In this paper,an image processing algorithm which is able to synthesize material textures of arbitrary shapes is proposed.The presented approach uses an arbitrary image to construct a structure layer of the material.T...In this paper,an image processing algorithm which is able to synthesize material textures of arbitrary shapes is proposed.The presented approach uses an arbitrary image to construct a structure layer of the material.The resulting structure layer is then used to constrain the material texture synthesis.The field of second-moment matrices is used to represent the structure layer.Many tests with various constraint images are conducted to ensure that the proposed approach accurately reproduces the visual aspects of the input material sample.The results demonstrate that the proposed algorithm is able to accurately synthesize arbitrary-shaped material textures while respecting the local characteristics of the exemplar.This paves the way toward the synthesis of 3D material textures of arbitrary shapes from 2D material samples,which has a wide application range in virtual material design and materials characterization.展开更多
Three-dimensional printing(3DP)offers valuable insight into the characterization of natural rocks and the verification of theoretical models due to its high reproducibility and accurate replication of complex defects ...Three-dimensional printing(3DP)offers valuable insight into the characterization of natural rocks and the verification of theoretical models due to its high reproducibility and accurate replication of complex defects such as cracks and pores.In this study,3DP gypsum samples with different printing directions were subjected to a series of uniaxial compression tests with in situ micro-computed tomography(micro-CT)scanning to quantitatively investigate their mechanical anisotropic properties and damage evolution characteristics.Based on the two-dimensional(2D)CT images obtained at different scanning steps,a novel void ratio variable was derived using the mean value and variance of CT intensity.Additionally,a constitutive model was formulated incorporating the proposed damage variable,utilizing the void ratio variable.The crack evolution and crack morphology of 3DP gypsum samples were obtained and analyzed using the 3D models reconstructed from the CT images.The results indicate that 3DP gypsum samples exhibit mechanical anisotropic characteristics similar to those found in naturally sedimentary rocks.The mechanical anisotropy is attributed to the bedding planes formed between adjacent layers and pillar-like structures along the printing direction formed by CaSO_(4)·2H_(2)O crystals of needle-like morphology.The mean gray intensity of the voids has a positive linear relationship with the threshold value,while the CT variance and void ratio have concave and convex relationships,respectively.The constitutive model can effectively match the stress–strain curves obtained from uniaxial compression experiments.This study provides comprehensive explanations of the failure modes and anisotropic mechanisms of 3DP gypsum samples,which is important for characterizing and understanding the failure mechanism and microstructural evolution of 3DP rocks when modeling natural rock behavior.展开更多
How to use a few defect samples to complete the defect classification is a key challenge in the production of mobile phone screens.An attention-relation network for the mobile phone screen defect classification is pro...How to use a few defect samples to complete the defect classification is a key challenge in the production of mobile phone screens.An attention-relation network for the mobile phone screen defect classification is proposed in this paper.The architecture of the attention-relation network contains two modules:a feature extract module and a feature metric module.Different from other few-shot models,an attention mechanism is applied to metric learning in our model to measure the distance between features,so as to pay attention to the correlation between features and suppress unwanted information.Besides,we combine dilated convolution and skip connection to extract more feature information for follow-up processing.We validate attention-relation network on the mobile phone screen defect dataset.The experimental results show that the classification accuracy of the attentionrelation network is 0.9486 under the 5-way 1-shot training strategy and 0.9039 under the 5-way 5-shot setting.It achieves the excellent effect of classification for mobile phone screen defects and outperforms with dominant advantages.展开更多
The encapsulation of lunar samples is a core research area in the third phase of the Chinese Lunar Exploration Program.The seal assembly,opening and closing mechanism(OCM),and locking mechanism are the core components...The encapsulation of lunar samples is a core research area in the third phase of the Chinese Lunar Exploration Program.The seal assembly,opening and closing mechanism(OCM),and locking mechanism are the core components of the encapsulation device of the lunar samples,and the requirements of a tight seal,lightweight,and low power make the design of these core components difficult.In this study,a combined sealing assembly,OCM,and locking mechanism were investigated for the device.The sealing architecture consists of rubber and an Ag-In alloy,and a theory was built to analyze the seal.Experiments of the electroplate Au coating on the knife-edge revealed that the hermetic seal can be significantly improved.The driving principle for coaxial double-helical pairs was investigated and used to design the OCM.Moreover,a locking mechanism was created using an electric initiating explosive device with orifice damping.By optimizing the design,the output parameters were adjusted to meet the requirements of the lunar explorer.The experimental results showed that the helium leak rate of the test pieces were not more than 5×10^(-11) Pa·m^(3)·s^(-1),the minimum power of the OCM was 0.3 W,and the total weight of the principle prototype was 2.9 kg.The explosive driven locking mechanism has low impact.This investigation solved the difficulties in achieving tight seal,light weight,and low power for the lunar explorer,and the results can also be used to explore other extraterrestrial objects in the future.展开更多
Objective To evaluate the diagnostic value of histopathological examination of ultrasound-guided puncture biopsy samples in extrapulmonary tuberculosis(EPTB).Methods This study was conducted at the Shanghai Public Hea...Objective To evaluate the diagnostic value of histopathological examination of ultrasound-guided puncture biopsy samples in extrapulmonary tuberculosis(EPTB).Methods This study was conducted at the Shanghai Public Health Clinical Center.A total of 115patients underwent ultrasound-guided puncture biopsy,followed by MGIT 960 culture(culture),smear,Gene Xpert MTB/RIF(Xpert),and histopathological examination.These assays were performed to evaluate their effectiveness in diagnosing EPTB in comparison to two different diagnostic criteria:liquid culture and composite reference standard(CRS).Results When CRS was used as the reference standard,the sensitivity and specificity of culture,smear,Xpert,and histopathological examination were(44.83%,89.29%),(51.72%,89.29%),(70.11%,96.43%),and(85.06%,82.14%),respectively.Based on liquid culture tests,the sensitivity and specificity of smear,Xpert,and pathological examination were(66.67%,72.60%),(83.33%,63.01%),and(92.86%,45.21%),respectively.Histopathological examination showed the highest sensitivity but lowest specificity.Further,we found that the combination of Xpert and histopathological examination showed a sensitivity of 90.80%and a specificity of 89.29%.Conclusion Ultrasound-guided puncture sampling is safe and effective for the diagnosis of EPTB.Compared with culture,smear,and Xpert,histopathological examination showed higher sensitivity but lower specificity.The combination of histopathology with Xpert showed the best performance characteristics.展开更多
