The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and hist...The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.展开更多
Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify sp...Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.展开更多
Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-a...Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.展开更多
Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning b...Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning based model,for the types identification.However,traditional approaches such as convolutional neural networks(CNNs)encounter difficulties in capturing global contextual information.In addition,they are computationally expensive,which restricts their usability in resource-limited environments.To tackle these issues,we present the Cloud Vision Transformer(CloudViT),a lightweight model that integrates CNNs with Transformers.The integration enables an effective balance between local and global feature extraction.To be specific,CloudViT comprises two innovative modules:Feature Extraction(E_Module)and Downsampling(D_Module).These modules are able to significantly reduce the number of model parameters and computational complexity while maintaining translation invariance and enhancing contextual comprehension.Overall,the CloudViT includes 0.93×10^(6)parameters,which decreases more than ten times compared to the SOTA(State-of-the-Art)model CloudNet.Comprehensive evaluations conducted on the HBMCD and SWIMCAT datasets showcase the outstanding performance of CloudViT.It achieves classification accuracies of 98.45%and 100%,respectively.Moreover,the efficiency and scalability of CloudViT make it an ideal candidate for deployment inmobile cloud observation systems,enabling real-time cloud image classification.The proposed hybrid architecture of CloudViT offers a promising approach for advancing ground-based cloud image classification.It holds significant potential for both optimizing performance and facilitating practical deployment scenarios.展开更多
Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image quality.This paper presents the UltraSegNet architecture that addres...Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image quality.This paper presents the UltraSegNet architecture that addresses these challenges through three key technical innovations:This work adds three things:(1)a changed ResNet-50 backbone with sequential 3×3 convolutions to keep fine anatomical details that are needed for finding lesion boundaries;(2)a computationally efficient regional attention mechanism that works on high-resolution features without using a transformer’s extra memory;and(3)an adaptive feature fusion strategy that changes local and global featuresbasedonhowthe image isbeing used.Extensive evaluation on two distinct datasets demonstrates UltraSegNet’s superior performance:On the BUSI dataset,it obtains a precision of 0.915,a recall of 0.908,and an F1 score of 0.911.In the UDAIT dataset,it achieves robust performance across the board,with a precision of 0.901 and recall of 0.894.Importantly,these improvements are achieved at clinically feasible computation times,taking 235 ms per image on standard GPU hardware.Notably,UltraSegNet does amazingly well on difficult small lesions(less than 10 mm),achieving a detection accuracy of 0.891.This is a huge improvement over traditional methods that have a hard time with small-scale features,as standard models can only achieve 0.63–0.71 accuracy.This improvement in small lesion detection is particularly crucial for early-stage breast cancer identification.Results from this work demonstrate that UltraSegNet can be practically deployable in clinical workflows to improve breast cancer screening accuracy.展开更多
Optical and hybrid convolutional neural networks(CNNs)recently have become of increasing interest to achieve low-latency,low-power image classification,and computer-vision tasks.However,implementing optical nonlineari...Optical and hybrid convolutional neural networks(CNNs)recently have become of increasing interest to achieve low-latency,low-power image classification,and computer-vision tasks.However,implementing optical nonlinearity is challenging,and omitting the nonlinear layers in a standard CNN comes with a significant reduction in accuracy.We use knowledge distillation to compress modified AlexNet to a single linear convolutional layer and an electronic backend(two fully connected layers).We obtain comparable performance with a purely electronic CNN with five convolutional layers and three fully connected layers.We implement the convolution optically via engineering the point spread function of an inverse-designed meta-optic.Using this hybrid approach,we estimate a reduction in multiply-accumulate operations from 17M in a conventional electronic modified AlexNet to only 86 K in the hybrid compressed network enabled by the optical front end.This constitutes over 2 orders of magnitude of reduction in latency and power consumption.Furthermore,we experimentally demonstrate that the classification accuracy of the system exceeds 93%on the MNIST dataset of handwritten digits.展开更多
Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feat...Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feature representation.However,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same image.Although some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different scales.To address these issues,we propose a two-stage,three-branch Transformer-based framework.The first stage incorporates multi-scale image feature extraction and hierarchical scale attention.This design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object scales.The second stage includes a global feature enhancement module and a region selection module.The global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and labels.Together,these components enable the efficient acquisition of class-specific precise feature representations.Extensive experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed method.Our approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,respectively.These results validate the reliability and superiority of our approach for multi-label image classification.展开更多
