Most predictive maintenance studies have emphasized accuracy but provide very little focus on Interpretability or deployment readiness.This study improves on prior methods by developing a small yet robust system that ...Most predictive maintenance studies have emphasized accuracy but provide very little focus on Interpretability or deployment readiness.This study improves on prior methods by developing a small yet robust system that can predict when turbofan engines will fail.It uses the NASA CMAPSS dataset,which has over 200,000 engine cycles from260 engines.The process begins with systematic preprocessing,which includes imputation,outlier removal,scaling,and labelling of the remaining useful life.Dimensionality is reduced using a hybrid selection method that combines variance filtering,recursive elimination,and gradient-boosted importance scores,yielding a stable set of 10 informative sensors.To mitigate class imbalance,minority cases are oversampled,and class-weighted losses are applied during training.Benchmarking is carried out with logistic regression,gradient boosting,and a recurrent design that integrates gated recurrent units with long short-term memory networks.The Long Short-Term Memory–Gated Recurrent Unit(LSTM–GRU)hybrid achieved the strongest performance with an F1 score of 0.92,precision of 0.93,recall of 0.91,ReceiverOperating Characteristic–AreaUnder the Curve(ROC-AUC)of 0.97,andminority recall of 0.75.Interpretability testing using permutation importance and Shapley values indicates that sensors 13,15,and 11 are the most important indicators of engine wear.The proposed system combines imbalance handling,feature reduction,and Interpretability into a practical design suitable for real industrial settings.展开更多
This paper investigates the verbal and non - verbal features of interpretation from Chinese into English . On the one hand the language of interpretation belongs to the category of oral language, So It determines the ...This paper investigates the verbal and non - verbal features of interpretation from Chinese into English . On the one hand the language of interpretation belongs to the category of oral language, So It determines the path an interpreter should follow while interpreting . On the other hand it is suggested that the non - verbal approach plays an important role in interpretation. Therefore an interpreter can not be a qualified interpreter unless he is, in addition to language techniques, skilled in the application of paralanguage.展开更多
Dear Editor,This letter proposes an end-to-end feature disentangled Transformer(FDTs)for entanglement-free and semantic feature representation to enable accurate and trustworthy pathology grading of squamous cell carc...Dear Editor,This letter proposes an end-to-end feature disentangled Transformer(FDTs)for entanglement-free and semantic feature representation to enable accurate and trustworthy pathology grading of squamous cell carcinoma(SCC).Existing vision transformers(ViTs)can implement representation learning for SCC grading,however,they all adopt the class-patch token fuzzy mapping for pattern prediction probability or window down-sampling to enhance the representation to contextual information.展开更多
This study was conducted to enable prompt classification of malware,which was becoming increasingly sophisticated.To do this,we analyzed the important features of malware and the relative importance of selected featur...This study was conducted to enable prompt classification of malware,which was becoming increasingly sophisticated.To do this,we analyzed the important features of malware and the relative importance of selected features according to a learning model to assess how those important features were identified.Initially,the analysis features were extracted using Cuckoo Sandbox,an open-source malware analysis tool,then the features were divided into five categories using the extracted information.The 804 extracted features were reduced by 70%after selecting only the most suitable ones for malware classification using a learning model-based feature selection method called the recursive feature elimination.Next,these important features were analyzed.The level of contribution from each one was assessed by the Random Forest classifier method.The results showed that System call features were mostly allocated.At the end,it was possible to accurately identify the malware type using only 36 to 76 features for each of the four types of malware with the most analysis samples available.These were the Trojan,Adware,Downloader,and Backdoor malware.展开更多
This paper is trying to analyze the E-C interpreting scripts of Inaugural Address, Remarks on Winning the Nobel Prize and Shanghai Speech by the 44th president of United States Barack Obama with a comparative method b...This paper is trying to analyze the E-C interpreting scripts of Inaugural Address, Remarks on Winning the Nobel Prize and Shanghai Speech by the 44th president of United States Barack Obama with a comparative method based on data collected. The analysis will be employed on the lexical, syntactic as well as rhetorical level and the features of E-C public speech interpreting will be achieved accordingly. The features may serve as reference for the interpreters in their interpretation practice in order to improve the interpretation effects.展开更多
The project delves into the preliminary findings of a survey of both trainers and students on the practice of using student peer feedback in interpreting practice.It first explains the theoretical foundation which jus...The project delves into the preliminary findings of a survey of both trainers and students on the practice of using student peer feedback in interpreting practice.It first explains the theoretical foundation which justifies the use of peer feedback in interpreting practice,the research methodology and data collection.Then it brings forth specific findings concerning the implementation of peer feedback in the interpreting class followed by discussions of the role and features of student peer feedback as a means to help students ready for the booth.Analysis of the results shows that peer feedback in interpreting practice keeps students on-task,attentive and help them spot their own problems.Trainers and students themselves point to similar features of student peer feedback as focusing on comprehension of the original,word choice and numbers.The preliminary findings of the survey demonstrate the roles and features of student peer feedback in interpreting practice and point to the possible way of enhancing student’s learning curve through more effective peer feedback.展开更多