Perovskite solar cells(PsCs)have developed tremendously over the past decade.However,the key factors influencing the power conversion efficiency(PCE)of PSCs remain incompletely understood,due to the complexity and cou...Perovskite solar cells(PsCs)have developed tremendously over the past decade.However,the key factors influencing the power conversion efficiency(PCE)of PSCs remain incompletely understood,due to the complexity and coupling of these structural and compositional parameters.In this research,we demon-strate an effective approach to optimize PSCs performance via machine learning(ML).To address chal-lenges posed by limited samples,we propose a feature mask(FM)method,which augments training samples through feature transformation rather than synthetic data.Using this approach,squeeze-and-excitation residual network(SEResNet)model achieves an accuracy with a root-mean-square-error(RMSE)of 0.833%and a Pearson's correlation coefficient(r)of 0.980.Furthermore,we employ the permu-tation importance(PI)algorithm to investigate key features for PCE.Subsequently,we predict PCE through high-throughput screenings,in which we study the relationship between PCE and chemical com-positions.After that,we conduct experiments to validate the consistency between predicted results by ML and experimental results.In this work,ML demonstrates the capability to predict device performance,extract key parameters from complex systems,and accelerate the transition from laboratory findings to commercialapplications.展开更多
Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersp...Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersphere boundary only describes the distribution of unlabeled samples,while the distribution of faulty samples cannot be effectively described and easilymisses detecting faulty data due to the imbalance of sample distribution.Meanwhile,selecting parameters is critical to the detection performance,and empirical parameterization is generally timeconsuming and laborious and may not result in finding the optimal parameters.Therefore,this paper proposes a semi-supervised data-driven method based on which the SVDD algorithm is improved and achieves excellent fault detection performance.By incorporating faulty samples into the underlying SVDD model,training deals better with the problem of missing detection of faulty samples caused by the imbalance in the distribution of abnormal samples,and the hypersphere boundary ismodified to classify the samplesmore accurately.The Bayesian Optimization NSVDD(BO-NSVDD)model was constructed to quickly and accurately optimize hyperparameter combinations.In the experiments,electric vehicle operation data with four common fault types are used to evaluate the performance with other five models,and the results show that the BO-NSVDD model presents superior detection performance for each type of fault data,especially in the imperceptible early and minor faults,which has seen very obvious advantages.Finally,the strong robustness of the proposed method is verified by adding different intensities of noise in the dataset.展开更多
The deep mining of coal resources is accompanied by severe environmental challenges and various potential engineering hazards.The implementation of NPR(negative Poisson's ratio)bolts are capable of controlling lar...The deep mining of coal resources is accompanied by severe environmental challenges and various potential engineering hazards.The implementation of NPR(negative Poisson's ratio)bolts are capable of controlling large deformations in the surrounding rock effectively.This paper focuses on studying the mechanical properties of the NPR bolt under static disturbance load.The deep nonlinear mechanical experimental system was used to study the mechanical behavior of rock samples with different anchored types(unanchored/PR anchored/2G NPR anchored)under static disturbance load.The whole process of rock samples was taken by high-speed camera to obtain the real-time failure characteristics under static disturbance load.At the same time,the acoustic emission signal was collected to obtain the key characteristic parameters of acoustic emission such as acoustic emission count,energy,and frequency.The deformation at the failure of the samples was calculated and analyzed by digital speckle software.The findings indicate that the failure mode of rock is influenced by different types of anchoring.The peak failure strength of 2G NPR bolt anchored rock samples exhibits an increase of 6.5%when compared to the unanchored rock samples.The cumulative count and cumulative energy of acoustic emission exhibit a decrease of 62.16%and 62.90%,respectively.The maximum deformation of bearing capacity exhibits an increase of 59.27%,while the failure time demonstrates a delay of 42.86%.The peak failure strength of the 2G NPR bolt anchored ones under static disturbance load exhibits an increase of 5.94%when compared to the rock anchored by PR(Poisson's ratio)bolt.The cumulative count and cumulative energy of acoustic emission exhibit a decrease of 47.16%and 43.86%,respectively.The maximum deformation of the bearing capacity exhibits an increase of 50.43%,and the failure time demonstrates a delay of 32%.After anchoring by 2G NPR bolt,anchoring support effectively reduces the risk of damage caused by static disturbance load.These results demonstrate that the support effect of 2G NPR bolt materials surpasses that of PR bolt.展开更多
Purpose This study introduces a methodology for correcting self-attenuation effects in γ-ray energy range 59 to 2614 keV.Methods Using simulation techniques,we examine the impact of material characteristics on attenu...Purpose This study introduces a methodology for correcting self-attenuation effects in γ-ray energy range 59 to 2614 keV.Methods Using simulation techniques,we examine the impact of material characteristics on attenuation.A comparative analysis with a reference standard sample of identical geometry but differing matrix and density enables the estimation of correction factors.Peak efficiency calculations include various matrices,including that present in nuclear fuel cycle and environmental field with densities ranging from 1 to 2 g/cm^(3).Results Monte Carlo simulations are employed to calculate peak efficiencies for epoxy reference materials within the same density and energy range.The self-attenuation correction factor is obtained by comparing the peak efficiencies of the assayed materials with those of the reference samples.The study discusses factors influencing self-attenuation correction,emphasizing its significance in accurate radionuclide measurements.Conclusion This method provides a standardized approach for calibrating and analyzing radionuclides in the materials present in the nuclear fuel cycle and environmental or NORM soil samples,detailing considerations for accurate measurement and correction of self-attenuation effects.展开更多
