Lightweight convolutional neural networks(CNNs)have simple structures but struggle to comprehensively and accurately extract important semantic information from images.While attention mechanisms can enhance CNNs by le...Lightweight convolutional neural networks(CNNs)have simple structures but struggle to comprehensively and accurately extract important semantic information from images.While attention mechanisms can enhance CNNs by learning distinctive representations,most existing spatial and hybrid attention methods focus on local regions with extensive parameters,making them unsuitable for lightweight CNNs.In this paper,we propose a self-attention mechanism tailored for lightweight networks,namely the brief self-attention module(BSAM).BSAM consists of the brief spatial attention(BSA)and advanced channel attention blocks.Unlike conventional self-attention methods with many parameters,our BSA block improves the performance of lightweight networks by effectively learning global semantic representations.Moreover,BSAM can be seamlessly integrated into lightweight CNNs for end-to-end training,maintaining the network’s lightweight and mobile characteristics.We validate the effectiveness of the proposed method on image classification tasks using the Food-101,Caltech-256,and Mini-ImageNet datasets.展开更多
In this paper,we introduce the notion of G_(C)-X-injective modules,where X denotes a class of left S-modules and C represents a faithfully semidualizing bimodule.Under the condition that X satisfies certain hypotheses...In this paper,we introduce the notion of G_(C)-X-injective modules,where X denotes a class of left S-modules and C represents a faithfully semidualizing bimodule.Under the condition that X satisfies certain hypotheses,some properties and some equivalent characterizations of G_(C)-X-injective modules are investigated,and we also show that the triple(■,cores■,■)is a weak co-AB-context.As an application,two complete cotorsion pairs and a new model structure in Mod S are given.展开更多
Many spore-forming Bacillus species can cause serious human diseases,because of accidental Bacillusspore infection.Thus,developing an identification strategy with both high sensitivity and specificity is greatly in de...Many spore-forming Bacillus species can cause serious human diseases,because of accidental Bacillusspore infection.Thus,developing an identification strategy with both high sensitivity and specificity is greatly in demand.In this work,we proposed a novel approach named multi-head self-attention mechanism-guided neural network Raman platform to identify living Bacillus spores within a single-cell resolution.The multi-head self-attention mechanism-guided neural network Raman platform was created by combining single-cell Raman spectroscopy,convolutional neural network(CNN),and multi-head self-attention mechanism.To address the limited size of the original spectra dataset,Gaussian noise-based spectra augmentation was employed to increase the number of single-cell Raman spectra datasets for CNN training.Owing to the assistance of both spectra augmentation and multi-head self-attention mechanism,the obtained prediction accuracy of five Bacillus spore species was further improved from 92.29±0.82%to 99.43±0.15%.To figure out the spectra differences covered by the multi-head self-attention mechanism-guided CNN,the relative classification weight from typical Raman bands was visualized via multi-head self-attention mechanism curve.In the process of spectra augmentation from 0 to 1000,the distribution of relative classification weight varied from a discrete state to a more concentrated phase.More importantly,these highlighted four Raman bands(1017,1449,1576,and 1660 cm^(-1))were assigned large weights,showing that the spectra differences in the Raman bands produced the largest contribution to prediction accuracy.It can be foreseen that,our proposed sorting platform has great potential in accurately identifying Bacillus and its related genera species at a single-cell level.展开更多
Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The prese...Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.展开更多
Fabrication of large-area perovskite solar modules under ambient air conditions remains a critical challenge due to air sensitivity of perovskite intermediate phases during crystallization.Here,we introduce 2-iodoimid...Fabrication of large-area perovskite solar modules under ambient air conditions remains a critical challenge due to air sensitivity of perovskite intermediate phases during crystallization.Here,we introduce 2-iodoimidazole(IIZ)into the perovskite precursor,enabling the formation of an air-stable pureδ-phase intermediate,which,upon annealing,fully transforms into a highly orientedα-phase perovskite film with reduced defects and variability.Leveraging this approach,we achieve a stabilized power conversion efficiency of 20.9%for 927.5 cm^(2)perovskite solar modules with high reproducibility.The encapsulated modules meet stringent international photovoltaic testing standards(IEC61215:2021),demonstrating excellent stability under continuous operation,thermal cycling(-40 to 85℃)and damp heat(85℃ and 85%relative humidity).展开更多
In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this pape...In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this paper proposes an efficient detection framework based on an improved YOLOv11 architecture.First,a Re-parameterized Convolution(RepConv)module is integrated into the backbone to enhance the model’s sensitivity to fine-grained defects—such as micro-cracks and hot spots—while maintaining high inference efficiency.Second,a Multi-Scale Feature Fusion Convolutional Block Attention Mechanism(MSFF-CBAM)is designed to guide the network toward critical defect regions by jointly modeling channel-wise and spatial attention.This mechanism effectively strengthens the specificity and robustness of feature representations.Third,a lightweight Dynamic Sampling Module(DySample)is employed to replace conventional upsampling operations,thereby improving the localization accuracy of small-scale defect targets.Experimental evaluations conducted on the PVEL-AD dataset demonstrate that the proposed RMDYOLOv11 model surpasses the baseline YOLOv11 in terms of mean Average Precision(mAP)@0.5,Precision,and Recall,achieving respective improvements of 4.70%,1.51%,and 5.50%.The model also exhibits notable advantages in inference speed and model compactness.Further validation on the ELPV dataset confirms the model’s generalization capability,showing respective performance gains of 1.99%,2.28%,and 1.45%across the same metrics.Overall,the enhanced model significantly improves the accuracy of micro-defect identification on PV module surfaces,effectively reducing both false negatives and false positives.This advancement provides a robust and reliable technical foundation for automated PV module defect detection.展开更多
Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained promine...Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis efficiency.Recently,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault diagnosis.However,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative model.This complexity results in high computational costs and limited industrial applicability.To tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault diagnosis.First,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration signals.Then,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global perspective.Finally,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and Transformer.This study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.展开更多
