A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification

Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.

Development of a convolutional neural network based geomechanical upscaling technique for heterogeneous geological reservoir

Geomechanical assessment using coupled reservoir-geomechanical simulation is becoming increasingly important for analyzing the potential geomechanical risks in subsurface geological developments.However,a robust and efficient geomechanical upscaling technique for heterogeneous geological reservoirs is lacking to advance the applications of three-dimensional(3D)reservoir-scale geomechanical simulation considering detailed geological heterogeneities.Here,we develop convolutional neural network(CNN)proxies that reproduce the anisotropic nonlinear geomechanical response caused by lithological heterogeneity,and compute upscaled geomechanical properties from CNN proxies.The CNN proxies are trained using a large dataset of randomly generated spatially correlated sand-shale realizations as inputs and simulation results of their macroscopic geomechanical response as outputs.The trained CNN models can provide the upscaled shear strength(R^(2)>0.949),stress-strain behavior(R^(2)>0.925),and volumetric strain changes(R^(2)>0.958)that highly agree with the numerical simulation results while saving over two orders of magnitude of computational time.This is a major advantage in computing the upscaled geomechanical properties directly from geological realizations without the need to perform local numerical simulations to obtain the geomechanical response.The proposed CNN proxybased upscaling technique has the ability to(1)bridge the gap between the fine-scale geocellular models considering geological uncertainties and computationally efficient geomechanical models used to assess the geomechanical risks of large-scale subsurface development,and(2)improve the efficiency of numerical upscaling techniques that rely on local numerical simulations,leading to significantly increased computational time for uncertainty quantification using numerous geological realizations.

Downscaling Seasonal Precipitation Forecasts over East Africa with Deep Convolutional Neural Networks

This study assesses the suitability of convolutional neural networks(CNNs) for downscaling precipitation over East Africa in the context of seasonal forecasting. To achieve this, we design a set of experiments that compare different CNN configurations and deployed the best-performing architecture to downscale one-month lead seasonal forecasts of June–July–August–September(JJAS) precipitation from the Nanjing University of Information Science and Technology Climate Forecast System version 1.0(NUIST-CFS1.0) for 1982–2020. We also perform hyper-parameter optimization and introduce predictors over a larger area to include information about the main large-scale circulations that drive precipitation over the East Africa region, which improves the downscaling results. Finally, we validate the raw model and downscaled forecasts in terms of both deterministic and probabilistic verification metrics, as well as their ability to reproduce the observed precipitation extreme and spell indicator indices. The results show that the CNN-based downscaling consistently improves the raw model forecasts, with lower bias and more accurate representations of the observed mean and extreme precipitation spatial patterns. Besides, CNN-based downscaling yields a much more accurate forecast of extreme and spell indicators and reduces the significant relative biases exhibited by the raw model predictions. Moreover, our results show that CNN-based downscaling yields better skill scores than the raw model forecasts over most portions of East Africa. The results demonstrate the potential usefulness of CNN in downscaling seasonal precipitation predictions over East Africa,particularly in providing improved forecast products which are essential for end users.

Coal/Gangue Volume Estimation with Convolutional Neural Network and Separation Based on Predicted Volume and Weight

In the coal mining industry,the gangue separation phase imposes a key challenge due to the high visual similaritybetween coal and gangue.Recently,separation methods have become more intelligent and efficient,using newtechnologies and applying different features for recognition.One such method exploits the difference in substancedensity,leading to excellent coal/gangue recognition.Therefore,this study uses density differences to distinguishcoal from gangue by performing volume prediction on the samples.Our training samples maintain a record of3-side images as input,volume,and weight as the ground truth for the classification.The prediction process relieson a Convolutional neural network(CGVP-CNN)model that receives an input of a 3-side image and then extractsthe needed features to estimate an approximation for the volume.The classification was comparatively performedvia ten different classifiers,namely,K-Nearest Neighbors(KNN),Linear Support Vector Machines(Linear SVM),Radial Basis Function(RBF)SVM,Gaussian Process,Decision Tree,Random Forest,Multi-Layer Perceptron(MLP),Adaptive Boosting(AdaBosst),Naive Bayes,and Quadratic Discriminant Analysis(QDA).After severalexperiments on testing and training data,results yield a classification accuracy of 100%,92%,95%,96%,100%,100%,100%,96%,81%,and 92%,respectively.The test reveals the best timing with KNN,which maintained anaccuracy level of 100%.Assessing themodel generalization capability to newdata is essential to ensure the efficiencyof the model,so by applying a cross-validation experiment,the model generalization was measured.The useddataset was isolated based on the volume values to ensure the model generalization not only on new images of thesame volume but with a volume outside the trained range.Then,the predicted volume values were passed to theclassifiers group,where classification reported accuracy was found to be(100%,100%,100%,98%,88%,87%,100%,87%,97%,100%),respectively.Although obtaining a classification with high accuracy is the main motive,this workhas a remarkable reduction in the data preprocessing time compared to related works.The CGVP-CNN modelmanaged to reduce the data preprocessing time of previous works to 0.017 s while maintaining high classificationaccuracy using the estimated volume value.

