Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classificati...Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.展开更多
In this paper,the class of starlike functions of complex order γ(γ∈ℂ−{0})is extended from the case on unit disk U=(z∈C:|z|<1)to the case on the unit ball B in a complex Banach space or the unit polydisk U^(n) i...In this paper,the class of starlike functions of complex order γ(γ∈ℂ−{0})is extended from the case on unit disk U=(z∈C:|z|<1)to the case on the unit ball B in a complex Banach space or the unit polydisk U^(n) in C^(n).Let g be a convex function in U. We mainly establish the sharp bounds of all terms of homogeneous polynomial expansions for a subclass of g-parametric starlike mappings of complex order γ on B (resp.U^(n))when the mappings f are k-fold symmetric, k ∈ N. Our results partly solve the Bieberbach conjecture in several complex variables and generalize some prior works.展开更多
Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however...Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however,the predicted results have uncertainty in providing accurate informa-tion to users because of the“black box”problem in the deep learning model.Therefore,this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect identification.The visual repre-sentative gradient-weights class activation mapping(Grad-CAM)method is adopted to provide visually explainable information.A visualizing evaluation index is proposed to quantitatively analyze visual representations;this index reflects a rough estimate of the concordance rate between the visualized heat map and intended defects.In addition,an ablation study,adopting three-branch combinations with the VGG16,is implemented to identify perfor-mance variations by visualizing predicted results.Experiments reveal that the proposed model,combined with hybrid pooling,batch normalization,and multi-attention modules,achieves the best performance with an accuracy of 97.77%,corresponding to an improvement of 2.49%compared with the baseline model.Consequently,this study demonstrates that reliable results from an automatic defect classification model can be provided to an inspector through the visual representation of the predicted results using CNN models.展开更多
Mind map has been widely recognized as an effective teaching and learning tool in all levels of education. This paper, based on the writer’s teaching practice, aimed to investigate the potential use of mind map in En...Mind map has been widely recognized as an effective teaching and learning tool in all levels of education. This paper, based on the writer’s teaching practice, aimed to investigate the potential use of mind map in English intensive reading classes of college students, and found that it could help students to understand and memorize the main ideas and important details of reading materials in a systematical way.展开更多
In this paper, a modified implicit Kirk-multistep iteration scheme and a strong convergence result for a general class of maps in a normed linear space was established. It was also shown that the convergence of this i...In this paper, a modified implicit Kirk-multistep iteration scheme and a strong convergence result for a general class of maps in a normed linear space was established. It was also shown that the convergence of this iteration scheme is equivalent to the convergency of some other implicit Kirk-type iteration (implicit Kirk-Noor, implicit Kirk-Ishikawa and implicit Kirk-Mann iterations) for the same class of maps. Some numerical examples were considered to show that the equivalence of convergence results to the fixed point is true. The results unify most equivalence results in literature.展开更多
On April 28,2023,the Map Museum of Zhengzhou University was officially opened in the historical Central Plains of China.The museum was founded by Mr.GAO Jun,Distinguished Academician of the Chinese Academy of Sciences...On April 28,2023,the Map Museum of Zhengzhou University was officially opened in the historical Central Plains of China.The museum was founded by Mr.GAO Jun,Distinguished Academician of the Chinese Academy of Sciences and Dean of the School of Geo-Science and Technology at Zhengzhou University.The establishment of the Map Museum reflects the vigorous development of Chinese cartography and its advancement toward world-class level.Additionally,it marks a significant milestone in promoting Chinese map culture.展开更多
In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can...In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.展开更多
This paper studies the judgement problem of full-period maps on Z(p^n) and proposes a novel congruential map with double modulus on Z(p^n). The full-period properties of the sequences generated by the novel map are st...This paper studies the judgement problem of full-period maps on Z(p^n) and proposes a novel congruential map with double modulus on Z(p^n). The full-period properties of the sequences generated by the novel map are studied completely. We prove some theorems including full-period judgement theorem on Z(p^n) and validate them by some numerical experiments. In the experiments, full-period sequences are generated by a full-period map on Z(p^n). By the binarization, full-period sequences are transformed into binary sequences. Then, we test the binary sequences with the NIST SP 800-22 software package and make the poker test. The passing rates of the statistical tests are high in NIST test and the sequences pass the poker test. So the randomness and statistic characteristics of the binary sequences are good. The analysis and experiments show that these full-period maps can be applied in the pseudo-random number generation(PRNG), cryptography, spread spectrum communications and so on.展开更多
It is important to describe misclassification errors in land cover maps and to quantify their propagation through geo-processing to resultant information products,such as land cover change maps.Geostatistical simulati...It is important to describe misclassification errors in land cover maps and to quantify their propagation through geo-processing to resultant information products,such as land cover change maps.Geostatistical simulation is widely used in error modeling,as it can generate equal-probable realizations of the fields being considered,which can be summarized to facilitate error propagation analysis.To fix noninvariance in indicator simulation,discriminant space-based methods were proposed to enhance consistency in area-class mapping and replicability in uncertainty modeling,as the former is achieved by imposing means while the latter is ensured by projecting spatio-temporal correlated residuals in discriminant space to geographic space through a mapping process.This paper explores discriminant models for error propagation in land cover change detection,followed by experiments based on bi-temporal remote sensing images.It was found that misclassification error propagation is effectively characterized with discriminant covariate-based stochastic simulation,where spatio-temporal interdependence is taken into account.展开更多
COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is requ...COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is required.A reverse transcript polymerase chain reaction(RT-PCR)test is often used to detect the disease.However,since this test is time-consuming,a chest computed tomography(CT)or plain chest X-ray(CXR)is sometimes indicated.The value of automated diagnosis is that it saves time and money by minimizing human effort.Three significant contributions are made by our research.Its initial purpose is to use the essential finetuning methodology to test the action and efficiency of a variety of vision models,ranging from Inception to Neural Architecture Search(NAS)networks.Second,by plotting class activationmaps(CAMs)for individual networks and assessing classification efficiency with AUC-ROC curves,the behavior of these models is visually analyzed.Finally,stacked ensembles techniques were used to provide greater generalization by combining finetuned models with six ensemble neural networks.Using stacked ensembles,the generalization of the models improved.Furthermore,the ensemble model created by combining all of the finetuned networks obtained a state-of-the-art COVID-19 accuracy detection score of 99.17%.The precision and recall rates were 99.99%and 89.79%,respectively,highlighting the robustness of stacked ensembles.The proposed ensemble approach performed well in the classification of the COVID-19 lesions on CXR according to the experimental results.展开更多
Through summarizing the related literature of school-enterprise integration and collaborative education at home and abroad, it is found that there are the most researches on school-enterprise collaborative innovation ...Through summarizing the related literature of school-enterprise integration and collaborative education at home and abroad, it is found that there are the most researches on school-enterprise collaborative innovation mechanism. Most scholars have studied the construction of school-enterprise collaborative innovation mechanism from the aspects of knowledge management, cooperative motivation, benefit distribution and collaborative mode, focusing on the operation mechanism of school-enterprise collaborative innovation activities, rather than the training mode of skilled talents. Based on the research of domestic and foreign enterprises participation in talent training mode in higher vocational colleges, this paper clarifies the current situation of school-enterprise collaborative education in China, analyzes its existing problems, and puts forward the strategy of "school-enterprise collaborative innovation" to cultivate skilled talents. Taking our schools talent training as an example, this paper constructs a new talent training mode in higher vocational colleges from the perspective of deep integration of schools and enterprises and collaborative education.展开更多
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(RS-2023-00249743).
文摘Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.
基金supported by the National Natural Science Foundation of China(12061035)the Research Foundation of Jiangxi Science and Technology Normal University of China(2021QNBJRC003)supported by the Graduate Innovation Fund of Jiangxi Science and Technology Normal University(YC2024-X10).
文摘In this paper,the class of starlike functions of complex order γ(γ∈ℂ−{0})is extended from the case on unit disk U=(z∈C:|z|<1)to the case on the unit ball B in a complex Banach space or the unit polydisk U^(n) in C^(n).Let g be a convex function in U. We mainly establish the sharp bounds of all terms of homogeneous polynomial expansions for a subclass of g-parametric starlike mappings of complex order γ on B (resp.U^(n))when the mappings f are k-fold symmetric, k ∈ N. Our results partly solve the Bieberbach conjecture in several complex variables and generalize some prior works.
基金supported by a Korea Agency for Infrastructure Technology Advancement(KAIA)grant funded by the Ministry of Land,Infrastructure,and Transport(Grant 22CTAP-C163951-02).
文摘Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces automatically.The CNN model demonstrates remarkable accuracy in image data analysis;however,the predicted results have uncertainty in providing accurate informa-tion to users because of the“black box”problem in the deep learning model.Therefore,this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect identification.The visual repre-sentative gradient-weights class activation mapping(Grad-CAM)method is adopted to provide visually explainable information.A visualizing evaluation index is proposed to quantitatively analyze visual representations;this index reflects a rough estimate of the concordance rate between the visualized heat map and intended defects.In addition,an ablation study,adopting three-branch combinations with the VGG16,is implemented to identify perfor-mance variations by visualizing predicted results.Experiments reveal that the proposed model,combined with hybrid pooling,batch normalization,and multi-attention modules,achieves the best performance with an accuracy of 97.77%,corresponding to an improvement of 2.49%compared with the baseline model.Consequently,this study demonstrates that reliable results from an automatic defect classification model can be provided to an inspector through the visual representation of the predicted results using CNN models.
文摘Mind map has been widely recognized as an effective teaching and learning tool in all levels of education. This paper, based on the writer’s teaching practice, aimed to investigate the potential use of mind map in English intensive reading classes of college students, and found that it could help students to understand and memorize the main ideas and important details of reading materials in a systematical way.
文摘In this paper, a modified implicit Kirk-multistep iteration scheme and a strong convergence result for a general class of maps in a normed linear space was established. It was also shown that the convergence of this iteration scheme is equivalent to the convergency of some other implicit Kirk-type iteration (implicit Kirk-Noor, implicit Kirk-Ishikawa and implicit Kirk-Mann iterations) for the same class of maps. Some numerical examples were considered to show that the equivalence of convergence results to the fixed point is true. The results unify most equivalence results in literature.