In the task of Facial Expression Recognition(FER),data uncertainty has been a critical factor affecting performance,typically arising from the ambiguity of facial expressions,low-quality images,and the subjectivity of...In the task of Facial Expression Recognition(FER),data uncertainty has been a critical factor affecting performance,typically arising from the ambiguity of facial expressions,low-quality images,and the subjectivity of annotators.Tracking the training history reveals that misclassified samples often exhibit high confidence and excessive uncertainty in the early stages of training.To address this issue,we propose an uncertainty-based robust sample selection strategy,which combines confidence error with RandAugment to improve image diversity,effectively reducing overfitting caused by uncertain samples during deep learning model training.To validate the effectiveness of the proposed method,extensive experiments were conducted on FER public benchmarks.The accuracy obtained were 89.08%on RAF-DB,63.12%on AffectNet,and 88.73%on FERPlus.展开更多
When dealing with imbalanced datasets,the traditional support vectormachine(SVM)tends to produce a classification hyperplane that is biased towards the majority class,which exhibits poor robustness.This paper proposes...When dealing with imbalanced datasets,the traditional support vectormachine(SVM)tends to produce a classification hyperplane that is biased towards the majority class,which exhibits poor robustness.This paper proposes a high-performance classification algorithm specifically designed for imbalanced datasets.The proposed method first uses a biased second-order cone programming support vectormachine(B-SOCP-SVM)to identify the support vectors(SVs)and non-support vectors(NSVs)in the imbalanced data.Then,it applies the synthetic minority over-sampling technique(SV-SMOTE)to oversample the support vectors of the minority class and uses the random under-sampling technique(NSV-RUS)multiple times to undersample the non-support vectors of the majority class.Combining the above-obtained minority class data set withmultiple majority class datasets can obtainmultiple new balanced data sets.Finally,SOCP-SVM is used to classify each data set,and the final result is obtained through the integrated algorithm.Experimental results demonstrate that the proposed method performs excellently on imbalanced datasets.展开更多
The sap flow method is widely used to estimate forest transpiration.However,at the individual tree level it has spatiotemporal variations due to the impacts of environmental conditions and spatial relationships among ...The sap flow method is widely used to estimate forest transpiration.However,at the individual tree level it has spatiotemporal variations due to the impacts of environmental conditions and spatial relationships among trees.Therefore,an in-depth understanding of the coupling effects of these factors is important for designing sap flow measurement methods and performing accurate assessments of stand scale transpiration.This study is based on observations of sap flux density(SF_(d))of nine sample trees with different Hegyi’s competition indices(HCIs),soil moisture,and meteorological conditions in a pure plantation of Larix gmelinii var.principis-rupprechtii during the 2021 growing season(May to September).A multifactorial model of sap flow was developed and possible errors in the stand scale sap flow estimates associated with sample sizes were determined using model-based predictions of sap flow.Temporal variations are controlled by vapour pressure deficit(VPD),solar radiation(R),and soil moisture,and these relationships can be described by polynomial or saturated exponential functions.Spatial(individual)differences were influenced by the HCI,as shown by the decaying power function.A simple SF_(d)model at the individual tree level was developed to describe the synergistic influences of VPD,R,soil moisture,and HCI.The coefficient of variations(CV)of the sap flow estimates gradually stabilized when the sample size was>10;at least six sample trees were needed if the CV was within 10%.This study improves understanding of the mechanisms of spatiotemporal variations in sap flow at the individual tree level and provides a new methodology for determining the optimal sample size for sap flow measurements.展开更多
Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,l...Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.展开更多
With the widespread use of blockchain technology for smart contracts and decentralized applications on the Ethereum platform, the blockchain has become a cornerstone of trust in the modern financial system. However, i...With the widespread use of blockchain technology for smart contracts and decentralized applications on the Ethereum platform, the blockchain has become a cornerstone of trust in the modern financial system. However, its anonymity has provided new ways for Ponzi schemes to commit fraud, posing significant risks to investors. Current research still has some limitations, for example, Ponzi schemes are difficult to detect in the early stages of smart contract deployment, and data imbalance is not considered. In addition, there is room for improving the detection accuracy. To address the above issues, this paper proposes LT-SPSD (LSTM-Transformer smart Ponzi schemes detection), which is a Ponzi scheme detection method that combines Long Short-Term Memory (LSTM) and Transformer considering the time-series transaction information of smart contracts as well as the global information. Based on the verified smart contract addresses, account features, and code features are extracted to construct a feature dataset, and the SMOTE-Tomek algorithm is used to deal with the imbalanced data classification problem. By comparing our method with the other four typical detection methods in the experiment, the LT-SPSD method shows significant performance improvement in precision, recall, and F1-score. The results of the experiment confirm the efficacy of the model, which has some application value in Ethereum Ponzi scheme smart contract detection.展开更多
Face Presentation Attack Detection(fPAD)plays a vital role in securing face recognition systems against various presentation attacks.While supervised learning-based methods demonstrate effectiveness,they are prone to ...Face Presentation Attack Detection(fPAD)plays a vital role in securing face recognition systems against various presentation attacks.While supervised learning-based methods demonstrate effectiveness,they are prone to overfitting to known attack types and struggle to generalize to novel attack scenarios.Recent studies have explored formulating fPAD as an anomaly detection problem or one-class classification task,enabling the training of generalized models for unknown attack detection.However,conventional anomaly detection approaches encounter difficulties in precisely delineating the boundary between bonafide samples and unknown attacks.To address this challenge,we propose a novel framework focusing on unknown attack detection using exclusively bonafide facial data during training.The core innovation lies in our pseudo-negative sample synthesis(PNSS)strategy,which facilitates learning of compact decision boundaries between bonafide faces and potential attack variations.Specifically,PNSS generates synthetic negative samples within low-likelihood regions of the bonafide feature space to represent diverse unknown attack patterns.To overcome the inherent imbalance between positive and synthetic negative samples during iterative training,we implement a dual-loss mechanism combining focal loss for classification optimization with pairwise confusion loss as a regularizer.This architecture effectively mitigates model bias towards bonafide samples while maintaining discriminative power.Comprehensive evaluations across three benchmark datasets validate the framework’s superior performance.Notably,our PNSS achieves 8%–18% average classification error rate(ACER)reduction compared with state-of-the-art one-class fPAD methods in cross-dataset evaluations on Idiap Replay-Attack and MSU-MFSD datasets.展开更多