The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring ef...The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.展开更多
In a context where urban satellite image processing technologies are undergoing rapid evolution,this article presents an innovative and rigorous approach to satellite image classification applied to urban planning.Thi...In a context where urban satellite image processing technologies are undergoing rapid evolution,this article presents an innovative and rigorous approach to satellite image classification applied to urban planning.This research proposes an integrated methodological framework,based on the principles of model-driven engineering(MDE),to transform a generic meta-model into a meta-model specifically dedicated to urban satellite image classification.We implemented this transformation using the Atlas Transformation Language(ATL),guaranteeing a smooth and consistent transition from platform-independent model(PIM)to platform-specific model(PSM),according to the principles of model-driven architecture(MDA).The application of this IDM methodology enables advanced structuring of satellite data for targeted urban planning analyses,making it possible to classify various urban zones such as built-up,cultivated,arid and water areas.The novelty of this approach lies in the automation and standardization of the classification process,which significantly reduces the need for manual intervention,and thus improves the reliability,reproducibility and efficiency of urban data analysis.By adopting this method,decision-makers and urban planners are provided with a powerful tool for systematically and consistently analyzing and interpreting satellite images,facilitating decision-making in critical areas such as urban space management,infrastructure planning and environmental preservation.展开更多
Carotid artery plaques represent a major contributor to the morbidity and mortality associated with cerebrovascular disease,and their clinical significance is largely determined by the risk linked to plaque vulnerabil...Carotid artery plaques represent a major contributor to the morbidity and mortality associated with cerebrovascular disease,and their clinical significance is largely determined by the risk linked to plaque vulnerability.Therefore,classifying plaque risk constitutes one of themost critical tasks in the clinicalmanagement of this condition.While classification models derived from individual medical centers have been extensively investigated,these singlecenter models often fail to generalize well to multi-center data due to variations in ultrasound images caused by differences in physician expertise and equipment.To address this limitation,a Dual-Classifier Label Correction Networkmodel(DCLCN)is proposed for the classification of carotid plaque ultrasound images acrossmultiplemedical centers.TheDCLCNdesigns amulti-center domain adaptationmodule that leverages a dual-classifier strategy to extract knowledge from both source and target centers,thereby reducing feature discrepancies through a domain adaptation layer.Additionally,to mitigate the impact of image noise,a label modeling and correction module is introduced to generate pseudo-labels for the target centers and iteratively refine them using an end-to-end correction mechanism.Experiments on the carotid plaque dataset collected fromthreemedical centers demonstrate that the DCLCN achieves commendable performance and robustness.展开更多
Medical image classification is crucial in disease diagnosis,treatment planning,and clinical decisionmaking.We introduced a novel medical image classification approach that integrates Bayesian Random Semantic Data Aug...Medical image classification is crucial in disease diagnosis,treatment planning,and clinical decisionmaking.We introduced a novel medical image classification approach that integrates Bayesian Random Semantic Data Augmentation(BSDA)with a Vision Mamba-based model for medical image classification(MedMamba),enhanced by residual connection blocks,we named the model BSDA-Mamba.BSDA augments medical image data semantically,enhancing the model’s generalization ability and classification performance.MedMamba,a deep learning-based state space model,excels in capturing long-range dependencies in medical images.By incorporating residual connections,BSDA-Mamba further improves feature extraction capabilities.Through comprehensive experiments on eight medical image datasets,we demonstrate that BSDA-Mamba outperforms existing models in accuracy,area under the curve,and F1-score.Our results highlight BSDA-Mamba’s potential as a reliable tool for medical image analysis,particularly in handling diverse imaging modalities from X-rays to MRI.The open-sourcing of our model’s code and datasets,will facilitate the reproduction and extension of our work.展开更多
The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natura...The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natural adversarial examples has posed significant challenges, as traditional defense methods against adversarial attacks have proven to be largely ineffective against these natural adversarial examples. This paper explores defenses against these natural adversarial examples from three perspectives: adversarial examples, model architecture, and dataset. First, it employs Class Activation Mapping (CAM) to visualize how models classify natural adversarial examples, identifying several typical attack patterns. Next, various common CNN models are analyzed to evaluate their susceptibility to these attacks, revealing that different architectures exhibit varying defensive capabilities. The study finds that as the depth of a network increases, its defenses against natural adversarial examples strengthen. Lastly, Finally, the impact of dataset class distribution on the defense capability of models is examined, focusing on two aspects: the number of classes in the training set and the number of predicted classes. This study investigates how these factors influence the model’s ability to defend against natural adversarial examples. Results indicate that reducing the number of training classes enhances the model’s defense against natural adversarial examples. Additionally, under a fixed number of training classes, some CNN models show an optimal range of predicted classes for achieving the best defense performance against these adversarial examples.展开更多