Photovoltaic (PV) modules, as essential components of solar power generation systems, significantly influence unitpower generation costs.The service life of these modules directly affects these costs. Over time, the p...Photovoltaic (PV) modules, as essential components of solar power generation systems, significantly influence unitpower generation costs.The service life of these modules directly affects these costs. Over time, the performanceof PV modules gradually declines due to internal degradation and external environmental factors.This cumulativedegradation impacts the overall reliability of photovoltaic power generation. This study addresses the complexdegradation process of PV modules by developing a two-stage Wiener process model. This approach accountsfor the distinct phases of degradation resulting from module aging and environmental influences. A powerdegradation model based on the two-stage Wiener process is constructed to describe individual differences inmodule degradation processes. To estimate the model parameters, a combination of the Expectation-Maximization(EM) algorithm and the Bayesian method is employed. Furthermore, the Schwarz Information Criterion (SIC) isutilized to identify critical change points in PV module degradation trajectories. To validate the universality andeffectiveness of the proposed method, a comparative analysis is conducted against other established life predictiontechniques for PV modules.展开更多
Located in northern China,the Hetao Plain is an important agro-economic zone and population centre.The deterioration of local groundwater quality has had a serious impact on human health and economic development.Nowad...Located in northern China,the Hetao Plain is an important agro-economic zone and population centre.The deterioration of local groundwater quality has had a serious impact on human health and economic development.Nowadays,the groundwater vulnerability assessment(GVA)has become an essential task to identify the current status and development trend of groundwater quality.In this study,the Convolutional Neural Network(CNN)and Long Short-Term Memory(LSTM)models are integrated to realize the spatio-temporal prediction of regional groundwater vulnerability by introducing the Self-attention mechanism.The study firstly builds the CNN-LSTM modelwith self-attention(SA)mechanism and evaluates the prediction accuracy of the model for groundwater vulnerability compared to other common machine learning models such as Support Vector Machine(SVM),Random Forest(RF),and Extreme Gradient Boosting(XGBoost).The results indicate that the CNNLSTM model outperforms thesemodels,demonstrating its significance in groundwater vulnerability assessment.It can be posited that the predictions indicate an increased risk of groundwater vulnerability in the study area over the coming years.This increase can be attributed to the synergistic impact of global climate anomalies and intensified local human activities.Moreover,the overall groundwater vulnerability risk in the entire region has increased,evident fromboth the notably high value and standard deviation.This suggests that the spatial variability of groundwater vulnerability in the area is expected to expand in the future due to the sustained progression of climate change and human activities.The model can be optimized for diverse applications across regional environmental assessment,pollution prediction,and risk statistics.This study holds particular significance for ecological protection and groundwater resource management.展开更多
Owing to the outstanding optoelectronic properties of perovskite materials,perovskite solar cells(PSCs)have been widely studied by academic organizations and industry corporations,with great potential to become the ne...Owing to the outstanding optoelectronic properties of perovskite materials,perovskite solar cells(PSCs)have been widely studied by academic organizations and industry corporations,with great potential to become the next-generation commercial solar cells.However,critical challenges remain in preserving high efficiency practical large-scale commercialized PSCs:a)the long-term stability of the cell materials and devices,b)lead leakage,and c)methods to scale the cells for larger area applications.This paper summarizes the prior-art strategies to address the above challenges,including the latest studies on the traditional glass-glass and thin-film encapsulation methods to better improve the reliability of PSCs,new technologies for preventing lead leakage,and geometric improvement strategies to enhance the reliability,efficiency,and performance of perovskite solar modules(PSMs).Through these strategies,the device achieved enhanced performance in long-term stability tests.The encapsulation resulted in a high lead leakage inhibition rate of up to 99%,and the PSMs possessed a geometric fill factor of 99.6%and a power conversion efficiency(PCE)of 20.7%.The dramatic improvement of efficiency and reliability of perovskite solar cells and modules indicate the great potential for mass production and commer-cialization of perovskite solar applications in the near future.展开更多
Target occlusion poses a significant challenge in computer vision,particularly in agricultural applications,where occlusion of crops can obscure key features and impair the model’s recognition performance.To address ...Target occlusion poses a significant challenge in computer vision,particularly in agricultural applications,where occlusion of crops can obscure key features and impair the model’s recognition performance.To address this challenge,a mushroom recognition method was proposed based on an erase module integrated into the EL-DenseNet model.EL-DenseNet,an extension of DenseNet,incorporated an erase attention module designed to enhance sensitivity to visible features.The erase module helped eliminate complex backgrounds and irrelevant information,allowing the mushroom body to be preserved and increasing recognition accuracy in cluttered environments.Considering the difficulty in distinguishing similar mushroom species,label smoothing regularization was employed to mitigate mislabeling errors that commonly arose from human observers.This strategy converted hard labels into soft labels during training,reducing the model’s overreliance on noisy labels and improving its generalization ability.Experimental results showed that the proposed EL-DenseNet,when combined with transfer learning,achieved a recognition accuracy of 96.7%for mushrooms in occluded and complex backgrounds.Compared with the original DenseNet and other classic models,this approach demonstrated superior accuracy and robustness,providing a promising solution for intelligent mushroom recognition.展开更多
