Multi-scale Convolutional Neural Network Research Articles

A method for photoplethysmography signal quality assessment fusing multi-class features with multi-scale series information

Photoplethysmography (PPG) is often affected by interference, which could lead to incorrect judgment of physiological information. Therefore, performing a quality assessment before extracting physiological information is crucial. This paper proposed a new PPG signal quality assessment by fusing multi-class features with multi-scale series information to address the problems of traditional machine learning methods with low accuracy and deep learning methods requiring a large number of samples for training. The multi-class features were extracted to reduce the dependence on the number of samples, and the multi-scale series information was extracted by a multi-scale convolutional neural network and bidirectional long short-term memory to improve the accuracy. The proposed method obtained the highest accuracy of 94.21%. It showed the best performance in all sensitivity, specificity, precision, and F1-score metrics, compared with 6 quality assessment methods on 14 700 samples from 7 experiments. This paper provides a new method for quality assessment in small samples of PPG signals and quality information mining, which is expected to be used for accurate extraction and monitoring of clinical and daily PPG physiological information.

Inter-patient congestive heart failure automatic recognition using attention-based multi-scale convolutional neural network

Accurate classification of congestive heart failure (CHF) is essential to reduce the mortality of cardiovascular disease. Many existing researches suffer from unsatisfactory performance in inter-patient scheme closer to clinical application. To address this issue, this paper presents a novel attention-based multi-scale convolutional neural network (AMCNN) to automatically detect CHF. An effective multi-scale convolution structure is designed to enhance feature extraction capability. By combining channel attention mechanism, the output feature maps of multi-scale CNN are reweighted to explore the most decisive information. To validate the proposed method, we conducted experiments under both intra- and inter- patient schemes using long term ECGs from 73 subjects. The overall accuracies yield 99.97% and 99.71% respectively, outperforming traditional CNN 98.97% accuracy and the state-of-the-art methods. Moreover, our method performs well on unbalanced data with noise at speed of 0.000127 s for recognizing per segment, which has potential values to provide reliable diagnostic advice for cardiologists.

Classification of liver lesions in CT images based on LivlesioNet, modified Multi-Scale CNN with bridge Scale method

Classification of liver lesions in CT images based on LivlesioNet, modified Multi-Scale CNN with bridge Scale method

Management Method Evaluation for Innovation and Entrepreneurship in College with Multi-Scale Feature Convolutional Network

ABSTRACT Since the full implementation of the innovation-driven development strategy in the country, all regions and departments have placed great emphasis on the work of mass entrepreneurship and innovation, resulting in a significant increase in innovation and entrepreneurship. The national focus on mass entrepreneurship and innovation has shifted from quantitative to qualitative improvements, with greater attention being paid to improving substance rather than expanding scope. There is a growing trend among colleges to recognize innovation and entrepreneurial management as a significant achievement in college education and teaching. By prioritizing innovation and entrepreneurship management and professional education, the aim is to cultivate college students with an entrepreneurial spirit, and to develop inventive and entrepreneurial talent. Cultivating innovative talent is one way to apply the innovation-driven development plan and build a creative country. However, the implementation of the innovation and entrepreneurship development plan in the country has posed both new opportunities and challenges to the management of innovation and entrepreneurship education in colleges across the country. As a result, innovation and entrepreneurship have become increasingly important tasks that can help improve the management of innovation and entrepreneurship in these institutions. In order to address this issue, this paper proposes a neural network for evaluating innovation and entrepreneurship management methods in colleges, which combines convolutional neural networks with these tasks. Specifically, a multi-scale convolutional neural network is designed to more efficiently extract innovation and entrepreneurship management features in colleges, ultimately leading to improved model performance.

Small sample fault diagnosis for wind turbine gearbox based on lightweight multiscale convolutional neural network

The maintenance and diagnosis of wind turbine gearboxes are crucial for enhancing the stability and operational efficiency of wind power systems. However, there are still two challenges in gearbox fault diagnosis methods based on deep learning: (1) limited failure sample; (2) interference of strong noise. To solve the above issues, a lightweight multiscale convolutional neural network (LMSCNN) based fault diagnosis method is proposed in this paper. Among them, a large kernel convolution is used to denoise the original vibration signal. A lightweight multiscale architecture is constructed using depthwise separable convolutional blocks, which mine fault features at different scales and improve the operational efficiency of the model. Moreover, a parallel global pooling block is designed to provide a more comprehensive feature for the fusion layer, enabling the effective diagnosis of vibration signals. Experiments are conducted on the datasets of two different gearboxes, which prove that LMSCNN has excellent generalization capability and diagnostic speed.