Mudflat vegetation plays a crucial role in the ecological function of wetland environment,and obtaining its fine spatial distri-bution is of great significance for wetland protection and management.Remote sensing tech...Mudflat vegetation plays a crucial role in the ecological function of wetland environment,and obtaining its fine spatial distri-bution is of great significance for wetland protection and management.Remote sensing techniques can realize the rapid extraction of wetland vegetation over a large area.However,the imaging of optical sensors is easily restricted by weather conditions,and the backs-cattered information reflected by Synthetic Aperture Radar(SAR)images is easily disturbed by many factors.Although both data sources have been applied in wetland vegetation classification,there is a lack of comparative study on how the selection of data sources affects the classification effect.This study takes the vegetation of the tidal flat wetland in Chongming Island,Shanghai,China,in 2019,as the research subject.A total of 22 optical feature parameters and 11 SAR feature parameters were extracted from the optical data source(Sentinel-2)and SAR data source(Sentinel-1),respectively.The performance of optical and SAR data and their feature paramet-ers in wetland vegetation classification was quantitatively compared and analyzed by different feature combinations.Furthermore,by simulating the scenario of missing optical images,the impact of optical image missing on vegetation classification accuracy and the compensatory effect of integrating SAR data were revealed.Results show that:1)under the same classification algorithm,the Overall Accuracy(OA)of the combined use of optical and SAR images was the highest,reaching 95.50%.The OA of using only optical images was slightly lower,while using only SAR images yields the lowest accuracy,but still achieved 86.48%.2)Compared to using the spec-tral reflectance of optical data and the backscattering coefficient of SAR data directly,the constructed optical and SAR feature paramet-ers contributed to improving classification accuracy.The inclusion of optical(vegetation index,spatial texture,and phenology features)and SAR feature parameters(SAR index and SAR texture features)in the classification algorithm resulted in an OA improvement of 4.56%and 9.47%,respectively.SAR backscatter,SAR index,optical phenological features,and vegetation index were identified as the top-ranking important features.3)When the optical data were missing continuously for six months,the OA dropped to a minimum of 41.56%.However,when combined with SAR data,the OA could be improved to 71.62%.This indicates that the incorporation of SAR features can effectively compensate for the loss of accuracy caused by optical image missing,especially in regions with long-term cloud cover.展开更多
The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textile...The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textiles.By fusing band combination optimization with deep learning,this study aims to achieve more efficient and accurate detection of film impurities in seed cotton on the production line.By applying hyperspectral imaging and a one-dimensional deep learning algorithm,we detect and classify impurities in seed cotton after harvest.The main categories detected include pure cotton,conveyor belt,film covering seed cotton,and film adhered to the conveyor belt.The proposed method achieves an impurity detection rate of 99.698%.To further ensure the feasibility and practical application potential of this strategy,we compare our results against existing mainstream methods.In addition,the model shows excellent recognition performance on pseudo-color images of real samples.With a processing time of 11.764μs per pixel from experimental data,it shows a much improved speed requirement while maintaining the accuracy of real production lines.This strategy provides an accurate and efficient method for removing impurities during cotton processing.展开更多
In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering...In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering correction(MSC)-maximum-minimum normalization(MN)was identified as the optimal preprocessing technique.The competitive adaptive reweighted sampling(CARS),successive projections algorithm(SPA),and their combined methods were employed to extract feature wavelengths.Classification models based on back propagation(BP),support vector machine(SVM),random forest(RF),and partial least squares(PLS)were established using full-band data and feature wavelengths.Among all models,the(CARS-SPA)-BP model achieved the highest accuracy rate of 98.44%.This study offers novel insights and methodologies for the rapid and accurate identification of corn seeds as well as other crop seeds.展开更多
In oil and gas exploration,small-scale karst cavities and faults are important targets.The former often serve as reservoir space for carbonate reservoirs,while the latter often provide migration pathways for oil and g...In oil and gas exploration,small-scale karst cavities and faults are important targets.The former often serve as reservoir space for carbonate reservoirs,while the latter often provide migration pathways for oil and gas.Due to these differences,the classification and identification of karst cavities and faults are of great significance for reservoir development.Traditional seismic attributes and diffraction imaging techniques can effectively identify discontinuities in seismic images,but these techniques do not distinguish whether these discontinuities are karst cavities,faults,or other structures.It poses a challenge for seismic interpretation to accurately locate and classify karst cavities or faults within the seismic attribute maps and diffraction imaging profiles.In seismic data,the scattering waves are associated with small-scale scatters like karst cavities,while diffracted waves are seismic responses from discontinuous