Multi-scale Convolutional Neural Network Research Articles

LDCNet: A Lightweight Multiscale Convolutional Neural Network Using Local Dense Connectivity for Image Recognition

LDCNet: A Lightweight Multiscale Convolutional Neural Network Using Local Dense Connectivity for Image Recognition

MSTSENet: Multiscale Spectral–Spatial Transformer with Squeeze and Excitation network for hyperspectral image classification

Hyperspectral image (HSI) classification pertains to the task of assigning a single label to each pixel by analyzing its spectral–spatial characteristics. Convolutional Neural Networks (CNNs) have garnered significant attention on account of their remarkable performance in feature representation. However, these approaches possess a restricted capacity to acquire highly similar spectral features. Recently, Attention-based approaches have been devised as a means to surmount the limitations inherent in CNNs. In this paper, we address a novel architecture for spectral–spatial feature extraction and HSI classification. The framework efficiently amalgamates the robustness and efficacy of three modern backbone networks, i.e., Multiscale CNN, Squeeze and Excitation (SE), and Transformer named MSTSENet. Initially, the multiscale convolution module integrates three branches of 3D convolution layers, each employing distinct kernel sizes, facilitating multiscale and multi-resolution feature extraction. Subsequently, the SE module enhances the inter-channel relationship by adaptively recalibrating the feature weight. The strategic fusion of the SE module with multiscale CNN strengthens deep feature extraction while introducing a minimal increment in overall parameters. Lastly, the Transformer module orchestrates information aggregation across different spectral–spatial regions, accurately modeling long-range contextual dependencies and capturing dominant feature representations. To evaluate the model performance, comprehensive experiments have been carried out on widely used benchmark HSI datasets. The overall accuracy of 98.74%, 99.83%, and 99.98% is achieved over the Indian Pines, Pavia University, and Salinas Valley datasets, respectively. The code of this work will be accessible at https://github.com/irfan01000/MSTSENet.

Multi-scale quaternion CNN and BiGRU with cross self-attention feature fusion for fault diagnosis of bearing

In recent years, deep learning has led to significant advances in bearing fault diagnosis (FD). Most techniques aim to achieve greater accuracy. However, they are sensitive to noise and lack robustness, resulting in insufficient domain adaptation and anti-noise ability. The comparison of studies reveals that giving equal attention to all features does not differentiate their significance. In this work, we propose a novel FD model by integrating multi-scale quaternion convolutional neural network (MQCNN), bidirectional gated recurrent unit (BiGRU), and cross self-attention feature fusion (CSAFF). We have developed innovative designs in two modules, namely MQCNN and CSAFF. Firstly, MQCNN applies quaternion convolution to multi-scale architecture for the first time, aiming to extract the rich hidden features of the original signal from multiple scales. Then, the extracted multi-scale information is input into CSAFF for feature fusion, where CSAFF innovatively incorporates cross self-attention mechanism to enhance discriminative interaction representation within features. Finally, BiGRU captures temporal dependencies while a softmax layer is employed for fault classification, achieving accurate FD. To assess the efficacy of our approach, we experiment on three public datasets (CWRU, MFPT, and Ottawa) and compare it with other excellent methods. The results confirm its state-of-the-art, which the average accuracies can achieve up to 99.99%, 100%, and 99.21% on CWRU, MFPT, and Ottawa datasets. Moreover, we perform practical tests and ablation experiments to validate the efficacy and robustness of the proposed approach. Code is available at https://github.com/mubai011/MQCCAF.

A deep learning methodology based on adaptive multiscale CNN and enhanced highway LSTM for industrial process fault diagnosis

Intelligent fault diagnostic techniques are crucial for ensuring the long-term reliability of manufacturing. The process variables collected by sensors in real industrial systems typically exhibit diverse time scales and data features. To overcome the above issues, we propose a comprehensive model known as adaptive multiscale CNN and enhanced highway LSTM (ACEL). To begin with, multiscale features under variable operating conditions are automatically extracted by constructing the parallel convolutional module. Then, to selectively focus on the feature representation within the channels, efficient channel attention is introduced to downplay the channels with less important information. In addition, the bidirectional LSTM is designed to generate more fine-grained hybrid features based on contextual information and local features learned by the CNN. An enhanced highway configuration is designed to be used to bolster the global temporal dependencies. Finally, ACEL is applied to the Tennessee Eastman benchmark and CSTR simulation, and multiple statistical metrics show that the proposed model outperforms other advanced fault diagnosis methods.