A novel SE-weighted multi-scale Hedging CNN approach for fault diagnosis of wind turbine

This paper proposes a novel weighted SE MSH CNNs approach to make full use of time-series data and solve the problem of low WT fault diagnosis accuracy. Firstly, the operating data of WTs are collected through the SCADA system and expanded by the SWM. Then, the SE network is constructed to adaptively determine the weights of each parameter to focus on the effective fault features, and the stacking layers are used to extract the multi-scale features. After that, the obtained features are hedged to get the differentiated features, and two global pooling layers are employed to extract further and fuse the multi-scale features. The proposed method is put into an application case to verify its superior effectiveness and generalization ability in WT fault diagnosis. Experimental results show that: (1) the proposed method effectively extracts multi-scale differentiated features, thereby improving the identifiability of WT faults; (2) the proposed model outperforms all the other considered models in terms of accuracy and other evaluation metrics, showing that it is more appropriate for WT fault diagnosis; (3) the superiority and generalization ability of the proposed method are further verified through various experimental strategies.

Target recognition algorithm based on HRRP time-spectrogram feature and multi-scale asymmetric convolutional neural network

A radar HRRP recognition algorithm based on time-spectrogram feature and multi-scale convolutional neural network is proposed to address the difficult feature extraction and low accuracy in space target recognition. Firstly, the normalization is used to eliminate the intensity sensitivity, the absolute alignment of multiple dominant scatterers is used to eliminate the translation sensitivity, and the radar Doppler velocity is used to eliminate the widening effect, distortion and wave crest splitting on HRRP caused by high-speed motion of the target. Then, the method applies the time-frequency analysis to the preprocessed HRRP to extract the time-frequency diagram. Finally, the time-frequency features are extracted with different scales of fineness and different directions through asymmetric convolution of different scales. The data processing results demonstrate that the present method has a high target recognition accuracy. In addition, the present improves the anti-posture sensitivity and target recognition on the same platform.

A Multi-View Multi-Scale Neural Network for Multi-Label ECG Classification

The 12-lead electrocardiogram (ECG) is a common method used to diagnose cardiovascular diseases. Recently, ECG classification using deep neural networks has been more accurate and efficient than traditional methods. Most ECG classification methods usually connect the 12-lead ECG into a matrix and then input this matrix into a deep neural network. We propose a multi-view and multi-scale deep neural network for ECG classification tasks considering different leads as different views, taking full advantage of the diversity of different lead features in a 12-lead ECG. The proposed network utilizes a multi-view approach to effectively fuse different lead features, and uses a multi-scale convolutional neural network structure to obtain the temporal features of an ECG at different scales. In addition, the spatial information and channel relationships of ECG features are captured by coordinate attention to enhance the feature representation of the network. Since our network contains six view networks, to reduce the size of the network, we also explore the distillation of dark knowledge from the multi-view network into a single-view network. Experimental results on multiple multi-label datasets show that our multi-view network outperforms existing state-of-the-art networks in multiple tasks.

A Fault Diagnosis Method for the Autonomous Underwater Vehicle via Meta-Self-Attention Multi-Scale CNN

Autonomous underwater vehicles (AUVs) are an important equipment for ocean investigation. Actuator fault diagnosis is essential to ensure the sailing safety of AUVs. However, the lack of failure data for training due to unknown ocean environments and unpredictable failure occurrences is challenging for fault diagnosis. In this paper, a meta-self-attention multi-scale convolution neural network (MSAMS–CNN) is proposed for the actuator fault diagnosis of AUVs. Specifically, a two-dimensional spectrogram of the vibration signals obtained by a vibration sensor is used as the neural network’s inputs. The diagnostic model is fitted by executing a subtask-based gradient optimization procedure to generate more general degradation knowledge. A self-attentive multi-scale feature extraction approach is used to utilize both global and local features for learning important parameters autonomously. In addition, a meta-learning method is utilized to train the diagnostic model without a large amount of labeled data, which enhances the generalization ability and allows for cross-task training. Experimental studies with real AUV data collected by vibration sensors are conducted to validate the effectiveness of the MSAMS–CNN. The results show that the proposed method can diagnose the rudder and thruster faults of AUVs in the cases of few-shot diagnosis.