structures such as faults,reflector edges and fractures.In order to achieve classification and identification of small-scale karst cavities and faults in seismic images,we propose a diffraction classification imaging method which classifies diffracted and scattered waves in the azimuth-dip angle image matrix using a modified DenseNet.We introduce a coordinate attention module into DenseNet,enabling more precise extraction of dynamic and azimuthal features of diffracted and scattered waves in the azimuth-dip angle image matrix.Leveraging these extracted features,the modified DenseNet can produce reliable probabilities for diffracted/scattered waves,achieving high-accuracy automatic classification of cavities and faults based on diffraction imaging.The proposed method achieves 96%classification accuracy on the synthetic dataset.The field data experiment demonstrates that the proposed method can accurately classify small-scale faults and scatterers,further enhancing the resolution of diffraction imaging in complex geologic structures,and contributing to the localization of karstic fracture-cavern reservoirs.展开更多
Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification...Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.展开更多
Few‐shot image classification is the task of classifying novel classes using extremely limited labelled samples.To perform classification using the limited samples,one solution is to learn the feature alignment(FA)in...Few‐shot image classification is the task of classifying novel classes using extremely limited labelled samples.To perform classification using the limited samples,one solution is to learn the feature alignment(FA)information between the labelled and unlabelled sample features.Most FA methods use the feature mean as the class prototype and calculate the correlation between prototype and unlabelled features to learn an alignment strategy.However,mean prototypes tend to degenerate informative features because spatial features at the same position may not be equally important for the final classification,leading to inaccurate correlation calculations.Therefore,the authors propose an effective intraclass FA strategy that aggregates semantically similar spatial features from an adaptive reference prototype in low‐dimensional feature space to obtain an informative prototype feature map for precise correlation computation.Moreover,a dual correlation module to learn the hard and soft correlations was developed by the authors.This module combines the correlation information between the prototype and unlabelled features in both the original and learnable feature spaces,aiming to produce a comprehensive cross‐correlation between the prototypes and unlabelled features.Using both FA and cross‐attention modules,our model can maintain informative class features and capture important shared features for classification.Experimental results on three few‐shot classification benchmarks show that the proposed method outperformed related methods and resulted in a 3%performance boost in the 1‐shot setting by inserting the proposed module into the related methods.展开更多
Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hier...Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local features.The network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information redundancy.In the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent slices.In the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation capability.The double-branch iterative multi-scale classification block is used to improve the classification performance.On the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation indicators.On the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.展开更多
Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods...Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods still need to solve this problem despite the numerous available approaches. Precise analysis of Magnetic Resonance Imaging (MRI) is crucial for detecting, segmenting, and classifying brain tumours in medical diagnostics. Magnetic Resonance Imaging is a vital component in medical diagnosis, and it requires precise, efficient, careful, efficient, and reliable image analysis techniques. The authors developed a Deep Learning (DL) fusion model to classify brain tumours reliably. Deep Learning models require large amounts of training data to achieve good results, so the researchers utilised data augmentation techniques to increase the dataset size for training models. VGG16, ResNet50, and convolutional deep belief networks networks extracted deep features from MRI images. Softmax was used as the classifier, and the training set was supplemented with intentionally created MRI images of brain tumours in addition to the genuine ones. The features of two DL models were combined in the proposed model to generate a fusion model, which significantly increased classification accuracy. An openly accessible dataset from the internet was used to test the model's performance, and the experimental results showed that the proposed fusion model achieved a classification accuracy of 98.98%. Finally, the results were compared with existing methods, and the proposed model outperformed them significantly.展开更多
文摘The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.
基金the Deanship of Scientifc Research at King Khalid University for funding this work through large group Research Project under grant number RGP2/421/45supported via funding from Prince Sattam bin Abdulaziz University project number(PSAU/2024/R/1446)+1 种基金supported by theResearchers Supporting Project Number(UM-DSR-IG-2023-07)Almaarefa University,Riyadh,Saudi Arabia.supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2021R1F1A1055408).
文摘Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.
文摘Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.
基金funded by Innovation and Development Special Project of China Meteorological Administration(CXFZ2022J038,CXFZ2024J035)Sichuan Science and Technology Program(No.2023YFQ0072)+1 种基金Key Laboratory of Smart Earth(No.KF2023YB03-07)Automatic Software Generation and Intelligent Service Key Laboratory of Sichuan Province(CUIT-SAG202210).