Review of Artificial Intelligence for Oil and Gas Exploration: Convolutional Neural Network Approaches and the U-Net 3D Model

Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.

Detection of Oscillations in Process Control Loops From Visual Image Space Using Deep Convolutional Networks

Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability.Although numerous automatic detection techniques have been proposed,most of them can only address part of the practical difficulties.An oscillation is heuristically defined as a visually apparent periodic variation.However,manual visual inspection is labor-intensive and prone to missed detection.Convolutional neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction capabilities.In this work,an exploration of the typical CNN models for visual oscillation detection is performed.Specifically,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation detection.The feasibility and validity of this framework are verified utilizing extensive numerical and industrial cases.Compared with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and mean-nonstationarity.In addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.

Pedestrian attribute classification with multi-scale and multi-label convolutional neural networks

Pedestrian attribute classification from a pedestrian image captured in surveillance scenarios is challenging due to diverse clothing appearances,varied poses and different camera views. A multiscale and multi-label convolutional neural network( MSMLCNN) is proposed to predict multiple pedestrian attributes simultaneously. The pedestrian attribute classification problem is firstly transformed into a multi-label problem including multiple binary attributes needed to be classified. Then,the multi-label problem is solved by fully connecting all binary attributes to multi-scale features with logistic regression functions. Moreover,the multi-scale features are obtained by concatenating those featured maps produced from multiple pooling layers of the MSMLCNN at different scales. Extensive experiment results show that the proposed MSMLCNN outperforms state-of-the-art pedestrian attribute classification methods with a large margin.

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

Authorship verification is a crucial task in digital forensic investigations,where it is often necessary to determine whether a specific individual wrote a particular piece of text.Convolutional Neural Networks(CNNs)have shown promise in solving this problem,but their performance highly depends on the choice of hyperparameters.In this paper,we explore the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship verification.We conduct experiments using a Hyper Tuned CNN model with three popular optimization algorithms:Adaptive Moment Estimation(ADAM),StochasticGradientDescent(SGD),andRoot Mean Squared Propagation(RMSPROP).The model is trained and tested on a dataset of text samples collected from various authors,and the performance is evaluated using accuracy,precision,recall,and F1 score.We compare the performance of the three optimization algorithms and demonstrate the effectiveness of hyperparameter tuning in improving the accuracy of the CNN model.Our results show that the Hyper Tuned CNN model with ADAM Optimizer achieves the highest accuracy of up to 90%.Furthermore,we demonstrate that hyperparameter tuning can help achieve significant performance improvements,even using a relatively simple model architecture like CNNs.Our findings suggest that the choice of the optimization algorithm is a crucial factor in the performance of CNNs for authorship verification and that hyperparameter tuning can be an effective way to optimize this choice.Overall,this paper demonstrates the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship verification in digital forensic investigations.Our findings have important implications for developing accurate and reliable authorship verification systems,which are crucial for various applications in digital forensics,such as identifying the author of anonymous threatening messages or detecting cases of plagiarism.