Vision-based fruit recognition via multi-scale attention CNN

Fruit quality assessment, grading and sorting are of vital importance to fruit processing, and all these involve fruit recognition. Vision-based fruit recognition can recognize fruit automatically and further support more applications such as fruit-picking robots, self-checkout service, and dietary guidance. Recent works resort to Convolutional Neural Networks (CNNs) for vision-based fruit recognition because of their powerful expressive capacity. However, most works simply utilize existing CNNs and ignore characteristics of fruit images, resulting in sub-optimal recognition performance. To solve this problem, we adopt a Multi-Scale Attention Network (MSANet), which explores attention from different layers of CNNs and aggregates various visual attentional features from different levels into final comprehensive representations. Extensive evaluations on four fruit benchmark datasets demonstrate that the method achieves state-of-the-art recognition performance. In addition, we report various experimental results from different deep networks as baselines. Codes and models will be released upon publication. Models and code are available at http://123.57.42.89/codes/msanet.html.

Uniting Multi-Scale Local Feature Awareness and the Self-Attention Mechanism for Named Entity Recognition

In recent years, a huge amount of text information requires processing to support the diagnosis and treatment of diabetes in the medical field; therefore, the named entity recognition of diabetes (DNER) is giving rise to the popularity of this research topic within this particular field. Although the mainstream methods for Chinese medical named entity recognition can effectively capture global context information, they ignore the potential local information in sentences, and hence cannot extract the local context features through an efficient framework. To overcome these challenges, this paper constructs a diabetes corpus and proposes the RMBC (RoBERTa Multi-scale CNN BiGRU Self-attention CRF) model. This model is a named entity recognition model that unites multi-scale local feature awareness and the self-attention mechanism. This paper first utilizes RoBERTa-wwm to encode the characters; then, it designs a local context-wise module, which captures the context information containing locally important features by fusing multi-window attention with residual convolution at the multi-scale and adds a self-attention mechanism to address the restriction of the bidirectional gated recurrent unit (BiGRU) capturing long-distance dependencies and to obtain global semantic information. Finally, conditional random fields (CRF) are relied on to learn of the dependency between adjacent tags and to obtain the optimal tag sequence. The experimental results on our constructed private dataset, termed DNER, along with two benchmark datasets, demonstrate the effectiveness of the model in this paper.

Prediction of Protein Secondary Structure based on Multi-scale Convolutional Neural Network

In the field of bioinformatics, the prediction of secondary structure of proteins is very important. It can be obtained from the prediction of primary structure (amino acid sequence) and can provide reference for the prediction of tertiary structure of proteins. Amino acid sequences of proteins are encoded with several features and then combined into the prediction network. Convolutional neural network has excellent performance in text and sequence information extraction. The amino acid sequence of protein is also a special sequence, so the convolutional neural network can be used to extract the information in the sequence. Moreover, the influence of amino acids on the formation of secondary structure varies with different distances, so in the experiment, convolutional neural networks with convolution nuclei of different sizes were used to form multi-scale convolution blocks to extract amino acid sequence information. At the same time, the sliding window technique is also used to show the interaction between the sequences, and a long amino acid sequence is divided into some amino acid fragments and input into the model. Finally, the accuracy of Q8 on the dataset CB6133_filtered reaches 71%.

MARC-Net: Terrain Classification in Parallel Network Architectures Containing Multiple Attention Mechanisms and Multi-Scale Residual Cascades

To address the problem that traditional deep learning algorithms cannot fully utilize the correlation properties between spectral sequence information and the feature differences between different spectra, this paper proposes a parallel network architecture land-use classification based on a combined multi-head attention mechanism and multiscale residual cascade called MARC-Net. This parallel framework is firstly implemented by deeply mining the features generated by grouped spectral embedding for information among spectral features by adding a multi-head attention mechanism, which allows semantic features to have expressions from more subspaces while fully considering all spatial location interrelationships. Secondly, a multiscale residual cascade CNN (convolutional neural network) is designed to fully utilize the fused feature information at different scales, thereby improving the network’s ability to represent different levels of information. Lastly, the features obtained by the multi-head attention mechanism are fused with those obtained by the CNN, and the merged resultant features are downgraded through the fully connected layer to obtain the classification results and achieve pixel-level multispectral image classification. The findings show that the algorithm proposed in this paper has an aggregate precision of 97.22%, compared to that of the Vision Transformer (ViT) with 95.08%; its performance on the Sentinel-2 dataset shows a huge improvement. Moreover, this article mainly focuses on the change rate of forest land in the study area. The Forest land area was 125.1143 km2 in 2017, 105.6089 km2 in 2019, and 76.3699 km2 in 2021, with an increase of 15.59%, an decrease of 0.97%, and increase of 14.76% in 2017–2019, 2019–2021 and 2017–2021, respectively.