文摘Accurate cloud classification plays a crucial role in aviation safety,climate monitoring,and localized weather forecasting.Current research has been focusing on machine learning techniques,particularly deep learning based model,for the types identification.However,traditional approaches such as convolutional neural networks(CNNs)encounter difficulties in capturing global contextual information.In addition,they are computationally expensive,which restricts their usability in resource-limited environments.To tackle these issues,we present the Cloud Vision Transformer(CloudViT),a lightweight model that integrates CNNs with Transformers.The integration enables an effective balance between local and global feature extraction.To be specific,CloudViT comprises two innovative modules:Feature Extraction(E_Module)and Downsampling(D_Module).These modules are able to significantly reduce the number of model parameters and computational complexity while maintaining translation invariance and enhancing contextual comprehension.Overall,the CloudViT includes 0.93×10^(6)parameters,which decreases more than ten times compared to the SOTA(State-of-the-Art)model CloudNet.Comprehensive evaluations conducted on the HBMCD and SWIMCAT datasets showcase the outstanding performance of CloudViT.It achieves classification accuracies of 98.45%and 100%,respectively.Moreover,the efficiency and scalability of CloudViT make it an ideal candidate for deployment inmobile cloud observation systems,enabling real-time cloud image classification.The proposed hybrid architecture of CloudViT offers a promising approach for advancing ground-based cloud image classification.It holds significant potential for both optimizing performance and facilitating practical deployment scenarios.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R435),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image quality.This paper presents the UltraSegNet architecture that addresses these challenges through three key technical innovations:This work adds three things:(1)a changed ResNet-50 backbone with sequential 3×3 convolutions to keep fine anatomical details that are needed for finding lesion boundaries;(2)a computationally efficient regional attention mechanism that works on high-resolution features without using a transformer’s extra memory;and(3)an adaptive feature fusion strategy that changes local and global featuresbasedonhowthe image isbeing used.Extensive evaluation on two distinct datasets demonstrates UltraSegNet’s superior performance:On the BUSI dataset,it obtains a precision of 0.915,a recall of 0.908,and an F1 score of 0.911.In the UDAIT dataset,it achieves robust performance across the board,with a precision of 0.901 and recall of 0.894.Importantly,these improvements are achieved at clinically feasible computation times,taking 235 ms per image on standard GPU hardware.Notably,UltraSegNet does amazingly well on difficult small lesions(less than 10 mm),achieving a detection accuracy of 0.891.This is a huge improvement over traditional methods that have a hard time with small-scale features,as standard models can only achieve 0.63–0.71 accuracy.This improvement in small lesion detection is particularly crucial for early-stage breast cancer identification.Results from this work demonstrate that UltraSegNet can be practically deployable in clinical workflows to improve breast cancer screening accuracy.
基金supported by the National Science Foundation(Grant Nos.NSF-ECCS-2127235 and EFRI-BRAID-2223495)Part of this work was conducted at the Washington Nanofabrication Facility/Molecular Analysis Facility,a National Nanotechnology Coordinated Infrastructure(NNCI)site at the University of Washington with partial support from the National Science Foundation(Grant Nos.NNCI-1542101 and NNCI-2025489).
文摘Optical and hybrid convolutional neural networks(CNNs)recently have become of increasing interest to achieve low-latency,low-power image classification,and computer-vision tasks.However,implementing optical nonlinearity is challenging,and omitting the nonlinear layers in a standard CNN comes with a significant reduction in accuracy.We use knowledge distillation to compress modified AlexNet to a single linear convolutional layer and an electronic backend(two fully connected layers).We obtain comparable performance with a purely electronic CNN with five convolutional layers and three fully connected layers.We implement the convolution optically via engineering the point spread function of an inverse-designed meta-optic.Using this hybrid approach,we estimate a reduction in multiply-accumulate operations from 17M in a conventional electronic modified AlexNet to only 86 K in the hybrid compressed network enabled by the optical front end.This constitutes over 2 orders of magnitude of reduction in latency and power consumption.Furthermore,we experimentally demonstrate that the classification accuracy of the system exceeds 93%on the MNIST dataset of handwritten digits.
基金supported by the National Natural Science Foundation of China(62302167,62477013)Natural Science Foundation of Shanghai(No.24ZR1456100)+1 种基金Science and Technology Commission of Shanghai Municipality(No.24DZ2305900)the Shanghai Municipal Special Fund for Promoting High-Quality Development of Industries(2211106).
文摘Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images.Obtaining class-specific precise representations at different scales is a key aspect of feature representation.However,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same image.Although some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different scales.To address these issues,we propose a two-stage,three-branch Transformer-based framework.The first stage incorporates multi-scale image feature extraction and hierarchical scale attention.This design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object scales.The second stage includes a global feature enhancement module and a region selection module.The global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and labels.Together,these components enable the efficient acquisition of class-specific precise feature representations.Extensive experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed method.Our approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,respectively.These results validate the reliability and superiority of our approach for multi-label image classification.
基金supported by the National Natural Science Foundation of China(Grant Nos.62071315 and 62271336).
文摘The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.