A multi-scale multi-channel CNN introducing a channel-spatial attention mechanism hyperspectral remote sensing image classification method

ABSTRACT Aiming the problems that the classification performance of hyperspectral images in existing classification algorithms is highly dependent on spatial-spectral information and that detailed features are ignored in single convolutional channel feature extraction, resulting in poor generalization performance of the feature extraction model, a multi-scale multi-channel convolutional neural network (MMC-CNN) model is proposed in this paper. First, the data set is divided into two kinds of pixel module, and then different channels are used for feature extraction. A channel-space attention mechanism module is also introduced, and a multi-scale multichannel convolutional neural network (CSAM-MMC) model with the introduction of channel-space attention mechanism is proposed for deeper spatial-spectral feature extraction of hyperspectral image elements while reducing the redundancy of convolutional pooling parameters to achieve better HSI classification. To evaluate the effectiveness of the proposed model, experiments were conducted on Indian Pines, Pavia Center and KSC datasets respectively, and the overall classification accuracies of this paper’s MMC-CNN model in the HSI dataset were 97.23%, 98.50%, and 97.85%, thus verifying the model’s high feature extraction accuracy. The CSAM-MMC model in this paper further improves 0.13%, 0.35%, and 0.71% relative to the MMC-CNN model, which provides higher overall accuracies relative to other state-of-the-art algorithms.

A Novel Approach for the Detection and Severity Grading of Chronic Obstructive Pulmonary Disease Based on Transformed Volumetric Capnography.

Chronic Obstructive Pulmonary Disease (COPD), as the third leading cause of death worldwide, is a major global health issue. The early detection and grading of COPD are pivotal for effective treatment. Traditional spirometry tests, requiring considerable physical effort and strict adherence to quality standards, pose challenges in COPD diagnosis. Volumetric capnography (VCap), which can be performed during natural breathing without requiring additional compliance, presents a promising alternative tool. In this study, the dataset comprised 279 subjects with normal pulmonary function and 148 patients diagnosed with COPD. We introduced a novel quantitative analysis method for VCap. Volumetric capnograms were converted into two-dimensional grayscale images through the application of Gramian Angular Field (GAF) transformation. Subsequently, a multi-scale convolutional neural network, CapnoNet, was conducted to extract features and facilitate classification. To improve CapnoNet's performance, two data augmentation techniques were implemented. The proposed model exhibited a detection accuracy for COPD of 95.83%, with precision, recall, and F1 measures of 95.21%, 95.70%, and 95.45%, respectively. In the task of grading the severity of COPD, the model attained an accuracy of 96.36%, complemented by precision, recall, and F1 scores of 88.49%, 89.99%, and 89.15%, respectively. This work provides a new perspective for the quantitative analysis of volumetric capnography and demonstrates the strong performance of the proposed CapnoNet in the diagnosis and grading of COPD. It offers direction and an effective solution for the clinical application of capnography.

Replacement of Fault Sensor of Cutter Suction Dredger Mud Pump Based on MCNN Transformer

The mud pump water sealing system (MPWSS) is important in the efficient operation and prolonged service life of the cutter suction dredger’s (CSD) mud pump. Considering that the underwater pump operates underwater and the shaft seal water pressure sensor is prone to failure, a hybrid deep learning model MCNN transformer is proposed to predict the underwater pump shaft seal water pressure in the event of sensor failure. This paper uses big data from the dredging project to deeply excavate the relationship between the shaft end sealing water pressure and other construction data by combining experience and artificial intelligence, and then uses multi-scale convolutional neural network (MCNN) to reconstruct the data, highlighting the time series characteristics of the multi-scale data were then input into the transformer model for prediction, and compared with a single MCNN, transformer model and four other neural networks. Finally, the cutter suction dredger “Hua An Long” was selected as an application research case; experimental comparisons were conducted on seven different models to verify the accuracy and applicability of the MCNN-transformer model.