This paper presents a state of the art machine learning-based approach for automation of a varied class of Internet of things(Io T) analytics problems targeted on 1-dimensional(1-D) sensor data. As feature recommendat...This paper presents a state of the art machine learning-based approach for automation of a varied class of Internet of things(Io T) analytics problems targeted on 1-dimensional(1-D) sensor data. As feature recommendation is a major bottleneck for general Io Tbased applications, this paper shows how this step can be successfully automated based on a Wide Learning architecture without sacrificing the decision-making accuracy, and thereby reducing the development time and the cost of hiring expensive resources for specific problems. Interpretation of meaningful features is another contribution of this research. Several data sets from different real-world applications are considered to realize the proof-of-concept. Results show that the interpretable feature recommendation techniques are quite effective for the problems at hand in terms of performance and drastic reduction in development time.展开更多
Electrocatalytic nitrogen reduction to ammonia has garnered significant attention with the blooming of single-atom catalysts(SACs),showcasing their potential for sustainable and energy-efficient ammonia production.How...Electrocatalytic nitrogen reduction to ammonia has garnered significant attention with the blooming of single-atom catalysts(SACs),showcasing their potential for sustainable and energy-efficient ammonia production.However,cost-effectively designing and screening efficient electrocatalysts remains a challenge.In this study,we have successfully established interpretable machine learning(ML)models to evaluate the catalytic activity of SACs by directly and accurately predicting reaction Gibbs free energy.Our models were trained using non-density functional theory(DFT)calculated features from a dataset comprising 90 graphene-supported SACs.Our results underscore the superior prediction accuracy of the gradient boosting regression(GBR)model for bothΔg(N_(2)→NNH)andΔG(NH_(2)→NH_(3)),boasting coefficient of determination(R^(2))score of 0.972 and 0.984,along with root mean square error(RMSE)of 0.051 and 0.085 eV,respectively.Moreover,feature importance analysis elucidates that the high accuracy of GBR model stems from its adept capture of characteristics pertinent to the active center and coordination environment,unveilling the significance of elementary descriptors,with the colvalent radius playing a dominant role.Additionally,Shapley additive explanations(SHAP)analysis provides global and local interpretation of the working mechanism of the GBR model.Our analysis identifies that a pyrrole-type coordination(flag=0),d-orbitals with a moderate occupation(N_(d)=5),and a moderate difference in covalent radius(r_(TM-ave)near 140 pm)are conducive to achieving high activity.Furthermore,we extend the prediction of activity to more catalysts without additional DFT calculations,validating the reliability of our feature engineering,model training,and design strategy.These findings not only highlight new opportunity for accelerating catalyst design using non-DFT calculated features,but also shed light on the working mechanism of"black box"ML model.Moreover,the model provides valuable guidance for catalytic material design in multiple proton-electron coupling reactions,particularly in driving sustainable CO_(2),O_(2),and N_(2) conversion.展开更多
Note-taking skill is a necessary component in interpreter training programs,and previous research has yielded findings such as note-taking training methods or features of interpreter trainees’notes.However,little res...Note-taking skill is a necessary component in interpreter training programs,and previous research has yielded findings such as note-taking training methods or features of interpreter trainees’notes.However,little research has been done to investigate the changes in note features and correlations between note features and interpreting quality concerning Chinese students’C-E(Chinese-English)and E-C(EnglishChinese)interpreting.Using the framework of Daniel Gile’s Effort Model and Interpretive Theory of Translation,this paper examined how 45 English Majors’notes develop within one semester(seventeen weeks)and the relationship between note features(quantity,form,and language choice of notes)and consecutive interpreting quality.The participants of this study were all beginner interpreting trainees,and the note-taking training was introduced in Week 6.The study employed note manuscripts,interpreting tests,and semi-structured interviews to track the features and changes in students’notes.Correlation analyses and T-tests showed that(a)after the note-taking training,the number of notes increased from Week 8 to Week 17,and it was positively correlated with interpreting quality(fidelity and delivery)for both C-E and E-C interpreting;(b)as for forms of notes,participants primarily employ single Chinese words and the percentages of abbreviations and symbols rose prominently from Week 8 to Week 17 for C-E interpreting.Besides,correlation analyses show that interpreting quality improves with fewer single Chinese words and more abbreviations and symbols.For E-C interpreting,notes were mainly in English,especially single English words and abbreviations.The percentages of single Chinese words and abbreviations ascended whereas those of single English words and symbols decreased.Furthermore,results show that the more abbreviations and symbols,the better target-text fidelity,and fewer abbreviations,the better the targettext delivery;(c)concerning language choice,notes were mainly in source language for both C-E and E-C interpreting and the percentage of target language notes went up significantly for C-E interpreting.Consequently,the percentage of target language notes was positively correlated with interpreting quality.Interviews indicate that most participants do not pay much attention to language selection in the first stage,and if the source text a familiar topic with little difficult vocabulary,he or she records the target language.Otherwise,it was safer to use the source language.展开更多