文摘In a context where urban satellite image processing technologies are undergoing rapid evolution,this article presents an innovative and rigorous approach to satellite image classification applied to urban planning.This research proposes an integrated methodological framework,based on the principles of model-driven engineering(MDE),to transform a generic meta-model into a meta-model specifically dedicated to urban satellite image classification.We implemented this transformation using the Atlas Transformation Language(ATL),guaranteeing a smooth and consistent transition from platform-independent model(PIM)to platform-specific model(PSM),according to the principles of model-driven architecture(MDA).The application of this IDM methodology enables advanced structuring of satellite data for targeted urban planning analyses,making it possible to classify various urban zones such as built-up,cultivated,arid and water areas.The novelty of this approach lies in the automation and standardization of the classification process,which significantly reduces the need for manual intervention,and thus improves the reliability,reproducibility and efficiency of urban data analysis.By adopting this method,decision-makers and urban planners are provided with a powerful tool for systematically and consistently analyzing and interpreting satellite images,facilitating decision-making in critical areas such as urban space management,infrastructure planning and environmental preservation.
基金supported by Shanghai Technical Service Computing Center of Science and Engineering,Shanghai University.
文摘Carotid artery plaques represent a major contributor to the morbidity and mortality associated with cerebrovascular disease,and their clinical significance is largely determined by the risk linked to plaque vulnerability.Therefore,classifying plaque risk constitutes one of themost critical tasks in the clinicalmanagement of this condition.While classification models derived from individual medical centers have been extensively investigated,these singlecenter models often fail to generalize well to multi-center data due to variations in ultrasound images caused by differences in physician expertise and equipment.To address this limitation,a Dual-Classifier Label Correction Networkmodel(DCLCN)is proposed for the classification of carotid plaque ultrasound images acrossmultiplemedical centers.TheDCLCNdesigns amulti-center domain adaptationmodule that leverages a dual-classifier strategy to extract knowledge from both source and target centers,thereby reducing feature discrepancies through a domain adaptation layer.Additionally,to mitigate the impact of image noise,a label modeling and correction module is introduced to generate pseudo-labels for the target centers and iteratively refine them using an end-to-end correction mechanism.Experiments on the carotid plaque dataset collected fromthreemedical centers demonstrate that the DCLCN achieves commendable performance and robustness.
文摘Medical image classification is crucial in disease diagnosis,treatment planning,and clinical decisionmaking.We introduced a novel medical image classification approach that integrates Bayesian Random Semantic Data Augmentation(BSDA)with a Vision Mamba-based model for medical image classification(MedMamba),enhanced by residual connection blocks,we named the model BSDA-Mamba.BSDA augments medical image data semantically,enhancing the model’s generalization ability and classification performance.MedMamba,a deep learning-based state space model,excels in capturing long-range dependencies in medical images.By incorporating residual connections,BSDA-Mamba further improves feature extraction capabilities.Through comprehensive experiments on eight medical image datasets,we demonstrate that BSDA-Mamba outperforms existing models in accuracy,area under the curve,and F1-score.Our results highlight BSDA-Mamba’s potential as a reliable tool for medical image analysis,particularly in handling diverse imaging modalities from X-rays to MRI.The open-sourcing of our model’s code and datasets,will facilitate the reproduction and extension of our work.
文摘The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natural adversarial examples has posed significant challenges, as traditional defense methods against adversarial attacks have proven to be largely ineffective against these natural adversarial examples. This paper explores defenses against these natural adversarial examples from three perspectives: adversarial examples, model architecture, and dataset. First, it employs Class Activation Mapping (CAM) to visualize how models classify natural adversarial examples, identifying several typical attack patterns. Next, various common CNN models are analyzed to evaluate their susceptibility to these attacks, revealing that different architectures exhibit varying defensive capabilities. The study finds that as the depth of a network increases, its defenses against natural adversarial examples strengthen. Lastly, Finally, the impact of dataset class distribution on the defense capability of models is examined, focusing on two aspects: the number of classes in the training set and the number of predicted classes. This study investigates how these factors influence the model’s ability to defend against natural adversarial examples. Results indicate that reducing the number of training classes enhances the model’s defense against natural adversarial examples. Additionally, under a fixed number of training classes, some CNN models show an optimal range of predicted classes for achieving the best defense performance against these adversarial examples.