Deep convolutional neural network for meteorology target detection in airborne weather radar images

Considering the problem that the scattering echo images of airborne Doppler weather radar are often reduced by ground clutters,the accuracy and confidence of meteorology target detection are reduced.In this paper,a deep convolutional neural network(DCNN)is proposed for meteorology target detection and ground clutter suppression with a large collection of airborne weather radar images as network input.For each weather radar image,the corresponding digital elevation model(DEM)image is extracted on basis of the radar antenna scan-ning parameters and plane position,and is further fed to the net-work as a supplement for ground clutter suppression.The fea-tures of actual meteorology targets are learned in each bottle-neck module of the proposed network and convolved into deeper iterations in the forward propagation process.Then the network parameters are updated by the back propagation itera-tion of the training error.Experimental results on the real mea-sured images show that our proposed DCNN outperforms the counterparts in terms of six evaluation factors.Meanwhile,the network outputs are in good agreement with the expected mete-orology detection results(labels).It is demonstrated that the pro-posed network would have a promising meteorology observa-tion application with minimal effort on network variables or parameter changes.

Quantitative algorithm for airborne gamma spectrum of large sample based on improved shuffled frog leaping-particle swarm optimization convolutional neural network

In airborne gamma ray spectrum processing,different analysis methods,technical requirements,analysis models,and calculation methods need to be established.To meet the engineering practice requirements of airborne gamma-ray measurements and improve computational efficiency,an improved shuffled frog leaping algorithm-particle swarm optimization convolutional neural network(SFLA-PSO CNN)for large-sample quantitative analysis of airborne gamma-ray spectra is proposed herein.This method was used to train the weight of the neural network,optimize the structure of the network,delete redundant connections,and enable the neural network to acquire the capability of quantitative spectrum processing.In full-spectrum data processing,this method can perform the functions of energy spectrum peak searching and peak area calculations.After network training,the mean SNR and RMSE of the spectral lines were 31.27 and 2.75,respectively,satisfying the demand for noise reduction.To test the processing ability of the algorithm in large samples of airborne gamma spectra,this study considered the measured data from the Saihangaobi survey area as an example to conduct data spectral analysis.The results show that calculation of the single-peak area takes only 0.13~0.15 ms,and the average relative errors of the peak area in the U,Th,and K spectra are 3.11,9.50,and 6.18%,indicating the high processing efficiency and accuracy of this algorithm.The performance of the model can be further improved by optimizing related parameters,but it can already meet the requirements of practical engineering measurement.This study provides a new idea for the full-spectrum processing of airborne gamma rays.

Smart Lung Tumor Prediction Using Dual Graph Convolutional Neural Network

A significant advantage of medical image processing is that it allows non-invasive exploration of internal anatomy in great detail.It is possible to create and study 3D models of anatomical structures to improve treatment outcomes,develop more effective medical devices,or arrive at a more accurate diagnosis.This paper aims to present a fused evolutionary algorithm that takes advantage of both whale optimization and bacterial foraging optimization to optimize feature extraction.The classification process was conducted with the aid of a convolu-tional neural network(CNN)with dual graphs.Evaluation of the performance of the fused model is carried out with various methods.In the initial input Com-puter Tomography(CT)image,150 images are pre-processed and segmented to identify cancerous and non-cancerous nodules.The geometrical,statistical,struc-tural,and texture features are extracted from the preprocessed segmented image using various methods such as Gray-level co-occurrence matrix(GLCM),Histo-gram-oriented gradient features(HOG),and Gray-level dependence matrix(GLDM).To select the optimal features,a novel fusion approach known as Whale-Bacterial Foraging Optimization is proposed.For the classification of lung cancer,dual graph convolutional neural networks have been employed.A com-parison of classification algorithms and optimization algorithms has been con-ducted.According to the evaluated results,the proposed fused algorithm is successful with an accuracy of 98.72%in predicting lung tumors,and it outper-forms other conventional approaches.