Currently,the main idea of iterative rendering methods is to allocate a fixed number of samples to pixels that have not been fully rendered by calculating the completion rate.It is obvious that this strategy ignores t...Currently,the main idea of iterative rendering methods is to allocate a fixed number of samples to pixels that have not been fully rendered by calculating the completion rate.It is obvious that this strategy ignores the changes in pixel values during the previous rendering process,which may result in additional iterative operations.展开更多
1 Introduction Large language models(LLMs)have achieved remarkable progress in the field of natural language processing(NLP),showing impressive abilities to generate human-like texts for a broad range of tasks[1].Cons...1 Introduction Large language models(LLMs)have achieved remarkable progress in the field of natural language processing(NLP),showing impressive abilities to generate human-like texts for a broad range of tasks[1].Consequently,recent works start to investigate the application of LLMs in recommender systems.They adopt LLMs for various recommendation tasks,and show promising performance from different aspects(e.g.,user profiling).In this letter,we mainly focus on promoting the sample efficiency of recommender systems by involving large language models.展开更多
[Objective] This study aimed to compare the residue situation of cimaterol,a kind of forbidden veterinary drug in hair, urine and flesh of pig, so as to provide theoretical basis for monitoring veterinary drug residue...[Objective] This study aimed to compare the residue situation of cimaterol,a kind of forbidden veterinary drug in hair, urine and flesh of pig, so as to provide theoretical basis for monitoring veterinary drug residue in bred animals. [Method]Total three different concentrations of cimaterol were administered to pigs, and the residue amounts of cimaterol in pig hair, urine and flesh were monitored at different raising stage. [Result] During the administration period, the residue amount of cimaterol was highest in urine, so urine is the suitable sample for rapid detection of cimaterol in manufacturing enterprises. Cimaterol could be accumulated in pig hair,where cimaterol was metabolized slowly. Thus, pig hair can be used as the test sample for tracing illegal use of veterinary drugs and for vivo detection. Flesh can be used as test sample for direct judgment whether cimaterol residue exceeds the relevant standard. [Conclusion] This study will provide certain theoretical basis for drug monitor in animal husbandry.展开更多
Pt nanoparticles entrapped in ordered mesoporous CMK-3 carbons with p6mm symmetry were prepared using a facile impregnation method, and the resulting materials were characterized using X-ray diffraction spectroscopy, ...Pt nanoparticles entrapped in ordered mesoporous CMK-3 carbons with p6mm symmetry were prepared using a facile impregnation method, and the resulting materials were characterized using X-ray diffraction spectroscopy, N2 adsorption-desorption, scanning electron microscopy, transmission electron microscopy, energy dispersive X-ray spectroscopy, and X-ray photoelectron spectroscopy. The Pt nanoparticles were highly dispersed in the CMK-3 with 43.7% dispersion. The Pt/CMK-3 catalyst was an effective catalyst for the liquid-phase hydrogenation of nitrobenzene and its derivatives under the experimental conditions studied here. The Pt/CMK-3 catalyst was more active than commercial Pt/C catalyst in most cases. A highest turnover frequency of 43.8 s-1 was measured when the Pt/CMK-3 catalyst was applied for the hydrogenation of 2-methyl-nitrobenzene in ethanol under optimal conditions. It is worthy of note that the Pt/CMK-3 catalyst could be recycled easily, and could be reused at least fourteen times without any loss in activity or selectivity for the hydrogenation of nitrobenzene in ethanol.展开更多
Background Chronic obstructive pulmonary diseases （COPD） is an emerging population at risk for invasive infection of Aspergillus. Isolation of Aspergillus from lower respiratory tract （LRT） samples is important fo...Background Chronic obstructive pulmonary diseases （COPD） is an emerging population at risk for invasive infection of Aspergillus. Isolation of Aspergillus from lower respiratory tract （LRT） samples is important for the diagnosis of invasive pulmonary aspergillosis （IPA）. The purpose of this study was to investigate the value of Aspergillus isolation from LRT samples for the diagnosis and prognosis of IPA in COPD population. Methods Clinical record with Aspergillus spp. isolation in COPD and immunocompromised patients was reviewed in a retrospective study. Patients were categorized and compared according to their severity of illness （admitted to general ward or ICU） and immunological function （COPD or immunocompromised）. Results Multivariate statistical analysis showed that, combined with Aspergillus spp. isolation, APACHE II scores 〉18, high cumulative doses of corticosteroids （〉350 mg prednisone or equivalent dose） and more than four kinds of broad-spectrum antibiotics received in hospital may be predictors of IPA in COPD （0R=9.076, P=0.001; 0R=4.073, P=-0.026; OR=4.448, P=-0.021, respectively）. The incidence of IPA, overall mortality, mortality of patients with IPA and mortality of patients with Aspergillus spp. colonization were higher in COPD patients in ICU than in general ward, but were similar between COPD and immunocompromised patients. Conclusions Aspergillus spp. isolation from LRT in COPD may be of similar importance as in immunocompromised patients, and may indicate an increased diagnosis possibility of IPA and worse prognosis when these patients received corticosteroids, antibiotics, and need to admit to ICU. Aspergillus spp. isolation from LRT samples combined with certain risk factors mav be useful in differentiating colonization from IPA and evaluating the prognosis of IPA in COPD patients.展开更多
文摘In this paper,an image processing algorithm which is able to synthesize material textures of arbitrary shapes is proposed.The presented approach uses an arbitrary image to construct a structure layer of the material.The resulting structure layer is then used to constrain the material texture synthesis.The field of second-moment matrices is used to represent the structure layer.Many tests with various constraint images are conducted to ensure that the proposed approach accurately reproduces the visual aspects of the input material sample.The results demonstrate that the proposed algorithm is able to accurately synthesize arbitrary-shaped material textures while respecting the local characteristics of the exemplar.This paves the way toward the synthesis of 3D material textures of arbitrary shapes from 2D material samples,which has a wide application range in virtual material design and materials characterization.