基金Under the auspices of the National Key Research and Development Program of China(No.2023YFC3208500)Shanghai Municipal Natural Science Foundation(No.22ZR1421500)+3 种基金National Natural Science Foundation of China(No.U2243207)National Science and Technology Basic Resources Survey Project(No.2023FY01001)Open Research Fund of State Key Laboratory of Estuarine and Coastal Research(No.SKLEC-KF202406)Project from Science and Technology Commission of Shanghai Municipality(No.22DZ1202700)。
文摘Mudflat vegetation plays a crucial role in the ecological function of wetland environment,and obtaining its fine spatial distri-bution is of great significance for wetland protection and management.Remote sensing techniques can realize the rapid extraction of wetland vegetation over a large area.However,the imaging of optical sensors is easily restricted by weather conditions,and the backs-cattered information reflected by Synthetic Aperture Radar(SAR)images is easily disturbed by many factors.Although both data sources have been applied in wetland vegetation classification,there is a lack of comparative study on how the selection of data sources affects the classification effect.This study takes the vegetation of the tidal flat wetland in Chongming Island,Shanghai,China,in 2019,as the research subject.A total of 22 optical feature parameters and 11 SAR feature parameters were extracted from the optical data source(Sentinel-2)and SAR data source(Sentinel-1),respectively.The performance of optical and SAR data and their feature paramet-ers in wetland vegetation classification was quantitatively compared and analyzed by different feature combinations.Furthermore,by simulating the scenario of missing optical images,the impact of optical image missing on vegetation classification accuracy and the compensatory effect of integrating SAR data were revealed.Results show that:1)under the same classification algorithm,the Overall Accuracy(OA)of the combined use of optical and SAR images was the highest,reaching 95.50%.The OA of using only optical images was slightly lower,while using only SAR images yields the lowest accuracy,but still achieved 86.48%.2)Compared to using the spec-tral reflectance of optical data and the backscattering coefficient of SAR data directly,the constructed optical and SAR feature paramet-ers contributed to improving classification accuracy.The inclusion of optical(vegetation index,spatial texture,and phenology features)and SAR feature parameters(SAR index and SAR texture features)in the classification algorithm resulted in an OA improvement of 4.56%and 9.47%,respectively.SAR backscatter,SAR index,optical phenological features,and vegetation index were identified as the top-ranking important features.3)When the optical data were missing continuously for six months,the OA dropped to a minimum of 41.56%.However,when combined with SAR data,the OA could be improved to 71.62%.This indicates that the incorporation of SAR features can effectively compensate for the loss of accuracy caused by optical image missing,especially in regions with long-term cloud cover.
基金supported in part by the Six Talent Peaks Project in Jiangsu Province under Grant 013040315in part by the China Textile Industry Federation Science and Technology Guidance Project under Grant 2017107+1 种基金in part by the National Natural Science Foundation of China under Grant 31570714in part by the China Scholarship Council under Grant 202108320290。
文摘The cleanliness of seed cotton plays a critical role in the pre-treatment of cotton textiles,and the removal of impurity during the harvesting process directly determines the quality and market value of cotton textiles.By fusing band combination optimization with deep learning,this study aims to achieve more efficient and accurate detection of film impurities in seed cotton on the production line.By applying hyperspectral imaging and a one-dimensional deep learning algorithm,we detect and classify impurities in seed cotton after harvest.The main categories detected include pure cotton,conveyor belt,film covering seed cotton,and film adhered to the conveyor belt.The proposed method achieves an impurity detection rate of 99.698%.To further ensure the feasibility and practical application potential of this strategy,we compare our results against existing mainstream methods.In addition,the model shows excellent recognition performance on pseudo-color images of real samples.With a processing time of 11.764μs per pixel from experimental data,it shows a much improved speed requirement while maintaining the accuracy of real production lines.This strategy provides an accurate and efficient method for removing impurities during cotton processing.
基金supported by the Science and Technology Development Plan Project of Jilin Provincial Department of Science and Technology (No.20220203112S)the Jilin Provincial Department of Education Science and Technology Research Project (No.JJKH20210039KJ)。
文摘In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering correction(MSC)-maximum-minimum normalization(MN)was identified as the optimal preprocessing technique.The competitive adaptive reweighted sampling(CARS),successive projections algorithm(SPA),and their combined methods were employed to extract feature wavelengths.Classification models based on back propagation(BP),support vector machine(SVM),random forest(RF),and partial least squares(PLS)were established using full-band data and feature wavelengths.Among all models,the(CARS-SPA)-BP model achieved the highest accuracy rate of 98.44%.This study offers novel insights and methodologies for the rapid and accurate identification of corn seeds as well as other crop seeds.
