Metal nanoparticles(NPs) supported on porous materials have shown great advantages in many catalytic application fields. Supported metal NPs are receiving extensive attention due to their significant contribution in a...Metal nanoparticles(NPs) supported on porous materials have shown great advantages in many catalytic application fields. Supported metal NPs are receiving extensive attention due to their significant contribution in a wide range of current and future applications, and this is arguably one of the fastest growing research fields. In this review, we highlight various types of metal catalysts that possess great potential in several catalytic reactions. The major focus has been on metal oxides, nanoporous metals and metal NPs supported on metal-organic frameworks(MOFs) and zeolites. Special attention has been given to the synthesis strategies and application of the NPs supported on MOFs and zeolites, which are considered highly interesting and rapidly expanding areas in heterogeneous catalysis. Finally, the prospects of these catalysts have been included in the concluding remarks.展开更多
In the paper, an iterative method is presented to the optimal control of batch processes. Generally it is very difficult to acquire an accurate mechanistic model for a batch process. Because support vector machine is ...In the paper, an iterative method is presented to the optimal control of batch processes. Generally it is very difficult to acquire an accurate mechanistic model for a batch process. Because support vector machine is powerful for the problems characterized by small samples, nonlinearity, high dimension and local minima, support vector regression models are developed for the optimal control of batch processes where end-point properties are required. The model parameters are selected within the Bayesian evidence framework. Based on the model, an iterative method is used to exploit the repetitive nature of batch processes to determine the optimal operating policy. Numerical simulation shows that the iterative optimal control can improve the process performance through iterations.展开更多
Sustainability is a key objective of water resources management and this paper describes a modelling and decision support framework that achieves this, illustrated by applications on the UK Thames and Mekong river bas...Sustainability is a key objective of water resources management and this paper describes a modelling and decision support framework that achieves this, illustrated by applications on the UK Thames and Mekong river basins. The decision support framework contains several modules, including an interactive user＇s interface linked to a GIS, a geo-database, knowledge base, simulation models and optimization procedures. Based on the analysis of scenarios and proposed interventions, efficient modelling and optimization tools form a comprehensive integrated decision support framework for the analysis and operational management of water resources in the river basin, our emphasis has been on a practical implementation through careful screening of alternatives, consideration of the institutional framework and direct involvement of stakeholders in the decision making process. Operating in this environment is transparent, reproducible and auditable, securing the trust of all interested parties. This paper discusses its applications to water utilisation on the Mekong river basin and drought management of the Lower Thames stored reservoir system.展开更多
The view that the traditional method of DSS development is outdated, which results to the diversiform disadvantages of DSS product. Therefore the ideas of application software framework based development to the genera...The view that the traditional method of DSS development is outdated, which results to the diversiform disadvantages of DSS product. Therefore the ideas of application software framework based development to the generation process of DSS is introduced and a modified flow chat of DSS development is proposed. Moreover, a formal description of the DSS software framework and its development is given. The analysis results indicates that not only does the new development flow ensure the DSS development global stability but also improves the software reusability level of the development process.展开更多
This paper proposes a novel approach, Markov Chain Monte Carlo (MCMC) sampling approximation, to deal with intractable high-dimension integral in the evidence framework applied to Support Vector Regression (SVR). Unli...This paper proposes a novel approach, Markov Chain Monte Carlo (MCMC) sampling approximation, to deal with intractable high-dimension integral in the evidence framework applied to Support Vector Regression (SVR). Unlike traditional variational or mean field method, the proposed approach follows the idea of MCMC, firstly draws some samples from the posterior distribution on SVR's weight vector, and then approximates the expected output integrals by finite sums. Experimental results show the proposed approach is feasible and robust to noise. It also shows the performance of proposed approach and Relevance Vector Machine (RVM) is comparable under the noise circumstances. They give better robustness compared to standard SVR.展开更多