Spectral decomposition has been widely used in the detection and identifi cation of underground anomalous features(such as faults,river channels,and karst caves).However,the conventional spectral decomposition method ...Spectral decomposition has been widely used in the detection and identifi cation of underground anomalous features(such as faults,river channels,and karst caves).However,the conventional spectral decomposition method is restrained by the window function,and hence,it mostly has low time–frequency focusing and resolution,thereby hampering the fi ne interpretation of seismic targets.To solve this problem,we investigated the sparse inverse spectral decomposition constrained by the lp norm(0<p≤1).Using a numerical model,we demonstrated the higher time–frequency resolution of this method and its capability for improving the seismic interpretation for thin layers.Moreover,given the actual underground geology that can be often complex,we further propose a p-norm constrained inverse spectral attribute interpretation method based on multiresolution time–frequency feature fusion.By comprehensively analyzing the time–frequency spectrum results constrained by the diff erent p-norms,we can obtain more refined interpretation results than those obtained by the traditional strategy,which incorporates a single norm constraint.Finally,the proposed strategy was applied to the processing and interpretation of actual three-dimensional seismic data for a study area covering about 230 km^(2) in western China.The results reveal that the surface water system in this area is characterized by stepwise convergence from a higher position in the north(a buried hill)toward the south and by the development of faults.We thus demonstrated that the proposed method has huge application potential in seismic interpretation.展开更多
Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of...Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.展开更多
With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural network...With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural networks.These intelligent and automated methods significantly reduce manual labor,particularly in the laborious task of manually labeling seismic facies.However,the extensive demand for training data imposes limitations on their wider application.To overcome this challenge,we adopt the UNet architecture as the foundational network structure for seismic facies classification,which has demonstrated effective segmentation results even with small-sample training data.Additionally,we integrate spatial pyramid pooling and dilated convolution modules into the network architecture to enhance the perception of spatial information across a broader range.The seismic facies classification test on the public data from the F3 block verifies the superior performance of our proposed improved network structure in delineating seismic facies boundaries.Comparative analysis against the traditional UNet model reveals that our method achieves more accurate predictive classification results,as evidenced by various evaluation metrics for image segmentation.Obviously,the classification accuracy reaches an impressive 96%.Furthermore,the results of seismic facies classification in the seismic slice dimension provide further confirmation of the superior performance of our proposed method,which accurately defines the range of different seismic facies.This approach holds significant potential for analyzing geological patterns and extracting valuable depositional information.展开更多
Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and di...Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and differences of various surface features.Currently,topographic maps are mainly stored in raster and vector formats.Extraction of the spatio-temporal knowledge in the maps—such as spatial distribution patterns,feature relationships,and dynamic evolution—still primarily relies on manual interpretation.However,manual interpretation is time-consuming and laborious,especially for large-scale,long-term map knowledge extraction and application.With the development of artificial intelligence technology,it is possible to improve the automation level of map knowledge interpretation.Therefore,the present study proposes an automatic interpretation method for raster topographic map knowledge based on deep learning.To address the limitations of current data-driven intelligent technology in learning map spatial relations and cognitive logic,we establish a formal description of map knowledge by mapping the relationship between map knowledge and features,thereby ensuring interpretation accuracy.Subsequently,deep learning techniques are employed to extract map features automatically,and the spatio-temporal knowledge is constructed by combining formal descriptions of geographic feature knowledge.Validation experiments demonstrate that the proposed method effectively achieves automatic interpretation of spatio-temporal knowledge of geographic features in maps,with an accuracy exceeding 80%.The findings of the present study contribute to machine understanding of spatio-temporal differences in map knowledge and advances the intelligent interpretation and utilization of cartographic information.展开更多