Detection of Omicron Caused Pneumonia from Radiology Images Using Convolution Neural Network(CNN)

COVID-19 disease caused by the SARS-CoV-2 virus has created social and economic disruption across theworld.The ability of the COVID-19 virus to quickly mutate and transfer has created serious concerns across the world.It is essential to detectCOVID-19 infection caused by different variants to take preventive measures accordingly.The existing method of detection of infections caused by COVID-19 and its variants is costly and time-consuming.The impacts of theCOVID-19 pandemic in developing countries are very drastic due to the unavailability of medical facilities and infrastructure to handle the pandemic.Pneumonia is the major symptom of COVID-19 infection.The radiology of the lungs in varies in the case of bacterial pneumonia as compared to COVID-19-caused pneumonia.The pattern of pneumonia in lungs in radiology images can also be used to identify the cause associated with pneumonia.In this paper,we propose the methodology of identifying the cause(either due to COVID-19 or other types of infections)of pneumonia from radiology images.Furthermore,because different variants of COVID-19 lead to different patterns of pneumonia,the proposed methodology identifies pneumonia,the COVID-19 caused pneumonia,and Omicron caused pneumonia from the radiology images.To fulfill the above-mentioned tasks,we have used three Convolution Neural Networks(CNNs)at each stage of the proposed methodology.The results unveil that the proposed step-by-step solution enhances the accuracy of pneumonia detection along with finding its cause,despite having a limited dataset.

A method of convolutional neural network based on frequency segmentation for monitoring the state of wind turbine blades

Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,variational mode decomposition filtering and Mel spectrogram drawing are conducted first.The Mel spectrogram is divided into two halves based on frequency characteristics and then sent into the convolutional neural network.Gaussian white noise is superimposed on the original signal and the output results are assessed based on score coefficients,considering the complexity of the real environment.The surfaces of Wind turbine blades are classified into four types:standard,attachments,polishing,and serrated trailing edge.The proposed method is evaluated and the detection accuracy in complicated background conditions is found to be 99.59%.In addition to support the differentiation of trained models,utilizing proper score coefficients also permit the screening of unknown types.

Hyperspectral Image Sharpening Based on Deep Convolutional Neural Network and Spatial-Spectral Spread Transform Models

In order to improve the spatial resolution of hyperspectral(HS)image and minimize the spectral distortion,an HS and multispectral(MS)image fusion approach based on convolutional neural network(CNN)is proposed.The proposed approach incorporates the linear spectral mixture model and spatial-spectral spread transform model into the learning phase of network,aiming to fully exploit the spatial-spectral information of HS and MS images,and improve the spectral fidelity of fusion images.Experiments on two real remote sensing data under different resolutions demonstrate that compared with some state-of-the-art HS and MS image fusion methods,the proposed approach achieves superior spectral fidelities and lower fusion errors.

MSSTNet:Multi-scale facial videos pulse extraction network based on separable spatiotemporal convolution and dimension separable attention

Background The use of remote photoplethysmography(rPPG)to estimate blood volume pulse in a noncontact manner has been an active research topic in recent years.Existing methods are primarily based on a singlescale region of interest(ROI).However,some noise signals that are not easily separated in a single-scale space can be easily separated in a multi-scale space.Also,existing spatiotemporal networks mainly focus on local spatiotemporal information and do not emphasize temporal information,which is crucial in pulse extraction problems,resulting in insufficient spatiotemporal feature modelling.Methods Here,we propose a multi-scale facial video pulse extraction network based on separable spatiotemporal convolution(SSTC)and dimension separable attention(DSAT).First,to solve the problem of a single-scale ROI,we constructed a multi-scale feature space for initial signal separation.Second,SSTC and DSAT were designed for efficient spatiotemporal correlation modeling,which increased the information interaction between the long-span time and space dimensions;this placed more emphasis on temporal features.Results The signal-to-noise ratio(SNR)of the proposed network reached 9.58dB on the PURE dataset and 6.77dB on the UBFC-rPPG dataset,outperforming state-of-the-art algorithms.Conclusions The results showed that fusing multi-scale signals yielded better results than methods based on only single-scale signals.The proposed SSTC and dimension-separable attention mechanism will contribute to more accurate pulse signal extraction.

Multi-Scale Convolutional Gated Recurrent Unit Networks for Tool Wear Prediction in Smart Manufacturing

As an integrated application of modern information technologies and artificial intelligence,Prognostic and Health Management(PHM)is important for machine health monitoring.Prediction of tool wear is one of the symbolic applications of PHM technology in modern manufacturing systems and industry.In this paper,a multi-scale Convolutional Gated Recurrent Unit network(MCGRU)is proposed to address raw sensory data for tool wear prediction.At the bottom of MCGRU,six parallel and independent branches with different kernel sizes are designed to form a multi-scale convolutional neural network,which augments the adaptability to features of different time scales.These features of different scales extracted from raw data are then fed into a Deep Gated Recurrent Unit network to capture long-term dependencies and learn significant representations.At the top of the MCGRU,a fully connected layer and a regression layer are built for cutting tool wear prediction.Two case studies are performed to verify the capability and effectiveness of the proposed MCGRU network and results show that MCGRU outperforms several state-of-the-art baseline models.