A healthy brain is vital to every person since the brain controls every movement and emotion.Sometimes,some brain cells grow unexpectedly to be uncontrollable and cancerous.These cancerous cells are called brain tumor...A healthy brain is vital to every person since the brain controls every movement and emotion.Sometimes,some brain cells grow unexpectedly to be uncontrollable and cancerous.These cancerous cells are called brain tumors.For diagnosed patients,their lives depend mainly on the early diagnosis of these tumors to provide suitable treatment plans.Nowadays,Physicians and radiologists rely on Magnetic Resonance Imaging(MRI)pictures for their clinical evaluations of brain tumors.These evaluations are time-consuming,expensive,and require expertise with high skills to provide an accurate diagnosis.Scholars and industrials have recently partnered to implement automatic solutions to diagnose the disease with high accuracy.Due to their accuracy,some of these solutions depend on deep-learning(DL)methodologies.These techniques have become important due to their roles in the diagnosis process,which includes identification and classification.Therefore,there is a need for a solid and robust approach based on a deep-learning method to diagnose brain tumors.The purpose of this study is to develop an intelligent automatic framework for brain tumor diagnosis.The proposed solution is based on a novel dense dynamic residual self-attention transfer adaptive learning fusion approach(NDDRSATALFA),carried over two implemented deep-learning networks:VGG19 and UNET to identify and classify brain tumors.In addition,this solution applies a transfer learning approach to exchange extracted features and data within the two neural networks.The presented framework is trained,validated,and tested on six public datasets of MRIs to detect brain tumors and categorize these tumors into three suitable classes,which are glioma,meningioma,and pituitary.The proposed framework yielded remarkable findings on variously evaluated performance indicators:99.32%accuracy,98.74%sensitivity,98.89%specificity,99.01%Dice,98.93%Area Under the Curve(AUC),and 99.81%F1-score.In addition,a comparative analysis with recent state-of-the-art methods was performed and according to the comparative analysis,NDDRSATALFA shows an admirable level of reliability in simplifying the timely identification of diverse brain tumors.Moreover,this framework can be applied by healthcare providers to assist radiologists,pathologists,and physicians in their evaluations.The attained outcomes open doors for advanced automatic solutions that improve clinical evaluations and provide reasonable treatment plans.展开更多
Medical image analysis based on deep learning has become an important technical requirement in the field of smart healthcare.In view of the difficulties in collaborative modeling of local details and global features i...Medical image analysis based on deep learning has become an important technical requirement in the field of smart healthcare.In view of the difficulties in collaborative modeling of local details and global features in multimodal image analysis of ophthalmology,as well as the existence of information redundancy in cross-modal data fusion,this paper proposes amultimodal fusion framework based on cross-modal collaboration and weighted attention mechanism.In terms of feature extraction,the framework collaboratively extracts local fine-grained features and global structural dependencies through a parallel dual-branch architecture,overcoming the limitations of traditional single-modality models in capturing either local or global information;in terms of fusion strategy,the framework innovatively designs a cross-modal dynamic fusion strategy,combining overlappingmulti-head self-attention modules with a bidirectional feature alignment mechanism,addressing the bottlenecks of low feature interaction efficiency and excessive attention fusion computations in traditional parallel fusion,and further introduces cross-domain local integration technology,which enhances the representation ability of the lesion area through pixel-level feature recalibration and optimizes the diagnostic robustness of complex cases.Experiments show that the framework exhibits excellent feature expression and generalization performance in cross-domain scenarios of ophthalmic medical images and natural images,providing a high-precision,low-redundancy fusion paradigm for multimodal medical image analysis,and promoting the upgrade of intelligent diagnosis and treatment fromsingle-modal static analysis to dynamic decision-making.展开更多
Deep Learning-based systems for Finger vein recognition have gained rising attention in recent years due to improved efficiency and enhanced security.The performance of existing CNN-based methods is limited by the pun...Deep Learning-based systems for Finger vein recognition have gained rising attention in recent years due to improved efficiency and enhanced security.The performance of existing CNN-based methods is limited by the puny generalization of learned features and deficiency of the finger vein image training data.Considering the concerns of existing methods,in this work,a simplified deep transfer learning-based framework for finger-vein recognition is developed using an EfficientNet model of deep learning with a self-attention mechanism.Data augmentation using various geometrical methods is employed to address the problem of training data shortage required for a deep learning model.The proposed model is tested using K-fold cross-validation on three publicly available datasets:HKPU,FVUSM,and SDUMLA.Also,the developed network is compared with other modern deep nets to check its effectiveness.In addition,a comparison of the proposed method with other existing Finger vein recognition(FVR)methods is also done.The experimental results exhibited superior recognition accuracy of the proposed method compared to other existing methods.In addition,the developed method proves to be more effective and less sophisticated at extracting robust features.The proposed EffAttenNet achieves an accuracy of 98.14%on HKPU,99.03%on FVUSM,and 99.50%on SDUMLA databases.展开更多
For image compression sensing reconstruction,most algorithms use the method of reconstructing image blocks one by one and stacking many convolutional layers,which usually have defects of obvious block effects,high com...For image compression sensing reconstruction,most algorithms use the method of reconstructing image blocks one by one and stacking many convolutional layers,which usually have defects of obvious block effects,high computational complexity,and long reconstruction time.An image compressed sensing reconstruction network based on self-attention mechanism(SAMNet)was proposed.For the compressed sampling,self-attention convolution was designed,which was conducive to capturing richer features,so that the compressed sensing measurement value retained more image structure information.For the reconstruction,a self-attention mechanism was introduced in the convolutional neural network.A reconstruction network including residual blocks,bottleneck transformer(BoTNet),and dense blocks was proposed,which strengthened the transfer of image features and reduced the amount of parameters dramatically.Under the Set5 dataset,when the measurement rates are 0.01,0.04,0.10,and 0.25,the average peak signal-to-noise ratio(PSNR)of SAMNet is improved by 1.27,1.23,0.50,and 0.15 dB,respectively,compared to the CSNet+.The running time of reconstructing a 256×256 image is reduced by 0.1473,0.1789,0.2310,and 0.2524 s compared to ReconNet.Experimental results showed that SAMNet improved the quality of reconstructed images and reduced the reconstruction time.展开更多