Finding a highly interpretable nonlinear model has been an important yet challenging problem, and related research is relatively scarce in the current literature. To tackle this issue, we propose a new algorithm calle...Finding a highly interpretable nonlinear model has been an important yet challenging problem, and related research is relatively scarce in the current literature. To tackle this issue, we propose a new algorithm called Feat-ABESS based on a framework that utilizes feature transformation and selection for re-interpreting many machine learning algorithms. The core idea behind Feat-ABESS is to parameterize interpretable feature transformation within this framework and construct an objective function based on these parameters. This approach enables us to identify a proper interpretable feature transformation from the optimization perspective. By leveraging a recently advanced optimization technique, Feat-ABESS can obtain a concise and interpretable model. Moreover, Feat-ABESS can perform nonlinear variable selection. Our extensive experiments on 205 benchmark datasets and case studies on two datasets have demonstrated that Feat-ABESS can achieve powerful prediction accuracy while maintaining a high level of interpretability. The comparison with existing nonlinear variable selection methods exhibits Feat-ABESS has a higher true positive rate and a lower false discovery rate.展开更多
Accurately estimating the interfacial bond capacity of the near-surface mounted(NSM)carbon fiber-reinforced polymer(CFRP)to concrete joint is a fundamental task in the strengthening and retrofit of existing reinforced...Accurately estimating the interfacial bond capacity of the near-surface mounted(NSM)carbon fiber-reinforced polymer(CFRP)to concrete joint is a fundamental task in the strengthening and retrofit of existing reinforced concrete(RC)structures.The machine learning(ML)approach may provide an alternative to the commonly used semi-empirical or semi-analytical methods.Therefore,in this work we have developed a predictive model based on an artificial neural network(ANN)approach,i.e.using a back propagation neural network(BPNN),to map the complex data pattern obtained from an NSM CFRP to concrete joint.It involves a set of nine material and geometric input parameters and one output value.Moreover,by employing the neural interpretation diagram(NID)technique,the BPNN model becomes interpretable,as the influence of each input variable on the model can be tracked and quantified based on the connection weights of the neural network.An extensive database including 163 pull-out testing samples,collected from the authors’research group and from published results in the literature,is used to train and verify the ANN.Our results show that the prediction given by the BPNN model agrees well with the experimental data and yields a coefficient of determination of 0.957 on the whole database.After removing one non-significant feature,the BPNN becomes even more computationally efficient and accurate.In addition,compared with the existed semi-analytical model,the ANN-based approach demonstrates a more accurate estimation.Therefore,the proposed ML method may be a promising alternative for predicting the bond strength of NSM CFRP to concrete joint for structural engineers.展开更多
The existence of time delay in complex industrial processes or dynamical systems is a common phenomenon and is a difficult problem to deal with in industrial control systems,as well as in the textile field.Accurate id...The existence of time delay in complex industrial processes or dynamical systems is a common phenomenon and is a difficult problem to deal with in industrial control systems,as well as in the textile field.Accurate identification of the time delay can greatly improve the efficiency of the design of industrial process control systems.The time delay identification methods based on mathematical modeling require prior knowledge of the structural information of the model,especially for nonlinear systems.The neural network-based identification method can predict the time delay of the system,but cannot accurately obtain the specific parameters of the time delay.Benefit from the interpretability of machine learning,a novel method for delay identification based on an interpretable regression decision tree is proposed.Utilizing the self-explanatory analysis of the decision tree model,the parameters with the highest feature importance are obtained to identify the time delay of the system.Excellent results are gained by the simulation data of linear and nonlinear control systems,and the time delay of the systems can be accurately identified.展开更多
The gravity and magnetic survey lines of about 13,500 km were carried out in the centraland northern parts of the South China Sea from 1977 to 1978. The results obtained showthat the Bouguer gravity and magnetic anoma...The gravity and magnetic survey lines of about 13,500 km were carried out in the centraland northern parts of the South China Sea from 1977 to 1978. The results obtained showthat the Bouguer gravity and magnetic anomalies have a tendency to increase gradually theirvalues from the northern continental shelf, through the slope, to the central abyssal basin of theSouth China Sea. The change in free-air gravity anomaly values coincides to a certain degreewith the undulation of the sea-bottom topography. The primary factor determining regionalvariation of the Bouguer gravity anomayl values is the Moho depth. The main factor deter-mining the magnetic anomly values is the nature of the basement rock. The high magnetieand Bouguer gravity anomaly values observed in some fault basin areas are inferred to becaused by draping the basic and ultrabasic magma extruding along the faults on the basementof the metamorphic rock,or by intrusion of the same magma into the basement.展开更多
基金supported by the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia Grant No.KFU253765.