FPDT: a multi-scale feature pyramidal object detection transformer

Object detection is a fundamental part of autonomous driving algorithms, and with the promotions of transformers in a couple of years, numerous computer vision tasks are integrating transformers into object detectors to acquire a better generalization ability. Building a pure transformer-based detector seems to be a wonderful choice; however, transformers are not omnipotent, and they come with painful drawbacks. Its fundamental operator, multi-head self-attention (MHSA), suffers from the need for computational resources due to its quadratic complexity, which demands an unreasonably high memory usage and critically low throughput. To address this issue, we use a convolution operation to simulate MHSA from transformers by referencing the philosophy and principle of MHSA and making an application migration on convolutional neural networks (CNNs). This gives a detector with power and speed simultaneously. Furthermore, a multi-scale pyramidal feature extractor gives the detector a better view over various scales. In general, our proposed object detector mainly follows the philosophy of attention mechanism, which is implemented by a multi-scale feature pyramidal CNN encoder that simulates the transformer, and a real transformer query neck to extract all of the objects once and, eventually, feed them to the output heads. After training on the COCO2017 dataset, by combining the construction philosophy of the object detector and the philosophy and characteristics of the transformer, our FPDT-Tiny gives an average precision (AP) of up to 34.1 in 150 lower epochs, which is 16.0 and 10.8 higher than CNN-based YOLOv3-Base and SSD-300, respectively. Also, the AP given by our FPDT-Small is up to 37.7 under the same epoch, which is 10.4 and 7.9 higher than the transformer-based detector YOLOS-Small and DETR-ResNet-152, respectively, also demonstrating a comparable performance.

Research on rolling bearing fault diagnosis method based on AMVMD and convolutional neural networks

Due to the uncertainty of the actual industrial environment, the effective features of the collected multivariate data are submerged by environmental noise. Due to the limited ability of single signal analysis method to recognize the features of multivariate data. Therefore, this paper proposes a rolling bearing fault diagnosis method based on adaptive multivariate variational mode decomposition (AMVMD) and multi-scale convolutional neural network (Multi-scale CNN). Firstly, based on the multivariate variational modal algorithm, the minimum modal overlapping component (MMOC) index is proposed and used as the objective function to seek the optimal solution of the main parameters of multivariate variational modes, to realize the adaptive decomposition and noise reduction of the original signal. Then, the multi-scale convolutional neural network was used to extract and recognize the denoising feature vectors in a deeper level, and finally the bearing fault diagnosis under complex working conditions is realized. Bearing data from Paderborn University were used to verify the proposed method. The results show that under the same conditions, the fault diagnosis accuracy of AMVMD-MSCNNs can achieve 98.60%, which has certain advantages and practical application significance.

Lightweight Multiscale CNN Model for Wheat Disease Detection

Wheat disease detection is crucial for disease diagnosis, pesticide application optimization, disease control, and wheat yield and quality improvement. However, the detection of wheat diseases is difficult due to their various types. Detecting wheat diseases in complex fields is also challenging. Traditional models are difficult to apply to mobile devices because they have large parameters, and high computation and resource requirements. To address these issues, this paper combines the residual module and the inception module to construct a lightweight multiscale CNN model, which introduces the CBAM and ECA modules into the residual block, enhances the model’s attention to diseases, and reduces the influence of complex backgrounds on disease recognition. The proposed method has an accuracy rate of 98.7% on the test dataset, which is higher than classic convolutional neural networks such as AlexNet, VGG16, and InceptionresnetV2 and lightweight models such as MobileNetV3 and EfficientNetb0. The proposed model has superior performance and can be applied to mobile terminals to quickly identify wheat diseases.