As the complexity of scientific satellite missions increases,the requirements for their magnetic fields,magnetic field fluctuations,and even magnetic field gradients and variations become increasingly stringent.Additi...As the complexity of scientific satellite missions increases,the requirements for their magnetic fields,magnetic field fluctuations,and even magnetic field gradients and variations become increasingly stringent.Additionally,there is a growing need to address the alternating magnetic fields produced by the spacecraft itself.This paper introduces a novel modeling method for spacecraft magnetic dipoles using an integrated self-attention mechanism and a transformer combined with Kolmogorov-Arnold Networks.The self-attention mechanism captures correlations among globally sparse data,establishing dependencies b.etween sparse magnetometer readings.Concurrently,the Kolmogorov-Arnold Network,proficient in modeling implicit numerical relationships between data features,enhances the ability to learn subtle patterns.Comparative experiments validate the capability of the proposed method to precisely model magnetic dipoles,achieving maximum Root Mean Square Errors of 24.06 mA·m^(2)and 0.32 cm for size and location modeling,respectively.The spacecraft magnetic model established using this method accurately computes magnetic fields and alternating magnetic fields at designated surfaces or points.This approach facilitates the rapid and precise construction of individual and complete spacecraft magnetic models,enabling the verification of magnetic specifications from the spacecraft design phase.展开更多
The development of deep learning has made non-biochemical methods for molecular property prediction screening a reality,which can increase the experimental speed and reduce the experimental cost of relevant experiment...The development of deep learning has made non-biochemical methods for molecular property prediction screening a reality,which can increase the experimental speed and reduce the experimental cost of relevant experiments.There are currently two main approaches to representing molecules:(a)representing molecules by fixing molecular descriptors,and(b)representing molecules by graph convolutional neural networks.Currently,both of these Representative methods have achieved some results in their respective experiments.Based on past efforts,we propose a Dual Self-attention Fusion Message Neural Network(DSFMNN).DSFMNN uses a combination of dual self-attention mechanism and graph convolutional neural network.Advantages of DSFMNN:(1)The dual self-attention mechanism focuses not only on the relationship between individual subunits in a molecule but also on the relationship between the atoms and chemical bonds contained in each subunit.(2)On the directed molecular graph,a message delivery approach centered on directed molecular bonds is used.We test the performance of the model on eight publicly available datasets and compare the performance with several models.Based on the current experimental results,DSFMNN has superior performance compared to previous models on the datasets applied in this paper.展开更多
Currently,most trains are equipped with dedicated cameras for capturing pantograph videos.Pantographs are core to the high-speed-railway pantograph-catenary system,and their failure directly affects the normal operati...Currently,most trains are equipped with dedicated cameras for capturing pantograph videos.Pantographs are core to the high-speed-railway pantograph-catenary system,and their failure directly affects the normal operation of high-speed trains.However,given the complex and variable real-world operational conditions of high-speed railways,there is no real-time and robust pantograph fault-detection method capable of handling large volumes of surveillance video.Hence,it is of paramount importance to maintain real-time monitoring and analysis of pantographs.Our study presents a real-time intelligent detection technology for identifying faults in high-speed railway pantographs,utilizing a fusion of self-attention and convolution features.We delved into lightweight multi-scale feature-extraction and fault-detection models based on deep learning to detect pantograph anomalies.Compared with traditional methods,this approach achieves high recall and accuracy in pantograph recognition,accurately pinpointing issues like discharge sparks,pantograph horns,and carbon pantograph-slide malfunctions.After experimentation and validation with actual surveillance videos of electric multiple-unit train,our algorithmic model demonstrates real-time,high-accuracy performance even under complex operational conditions.展开更多
The fabrication of efficient and stable flexible perovskite solar modules(F-PSMs)using poly[bis(4-phenyl)(2,4,6-trimethylphenyl)amine](PTAA)remains a significant challenge due to its hydrophobic properties and the mis...The fabrication of efficient and stable flexible perovskite solar modules(F-PSMs)using poly[bis(4-phenyl)(2,4,6-trimethylphenyl)amine](PTAA)remains a significant challenge due to its hydrophobic properties and the mismatch in interface energy-level alignment.Here,we introduced[2-(3,6-dimethoxy-9H-carba zol-9-yl)ethyl]phosphonic acid(MeO-2PACz)to modify the PTAA layer,which effectively suppressed surface potential fluctuations and aligned energy levels at the interface of PTAA/perovskite.Additionally,MeO-2PACz enhanced the hydrophilicity of PTAA,facilitating the fabrication of dense,uniform,and pinhole-free perovskite films on large-area flexible substrates.As a result,we achieved an F-PSM with a power conversion efficiency(PCE)of 16.6% and an aperture area of 64 cm^(2),which is the highest reported value among F-PSMs with an active area exceeding 35 cm^(2)based on PTAA.Moreover,the encapsulated module demonstrated outstanding long-term operational stability,retaining 90.2% of its initial efficiency after 1000 bending cycles(5 mm radius),87.2% after 1000 h of continuous illumination,and 80.3% under combined thermal and humid conditions(85℃ and 85% relative humidity),representing one of the most stable F-PSMs reported to date.展开更多
文摘Lightweight convolutional neural networks(CNNs)have simple structures but struggle to comprehensively and accurately extract important semantic information from images.While attention mechanisms can enhance CNNs by learning distinctive representations,most existing spatial and hybrid attention methods focus on local regions with extensive parameters,making them unsuitable for lightweight CNNs.In this paper,we propose a self-attention mechanism tailored for lightweight networks,namely the brief self-attention module(BSAM).BSAM consists of the brief spatial attention(BSA)and advanced channel attention blocks.Unlike conventional self-attention methods with many parameters,our BSA block improves the performance of lightweight networks by effectively learning global semantic representations.Moreover,BSAM can be seamlessly integrated into lightweight CNNs for end-to-end training,maintaining the network’s lightweight and mobile characteristics.We validate the effectiveness of the proposed method on image classification tasks using the Food-101,Caltech-256,and Mini-ImageNet datasets.