Deep-learning enhanced high-quality imaging in metalens-integrated camera.

Because of their ultra-light, ultra-thin, and flexible design, metalenses exhibit significant potential in the development of highly integrated cameras. However, the performances of metalens-integrated camera are constrained by their fixed architectures. Here we proposed a high-quality imaging method based on deep learning to overcome this constraint. We employed a multi-scale convolutional neural network (MSCNN) to train an extensive pair of high-quality and low-quality images obtained from a convolutional imaging model. Through our method, the imaging resolution, contrast, and distortion have all been improved, resulting in a noticeable overall image quality with SSIM over 0.9 and an improvement in PSNR over 3 dB. Our approach enables cameras to combine the advantages of high integration with enhanced imaging performances, revealing tremendous potential for a future groundbreaking imaging technology.

An improved multi-scale convolutional neural network with gated recurrent neural network model for protein secondary structure prediction

An improved multi-scale convolutional neural network with gated recurrent neural network model for protein secondary structure prediction

Image Deblurring Based on Efficient Transformer and Multi-scale CNN

The study of image deblurring techniques in dynamic scenes is a high-profile research direction. Recently, given the excellence of Convolutional Neural Networks (CNNs) in extracting feature information, it has become a common and effective practice to utilize them for blurred image restoration work. However, CNN can only model local information and has a limited receptive field, which inhibits the deblurring effect. Transformer can model global information, so it can be combined with CNN to expand the receptive field and enhance the deblurring effect. Unfortunately, as the spatial resolution of the input image increases, the computational complexity of the Transformer increases dramatically, showing a trend of square-level growth, which makes it difficult to cope with the task of processing high-resolution images. To address the above problems, this paper proposes an image deblurring network based on efficient Transformer and multi-scale CNN called ET-MIMO-UNet. The local spatial features are extracted using multi-scale CNN and embedded into the global characteristics of the Transformer, modelling both local and global information. To solve the problem of difficult training due to large image size and to improve the computational efficiency, an efficient Transformer layer (ETL) is designed, which contains a multi-dconv head transposed attention (MHTA) and a gated-dconv feed-forward network(GFFN). In addition, a multi-layer feature fusion block (MFFB) is introduced to fuse full-scale features and reduce feature loss. On the GoPro test dataset, compared with the MIMO-UNet base network, the PSNR of the three models of ET-MIMO-UNet is improved by 0.39dB, 0.54dB, and 0.66dB, respectively; ET-MIMO-UNet reduces the number of parameters by half compared with MPRNet. The experimental data fully proved that the method demonstrated a significant processing effect in coping with the image-blurring problem in dynamic scenes.

EEG classification model for virtual reality motion sickness based on multi-scale CNN feature correlation

BackgroundVirtual reality motion sickness (VRMS) is a key issue hindering the development of virtual reality technology, and accurate detection of its occurrence is the first prerequisite for solving the issue. ObjectiveIn this paper, a convolutional neural network (CNN) EEG detection model based on multi-scale feature correlation is proposed for detecting VRMS. MethodsThe model uses multi-scale 1D convolutional layers to extract multi-scale temporal features from the multi-lead EEG data, and then calculates the feature correlations of the extracted multi-scale features among all the leads to form the feature adjacent matrixes, which converts the time-domain features to correlation-based brain network features, thus strengthen the feature representation. Finally, the correlation features of each layer are fused. The fused features are then fed into the channel attention module to filter the channels and classify them using a fully connected network. Finally, we recruit subjects to experience 6 different modes of virtual roller coaster scenes, and collect resting EEG data before and after the task to verify the model. Results: The results show that the accuracy, precision, recall and F1-score of this model for the recognition of VRMS are 98.66 %, 98.65 %, 98.68 %, and 98.66 %, respectively. The proposed model outperforms the current classic and advanced EEG recognition models. SignificanceIt shows that this model can be used for the recognition of VRMS based on the resting state EEG.