基金supported by Science Fund for Creative Research Groups of the National Natural Science Foundation of China,No.42321002。
文摘In oil and gas exploration,small-scale karst cavities and faults are important targets.The former often serve as reservoir space for carbonate reservoirs,while the latter often provide migration pathways for oil and gas.Due to these differences,the classification and identification of karst cavities and faults are of great significance for reservoir development.Traditional seismic attributes and diffraction imaging techniques can effectively identify discontinuities in seismic images,but these techniques do not distinguish whether these discontinuities are karst cavities,faults,or other structures.It poses a challenge for seismic interpretation to accurately locate and classify karst cavities or faults within the seismic attribute maps and diffraction imaging profiles.In seismic data,the scattering waves are associated with small-scale scatters like karst cavities,while diffracted waves are seismic responses from discontinuous structures such as faults,reflector edges and fractures.In order to achieve classification and identification of small-scale karst cavities and faults in seismic images,we propose a diffraction classification imaging method which classifies diffracted and scattered waves in the azimuth-dip angle image matrix using a modified DenseNet.We introduce a coordinate attention module into DenseNet,enabling more precise extraction of dynamic and azimuthal features of diffracted and scattered waves in the azimuth-dip angle image matrix.Leveraging these extracted features,the modified DenseNet can produce reliable probabilities for diffracted/scattered waves,achieving high-accuracy automatic classification of cavities and faults based on diffraction imaging.The proposed method achieves 96%classification accuracy on the synthetic dataset.The field data experiment demonstrates that the proposed method can accurately classify small-scale faults and scatterers,further enhancing the resolution of diffraction imaging in complex geologic structures,and contributing to the localization of karstic fracture-cavern reservoirs.
基金National Natural Science Foundation of China(No.62201457)Natural Science Foundation of Shaanxi Province(Nos.2022JQ-668,2022JQ-588)。
文摘Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.
基金Institute of Information&Communications Technology Planning&Evaluation,Grant/Award Number:2022-0-00074。
文摘Few‐shot image classification is the task of classifying novel classes using extremely limited labelled samples.To perform classification using the limited samples,one solution is to learn the feature alignment(FA)information between the labelled and unlabelled sample features.Most FA methods use the feature mean as the class prototype and calculate the correlation between prototype and unlabelled features to learn an alignment strategy.However,mean prototypes tend to degenerate informative features because spatial features at the same position may not be equally important for the final classification,leading to inaccurate correlation calculations.Therefore,the authors propose an effective intraclass FA strategy that aggregates semantically similar spatial features from an adaptive reference prototype in low‐dimensional feature space to obtain an informative prototype feature map for precise correlation computation.Moreover,a dual correlation module to learn the hard and soft correlations was developed by the authors.This module combines the correlation information between the prototype and unlabelled features in both the original and learnable feature spaces,aiming to produce a comprehensive cross‐correlation between the prototypes and unlabelled features.Using both FA and cross‐attention modules,our model can maintain informative class features and capture important shared features for classification.Experimental results on three few‐shot classification benchmarks show that the proposed method outperformed related methods and resulted in a 3%performance boost in the 1‐shot setting by inserting the proposed module into the related methods.
基金Major Program of National Natural Science Foundation of China(NSFC12292980,NSFC12292984)National Key R&D Program of China(2023YFA1009000,2023YFA1009004,2020YFA0712203,2020YFA0712201)+2 种基金Major Program of National Natural Science Foundation of China(NSFC12031016)Beijing Natural Science Foundation(BNSFZ210003)Department of Science,Technology and Information of the Ministry of Education(8091B042240).
文摘Gliomas have the highest mortality rate of all brain tumors.Correctly classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival rates.This paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local features.The network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information redundancy.In the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent slices.In the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation capability.The double-branch iterative multi-scale classification block is used to improve the classification performance.On the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation indicators.On the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.
基金Ministry of Education,Youth and Sports of the Chezk Republic,Grant/Award Numbers:SP2023/039,SP2023/042the European Union under the REFRESH,Grant/Award Number:CZ.10.03.01/00/22_003/0000048。
文摘Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods still need to solve this problem despite the numerous available approaches. Precise analysis of Magnetic Resonance Imaging (MRI) is crucial for detecting, segmenting, and classifying brain tumours in medical diagnostics. Magnetic Resonance Imaging is a vital component in medical diagnosis, and it requires precise, efficient, careful, efficient, and reliable image analysis techniques. The authors developed a Deep Learning (DL) fusion model to classify brain tumours reliably. Deep Learning models require large amounts of training data to achieve good results, so the researchers utilised data augmentation techniques to increase the dataset size for training models. VGG16, ResNet50, and convolutional deep belief networks networks extracted deep features from MRI images. Softmax was used as the classifier, and the training set was supplemented with intentionally created MRI images of brain tumours in addition to the genuine ones. The features of two DL models were combined in the proposed model to generate a fusion model, which significantly increased classification accuracy. An openly accessible dataset from the internet was used to test the model's performance, and the experimental results showed that the proposed fusion model achieved a classification accuracy of 98.98%. Finally, the results were compared with existing methods, and the proposed model outperformed them significantly.