文摘On April 28,2023,the Map Museum of Zhengzhou University was officially opened in the historical Central Plains of China.The museum was founded by Mr.GAO Jun,Distinguished Academician of the Chinese Academy of Sciences and Dean of the School of Geo-Science and Technology at Zhengzhou University.The establishment of the Map Museum reflects the vigorous development of Chinese cartography and its advancement toward world-class level.Additionally,it marks a significant milestone in promoting Chinese map culture.
文摘In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.
基金supported in part by the National Natural Science Foundation of China(NSFC)(Grant Nos.11365023)the Science and Technology Program of Shaanxi Province(Grant Nos.2018GY-050)+1 种基金the Key Scientific Research Program of Department of Education of Shaanxi Province(Grant No.16JS008)the Key Projects of Baoji University of Arts and Sciences(Grant Nos.ZK2017037)
文摘This paper studies the judgement problem of full-period maps on Z(p^n) and proposes a novel congruential map with double modulus on Z(p^n). The full-period properties of the sequences generated by the novel map are studied completely. We prove some theorems including full-period judgement theorem on Z(p^n) and validate them by some numerical experiments. In the experiments, full-period sequences are generated by a full-period map on Z(p^n). By the binarization, full-period sequences are transformed into binary sequences. Then, we test the binary sequences with the NIST SP 800-22 software package and make the poker test. The passing rates of the statistical tests are high in NIST test and the sequences pass the poker test. So the randomness and statistic characteristics of the binary sequences are good. The analysis and experiments show that these full-period maps can be applied in the pseudo-random number generation(PRNG), cryptography, spread spectrum communications and so on.
基金Supported by the National Natural Science Foundation of China(Nos.41071286&41171346)Hubei Provincial Science and Technology Department(2007ABA276).
文摘It is important to describe misclassification errors in land cover maps and to quantify their propagation through geo-processing to resultant information products,such as land cover change maps.Geostatistical simulation is widely used in error modeling,as it can generate equal-probable realizations of the fields being considered,which can be summarized to facilitate error propagation analysis.To fix noninvariance in indicator simulation,discriminant space-based methods were proposed to enhance consistency in area-class mapping and replicability in uncertainty modeling,as the former is achieved by imposing means while the latter is ensured by projecting spatio-temporal correlated residuals in discriminant space to geographic space through a mapping process.This paper explores discriminant models for error propagation in land cover change detection,followed by experiments based on bi-temporal remote sensing images.It was found that misclassification error propagation is effectively characterized with discriminant covariate-based stochastic simulation,where spatio-temporal interdependence is taken into account.
基金The research is funded by the Researchers Supporting Project at King Saud University,(Project#RSP-2021/305).
文摘COVID-19 is a growing problem worldwide with a high mortality rate.As a result,the World Health Organization(WHO)declared it a pandemic.In order to limit the spread of the disease,a fast and accurate diagnosis is required.A reverse transcript polymerase chain reaction(RT-PCR)test is often used to detect the disease.However,since this test is time-consuming,a chest computed tomography(CT)or plain chest X-ray(CXR)is sometimes indicated.The value of automated diagnosis is that it saves time and money by minimizing human effort.Three significant contributions are made by our research.Its initial purpose is to use the essential finetuning methodology to test the action and efficiency of a variety of vision models,ranging from Inception to Neural Architecture Search(NAS)networks.Second,by plotting class activationmaps(CAMs)for individual networks and assessing classification efficiency with AUC-ROC curves,the behavior of these models is visually analyzed.Finally,stacked ensembles techniques were used to provide greater generalization by combining finetuned models with six ensemble neural networks.Using stacked ensembles,the generalization of the models improved.Furthermore,the ensemble model created by combining all of the finetuned networks obtained a state-of-the-art COVID-19 accuracy detection score of 99.17%.The precision and recall rates were 99.99%and 89.79%,respectively,highlighting the robustness of stacked ensembles.The proposed ensemble approach performed well in the classification of the COVID-19 lesions on CXR according to the experimental results.
文摘Through summarizing the related literature of school-enterprise integration and collaborative education at home and abroad, it is found that there are the most researches on school-enterprise collaborative innovation mechanism. Most scholars have studied the construction of school-enterprise collaborative innovation mechanism from the aspects of knowledge management, cooperative motivation, benefit distribution and collaborative mode, focusing on the operation mechanism of school-enterprise collaborative innovation activities, rather than the training mode of skilled talents. Based on the research of domestic and foreign enterprises participation in talent training mode in higher vocational colleges, this paper clarifies the current situation of school-enterprise collaborative education in China, analyzes its existing problems, and puts forward the strategy of "school-enterprise collaborative innovation" to cultivate skilled talents. Taking our schools talent training as an example, this paper constructs a new talent training mode in higher vocational colleges from the perspective of deep integration of schools and enterprises and collaborative education.