文摘In this paper,we introduce the notion of G_(C)-X-injective modules,where X denotes a class of left S-modules and C represents a faithfully semidualizing bimodule.Under the condition that X satisfies certain hypotheses,some properties and some equivalent characterizations of G_(C)-X-injective modules are investigated,and we also show that the triple(■,cores■,■)is a weak co-AB-context.As an application,two complete cotorsion pairs and a new model structure in Mod S are given.
基金partially supported by the National Natural Science Foundation of China(62075137)the Guangdong Basic and Applied Basic Research Foundation(2023A1515140161)+3 种基金the Guangxi Natural Science Foundation of China(2021JJB 110003)the Dongguan Science and Technology of Social Development Program(20231800936312)the high-level talent program of Dongguan University of Technology(No.221110080)the Sanming Project of Medicine in Shenzhen(No.SZSM202103014).
文摘Many spore-forming Bacillus species can cause serious human diseases,because of accidental Bacillusspore infection.Thus,developing an identification strategy with both high sensitivity and specificity is greatly in demand.In this work,we proposed a novel approach named multi-head self-attention mechanism-guided neural network Raman platform to identify living Bacillus spores within a single-cell resolution.The multi-head self-attention mechanism-guided neural network Raman platform was created by combining single-cell Raman spectroscopy,convolutional neural network(CNN),and multi-head self-attention mechanism.To address the limited size of the original spectra dataset,Gaussian noise-based spectra augmentation was employed to increase the number of single-cell Raman spectra datasets for CNN training.Owing to the assistance of both spectra augmentation and multi-head self-attention mechanism,the obtained prediction accuracy of five Bacillus spore species was further improved from 92.29±0.82%to 99.43±0.15%.To figure out the spectra differences covered by the multi-head self-attention mechanism-guided CNN,the relative classification weight from typical Raman bands was visualized via multi-head self-attention mechanism curve.In the process of spectra augmentation from 0 to 1000,the distribution of relative classification weight varied from a discrete state to a more concentrated phase.More importantly,these highlighted four Raman bands(1017,1449,1576,and 1660 cm^(-1))were assigned large weights,showing that the spectra differences in the Raman bands produced the largest contribution to prediction accuracy.It can be foreseen that,our proposed sorting platform has great potential in accurately identifying Bacillus and its related genera species at a single-cell level.
基金funded by the Deanship of Scientific Research and Libraries at Princess Nourah bint Abdulrahman University,through the“Nafea”Program,Grant No.(NP-45-082).
文摘Sustainable energy systems will entail a change in the carbon intensity projections,which should be carried out in a proper manner to facilitate the smooth running of the grid and reduce greenhouse emissions.The present article outlines the TransCarbonNet,a novel hybrid deep learning framework with self-attention characteristics added to the bidirectional Long Short-Term Memory(Bi-LSTM)network to forecast the carbon intensity of the grid several days.The proposed temporal fusion model not only learns the local temporal interactions but also the long-term patterns of the carbon emission data;hence,it is able to give suitable forecasts over a period of seven days.TransCarbonNet takes advantage of a multi-head self-attention element to identify significant temporal connections,which means the Bi-LSTM element calculates sequential dependencies in both directions.Massive tests on two actual data sets indicate much improved results in comparison with the existing results,with mean relative errors of 15.3 percent and 12.7 percent,respectively.The framework has given explicable weights of attention that reveal critical periods that influence carbon intensity alterations,and informed decisions on the management of carbon sustainability.The effectiveness of the proposed solution has been validated in numerous cases of operations,and TransCarbonNet is established to be an effective tool when it comes to carbon-friendly optimization of the grid.
基金supported by the National Key R&D Program of China(2023YFB4204504)National Science Fund for Dis-tinguished Young Scholars(T2325016)+7 种基金National Natural Science Foundation of China(U21A2076)Natural Science Foundation of Jiangsu Province(BK20232022,BE2022021 and BE2022026)Fundamental Research Funds for the Central Universities(0213/14380206 and 0205/14380252)Frontiers Science Center for Critical Earth Material Cycling Fund(DLTD2109 and 2024ZD06)Program for Innovative Talents and Entrepreneur in JiangsuChina Postdoctoral Science Foundation(2023M731579)Jiangsu Funding Program for Excellent Postdoctoral Talent(2023ZB348)Postdoctoral Innovative Talents Support Project from the China Postdoctoral Science Foundation(BX20230157)。
文摘Fabrication of large-area perovskite solar modules under ambient air conditions remains a critical challenge due to air sensitivity of perovskite intermediate phases during crystallization.Here,we introduce 2-iodoimidazole(IIZ)into the perovskite precursor,enabling the formation of an air-stable pureδ-phase intermediate,which,upon annealing,fully transforms into a highly orientedα-phase perovskite film with reduced defects and variability.Leveraging this approach,we achieve a stabilized power conversion efficiency of 20.9%for 927.5 cm^(2)perovskite solar modules with high reproducibility.The encapsulated modules meet stringent international photovoltaic testing standards(IEC61215:2021),demonstrating excellent stability under continuous operation,thermal cycling(-40 to 85℃)and damp heat(85℃ and 85%relative humidity).
基金supported by the Gansu Provincial Department of Education Industry Support Plan Project(2025CYZC-018).