In the last decade, turbulent times and uncertainti es in the business environment have made ground for a new business era, and "chang e" has become a major characteristic of the new era. This has resulted i...In the last decade, turbulent times and uncertainti es in the business environment have made ground for a new business era, and "chang e" has become a major characteristic of the new era. This has resulted in tirele ss evolution of business systems and the creation of new manufacturing and manag ement philosophies. Agile Manufacturing (AM) is a step forward in generation of new means for better performance and success of business, and in practice is a s trategic approach to manufacturing by considering the new conditions of the business environment. This paper discusses the concepts and development of a met hodology to achieve agility in manufacturing organisations. Following an introdu ction of the subject of agility, a discussion of the methodology and practical t ools to support the implementation of the methodology, including metrics for the assessment of agility drivers, capability and performance are given. Aspects of the tools are tested in an aerospace company.展开更多
The command and control（C2） is a decision-making process based on human cognition,which contains operational,physical,and human characteristics,so it takes on uncertainty and complexity.As a decision support approac...The command and control（C2） is a decision-making process based on human cognition,which contains operational,physical,and human characteristics,so it takes on uncertainty and complexity.As a decision support approach,Bayesian networks（BNs） provide a framework in which a decision is made by combining the experts＇ knowledge and the specific data.In addition,an expert system represented by human cognitive framework is adopted to express the real-time decision-making process of the decision maker.The combination of the Bayesian decision support and human cognitive framework in the C2 of a specific application field is modeled and executed by colored Petri nets（CPNs）,and the consequences of execution manifest such combination can perfectly present the decision-making process in C2.展开更多
Covalent organic frameworks （COFs）, established as an emerging class of crystalline porous polymers with high surface area, structural diversity, and esignability, attract much interest and exhibit potential applica...Covalent organic frameworks （COFs）, established as an emerging class of crystalline porous polymers with high surface area, structural diversity, and esignability, attract much interest and exhibit potential applications in catalysis. In this review, we summarize the use of COFs as a versatile platform to develop heterogeneous catalysts for a variety of chemical reactions. Catalytic COFs are categorized in accordance with the types of active sites, involving single functional active sites, bifunctional active sites, and metal nanoparticles （NPs） embedded in pores. Special emphasis is placed on the deliberate or incidental synthesis strategies, the stability, the heterogeneity, and the shape/size selectivity for COF catalysis. Moreover, a description of the application of COFs as photocatalysts and electrocatalysts is presented. Finally, the prospects of COFs in catalysis and remaining issues in this field are indicated.展开更多
During the last decade, metal-organic frameworks(MOFs) have been applied in various fields due to their unique chemical and functional advantages. One of the widespread research hotspots is MOF-based membranes for sep...During the last decade, metal-organic frameworks(MOFs) have been applied in various fields due to their unique chemical and functional advantages. One of the widespread research hotspots is MOF-based membranes for separations, specifically continuous defect-free MOF membranes, which are usually grown on porous substrates. The substrate not only serves as the MOF layer support but also has a great influence on the membrane fabrication process and the final separation performance of the resultant membrane. In this review, we mainly introduce the progress focused on the substrates for MOF membranes fabrication. The substrate modifications and seeding methods aimed at synthesizing highquality MOF membranes are also summarized systematically.展开更多
Photocatalysis using the abundant solar energy is an environmentally friendly and efficient way to degrade organic matter.Covalent triazine frameworks(CTFs),a new class of metal-free organic semiconductors responsive ...Photocatalysis using the abundant solar energy is an environmentally friendly and efficient way to degrade organic matter.Covalent triazine frameworks(CTFs),a new class of metal-free organic semiconductors responsive to visible light,are promising materials for water treatment.In this study,an original CTF,namely CTF-1,was modified by S-doping to form CTFSx,which were used as metal-free catalysts for degradation of methyl orange(MO)and bisphenol A(BPA).The outcomes demonstrated that the photocatalytic degradation of MO and BPA by CTFSxwas superior to that by CTF-1,with better stability and reusability.Within 6 h,53.2%MO and 84.7%BPA were degraded by CTFS5,and the degradation rate constants were 0.145 h-1and 0.29 h-1,respectively,which were 3.6 and 5.8 times higher than those of CTF-1.Further investigation revealed that enhanced visible light absorption,a reduced degree of free carrier recombination,rapid separation and transfer of photogenerated electrons and holes,and improved·OH oxidation capacity were important factors contributing to the significantly enhanced photocatalytic activity.The S-doping method effectively improved the light absorption performance,electronic structure,and modulation band structure of CTF-1.This work highlights the potential application of low-cost metal-free catalysts driven by visible light for the removal of organic pollutants from wastewater.展开更多