An adaptive multiscale fully convolutional network for bearing fault diagnosis under noisy environments

Intelligent algorithms based on convolutional neural network (CNN) has demonstrated remarkable potential in diagnosing bearing faults. However, Accurate and robust fault diagnosis using CNNs in noisy environments remains a challenge. In this paper, we propose an end-to-end adaptive multiscale fully convolutional network (AMFCN) for intelligent bearing fault diagnosis under various noise environments. Firstly, we enhance noise adaptability by retrofitting raw signals with random sampling. Then the convolution with huge kernel is innovatively applied for wide-area temporal feature extraction and high-frequency noise suppression. By stacked residual adaptive multiscale convolution (Res_AM) blocks, the AMFCN can adaptively adjust the feature weights from different convolution scales and selectively focus on important features. The AMFCN outstrips five advanced baseline models across two bearing fault datasets with various noise environments. The proposed AMFCN significantly enhances the feature extraction ability, noise immunity, and robustness, surpassing conventional CNNs and other advanced multi-scale CNNs.

Rolling Bearing Fault Diagnosis Method Based on Self-Calibrated Coordinate Attention Mechanism and Multi-Scale Convolutional Neural Network Under Small Samples

Aiming at the problem of poor fault diagnosis performance of rolling bearings under small sample conditions, a novel method based on self-calibrated coordinate attention mechanism and multi-scale convolutional neural network (SC-MSCNN) is proposed in this paper. Firstly, Markov transition field (MTF) is used to convert the original vibration signals into MTF images with temporal correlation. Then, the self-calibrated coordinate attention mechanism is presented, which obtains feature location information and feature channel information from two directions, and locates useful features more accurately. Finally, the SC-MSCNN model is built, and the MTF images are input into the model to complete the classification. The SC-MSCNN model simplifies the structure of the model by adding jump connections, which greatly reduces the number of learnable parameters and thus alleviates the overfitting problem. The approach is demonstrated using two bearing datasets, and the results show that SC-MSCNN can accurately diagnose different fault modes using small samples under given and variable working conditions, which is superior to other popular CNNs.

Application of Multi-Scale Convolutional Neural Networks and Extreme Learning Machines in Mechanical Fault Diagnosis

Extracting fault features in mechanical fault diagnosis is challenging and leads to low diagnosis accuracy. A novel fault diagnosis method using multi-scale convolutional neural networks (MSCNN) and extreme learning machines is presented in this research, which was conducted in three stages: First, the collected vibration signals were transformed into images using the continuous wavelet transform. Subsequently, an MSCNN was designed to extract all detailed features of the original images. The final feature maps were obtained by fusing multiple feature layers. The parameters in the network were randomly generated and remained unchanged, which could effectively accelerate the calculation. Finally, an extreme learning machine was used to classify faults based on the fused feature maps, and the potential relationship between the fault and labels was established. The effectiveness of the proposed method was confirmed. This method performs better in mechanical fault diagnosis and classification than existing methods.

MaskSleepNet: A Cross-modality Adaptation Neural Network for Heterogeneous Signals Processing in Sleep Staging.

Deep learning methods have become an important tool for automatic sleep staging in recent years. However, most of the existing deep learning-based approaches are sharply constrained by the input modalities, where any insertion, substitution, and deletion of input modalities would directly lead to the unusable of the model or a deterioration in the performance. To solve the modality heterogeneity problems, a novel network architecture named MaskSleepNet is proposed. It consists of a masking module, a multi-scale convolutional neural network (MSCNN), a squeezing and excitation (SE) block, and a multi-headed attention (MHA) module. The masking module consists of a modality adaptation paradigm that can cooperate with modality discrepancy. The MSCNN extracts features from multiple scales and specially designs the size of the feature concatenation layer to prevent invalid or redundant features from zero-setting channels. The SE block further optimizes the weights of the features to optimize the network learning efficiency. The MHA module outputs the prediction results by learning the temporal information between the sleeping features. The performance of the proposed model was validated on two publicly available datasets, Sleep-EDF Expanded (Sleep-EDFX) and Montreal Archive of Sleep Studies (MASS), and a clinical dataset, Huashan Hospital Fudan University (HSFU). The proposed MaskSleepNet can achieve favorable performance with input modality discrepancy, e.g. for single-channel EEG signal, it can reach 83.8%, 83.4%, 80.5%, for two-channel EEG+EOG signals it can reach 85.0%, 84.9%, 81.9% and for three-channel EEG+EOG+EMG signals, it can reach 85.7%, 87.5%, 81.1% on Sleep-EDFX, MASS, and HSFU, respectively. In contrast the accuracy of the state-of-the-art approach which fluctuated widely between 69.0% and 89.4%. The experimental results exhibit that the proposed model can maintain superior performance and robustness in handling input modality discrepancy issues.