文摘In order to address the challenges posed by complex background interference,high miss-detection rates of micro-scale defects,and limited model deployment efficiency in photovoltaic(PV)module defect detection,this paper proposes an efficient detection framework based on an improved YOLOv11 architecture.First,a Re-parameterized Convolution(RepConv)module is integrated into the backbone to enhance the model’s sensitivity to fine-grained defects—such as micro-cracks and hot spots—while maintaining high inference efficiency.Second,a Multi-Scale Feature Fusion Convolutional Block Attention Mechanism(MSFF-CBAM)is designed to guide the network toward critical defect regions by jointly modeling channel-wise and spatial attention.This mechanism effectively strengthens the specificity and robustness of feature representations.Third,a lightweight Dynamic Sampling Module(DySample)is employed to replace conventional upsampling operations,thereby improving the localization accuracy of small-scale defect targets.Experimental evaluations conducted on the PVEL-AD dataset demonstrate that the proposed RMDYOLOv11 model surpasses the baseline YOLOv11 in terms of mean Average Precision(mAP)@0.5,Precision,and Recall,achieving respective improvements of 4.70%,1.51%,and 5.50%.The model also exhibits notable advantages in inference speed and model compactness.Further validation on the ELPV dataset confirms the model’s generalization capability,showing respective performance gains of 1.99%,2.28%,and 1.45%across the same metrics.Overall,the enhanced model significantly improves the accuracy of micro-defect identification on PV module surfaces,effectively reducing both false negatives and false positives.This advancement provides a robust and reliable technical foundation for automated PV module defect detection.
基金supported by the National Natural Science Foundation of China(No.52277055).
文摘Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain limitations.Conversely,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis efficiency.Recently,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault diagnosis.However,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative model.This complexity results in high computational costs and limited industrial applicability.To tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault diagnosis.First,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration signals.Then,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global perspective.Finally,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and Transformer.This study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.
基金supported by the National Natural Science Foundation of China(51767017)the Basic Research Innovation Group Project of Gansu Province(18JR3RA133)the Industrial Support and Guidance Project of Universities in Gansu Province(2022CYZC-22).
文摘Photovoltaic (PV) modules, as essential components of solar power generation systems, significantly influence unitpower generation costs.The service life of these modules directly affects these costs. Over time, the performanceof PV modules gradually declines due to internal degradation and external environmental factors.This cumulativedegradation impacts the overall reliability of photovoltaic power generation. This study addresses the complexdegradation process of PV modules by developing a two-stage Wiener process model. This approach accountsfor the distinct phases of degradation resulting from module aging and environmental influences. A powerdegradation model based on the two-stage Wiener process is constructed to describe individual differences inmodule degradation processes. To estimate the model parameters, a combination of the Expectation-Maximization(EM) algorithm and the Bayesian method is employed. Furthermore, the Schwarz Information Criterion (SIC) isutilized to identify critical change points in PV module degradation trajectories. To validate the universality andeffectiveness of the proposed method, a comparative analysis is conducted against other established life predictiontechniques for PV modules.
基金supported by the National Key Research and Development Program of China(No.2021YFA0715900).
文摘Located in northern China,the Hetao Plain is an important agro-economic zone and population centre.The deterioration of local groundwater quality has had a serious impact on human health and economic development.Nowadays,the groundwater vulnerability assessment(GVA)has become an essential task to identify the current status and development trend of groundwater quality.In this study,the Convolutional Neural Network(CNN)and Long Short-Term Memory(LSTM)models are integrated to realize the spatio-temporal prediction of regional groundwater vulnerability by introducing the Self-attention mechanism.The study firstly builds the CNN-LSTM modelwith self-attention(SA)mechanism and evaluates the prediction accuracy of the model for groundwater vulnerability compared to other common machine learning models such as Support Vector Machine(SVM),Random Forest(RF),and Extreme Gradient Boosting(XGBoost).The results indicate that the CNNLSTM model outperforms thesemodels,demonstrating its significance in groundwater vulnerability assessment.It can be posited that the predictions indicate an increased risk of groundwater vulnerability in the study area over the coming years.This increase can be attributed to the synergistic impact of global climate anomalies and intensified local human activities.Moreover,the overall groundwater vulnerability risk in the entire region has increased,evident fromboth the notably high value and standard deviation.This suggests that the spatial variability of groundwater vulnerability in the area is expected to expand in the future due to the sustained progression of climate change and human activities.The model can be optimized for diverse applications across regional environmental assessment,pollution prediction,and risk statistics.This study holds particular significance for ecological protection and groundwater resource management.
基金supported by the National Natural Science Foundation of China(No.62404041)the Natural Science Foundation of Jiangsu Province of China(No.BK20230830).
文摘Owing to the outstanding optoelectronic properties of perovskite materials,perovskite solar cells(PSCs)have been widely studied by academic organizations and industry corporations,with great potential to become the next-generation commercial solar cells.However,critical challenges remain in preserving high efficiency practical large-scale commercialized PSCs:a)the long-term stability of the cell materials and devices,b)lead leakage,and c)methods to scale the cells for larger area applications.This paper summarizes the prior-art strategies to address the above challenges,including the latest studies on the traditional glass-glass and thin-film encapsulation methods to better improve the reliability of PSCs,new technologies for preventing lead leakage,and geometric improvement strategies to enhance the reliability,efficiency,and performance of perovskite solar modules(PSMs).Through these strategies,the device achieved enhanced performance in long-term stability tests.The encapsulation resulted in a high lead leakage inhibition rate of up to 99%,and the PSMs possessed a geometric fill factor of 99.6%and a power conversion efficiency(PCE)of 20.7%.The dramatic improvement of efficiency and reliability of perovskite solar cells and modules indicate the great potential for mass production and commer-cialization of perovskite solar applications in the near future.
