prediction of coal and electricity consumption in the next 5 min. The sliding window method is designed to extract time-varying delay characteristics of time series data to overcome its influence on energy consumption prediction. The effect of redundant parameters between weakly correlated variables on energy prediction is reduced by designing a dual-channel structure. We experimented and compared with excellent models Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and Gate Recurrent Unit (GRU) on an actual cement production data in Shanxi Province, China. Experimental results show that the proposed SWDC-CNN model has good performance, the highest prediction accuracy, and can meet the expected requirements.