基金supported by grants from the Human Resources Development program(Grant No.20204010600250)the Training Program of CCUS for the Green Growth(Grant No.20214000000500)by the Korea Institute of Energy Technology Evaluation and Planning(KETEP)funded by the Ministry of Trade,Industry,and Energy of the Korean Government(MOTIE).
文摘Three-dimensional printing(3DP)offers valuable insight into the characterization of natural rocks and the verification of theoretical models due to its high reproducibility and accurate replication of complex defects such as cracks and pores.In this study,3DP gypsum samples with different printing directions were subjected to a series of uniaxial compression tests with in situ micro-computed tomography(micro-CT)scanning to quantitatively investigate their mechanical anisotropic properties and damage evolution characteristics.Based on the two-dimensional(2D)CT images obtained at different scanning steps,a novel void ratio variable was derived using the mean value and variance of CT intensity.Additionally,a constitutive model was formulated incorporating the proposed damage variable,utilizing the void ratio variable.The crack evolution and crack morphology of 3DP gypsum samples were obtained and analyzed using the 3D models reconstructed from the CT images.The results indicate that 3DP gypsum samples exhibit mechanical anisotropic characteristics similar to those found in naturally sedimentary rocks.The mechanical anisotropy is attributed to the bedding planes formed between adjacent layers and pillar-like structures along the printing direction formed by CaSO_(4)·2H_(2)O crystals of needle-like morphology.The mean gray intensity of the voids has a positive linear relationship with the threshold value,while the CT variance and void ratio have concave and convex relationships,respectively.The constitutive model can effectively match the stress–strain curves obtained from uniaxial compression experiments.This study provides comprehensive explanations of the failure modes and anisotropic mechanisms of 3DP gypsum samples,which is important for characterizing and understanding the failure mechanism and microstructural evolution of 3DP rocks when modeling natural rock behavior.
文摘How to use a few defect samples to complete the defect classification is a key challenge in the production of mobile phone screens.An attention-relation network for the mobile phone screen defect classification is proposed in this paper.The architecture of the attention-relation network contains two modules:a feature extract module and a feature metric module.Different from other few-shot models,an attention mechanism is applied to metric learning in our model to measure the distance between features,so as to pay attention to the correlation between features and suppress unwanted information.Besides,we combine dilated convolution and skip connection to extract more feature information for follow-up processing.We validate attention-relation network on the mobile phone screen defect dataset.The experimental results show that the classification accuracy of the attentionrelation network is 0.9486 under the 5-way 1-shot training strategy and 0.9039 under the 5-way 5-shot setting.It achieves the excellent effect of classification for mobile phone screen defects and outperforms with dominant advantages.
基金Supported by Research Foundation of CLEP of China (Grant No.TY3Q20110003)。
文摘The encapsulation of lunar samples is a core research area in the third phase of the Chinese Lunar Exploration Program.The seal assembly,opening and closing mechanism(OCM),and locking mechanism are the core components of the encapsulation device of the lunar samples,and the requirements of a tight seal,lightweight,and low power make the design of these core components difficult.In this study,a combined sealing assembly,OCM,and locking mechanism were investigated for the device.The sealing architecture consists of rubber and an Ag-In alloy,and a theory was built to analyze the seal.Experiments of the electroplate Au coating on the knife-edge revealed that the hermetic seal can be significantly improved.The driving principle for coaxial double-helical pairs was investigated and used to design the OCM.Moreover,a locking mechanism was created using an electric initiating explosive device with orifice damping.By optimizing the design,the output parameters were adjusted to meet the requirements of the lunar explorer.The experimental results showed that the helium leak rate of the test pieces were not more than 5×10^(-11) Pa·m^(3)·s^(-1),the minimum power of the OCM was 0.3 W,and the total weight of the principle prototype was 2.9 kg.The explosive driven locking mechanism has low impact.This investigation solved the difficulties in achieving tight seal,light weight,and low power for the lunar explorer,and the results can also be used to explore other extraterrestrial objects in the future.
基金funded by the grants from the National Key Research and Development Program of China[2021YFC2301503,2022YFC2302900]the National Natural and Science Foundation of China[82171739,82171815,81873884]。
文摘Objective To evaluate the diagnostic value of histopathological examination of ultrasound-guided puncture biopsy samples in extrapulmonary tuberculosis(EPTB).Methods This study was conducted at the Shanghai Public Health Clinical Center.A total of 115patients underwent ultrasound-guided puncture biopsy,followed by MGIT 960 culture(culture),smear,Gene Xpert MTB/RIF(Xpert),and histopathological examination.These assays were performed to evaluate their effectiveness in diagnosing EPTB in comparison to two different diagnostic criteria:liquid culture and composite reference standard(CRS).Results When CRS was used as the reference standard,the sensitivity and specificity of culture,smear,Xpert,and histopathological examination were(44.83%,89.29%),(51.72%,89.29%),(70.11%,96.43%),and(85.06%,82.14%),respectively.Based on liquid culture tests,the sensitivity and specificity of smear,Xpert,and pathological examination were(66.67%,72.60%),(83.33%,63.01%),and(92.86%,45.21%),respectively.Histopathological examination showed the highest sensitivity but lowest specificity.Further,we found that the combination of Xpert and histopathological examination showed a sensitivity of 90.80%and a specificity of 89.29%.Conclusion Ultrasound-guided puncture sampling is safe and effective for the diagnosis of EPTB.Compared with culture,smear,and Xpert,histopathological examination showed higher sensitivity but lower specificity.The combination of histopathology with Xpert showed the best performance characteristics.