文摘Target occlusion poses a significant challenge in computer vision,particularly in agricultural applications,where occlusion of crops can obscure key features and impair the model’s recognition performance.To address this challenge,a mushroom recognition method was proposed based on an erase module integrated into the EL-DenseNet model.EL-DenseNet,an extension of DenseNet,incorporated an erase attention module designed to enhance sensitivity to visible features.The erase module helped eliminate complex backgrounds and irrelevant information,allowing the mushroom body to be preserved and increasing recognition accuracy in cluttered environments.Considering the difficulty in distinguishing similar mushroom species,label smoothing regularization was employed to mitigate mislabeling errors that commonly arose from human observers.This strategy converted hard labels into soft labels during training,reducing the model’s overreliance on noisy labels and improving its generalization ability.Experimental results showed that the proposed EL-DenseNet,when combined with transfer learning,achieved a recognition accuracy of 96.7%for mushrooms in occluded and complex backgrounds.Compared with the original DenseNet and other classic models,this approach demonstrated superior accuracy and robustness,providing a promising solution for intelligent mushroom recognition.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,Saudi Arabia under Grant No.(GPIP:1055-829-2024).
文摘A healthy brain is vital to every person since the brain controls every movement and emotion.Sometimes,some brain cells grow unexpectedly to be uncontrollable and cancerous.These cancerous cells are called brain tumors.For diagnosed patients,their lives depend mainly on the early diagnosis of these tumors to provide suitable treatment plans.Nowadays,Physicians and radiologists rely on Magnetic Resonance Imaging(MRI)pictures for their clinical evaluations of brain tumors.These evaluations are time-consuming,expensive,and require expertise with high skills to provide an accurate diagnosis.Scholars and industrials have recently partnered to implement automatic solutions to diagnose the disease with high accuracy.Due to their accuracy,some of these solutions depend on deep-learning(DL)methodologies.These techniques have become important due to their roles in the diagnosis process,which includes identification and classification.Therefore,there is a need for a solid and robust approach based on a deep-learning method to diagnose brain tumors.The purpose of this study is to develop an intelligent automatic framework for brain tumor diagnosis.The proposed solution is based on a novel dense dynamic residual self-attention transfer adaptive learning fusion approach(NDDRSATALFA),carried over two implemented deep-learning networks:VGG19 and UNET to identify and classify brain tumors.In addition,this solution applies a transfer learning approach to exchange extracted features and data within the two neural networks.The presented framework is trained,validated,and tested on six public datasets of MRIs to detect brain tumors and categorize these tumors into three suitable classes,which are glioma,meningioma,and pituitary.The proposed framework yielded remarkable findings on variously evaluated performance indicators:99.32%accuracy,98.74%sensitivity,98.89%specificity,99.01%Dice,98.93%Area Under the Curve(AUC),and 99.81%F1-score.In addition,a comparative analysis with recent state-of-the-art methods was performed and according to the comparative analysis,NDDRSATALFA shows an admirable level of reliability in simplifying the timely identification of diverse brain tumors.Moreover,this framework can be applied by healthcare providers to assist radiologists,pathologists,and physicians in their evaluations.The attained outcomes open doors for advanced automatic solutions that improve clinical evaluations and provide reasonable treatment plans.
基金funded by the Ongoing Research Funding Program(ORF-2025-102),King Saud University,Riyadh,Saudi Arabiaby the Science and Technology Research Programof Chongqing Municipal Education Commission(Grant No.KJQN202400813)by the Graduate Research Innovation Project(Grant Nos.yjscxx2025-269-193 and CYS25618).
文摘Medical image analysis based on deep learning has become an important technical requirement in the field of smart healthcare.In view of the difficulties in collaborative modeling of local details and global features in multimodal image analysis of ophthalmology,as well as the existence of information redundancy in cross-modal data fusion,this paper proposes amultimodal fusion framework based on cross-modal collaboration and weighted attention mechanism.In terms of feature extraction,the framework collaboratively extracts local fine-grained features and global structural dependencies through a parallel dual-branch architecture,overcoming the limitations of traditional single-modality models in capturing either local or global information;in terms of fusion strategy,the framework innovatively designs a cross-modal dynamic fusion strategy,combining overlappingmulti-head self-attention modules with a bidirectional feature alignment mechanism,addressing the bottlenecks of low feature interaction efficiency and excessive attention fusion computations in traditional parallel fusion,and further introduces cross-domain local integration technology,which enhances the representation ability of the lesion area through pixel-level feature recalibration and optimizes the diagnostic robustness of complex cases.Experiments show that the framework exhibits excellent feature expression and generalization performance in cross-domain scenarios of ophthalmic medical images and natural images,providing a high-precision,low-redundancy fusion paradigm for multimodal medical image analysis,and promoting the upgrade of intelligent diagnosis and treatment fromsingle-modal static analysis to dynamic decision-making.
文摘Deep Learning-based systems for Finger vein recognition have gained rising attention in recent years due to improved efficiency and enhanced security.The performance of existing CNN-based methods is limited by the puny generalization of learned features and deficiency of the finger vein image training data.Considering the concerns of existing methods,in this work,a simplified deep transfer learning-based framework for finger-vein recognition is developed using an EfficientNet model of deep learning with a self-attention mechanism.Data augmentation using various geometrical methods is employed to address the problem of training data shortage required for a deep learning model.The proposed model is tested using K-fold cross-validation on three publicly available datasets:HKPU,FVUSM,and SDUMLA.Also,the developed network is compared with other modern deep nets to check its effectiveness.In addition,a comparison of the proposed method with other existing Finger vein recognition(FVR)methods is also done.The experimental results exhibited superior recognition accuracy of the proposed method compared to other existing methods.In addition,the developed method proves to be more effective and less sophisticated at extracting robust features.The proposed EffAttenNet achieves an accuracy of 98.14%on HKPU,99.03%on FVUSM,and 99.50%on SDUMLA databases.
基金supported by National Natural Science Foundation of China(Nos.61261016,61661025)Science and Technology Plan of Gansu Province(No.20JR10RA273).