文摘Most predictive maintenance studies have emphasized accuracy but provide very little focus on Interpretability or deployment readiness.This study improves on prior methods by developing a small yet robust system that can predict when turbofan engines will fail.It uses the NASA CMAPSS dataset,which has over 200,000 engine cycles from260 engines.The process begins with systematic preprocessing,which includes imputation,outlier removal,scaling,and labelling of the remaining useful life.Dimensionality is reduced using a hybrid selection method that combines variance filtering,recursive elimination,and gradient-boosted importance scores,yielding a stable set of 10 informative sensors.To mitigate class imbalance,minority cases are oversampled,and class-weighted losses are applied during training.Benchmarking is carried out with logistic regression,gradient boosting,and a recurrent design that integrates gated recurrent units with long short-term memory networks.The Long Short-Term Memory–Gated Recurrent Unit(LSTM–GRU)hybrid achieved the strongest performance with an F1 score of 0.92,precision of 0.93,recall of 0.91,ReceiverOperating Characteristic–AreaUnder the Curve(ROC-AUC)of 0.97,andminority recall of 0.75.Interpretability testing using permutation importance and Shapley values indicates that sensors 13,15,and 11 are the most important indicators of engine wear.The proposed system combines imbalance handling,feature reduction,and Interpretability into a practical design suitable for real industrial settings.
文摘This paper investigates the verbal and non - verbal features of interpretation from Chinese into English . On the one hand the language of interpretation belongs to the category of oral language, So It determines the path an interpreter should follow while interpreting . On the other hand it is suggested that the non - verbal approach plays an important role in interpretation. Therefore an interpreter can not be a qualified interpreter unless he is, in addition to language techniques, skilled in the application of paralanguage.
基金supported by the National Natural Science Foundation of China(62272078)the Chongqing Natural Science Foundation(CSTB2023NSCQ-LZX0069).
文摘Dear Editor,This letter proposes an end-to-end feature disentangled Transformer(FDTs)for entanglement-free and semantic feature representation to enable accurate and trustworthy pathology grading of squamous cell carcinoma(SCC).Existing vision transformers(ViTs)can implement representation learning for SCC grading,however,they all adopt the class-patch token fuzzy mapping for pattern prediction probability or window down-sampling to enhance the representation to contextual information.
基金supported by the Research Program through the National Research Foundation of Korea,NRF-2018R1D1A1B07050864.
文摘This study was conducted to enable prompt classification of malware,which was becoming increasingly sophisticated.To do this,we analyzed the important features of malware and the relative importance of selected features according to a learning model to assess how those important features were identified.Initially,the analysis features were extracted using Cuckoo Sandbox,an open-source malware analysis tool,then the features were divided into five categories using the extracted information.The 804 extracted features were reduced by 70%after selecting only the most suitable ones for malware classification using a learning model-based feature selection method called the recursive feature elimination.Next,these important features were analyzed.The level of contribution from each one was assessed by the Random Forest classifier method.The results showed that System call features were mostly allocated.At the end,it was possible to accurately identify the malware type using only 36 to 76 features for each of the four types of malware with the most analysis samples available.These were the Trojan,Adware,Downloader,and Backdoor malware.
文摘This paper is trying to analyze the E-C interpreting scripts of Inaugural Address, Remarks on Winning the Nobel Prize and Shanghai Speech by the 44th president of United States Barack Obama with a comparative method based on data collected. The analysis will be employed on the lexical, syntactic as well as rhetorical level and the features of E-C public speech interpreting will be achieved accordingly. The features may serve as reference for the interpreters in their interpretation practice in order to improve the interpretation effects.
文摘The project delves into the preliminary findings of a survey of both trainers and students on the practice of using student peer feedback in interpreting practice.It first explains the theoretical foundation which justifies the use of peer feedback in interpreting practice,the research methodology and data collection.Then it brings forth specific findings concerning the implementation of peer feedback in the interpreting class followed by discussions of the role and features of student peer feedback as a means to help students ready for the booth.Analysis of the results shows that peer feedback in interpreting practice keeps students on-task,attentive and help them spot their own problems.Trainers and students themselves point to similar features of student peer feedback as focusing on comprehension of the original,word choice and numbers.The preliminary findings of the survey demonstrate the roles and features of student peer feedback in interpreting practice and point to the possible way of enhancing student’s learning curve through more effective peer feedback.
文摘This paper presents a state of the art machine learning-based approach for automation of a varied class of Internet of things(Io T) analytics problems targeted on 1-dimensional(1-D) sensor data. As feature recommendation is a major bottleneck for general Io Tbased applications, this paper shows how this step can be successfully automated based on a Wide Learning architecture without sacrificing the decision-making accuracy, and thereby reducing the development time and the cost of hiring expensive resources for specific problems. Interpretation of meaningful features is another contribution of this research. Several data sets from different real-world applications are considered to realize the proof-of-concept. Results show that the interpretable feature recommendation techniques are quite effective for the problems at hand in terms of performance and drastic reduction in development time.