基金supported by the National Key Research and Development Program (2022YFF0609504)the National Natural Science Foundation of China (61974126,51902273,62005230,62001405)the Natural Science Foundation of Fujian Province of China (No.2021J06009)
文摘Perovskite solar cells(PsCs)have developed tremendously over the past decade.However,the key factors influencing the power conversion efficiency(PCE)of PSCs remain incompletely understood,due to the complexity and coupling of these structural and compositional parameters.In this research,we demon-strate an effective approach to optimize PSCs performance via machine learning(ML).To address chal-lenges posed by limited samples,we propose a feature mask(FM)method,which augments training samples through feature transformation rather than synthetic data.Using this approach,squeeze-and-excitation residual network(SEResNet)model achieves an accuracy with a root-mean-square-error(RMSE)of 0.833%and a Pearson's correlation coefficient(r)of 0.980.Furthermore,we employ the permu-tation importance(PI)algorithm to investigate key features for PCE.Subsequently,we predict PCE through high-throughput screenings,in which we study the relationship between PCE and chemical com-positions.After that,we conduct experiments to validate the consistency between predicted results by ML and experimental results.In this work,ML demonstrates the capability to predict device performance,extract key parameters from complex systems,and accelerate the transition from laboratory findings to commercialapplications.
基金supported partially by NationalNatural Science Foundation of China(NSFC)(No.U21A20146)Collaborative Innovation Project of Anhui Universities(No.GXXT-2020-070)+8 种基金Cooperation Project of Anhui Future Technology Research Institute and Enterprise(No.2023qyhz32)Development of a New Dynamic Life Prediction Technology for Energy Storage Batteries(No.KH10003598)Opening Project of Key Laboratory of Electric Drive and Control of Anhui Province(No.DQKJ202304)Anhui Provincial Department of Education New Era Education Quality Project(No.2023dshwyx019)Special Fund for Collaborative Innovation between Anhui Polytechnic University and Jiujiang District(No.2022cyxtb10)Key Research and Development Program of Wuhu City(No.2022yf42)Open Research Fund of Anhui Key Laboratory of Detection Technology and Energy Saving Devices(No.JCKJ2021B06)Anhui Provincial Graduate Student Innovation and Entrepreneurship Practice Project(No.2022cxcysj123)Key Scientific Research Project for Anhui Universities(No.2022AH050981).
文摘Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersphere boundary only describes the distribution of unlabeled samples,while the distribution of faulty samples cannot be effectively described and easilymisses detecting faulty data due to the imbalance of sample distribution.Meanwhile,selecting parameters is critical to the detection performance,and empirical parameterization is generally timeconsuming and laborious and may not result in finding the optimal parameters.Therefore,this paper proposes a semi-supervised data-driven method based on which the SVDD algorithm is improved and achieves excellent fault detection performance.By incorporating faulty samples into the underlying SVDD model,training deals better with the problem of missing detection of faulty samples caused by the imbalance in the distribution of abnormal samples,and the hypersphere boundary ismodified to classify the samplesmore accurately.The Bayesian Optimization NSVDD(BO-NSVDD)model was constructed to quickly and accurately optimize hyperparameter combinations.In the experiments,electric vehicle operation data with four common fault types are used to evaluate the performance with other five models,and the results show that the BO-NSVDD model presents superior detection performance for each type of fault data,especially in the imperceptible early and minor faults,which has seen very obvious advantages.Finally,the strong robustness of the proposed method is verified by adding different intensities of noise in the dataset.
基金provided by the National Natural Science Foundation of China(52074300)the Program of China Scholarship Council(202206430024)+2 种基金the National Natural Science Foundation of China Youth Science(52104139)Yueqi Young Scholars Project of China University of Mining and Technology Beijing(2602021RC84)Guizhou province science and technology planning project([2020]3007,[2020]3008)。
文摘The deep mining of coal resources is accompanied by severe environmental challenges and various potential engineering hazards.The implementation of NPR(negative Poisson's ratio)bolts are capable of controlling large deformations in the surrounding rock effectively.This paper focuses on studying the mechanical properties of the NPR bolt under static disturbance load.The deep nonlinear mechanical experimental system was used to study the mechanical behavior of rock samples with different anchored types(unanchored/PR anchored/2G NPR anchored)under static disturbance load.The whole process of rock samples was taken by high-speed camera to obtain the real-time failure characteristics under static disturbance load.At the same time,the acoustic emission signal was collected to obtain the key characteristic parameters of acoustic emission such as acoustic emission count,energy,and frequency.The deformation at the failure of the samples was calculated and analyzed by digital speckle software.The findings indicate that the failure mode of rock is influenced by different types of anchoring.The peak failure strength of 2G NPR bolt anchored rock samples exhibits an increase of 6.5%when compared to the unanchored rock samples.The cumulative count and cumulative energy of acoustic emission exhibit a decrease of 62.16%and 62.90%,respectively.The maximum deformation of bearing capacity exhibits an increase of 59.27%,while the failure time demonstrates a delay of 42.86%.The peak failure strength of the 2G NPR bolt anchored ones under static disturbance load exhibits an increase of 5.94%when compared to the rock anchored by PR(Poisson's ratio)bolt.The cumulative count and cumulative energy of acoustic emission exhibit a decrease of 47.16%and 43.86%,respectively.The maximum deformation of the bearing capacity exhibits an increase of 50.43%,and the failure time demonstrates a delay of 32%.After anchoring by 2G NPR bolt,anchoring support effectively reduces the risk of damage caused by static disturbance load.These results demonstrate that the support effect of 2G NPR bolt materials surpasses that of PR bolt.