An approach was proposed for optimizing beamforming that was based on Support Vector Regression (SVR). After studying the mathematical principal of the SVR algorithm and its primal cost function, the modified cost fun...An approach was proposed for optimizing beamforming that was based on Support Vector Regression (SVR). After studying the mathematical principal of the SVR algorithm and its primal cost function, the modified cost function was first applied to uniform array beamforming, and then the corresponding parameters of the beamforming were optimized. The framework of SVR uniform array beamforming was then established. Simulation results show that SVR beamforming can not only approximate the performance of conventional beamforming in the area without noise and with small data sets, but also improve the generalization ability and reduce the computation burden. Also, the side lobe level of both linear and circular arrays by the SVR algorithm is improved sharply through comparison with the conventional one. SVR beamforming is superior to the conventional method in both linear and circular arrays, under single source or double non-coherent sources.展开更多
In the last decade, a large amount of data has been published in different fields and can be used as a data source for research and study. However, identifying a specific type of data requires processing, which involv...In the last decade, a large amount of data has been published in different fields and can be used as a data source for research and study. However, identifying a specific type of data requires processing, which involves machine learning classifying techniques. To facilitate this, we propose a general framework that can be applied to any social media content to develop an intelligent system. The framework consists of three main parts: an interface, classifier and ana-lyzer. The analyzer uses media recognition to identify specific features. Then, the classifier uses these features and involves them in the classification process. The interface organizes the interaction between the system compo-nents. We tested the framework and developed a system to be applied to im-age-based social media networks (Instagram). The system was implemented as a mobile application (My Interests) that works as a recommendation and filtering system for Instagram users and reduces the time they spend on irre-levant information. It analyzes the images, categorizes them, identifies the in-teresting ones, and finally, reports the results. We used the Cloud Vision API as a tool to analyze the images and extract their features. Furthermore, we adapted support vector machine (SVM), a machine learning method, to classify images and to predict the preferred ones.展开更多
In this study,Co/Zr-metal organic framework(MOF)precursors were obtained by a roomtemperature liquid-phase precipitation method and the equivalent-volume impregnation method,respectively,using a Zr-MOF as the support,...In this study,Co/Zr-metal organic framework(MOF)precursors were obtained by a roomtemperature liquid-phase precipitation method and the equivalent-volume impregnation method,respectively,using a Zr-MOF as the support,and Co/Zr-MOF-M and Co/Zr-MOF-N catalysts were prepared after calcination in a hydrogen-argon mixture gases(VAr:V_(H_(2))=9:1)at 350℃for 2 h.The catalytic activities of the prepared samples for CO_(2)methanation under atmosphericpressure cold plasma were studied.The results showed that Co/Zr-MOF-M had a good synergistic effect with cold plasma.At a discharge power of 13.0 W,V_(H_(2)):VCO_(2)=4:1 and a gas flow rate of 30 ml·min^(-1),the CO_(2)conversion was 58.9%and the CH4 selectivity reached 94.7%,which was higher than for Co/Zr-MOF-N under plasma(CO_(2)conversion 24.8%,CH4 selectivity 9.8%).X-ray diffraction,scanning electron microscopy,transmission electron microscopy,N_(2)adsorption and desorption(Brunauer-Emmett-Teller)and x-ray photoelectron spectroscopy analysis results showed that Co/Zr-MOF-M and Co/Zr-MOF-N retained a good Zr-MOF framework structure,and the Co oxide was uniformly dispersed on the surface of the Zr-MOF.Compared with Co/Zr-MOF-N,the Co/Zr-MOF-M catalyst has a larger specific surface area and higher Co^(2+)/Cototaland Co/Zr ratios.Additionally,the Co oxide in Co/ZrMOF-M is distributed on the surface of the Zr-MOF in the form of porous particles,which may be the main reason why the catalytic activity of Co/Zr-MOF-M is higher than that of Co/ZrMOF-N.展开更多
In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable progress.Accurate predictivemodels for thyroi...In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable progress.Accurate predictivemodels for thyroid cancer enhance early detection,improve resource allocation,and reduce overtreatment.However,the widespread adoption of these models in clinical practice demands predictive performance along with interpretability and transparency.This paper proposes a novel association-rule based feature-integratedmachine learning model which shows better classification and prediction accuracy than present state-of-the-artmodels.Our study also focuses on the application of SHapley Additive exPlanations(SHAP)values as a powerful tool for explaining thyroid cancer prediction models.In the proposed method,the association-rule based feature integration framework identifies frequently occurring attribute combinations in the dataset.The original dataset is used in trainingmachine learning models,and further used in generating SHAP values fromthesemodels.In the