基金supported by the Research Grants Council of Hong Kong (City U 11305919 and 11308620)the NSFC/RGC Joint Research Scheme N_City U104/19The Hong Kong Research Grant Council Collaborative Research Fund:C1002-21G and C1017-22G。
文摘Electrocatalytic nitrogen reduction to ammonia has garnered significant attention with the blooming of single-atom catalysts(SACs),showcasing their potential for sustainable and energy-efficient ammonia production.However,cost-effectively designing and screening efficient electrocatalysts remains a challenge.In this study,we have successfully established interpretable machine learning(ML)models to evaluate the catalytic activity of SACs by directly and accurately predicting reaction Gibbs free energy.Our models were trained using non-density functional theory(DFT)calculated features from a dataset comprising 90 graphene-supported SACs.Our results underscore the superior prediction accuracy of the gradient boosting regression(GBR)model for bothΔg(N_(2)→NNH)andΔG(NH_(2)→NH_(3)),boasting coefficient of determination(R^(2))score of 0.972 and 0.984,along with root mean square error(RMSE)of 0.051 and 0.085 eV,respectively.Moreover,feature importance analysis elucidates that the high accuracy of GBR model stems from its adept capture of characteristics pertinent to the active center and coordination environment,unveilling the significance of elementary descriptors,with the colvalent radius playing a dominant role.Additionally,Shapley additive explanations(SHAP)analysis provides global and local interpretation of the working mechanism of the GBR model.Our analysis identifies that a pyrrole-type coordination(flag=0),d-orbitals with a moderate occupation(N_(d)=5),and a moderate difference in covalent radius(r_(TM-ave)near 140 pm)are conducive to achieving high activity.Furthermore,we extend the prediction of activity to more catalysts without additional DFT calculations,validating the reliability of our feature engineering,model training,and design strategy.These findings not only highlight new opportunity for accelerating catalyst design using non-DFT calculated features,but also shed light on the working mechanism of"black box"ML model.Moreover,the model provides valuable guidance for catalytic material design in multiple proton-electron coupling reactions,particularly in driving sustainable CO_(2),O_(2),and N_(2) conversion.
文摘Note-taking skill is a necessary component in interpreter training programs,and previous research has yielded findings such as note-taking training methods or features of interpreter trainees’notes.However,little research has been done to investigate the changes in note features and correlations between note features and interpreting quality concerning Chinese students’C-E(Chinese-English)and E-C(EnglishChinese)interpreting.Using the framework of Daniel Gile’s Effort Model and Interpretive Theory of Translation,this paper examined how 45 English Majors’notes develop within one semester(seventeen weeks)and the relationship between note features(quantity,form,and language choice of notes)and consecutive interpreting quality.The participants of this study were all beginner interpreting trainees,and the note-taking training was introduced in Week 6.The study employed note manuscripts,interpreting tests,and semi-structured interviews to track the features and changes in students’notes.Correlation analyses and T-tests showed that(a)after the note-taking training,the number of notes increased from Week 8 to Week 17,and it was positively correlated with interpreting quality(fidelity and delivery)for both C-E and E-C interpreting;(b)as for forms of notes,participants primarily employ single Chinese words and the percentages of abbreviations and symbols rose prominently from Week 8 to Week 17 for C-E interpreting.Besides,correlation analyses show that interpreting quality improves with fewer single Chinese words and more abbreviations and symbols.For E-C interpreting,notes were mainly in English,especially single English words and abbreviations.The percentages of single Chinese words and abbreviations ascended whereas those of single English words and symbols decreased.Furthermore,results show that the more abbreviations and symbols,the better target-text fidelity,and fewer abbreviations,the better the targettext delivery;(c)concerning language choice,notes were mainly in source language for both C-E and E-C interpreting and the percentage of target language notes went up significantly for C-E interpreting.Consequently,the percentage of target language notes was positively correlated with interpreting quality.Interviews indicate that most participants do not pay much attention to language selection in the first stage,and if the source text a familiar topic with little difficult vocabulary,he or she records the target language.Otherwise,it was safer to use the source language.
基金supported by National Natural Science Foundation of China (Grant No. 41974140)the PetroChina Prospective,Basic,and Strategic Technology Research Project (No. 2021DJ0606)
文摘Spectral decomposition has been widely used in the detection and identifi cation of underground anomalous features(such as faults,river channels,and karst caves).However,the conventional spectral decomposition method is restrained by the window function,and hence,it mostly has low time–frequency focusing and resolution,thereby hampering the fi ne interpretation of seismic targets.To solve this problem,we investigated the sparse inverse spectral decomposition constrained by the lp norm(0<p≤1).Using a numerical model,we demonstrated the higher time–frequency resolution of this method and its capability for improving the seismic interpretation for thin layers.Moreover,given the actual underground geology that can be often complex,we further propose a p-norm constrained inverse spectral attribute interpretation method based on multiresolution time–frequency feature fusion.By comprehensively analyzing the time–frequency spectrum results constrained by the diff erent p-norms,we can obtain more refined interpretation results than those obtained by the traditional strategy,which incorporates a single norm constraint.Finally,the proposed strategy was applied to the processing and interpretation of actual three-dimensional seismic data for a study area covering about 230 km^(2) in western China.The results reveal that the surface water system in this area is characterized by stepwise convergence from a higher position in the north(a buried hill)toward the south and by the development of faults.We thus demonstrated that the proposed method has huge application potential in seismic interpretation.