文摘Purpose This study introduces a methodology for correcting self-attenuation effects in γ-ray energy range 59 to 2614 keV.Methods Using simulation techniques,we examine the impact of material characteristics on attenuation.A comparative analysis with a reference standard sample of identical geometry but differing matrix and density enables the estimation of correction factors.Peak efficiency calculations include various matrices,including that present in nuclear fuel cycle and environmental field with densities ranging from 1 to 2 g/cm^(3).Results Monte Carlo simulations are employed to calculate peak efficiencies for epoxy reference materials within the same density and energy range.The self-attenuation correction factor is obtained by comparing the peak efficiencies of the assayed materials with those of the reference samples.The study discusses factors influencing self-attenuation correction,emphasizing its significance in accurate radionuclide measurements.Conclusion This method provides a standardized approach for calibrating and analyzing radionuclides in the materials present in the nuclear fuel cycle and environmental or NORM soil samples,detailing considerations for accurate measurement and correction of self-attenuation effects.
文摘In the task of Facial Expression Recognition(FER),data uncertainty has been a critical factor affecting performance,typically arising from the ambiguity of facial expressions,low-quality images,and the subjectivity of annotators.Tracking the training history reveals that misclassified samples often exhibit high confidence and excessive uncertainty in the early stages of training.To address this issue,we propose an uncertainty-based robust sample selection strategy,which combines confidence error with RandAugment to improve image diversity,effectively reducing overfitting caused by uncertain samples during deep learning model training.To validate the effectiveness of the proposed method,extensive experiments were conducted on FER public benchmarks.The accuracy obtained were 89.08%on RAF-DB,63.12%on AffectNet,and 88.73%on FERPlus.
基金supported by the Natural Science Basic Research Program of Shaanxi(Program No.2024JC-YBMS-026).
文摘When dealing with imbalanced datasets,the traditional support vectormachine(SVM)tends to produce a classification hyperplane that is biased towards the majority class,which exhibits poor robustness.This paper proposes a high-performance classification algorithm specifically designed for imbalanced datasets.The proposed method first uses a biased second-order cone programming support vectormachine(B-SOCP-SVM)to identify the support vectors(SVs)and non-support vectors(NSVs)in the imbalanced data.Then,it applies the synthetic minority over-sampling technique(SV-SMOTE)to oversample the support vectors of the minority class and uses the random under-sampling technique(NSV-RUS)multiple times to undersample the non-support vectors of the majority class.Combining the above-obtained minority class data set withmultiple majority class datasets can obtainmultiple new balanced data sets.Finally,SOCP-SVM is used to classify each data set,and the final result is obtained through the integrated algorithm.Experimental results demonstrate that the proposed method performs excellently on imbalanced datasets.
基金supported by the Fundamental Research Funds of the Chinese Academy of Forestry(CAFYBB2020QB004)the National Natural Science Foundation of China(41971038,32171559,U20A2085,and U21A2005).
文摘The sap flow method is widely used to estimate forest transpiration.However,at the individual tree level it has spatiotemporal variations due to the impacts of environmental conditions and spatial relationships among trees.Therefore,an in-depth understanding of the coupling effects of these factors is important for designing sap flow measurement methods and performing accurate assessments of stand scale transpiration.This study is based on observations of sap flux density(SF_(d))of nine sample trees with different Hegyi’s competition indices(HCIs),soil moisture,and meteorological conditions in a pure plantation of Larix gmelinii var.principis-rupprechtii during the 2021 growing season(May to September).A multifactorial model of sap flow was developed and possible errors in the stand scale sap flow estimates associated with sample sizes were determined using model-based predictions of sap flow.Temporal variations are controlled by vapour pressure deficit(VPD),solar radiation(R),and soil moisture,and these relationships can be described by polynomial or saturated exponential functions.Spatial(individual)differences were influenced by the HCI,as shown by the decaying power function.A simple SF_(d)model at the individual tree level was developed to describe the synergistic influences of VPD,R,soil moisture,and HCI.The coefficient of variations(CV)of the sap flow estimates gradually stabilized when the sample size was>10;at least six sample trees were needed if the CV was within 10%.This study improves understanding of the mechanisms of spatiotemporal variations in sap flow at the individual tree level and provides a new methodology for determining the optimal sample size for sap flow measurements.
基金sponsored by the National Natural Science Foundation of China Grant No.62271302the Shanghai Municipal Natural Science Foundation Grant 20ZR1423500.
文摘Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.
基金This work was granted by Qin Xin Talents Cultivation Program(No.QXTCP C202115)Beijing Information Science and Technology University+1 种基金the Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Fund(No.GJJ-23)National Social Science Foundation,China(No.21BTQ079).
文摘With the widespread use of blockchain technology for smart contracts and decentralized applications on the Ethereum platform, the blockchain has become a cornerstone of trust in the modern financial system. However, its anonymity has provided new ways for Ponzi schemes to commit fraud, posing significant risks to investors. Current research still has some limitations, for example, Ponzi schemes are difficult to detect in the early stages of smart contract deployment, and data imbalance is not considered. In addition, there is room for improving the detection accuracy. To address the above issues, this paper proposes LT-SPSD (LSTM-Transformer smart Ponzi schemes detection), which is a Ponzi scheme detection method that combines Long Short-Term Memory (LSTM) and Transformer considering the time-series transaction information of smart contracts as well as the global information. Based on the verified smart contract addresses, account features, and code features are extracted to construct a feature dataset, and the SMOTE-Tomek algorithm is used to deal with the imbalanced data classification problem. By comparing our method with the other four typical detection methods in the experiment, the LT-SPSD method shows significant performance improvement in precision, recall, and F1-score. The results of the experiment confirm the efficacy of the model, which has some application value in Ethereum Ponzi scheme smart contract detection.
基金supported in part by the National Natural Science Foundation of China under Grants 61972267,and 61772070in part by the Natural Science Foundation of Hebei Province under Grant F2024210005.