next phase,the dataset is integrated with the dominant feature sets identified through association-rule based analysis.This new integrated dataset is used in re-training the machine learning models.The new SHAP values generated from these models help in validating the contributions of feature sets in predicting malignancy.The conventional machine learning models lack interpretability,which can hinder their integration into clinical decision-making systems.In this study,the SHAP values are introduced along with association-rule based feature integration as a comprehensive framework for understanding the contributions of feature sets inmodelling the predictions.The study discusses the importance of reliable predictive models for early diagnosis of thyroid cancer,and a validation framework of explainability.The proposed model shows an accuracy of 93.48%.Performance metrics such as precision,recall,F1-score,and the area under the receiver operating characteristic(AUROC)are also higher than the baseline models.The results of the proposed model help us identify the dominant feature sets that impact thyroid cancer classification and prediction.The features{calcification}and{shape}consistently emerged as the top-ranked features associated with thyroid malignancy,in both association-rule based interestingnessmetric values and SHAPmethods.The paper highlights the potential of the rule-based integrated models with SHAP in bridging the gap between the machine learning predictions and the interpretability of this prediction which is required for real-world medical applications.展开更多
Intelligent Intrusion Detection System(IIDS)for networks provide a resourceful solution to network security than conventional intrusion defence mechanisms like a firewall.The efficiency of IIDS highly relies on the al...Intelligent Intrusion Detection System(IIDS)for networks provide a resourceful solution to network security than conventional intrusion defence mechanisms like a firewall.The efficiency of IIDS highly relies on the algorithm performance.The enhancements towards these methods are utilized to enhance the classification accuracy and diminish the testing and training time of these algorithms.Here,a novel and intelligent learning approach are known as the stabbing of intrusion with learning framework(SILF),is proposed to learn the attack features and reduce the dimensionality.It also reduces the testing and training time effectively and enhances Linear Support Vector Machine(l-SVM).It constructs an auto-encoder method,an efficient learning approach for feature construction unsupervised manner.Here,the inclusive certified signature(ICS)is added to the encoder and decoder to preserve the sensitive data without being harmed by the attackers.By training the samples in the preliminary stage,the selected features are provided into the classifier(lSVM)to enhance the prediction ability for intrusion and classification accuracy.Thus,the model efficiency is learned linearly.The multi-classification is examined and compared with various classifier approaches like conventional SVM,Random Forest(RF),Recurrent Neural Network(RNN),STL-IDS and game theory.The outcomes show that the proposed l-SVM has triggered the prediction rate by effectual testing and training and proves that the model is more efficient than the traditional approaches in terms of performance metrics like accuracy,precision,recall,F-measure,pvalue,MCC and so on.The proposed SILF enhances network intrusion detection and offers a novel research methodology for intrusion detection.Here,the simulation is done with a MATLAB environment where the proposed model shows a better trade-off compared to prevailing approaches.展开更多
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(Nos.NRF-2015R1A4A1041036 and NRF-2018R1C1B6006076)。
文摘Metal nanoparticles(NPs) supported on porous materials have shown great advantages in many catalytic application fields. Supported metal NPs are receiving extensive attention due to their significant contribution in a wide range of current and future applications, and this is arguably one of the fastest growing research fields. In this review, we highlight various types of metal catalysts that possess great potential in several catalytic reactions. The major focus has been on metal oxides, nanoporous metals and metal NPs supported on metal-organic frameworks(MOFs) and zeolites. Special attention has been given to the synthesis strategies and application of the NPs supported on MOFs and zeolites, which are considered highly interesting and rapidly expanding areas in heterogeneous catalysis. Finally, the prospects of these catalysts have been included in the concluding remarks.
基金Project supported by the National Natural Science Foundation of China(Grant No.60504033)
文摘In the paper, an iterative method is presented to the optimal control of batch processes. Generally it is very difficult to acquire an accurate mechanistic model for a batch process. Because support vector machine is powerful for the problems characterized by small samples, nonlinearity, high dimension and local minima, support vector regression models are developed for the optimal control of batch processes where end-point properties are required. The model parameters are selected within the Bayesian evidence framework. Based on the model, an iterative method is used to exploit the repetitive nature of batch processes to determine the optimal operating policy. Numerical simulation shows that the iterative optimal control can improve the process performance through iterations.