Convolutional Neural Network-Based Deep Q-Network (CNN-DQN) Resource Management in Cloud Radio Access Network

The recent surge of mobile subscribers and user data traffic has accelerated the telecommunication sector towards the adoption of the fifth-generation (5G) mobile networks. Cloud radio access network (CRAN) is a prominent framework in the 5G mobile network to meet the above requirements by deploying low-cost and intelligent multiple distributed antennas known as remote radio heads (RRHs). However, achieving the optimal resource allocation (RA) in CRAN using the traditional approach is still challenging due to the complex structure. In this paper, we introduce the convolutional neural network-based deep Q-network (CNN-DQN) to balance the energy consumption and guarantee the user quality of service (QoS) demand in downlink CRAN. We first formulate the Markov decision process (MDP) for energy efficiency (EE) and build up a 3-layer CNN to capture the environment feature as an input state space. We then use DQN to turn on/off the RRHs dynamically based on the user QoS demand and energy consumption in the CRAN. Finally, we solve the RA problem based on the user constraint and transmit power to guarantee the user QoS demand and maximize the EE with a minimum number of active RRHs. In the end, we conduct the simulation to compare our proposed scheme with nature DQN and the traditional approach.

基于CNN-Swin Transformer Network的LPI雷达信号识别

针对在低信噪比(SNR)条件下,低截获概率雷达信号调制方式识别准确率低的问题,提出一种基于Transformer和卷积神经网络(CNN)的雷达信号识别方法。首先,引入Swin Transformer模型并在模型前端设计CNN特征提取层构建了CNN+Swin Transformer网络(CSTN),然后利用时频分析获取雷达信号的时频特征,对图像进行预处理后输入CSTN模型进行训练,由网络的底部到顶部不断提取图像更丰富的语义信息,最后通过Softmax分类器对六类不同调制方式信号进行分类识别。仿真实验表明:在SNR为-18 dB时,该方法对六类典型雷达信号的平均识别率达到了94.26%,证明了所提方法的可行性。

Text Feature Extraction and Classification Based on Convolutional Neural Network(CNN)

With the high-speed development of the Internet,a growing number of Internet users like giving their subjective comments in the BBS,blog and shopping website.These comments contains critics’attitudes,emotions,views and other information.Using these information reasonablely can help understand the social public opinion and make a timely response and help dealer to improve quality and service of products and make consumers know merchandise.This paper mainly discusses using convolutional neural network(CNN)for the operation of the text feature extraction.The concrete realization are discussed.Then combining with other text classifier make class operation.The experiment result shows the effectiveness of the method which is proposed in this paper.

Fine-Grained Sleep Apnea Detection Method from Multichannel Ballistocardiogram Using Convolution Neural Network

Sleep apnea is a common health condition that can affect numerous aspects of life and may cause a lot of health problems especially in the middle-aged and elderly population.Polysomnography(PSG),as the gold standard,is an expensive and inconvenient way to diagnose sleep apnea.However,ballistocardiogram can be collected by devices embedded in the surrounding environment,enabling inperceptible sleep apnea detection.Moreover,to obtain the fine-grained apnea fragments,a multistage sleep apnea detection model has been proposed.This model firstly uses an improved convolution neural network(CNN)model to coarsely identify apnea events and then a U-Net based model is applied to finely segment apnea fragments.In the experiment,sleep data of 11 patients with apnea for about 70 h have been collected,including BCG data derived from 18 piezoelectric polyvinylidene fluoride(PVDF)sensors embedded in the mattress and PSG data collected synchronously.The results show the accuracy of the classification model as good as 95.7%with 0.818 dice coefficient of the segmentation model,which indicates that the proposed model can almost match the performance of PSG in detecting apnea.