文摘Face Presentation Attack Detection(fPAD)plays a vital role in securing face recognition systems against various presentation attacks.While supervised learning-based methods demonstrate effectiveness,they are prone to overfitting to known attack types and struggle to generalize to novel attack scenarios.Recent studies have explored formulating fPAD as an anomaly detection problem or one-class classification task,enabling the training of generalized models for unknown attack detection.However,conventional anomaly detection approaches encounter difficulties in precisely delineating the boundary between bonafide samples and unknown attacks.To address this challenge,we propose a novel framework focusing on unknown attack detection using exclusively bonafide facial data during training.The core innovation lies in our pseudo-negative sample synthesis(PNSS)strategy,which facilitates learning of compact decision boundaries between bonafide faces and potential attack variations.Specifically,PNSS generates synthetic negative samples within low-likelihood regions of the bonafide feature space to represent diverse unknown attack patterns.To overcome the inherent imbalance between positive and synthetic negative samples during iterative training,we implement a dual-loss mechanism combining focal loss for classification optimization with pairwise confusion loss as a regularizer.This architecture effectively mitigates model bias towards bonafide samples while maintaining discriminative power.Comprehensive evaluations across three benchmark datasets validate the framework’s superior performance.Notably,our PNSS achieves 8%–18% average classification error rate(ACER)reduction compared with state-of-the-art one-class fPAD methods in cross-dataset evaluations on Idiap Replay-Attack and MSU-MFSD datasets.
基金supported partially by the National Natural Science Foundation of China(No.U19A2063)the Jilin Provincial Science&Technology Development Program of China(No.20230201080GX)。
文摘Currently,the main idea of iterative rendering methods is to allocate a fixed number of samples to pixels that have not been fully rendered by calculating the completion rate.It is obvious that this strategy ignores the changes in pixel values during the previous rendering process,which may result in additional iterative operations.
基金supported by the National Natural Science Foundation of China(Grant No.62177033).
文摘1 Introduction Large language models(LLMs)have achieved remarkable progress in the field of natural language processing(NLP),showing impressive abilities to generate human-like texts for a broad range of tasks[1].Consequently,recent works start to investigate the application of LLMs in recommender systems.They adopt LLMs for various recommendation tasks,and show promising performance from different aspects(e.g.,user profiling).In this letter,we mainly focus on promoting the sample efficiency of recommender systems by involving large language models.
基金Supported by Key Science and Technology Program(GKZ1222003-2-2)~~
文摘[Objective] This study aimed to compare the residue situation of cimaterol,a kind of forbidden veterinary drug in hair, urine and flesh of pig, so as to provide theoretical basis for monitoring veterinary drug residue in bred animals. [Method]Total three different concentrations of cimaterol were administered to pigs, and the residue amounts of cimaterol in pig hair, urine and flesh were monitored at different raising stage. [Result] During the administration period, the residue amount of cimaterol was highest in urine, so urine is the suitable sample for rapid detection of cimaterol in manufacturing enterprises. Cimaterol could be accumulated in pig hair,where cimaterol was metabolized slowly. Thus, pig hair can be used as the test sample for tracing illegal use of veterinary drugs and for vivo detection. Flesh can be used as test sample for direct judgment whether cimaterol residue exceeds the relevant standard. [Conclusion] This study will provide certain theoretical basis for drug monitor in animal husbandry.
基金supported by the National Natural Science Foundation of China(21273076 and 21373089)the Open Research Fund of Top Key Discipline of Chemistry in Zhejiang Provincial Colleges and Key Laboratory of the Ministry of Education for Catalysis Materials(Zhejiang Normal University,ZJHX2013)Shanghai Leading Academic Discipline Project (B409)~~
文摘Pt nanoparticles entrapped in ordered mesoporous CMK-3 carbons with p6mm symmetry were prepared using a facile impregnation method, and the resulting materials were characterized using X-ray diffraction spectroscopy, N2 adsorption-desorption, scanning electron microscopy, transmission electron microscopy, energy dispersive X-ray spectroscopy, and X-ray photoelectron spectroscopy. The Pt nanoparticles were highly dispersed in the CMK-3 with 43.7% dispersion. The Pt/CMK-3 catalyst was an effective catalyst for the liquid-phase hydrogenation of nitrobenzene and its derivatives under the experimental conditions studied here. The Pt/CMK-3 catalyst was more active than commercial Pt/C catalyst in most cases. A highest turnover frequency of 43.8 s-1 was measured when the Pt/CMK-3 catalyst was applied for the hydrogenation of 2-methyl-nitrobenzene in ethanol under optimal conditions. It is worthy of note that the Pt/CMK-3 catalyst could be recycled easily, and could be reused at least fourteen times without any loss in activity or selectivity for the hydrogenation of nitrobenzene in ethanol.
文摘Background Chronic obstructive pulmonary diseases （COPD） is an emerging population at risk for invasive infection of Aspergillus. Isolation of Aspergillus from lower respiratory tract （LRT） samples is important for the diagnosis of invasive pulmonary aspergillosis （IPA）. The purpose of this study was to investigate the value of Aspergillus isolation from LRT samples for the diagnosis and prognosis of IPA in COPD population. Methods Clinical record with Aspergillus spp. isolation in COPD and immunocompromised patients was reviewed in a retrospective study. Patients were categorized and compared according to their severity of illness （admitted to general ward or ICU） and immunological function （COPD or immunocompromised）. Results Multivariate statistical analysis showed that, combined with Aspergillus spp. isolation, APACHE II scores 〉18, high cumulative doses of corticosteroids （〉350 mg prednisone or equivalent dose） and more than four kinds of broad-spectrum antibiotics received in hospital may be predictors of IPA in COPD （0R=9.076, P=0.001; 0R=4.073, P=-0.026; OR=4.448, P=-0.021, respectively）. The incidence of IPA, overall mortality, mortality of patients with IPA and mortality of patients with Aspergillus spp. colonization were higher in COPD patients in ICU than in general ward, but were similar between COPD and immunocompromised patients. Conclusions Aspergillus spp. isolation from LRT in COPD may be of similar importance as in immunocompromised patients, and may indicate an increased diagnosis possibility of IPA and worse prognosis when these patients received corticosteroids, antibiotics, and need to admit to ICU. Aspergillus spp. isolation from LRT samples combined with certain risk factors mav be useful in differentiating colonization from IPA and evaluating the prognosis of IPA in COPD patients.