文摘Sustainability is a key objective of water resources management and this paper describes a modelling and decision support framework that achieves this, illustrated by applications on the UK Thames and Mekong river basins. The decision support framework contains several modules, including an interactive user＇s interface linked to a GIS, a geo-database, knowledge base, simulation models and optimization procedures. Based on the analysis of scenarios and proposed interventions, efficient modelling and optimization tools form a comprehensive integrated decision support framework for the analysis and operational management of water resources in the river basin, our emphasis has been on a practical implementation through careful screening of alternatives, consideration of the institutional framework and direct involvement of stakeholders in the decision making process. Operating in this environment is transparent, reproducible and auditable, securing the trust of all interested parties. This paper discusses its applications to water utilisation on the Mekong river basin and drought management of the Lower Thames stored reservoir system.
文摘The view that the traditional method of DSS development is outdated, which results to the diversiform disadvantages of DSS product. Therefore the ideas of application software framework based development to the generation process of DSS is introduced and a modified flow chat of DSS development is proposed. Moreover, a formal description of the DSS software framework and its development is given. The analysis results indicates that not only does the new development flow ensure the DSS development global stability but also improves the software reusability level of the development process.
基金Supported by the National Natural Science Foundation of China (No. 60972106, 61072103)China Postdoctoral Science Foundation (No. 20090450750)
文摘This paper proposes a novel approach, Markov Chain Monte Carlo (MCMC) sampling approximation, to deal with intractable high-dimension integral in the evidence framework applied to Support Vector Regression (SVR). Unlike traditional variational or mean field method, the proposed approach follows the idea of MCMC, firstly draws some samples from the posterior distribution on SVR's weight vector, and then approximates the expected output integrals by finite sums. Experimental results show the proposed approach is feasible and robust to noise. It also shows the performance of proposed approach and Relevance Vector Machine (RVM) is comparable under the noise circumstances. They give better robustness compared to standard SVR.
文摘In the last decade, turbulent times and uncertainti es in the business environment have made ground for a new business era, and "chang e" has become a major characteristic of the new era. This has resulted in tirele ss evolution of business systems and the creation of new manufacturing and manag ement philosophies. Agile Manufacturing (AM) is a step forward in generation of new means for better performance and success of business, and in practice is a s trategic approach to manufacturing by considering the new conditions of the business environment. This paper discusses the concepts and development of a met hodology to achieve agility in manufacturing organisations. Following an introdu ction of the subject of agility, a discussion of the methodology and practical t ools to support the implementation of the methodology, including metrics for the assessment of agility drivers, capability and performance are given. Aspects of the tools are tested in an aerospace company.
基金supported by the National Natural Science Foundation of China (60874068)
文摘The command and control（C2） is a decision-making process based on human cognition,which contains operational,physical,and human characteristics,so it takes on uncertainty and complexity.As a decision support approach,Bayesian networks（BNs） provide a framework in which a decision is made by combining the experts＇ knowledge and the specific data.In addition,an expert system represented by human cognitive framework is adopted to express the real-time decision-making process of the decision maker.The combination of the Bayesian decision support and human cognitive framework in the C2 of a specific application field is modeled and executed by colored Petri nets（CPNs）,and the consequences of execution manifest such combination can perfectly present the decision-making process in C2.
基金supported by the National Natural Science Foundation of China (21473196, 21406215)the State Key Laboratory of Fine Chemicals, Dalian University of Technology (KF1415)the funding from Dalian Institute of Chemical Physics, Chinese Academy of Sciences (DICP_M201401)~~
文摘Covalent organic frameworks （COFs）, established as an emerging class of crystalline porous polymers with high surface area, structural diversity, and esignability, attract much interest and exhibit potential applications in catalysis. In this review, we summarize the use of COFs as a versatile platform to develop heterogeneous catalysts for a variety of chemical reactions. Catalytic COFs are categorized in accordance with the types of active sites, involving single functional active sites, bifunctional active sites, and metal nanoparticles （NPs） embedded in pores. Special emphasis is placed on the deliberate or incidental synthesis strategies, the stability, the heterogeneity, and the shape/size selectivity for COF catalysis. Moreover, a description of the application of COFs as photocatalysts and electrocatalysts is presented. Finally, the prospects of COFs in catalysis and remaining issues in this field are indicated.