基金supported in part by the National Natural Science Foundation of China(82072019)the Shenzhen Basic Research Program(JCYJ20210324130209023)+5 种基金the Shenzhen-Hong Kong-Macao S&T Program(Category C)(SGDX20201103095002019)the Mainland-Hong Kong Joint Funding Scheme(MHKJFS)(MHP/005/20),the Project of Strategic Importance Fund(P0035421)the Projects of RISA(P0043001)from the Hong Kong Polytechnic University,the Natural Science Foundation of Jiangsu Province(BK20201441)the Provincial and Ministry Co-constructed Project of Henan Province Medical Science and Technology Research(SBGJ202103038,SBGJ202102056)the Henan Province Key R&D and Promotion Project(Science and Technology Research)(222102310015)the Natural Science Foundation of Henan Province(222300420575),and the Henan Province Science and Technology Research(222102310322).
文摘Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients’anatomy.However,the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians.Moreover,some potentially useful quantitative information in medical images,especially that which is not visible to the naked eye,is often ignored during clinical practice.In contrast,radiomics performs high-throughput feature extraction from medical images,which enables quantitative analysis of medical images and prediction of various clinical endpoints.Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis,demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine.However,radiomics remains in a developmental phase as numerous technical challenges have yet to be solved,especially in feature engineering and statistical modeling.In this review,we introduce the current utility of radiomics by summarizing research on its application in the diagnosis,prognosis,and prediction of treatment responses in patients with cancer.We focus on machine learning approaches,for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling.Furthermore,we introduce the stability,reproducibility,and interpretability of features,and the generalizability and interpretability of models.Finally,we offer possible solutions to current challenges in radiomics research.
基金funded by the Fundamental Research Project of CNPC Geophysical Key Lab(2022DQ0604-4)the Strategic Cooperation Technology Projects of China National Petroleum Corporation and China University of Petroleum-Beijing(ZLZX 202003)。
文摘With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural networks.These intelligent and automated methods significantly reduce manual labor,particularly in the laborious task of manually labeling seismic facies.However,the extensive demand for training data imposes limitations on their wider application.To overcome this challenge,we adopt the UNet architecture as the foundational network structure for seismic facies classification,which has demonstrated effective segmentation results even with small-sample training data.Additionally,we integrate spatial pyramid pooling and dilated convolution modules into the network architecture to enhance the perception of spatial information across a broader range.The seismic facies classification test on the public data from the F3 block verifies the superior performance of our proposed improved network structure in delineating seismic facies boundaries.Comparative analysis against the traditional UNet model reveals that our method achieves more accurate predictive classification results,as evidenced by various evaluation metrics for image segmentation.Obviously,the classification accuracy reaches an impressive 96%.Furthermore,the results of seismic facies classification in the seismic slice dimension provide further confirmation of the superior performance of our proposed method,which accurately defines the range of different seismic facies.This approach holds significant potential for analyzing geological patterns and extracting valuable depositional information.
基金Deep-time Digital Earth(DDE)Big Science Program(No.GJ-C03-SGF-2025-004)National Natural Science Foundation of China(No.42394063)Sichuan Science and Technology Program(No.2025ZNSFSC0325).
文摘Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and differences of various surface features.Currently,topographic maps are mainly stored in raster and vector formats.Extraction of the spatio-temporal knowledge in the maps—such as spatial distribution patterns,feature relationships,and dynamic evolution—still primarily relies on manual interpretation.However,manual interpretation is time-consuming and laborious,especially for large-scale,long-term map knowledge extraction and application.With the development of artificial intelligence technology,it is possible to improve the automation level of map knowledge interpretation.Therefore,the present study proposes an automatic interpretation method for raster topographic map knowledge based on deep learning.To address the limitations of current data-driven intelligent technology in learning map spatial relations and cognitive logic,we establish a formal description of map knowledge by mapping the relationship between map knowledge and features,thereby ensuring interpretation accuracy.Subsequently,deep learning techniques are employed to extract map features automatically,and the spatio-temporal knowledge is constructed by combining formal descriptions of geographic feature knowledge.Validation experiments demonstrate that the proposed method effectively achieves automatic interpretation of spatio-temporal knowledge of geographic features in maps,with an accuracy exceeding 80%.The findings of the present study contribute to machine understanding of spatio-temporal differences in map knowledge and advances the intelligent interpretation and utilization of cartographic information.