文摘For image compression sensing reconstruction,most algorithms use the method of reconstructing image blocks one by one and stacking many convolutional layers,which usually have defects of obvious block effects,high computational complexity,and long reconstruction time.An image compressed sensing reconstruction network based on self-attention mechanism(SAMNet)was proposed.For the compressed sampling,self-attention convolution was designed,which was conducive to capturing richer features,so that the compressed sensing measurement value retained more image structure information.For the reconstruction,a self-attention mechanism was introduced in the convolutional neural network.A reconstruction network including residual blocks,bottleneck transformer(BoTNet),and dense blocks was proposed,which strengthened the transfer of image features and reduced the amount of parameters dramatically.Under the Set5 dataset,when the measurement rates are 0.01,0.04,0.10,and 0.25,the average peak signal-to-noise ratio(PSNR)of SAMNet is improved by 1.27,1.23,0.50,and 0.15 dB,respectively,compared to the CSNet+.The running time of reconstructing a 256×256 image is reduced by 0.1473,0.1789,0.2310,and 0.2524 s compared to ReconNet.Experimental results showed that SAMNet improved the quality of reconstructed images and reduced the reconstruction time.
基金supported by the National Key Research and Development Program of China(2020YFC2200901)。
文摘As the complexity of scientific satellite missions increases,the requirements for their magnetic fields,magnetic field fluctuations,and even magnetic field gradients and variations become increasingly stringent.Additionally,there is a growing need to address the alternating magnetic fields produced by the spacecraft itself.This paper introduces a novel modeling method for spacecraft magnetic dipoles using an integrated self-attention mechanism and a transformer combined with Kolmogorov-Arnold Networks.The self-attention mechanism captures correlations among globally sparse data,establishing dependencies b.etween sparse magnetometer readings.Concurrently,the Kolmogorov-Arnold Network,proficient in modeling implicit numerical relationships between data features,enhances the ability to learn subtle patterns.Comparative experiments validate the capability of the proposed method to precisely model magnetic dipoles,achieving maximum Root Mean Square Errors of 24.06 mA·m^(2)and 0.32 cm for size and location modeling,respectively.The spacecraft magnetic model established using this method accurately computes magnetic fields and alternating magnetic fields at designated surfaces or points.This approach facilitates the rapid and precise construction of individual and complete spacecraft magnetic models,enabling the verification of magnetic specifications from the spacecraft design phase.
文摘The development of deep learning has made non-biochemical methods for molecular property prediction screening a reality,which can increase the experimental speed and reduce the experimental cost of relevant experiments.There are currently two main approaches to representing molecules:(a)representing molecules by fixing molecular descriptors,and(b)representing molecules by graph convolutional neural networks.Currently,both of these Representative methods have achieved some results in their respective experiments.Based on past efforts,we propose a Dual Self-attention Fusion Message Neural Network(DSFMNN).DSFMNN uses a combination of dual self-attention mechanism and graph convolutional neural network.Advantages of DSFMNN:(1)The dual self-attention mechanism focuses not only on the relationship between individual subunits in a molecule but also on the relationship between the atoms and chemical bonds contained in each subunit.(2)On the directed molecular graph,a message delivery approach centered on directed molecular bonds is used.We test the performance of the model on eight publicly available datasets and compare the performance with several models.Based on the current experimental results,DSFMNN has superior performance compared to previous models on the datasets applied in this paper.
基金supported by the National Key R&D Program of China(No.2022YFB4301102).
文摘Currently,most trains are equipped with dedicated cameras for capturing pantograph videos.Pantographs are core to the high-speed-railway pantograph-catenary system,and their failure directly affects the normal operation of high-speed trains.However,given the complex and variable real-world operational conditions of high-speed railways,there is no real-time and robust pantograph fault-detection method capable of handling large volumes of surveillance video.Hence,it is of paramount importance to maintain real-time monitoring and analysis of pantographs.Our study presents a real-time intelligent detection technology for identifying faults in high-speed railway pantographs,utilizing a fusion of self-attention and convolution features.We delved into lightweight multi-scale feature-extraction and fault-detection models based on deep learning to detect pantograph anomalies.Compared with traditional methods,this approach achieves high recall and accuracy in pantograph recognition,accurately pinpointing issues like discharge sparks,pantograph horns,and carbon pantograph-slide malfunctions.After experimentation and validation with actual surveillance videos of electric multiple-unit train,our algorithmic model demonstrates real-time,high-accuracy performance even under complex operational conditions.
基金financially supported by the Key Fund of Tianjin Natural Science Foundation,China Project of Tianjin Natural Science Foundation(24JCZDJC00510)the National Natural Science Foundation of China,China(22475147)the Fundamental Research Funds for the Central Universities,China。
文摘The fabrication of efficient and stable flexible perovskite solar modules(F-PSMs)using poly[bis(4-phenyl)(2,4,6-trimethylphenyl)amine](PTAA)remains a significant challenge due to its hydrophobic properties and the mismatch in interface energy-level alignment.Here,we introduced[2-(3,6-dimethoxy-9H-carba zol-9-yl)ethyl]phosphonic acid(MeO-2PACz)to modify the PTAA layer,which effectively suppressed surface potential fluctuations and aligned energy levels at the interface of PTAA/perovskite.Additionally,MeO-2PACz enhanced the hydrophilicity of PTAA,facilitating the fabrication of dense,uniform,and pinhole-free perovskite films on large-area flexible substrates.As a result,we achieved an F-PSM with a power conversion efficiency(PCE)of 16.6% and an aperture area of 64 cm^(2),which is the highest reported value among F-PSMs with an active area exceeding 35 cm^(2)based on PTAA.Moreover,the encapsulated module demonstrated outstanding long-term operational stability,retaining 90.2% of its initial efficiency after 1000 bending cycles(5 mm radius),87.2% after 1000 h of continuous illumination,and 80.3% under combined thermal and humid conditions(85℃ and 85% relative humidity),representing one of the most stable F-PSMs reported to date.