A multi-branch multi-scale convolutional neural network using automatic detection of fetal arrhythmia

A multi-branch multi-scale convolutional neural network using automatic detection of fetal arrhythmia

Scene text image super-resolution using multi-scale convolutional neural network with skip connections

Scene text image super-resolution using multi-scale convolutional neural network with skip connections

A novel multi-sensor hybrid fusion framework

Multi-sensor data fusion has emerged as a powerful approach to enhance the accuracy and robustness of diagnostic systems. However, effectively integrating multiple sensor data remains a challenge. To address this issue, this paper proposes a novel multi-sensor fusion framework. Firstly, a vibration signal weighted fusion rule based on Kullback–Leibler divergence-permutation entropy is introduced, which adaptively determines the weighting coefficients by considering the positional differences of different sensors. Secondly, a lightweight multi-scale convolutional neural network is designed for feature extraction and fusion of multi-sensor data. An ensemble classifier is employed for fault classification, and an improved hard voting strategy is proposed to achieve more reliable decision fusion. Finally, the superiority of the proposed method is validated using modular state detection data from the Kaggle database.

Quality Prediction Modeling for Industrial Processes Using Multiscale Attention-Based Convolutional Neural Network.

Soft sensors have been increasingly applied for quality prediction in complex industrial processes, which often have different scales of topology and highly coupled spatiotemporal features. However, the existing soft sensing models usually face difficulties in extracting the multiscale local spatiotemporal features in multicoupled complex process data and harnessing them to their full potential to improve the prediction performance. Therefore, a multiscale attention-based CNN (MSACNN) is proposed in this article to alleviate such problems. In MSACNN, convolutional kernels of different sizes are first designed in parallel in the convolutional layers, which can generate feature maps containing local spatiotemporal features at different scales. Meanwhile, a channel-wise attention mechanism is designed on the feature maps in parallel to get their attention weights, representing the significance of the local spatiotemporal feature at different scales. The superiority of the proposed MSACNN over the other state-of-the-art methods is validated through the performance evaluation in two real industrial processes.

Deep Multiscale Soft-Threshold Support Vector Data Description for Enhanced Heavy-Duty Gas Turbine Generator Sets’ Anomaly Detection

This paper introduces an innovative approach, Deep Multiscale Soft-Threshold Support Vector Data Description (DMS-SVDD), designed for the detection of anomalies and prediction of faults in heavy-duty gas turbine generator sets (GENSETs). The model combines a support vector data description (SVDD) with a deep autoencoder backbone network framework, integrating a multiscale convolutional neural network (M) and soft-threshold activation network (S) into the Deep-SVDD framework. In comparison with conventional methods, such as One-Class Support Vector Machine (OCSVM) and autoencoder (AE), DMS-SVDD demonstrates improvements in accuracy (by 22.94%), recall (by 32%), F1 score (by 12.02%), and smoothness (by 39.15%). The model excels particularly in feature extraction, denoising, and early fault detection, offering a proactive strategy for maintenance. Furthermore, the DMS-SVDD demonstrated enhanced training efficiency with a reduction in the convergence rounds by 66% and overall training times by 34.13%. The study concludes that DMS-SVDD presents a robust and efficient solution for gas turbine anomaly detection, with practical advantages for decision support in turbine maintenance. Future research could explore additional refinements and applications of the DMS-SVDD model across diverse industrial contexts.