基金the funding from the National Natural Science Foundation of China (22078107, 22022805)the National Key Research and Development Program (2021YFB3802500)。
文摘During the last decade, metal-organic frameworks(MOFs) have been applied in various fields due to their unique chemical and functional advantages. One of the widespread research hotspots is MOF-based membranes for separations, specifically continuous defect-free MOF membranes, which are usually grown on porous substrates. The substrate not only serves as the MOF layer support but also has a great influence on the membrane fabrication process and the final separation performance of the resultant membrane. In this review, we mainly introduce the progress focused on the substrates for MOF membranes fabrication. The substrate modifications and seeding methods aimed at synthesizing highquality MOF membranes are also summarized systematically.
基金supported by the National Natural Science Foundation of China(Nos.22006131 and 22276171)the Zhejiang Provincial Natural Science Foundation of China(No.LQ20B070010)+1 种基金the China Postdoctoral Science Foundation(Nos.2020T130598 and 2019M662106)the Fund of Zhuhai Science and Technology Bureau,China(No.ZH22017003210025PWC)。
文摘Photocatalysis using the abundant solar energy is an environmentally friendly and efficient way to degrade organic matter.Covalent triazine frameworks(CTFs),a new class of metal-free organic semiconductors responsive to visible light,are promising materials for water treatment.In this study,an original CTF,namely CTF-1,was modified by S-doping to form CTFSx,which were used as metal-free catalysts for degradation of methyl orange(MO)and bisphenol A(BPA).The outcomes demonstrated that the photocatalytic degradation of MO and BPA by CTFSxwas superior to that by CTF-1,with better stability and reusability.Within 6 h,53.2%MO and 84.7%BPA were degraded by CTFS5,and the degradation rate constants were 0.145 h-1and 0.29 h-1,respectively,which were 3.6 and 5.8 times higher than those of CTF-1.Further investigation revealed that enhanced visible light absorption,a reduced degree of free carrier recombination,rapid separation and transfer of photogenerated electrons and holes,and improved·OH oxidation capacity were important factors contributing to the significantly enhanced photocatalytic activity.The S-doping method effectively improved the light absorption performance,electronic structure,and modulation band structure of CTF-1.This work highlights the potential application of low-cost metal-free catalysts driven by visible light for the removal of organic pollutants from wastewater.
基金the Foundation of Returned Scholar of Shaanxi Province(SLZ2008006)
文摘An approach was proposed for optimizing beamforming that was based on Support Vector Regression (SVR). After studying the mathematical principal of the SVR algorithm and its primal cost function, the modified cost function was first applied to uniform array beamforming, and then the corresponding parameters of the beamforming were optimized. The framework of SVR uniform array beamforming was then established. Simulation results show that SVR beamforming can not only approximate the performance of conventional beamforming in the area without noise and with small data sets, but also improve the generalization ability and reduce the computation burden. Also, the side lobe level of both linear and circular arrays by the SVR algorithm is improved sharply through comparison with the conventional one. SVR beamforming is superior to the conventional method in both linear and circular arrays, under single source or double non-coherent sources.
文摘In the last decade, a large amount of data has been published in different fields and can be used as a data source for research and study. However, identifying a specific type of data requires processing, which involves machine learning classifying techniques. To facilitate this, we propose a general framework that can be applied to any social media content to develop an intelligent system. The framework consists of three main parts: an interface, classifier and ana-lyzer. The analyzer uses media recognition to identify specific features. Then, the classifier uses these features and involves them in the classification process. The interface organizes the interaction between the system compo-nents. We tested the framework and developed a system to be applied to im-age-based social media networks (Instagram). The system was implemented as a mobile application (My Interests) that works as a recommendation and filtering system for Instagram users and reduces the time they spend on irre-levant information. It analyzes the images, categorizes them, identifies the in-teresting ones, and finally, reports the results. We used the Cloud Vision API as a tool to analyze the images and extract their features. Furthermore, we adapted support vector machine (SVM), a machine learning method, to classify images and to predict the preferred ones.