基金Supported by NSFC (Grant Nos. 72171216, 12231017, 71921001 and 71991474)the National Key R&D Program of China (Grant No. 2022YFA1003803)。
文摘Finding a highly interpretable nonlinear model has been an important yet challenging problem, and related research is relatively scarce in the current literature. To tackle this issue, we propose a new algorithm called Feat-ABESS based on a framework that utilizes feature transformation and selection for re-interpreting many machine learning algorithms. The core idea behind Feat-ABESS is to parameterize interpretable feature transformation within this framework and construct an objective function based on these parameters. This approach enables us to identify a proper interpretable feature transformation from the optimization perspective. By leveraging a recently advanced optimization technique, Feat-ABESS can obtain a concise and interpretable model. Moreover, Feat-ABESS can perform nonlinear variable selection. Our extensive experiments on 205 benchmark datasets and case studies on two datasets have demonstrated that Feat-ABESS can achieve powerful prediction accuracy while maintaining a high level of interpretability. The comparison with existing nonlinear variable selection methods exhibits Feat-ABESS has a higher true positive rate and a lower false discovery rate.
基金the National Natural Science Foundation of China(No.51808056)the Hunan Provincial Natural Science Foundation of China(No.2020JJ5583)+1 种基金the Research Foundation of Education Bureau of Hunan Province(No.19B012)the China Scholarship Council(No.201808430232)。
文摘Accurately estimating the interfacial bond capacity of the near-surface mounted(NSM)carbon fiber-reinforced polymer(CFRP)to concrete joint is a fundamental task in the strengthening and retrofit of existing reinforced concrete(RC)structures.The machine learning(ML)approach may provide an alternative to the commonly used semi-empirical or semi-analytical methods.Therefore,in this work we have developed a predictive model based on an artificial neural network(ANN)approach,i.e.using a back propagation neural network(BPNN),to map the complex data pattern obtained from an NSM CFRP to concrete joint.It involves a set of nine material and geometric input parameters and one output value.Moreover,by employing the neural interpretation diagram(NID)technique,the BPNN model becomes interpretable,as the influence of each input variable on the model can be tracked and quantified based on the connection weights of the neural network.An extensive database including 163 pull-out testing samples,collected from the authors’research group and from published results in the literature,is used to train and verify the ANN.Our results show that the prediction given by the BPNN model agrees well with the experimental data and yields a coefficient of determination of 0.957 on the whole database.After removing one non-significant feature,the BPNN becomes even more computationally efficient and accurate.In addition,compared with the existed semi-analytical model,the ANN-based approach demonstrates a more accurate estimation.Therefore,the proposed ML method may be a promising alternative for predicting the bond strength of NSM CFRP to concrete joint for structural engineers.
基金Shanghai Philosophy and Social Science Program,China(No.2019BGL004)。
文摘The existence of time delay in complex industrial processes or dynamical systems is a common phenomenon and is a difficult problem to deal with in industrial control systems,as well as in the textile field.Accurate identification of the time delay can greatly improve the efficiency of the design of industrial process control systems.The time delay identification methods based on mathematical modeling require prior knowledge of the structural information of the model,especially for nonlinear systems.The neural network-based identification method can predict the time delay of the system,but cannot accurately obtain the specific parameters of the time delay.Benefit from the interpretability of machine learning,a novel method for delay identification based on an interpretable regression decision tree is proposed.Utilizing the self-explanatory analysis of the decision tree model,the parameters with the highest feature importance are obtained to identify the time delay of the system.Excellent results are gained by the simulation data of linear and nonlinear control systems,and the time delay of the systems can be accurately identified.
文摘The gravity and magnetic survey lines of about 13,500 km were carried out in the centraland northern parts of the South China Sea from 1977 to 1978. The results obtained showthat the Bouguer gravity and magnetic anomalies have a tendency to increase gradually theirvalues from the northern continental shelf, through the slope, to the central abyssal basin of theSouth China Sea. The change in free-air gravity anomaly values coincides to a certain degreewith the undulation of the sea-bottom topography. The primary factor determining regionalvariation of the Bouguer gravity anomayl values is the Moho depth. The main factor deter-mining the magnetic anomly values is the nature of the basement rock. The high magnetieand Bouguer gravity anomaly values observed in some fault basin areas are inferred to becaused by draping the basic and ultrabasic magma extruding along the faults on the basementof the metamorphic rock,or by intrusion of the same magma into the basement.