Research on fault diagnosis method based on the Markov transition field with enhanced properties and AM-MSCNN under different external environmental interference

The mechanical equipment often faces complex working environments in practical operating conditions, and the external environmental interference generated by operating conditions, environmental factors and other components causes the vibration signals to exhibit characteristics with frequency distortion and multi-modality. The existing fault diagnosis methods rarely consider the issue of external environmental interference. Aiming at the background of fault diagnosis under external environment interference, a fault diagnosis method based on Markov transfer field (MTF) with enhanced properties and multi-scale convolutional neural network with attention mechanism (AM-MSCNN) is proposed. The fault features embedded in vibration signals under external environmental interference can be extracted, and an important contribution to the fault diagnosis method under external environmental interference can be made. Firstly, an interference mode selection model based on symplectic geometry modal decomposition is constructed to address the issues of distortion and multi-modality caused by external environmental interference. Next, a two-dimensional feature extraction method based on the MTF with enhanced properties is established. The challenge of extracting temporal correlation features from one-dimensional vibration signals affected by external environmental interference is addressed by Markov transition probability. The impact of external environmental interference can be mitigated, and that has strong anti-interference capability and robustness. Finally, an attention mechanism that can adaptively assign weights is designed, and the AM-MSCNN model is designed to effectively extract global features by incorporating attention mechanisms in the parallel layers of MSCNN and the attention mechanism helps to suppress external environmental interference and improve the diagnostic results. An experimental platform for simulating the typical faults under external environmental interference is constructed, and the experimental results demonstrate that the proposed method exhibits superior generalization performance under varying degrees of different interference environments. The overall average accuracy reaches 92.2%, and the highest accuracy reaches 94.0% for external interference working conditions.

Novel Multi-flow Multi-scale Convolutional Neural Network Developed for Quality Prediction of Batch Processes to Fuse Data With Different Sampling Frequencies

Novel Multi-flow Multi-scale Convolutional Neural Network Developed for Quality Prediction of Batch Processes to Fuse Data With Different Sampling Frequencies

CDAM-Net: Channel shuffle dual attention based multi-scale CNN for efficient glaucoma detection using fundus images

Glaucoma is a typical eye disorder that induces damage to the optic nerve due to increased intraocular pressure. It ultimately leads to partial or complete blindness without clinical reversal. Hence, it is of utmost importance to screen and detect glaucoma at an early stage. Most of the earlier glaucoma diagnosis methods rely on manual feature engineering, which is time-consuming and requires domain experts. Although recent methods, particularly, convolutional neural networks (CNNs) facilitate learning high-level feature representations from fundus images, they need extensive parameters and pose overfitting issues due to insufficient training samples. Further, conventional CNNs often ignore the minute changes in the lesion region. To overcome these issues, we propose a lightweight multi-scale CNN architecture called as CDAM-Net for effective glaucoma identification from retinal fundus images. Additionally, we introduce an attention module called channel shuffle dual attention (CSDA), comprising of a channel attention block, a spatial attention block and a channel shuffle unit, to focus on important regions in the fundus images, thereby extracting class-specific features. The CDAM-Net mainly consists of multi-scale feature representation (MFR) blocks that enable the extraction of multi-scale features from fundus images. Each MFR block is followed by a CSDA module, which further helps enrich the feature representation. The CDAM-Net is evaluated on a retinal fundus image (RFI) dataset containing 1426 fundus images (837 glaucoma and 589 normal), and the results indicate that CDAM-Net yields promising classification performance compared to existing techniques. Also, ablation studies are carried out to test the effectiveness of each component of the CDAM-Net.

A multiscale electricity theft detection model based on feature engineering

With the widespread adoption of smart meters and the growing availability of data mining and machine learning algorithms, there is a pressing demand for methods that are both accurate and explicable in identifying electricity theft patterns among end-users. To address this need, this study proposes a multi-scale anomaly detection model based on feature engineering.Specifically, tsfresh is utilized in feature engineering to extract electricity consumption features from the raw data, and XGBoost is employed to select features that are highly correlated with anomalous behavior, which have clear physical interpretations. Multi-scale convolutional neural networks are then used to analyze and process the data at different temporal and frequency scales. Attention mechanisms are applied to assign weights to different feature channels, and all of the extracted information is fused for anomaly detection. The combination of feature engineering and multi-scale convolutional neural networks not only enhances the interpretability of the model but also improves its performance, as demonstrated by the experimental results, which show that the proposed method outperforms traditional anomaly detection approaches across multiple evaluation metrics.