基金supported by National Natural Science Foundation of China(Nos.21673026,11605020)Innovative Training Program for College Student of Liaoning Province(No.S202011258068)。
文摘In this study,Co/Zr-metal organic framework(MOF)precursors were obtained by a roomtemperature liquid-phase precipitation method and the equivalent-volume impregnation method,respectively,using a Zr-MOF as the support,and Co/Zr-MOF-M and Co/Zr-MOF-N catalysts were prepared after calcination in a hydrogen-argon mixture gases(VAr:V_(H_(2))=9:1)at 350℃for 2 h.The catalytic activities of the prepared samples for CO_(2)methanation under atmosphericpressure cold plasma were studied.The results showed that Co/Zr-MOF-M had a good synergistic effect with cold plasma.At a discharge power of 13.0 W,V_(H_(2)):VCO_(2)=4:1 and a gas flow rate of 30 ml·min^(-1),the CO_(2)conversion was 58.9%and the CH4 selectivity reached 94.7%,which was higher than for Co/Zr-MOF-N under plasma(CO_(2)conversion 24.8%,CH4 selectivity 9.8%).X-ray diffraction,scanning electron microscopy,transmission electron microscopy,N_(2)adsorption and desorption(Brunauer-Emmett-Teller)and x-ray photoelectron spectroscopy analysis results showed that Co/Zr-MOF-M and Co/Zr-MOF-N retained a good Zr-MOF framework structure,and the Co oxide was uniformly dispersed on the surface of the Zr-MOF.Compared with Co/Zr-MOF-N,the Co/Zr-MOF-M catalyst has a larger specific surface area and higher Co^(2+)/Cototaland Co/Zr ratios.Additionally,the Co oxide in Co/ZrMOF-M is distributed on the surface of the Zr-MOF in the form of porous particles,which may be the main reason why the catalytic activity of Co/Zr-MOF-M is higher than that of Co/ZrMOF-N.
文摘In the era of advanced machine learning techniques,the development of accurate predictive models for complex medical conditions,such as thyroid cancer,has shown remarkable progress.Accurate predictivemodels for thyroid cancer enhance early detection,improve resource allocation,and reduce overtreatment.However,the widespread adoption of these models in clinical practice demands predictive performance along with interpretability and transparency.This paper proposes a novel association-rule based feature-integratedmachine learning model which shows better classification and prediction accuracy than present state-of-the-artmodels.Our study also focuses on the application of SHapley Additive exPlanations(SHAP)values as a powerful tool for explaining thyroid cancer prediction models.In the proposed method,the association-rule based feature integration framework identifies frequently occurring attribute combinations in the dataset.The original dataset is used in trainingmachine learning models,and further used in generating SHAP values fromthesemodels.In the next phase,the dataset is integrated with the dominant feature sets identified through association-rule based analysis.This new integrated dataset is used in re-training the machine learning models.The new SHAP values generated from these models help in validating the contributions of feature sets in predicting malignancy.The conventional machine learning models lack interpretability,which can hinder their integration into clinical decision-making systems.In this study,the SHAP values are introduced along with association-rule based feature integration as a comprehensive framework for understanding the contributions of feature sets inmodelling the predictions.The study discusses the importance of reliable predictive models for early diagnosis of thyroid cancer,and a validation framework of explainability.The proposed model shows an accuracy of 93.48%.Performance metrics such as precision,recall,F1-score,and the area under the receiver operating characteristic(AUROC)are also higher than the baseline models.The results of the proposed model help us identify the dominant feature sets that impact thyroid cancer classification and prediction.The features{calcification}and{shape}consistently emerged as the top-ranked features associated with thyroid malignancy,in both association-rule based interestingnessmetric values and SHAPmethods.The paper highlights the potential of the rule-based integrated models with SHAP in bridging the gap between the machine learning predictions and the interpretability of this prediction which is required for real-world medical applications.
文摘Intelligent Intrusion Detection System(IIDS)for networks provide a resourceful solution to network security than conventional intrusion defence mechanisms like a firewall.The efficiency of IIDS highly relies on the algorithm performance.The enhancements towards these methods are utilized to enhance the classification accuracy and diminish the testing and training time of these algorithms.Here,a novel and intelligent learning approach are known as the stabbing of intrusion with learning framework(SILF),is proposed to learn the attack features and reduce the dimensionality.It also reduces the testing and training time effectively and enhances Linear Support Vector Machine(l-SVM).It constructs an auto-encoder method,an efficient learning approach for feature construction unsupervised manner.Here,the inclusive certified signature(ICS)is added to the encoder and decoder to preserve the sensitive data without being harmed by the attackers.By training the samples in the preliminary stage,the selected features are provided into the classifier(lSVM)to enhance the prediction ability for intrusion and classification accuracy.Thus,the model efficiency is learned linearly.The multi-classification is examined and compared with various classifier approaches like conventional SVM,Random Forest(RF),Recurrent Neural Network(RNN),STL-IDS and game theory.The outcomes show that the proposed l-SVM has triggered the prediction rate by effectual testing and training and proves that the model is more efficient than the traditional approaches in terms of performance metrics like accuracy,precision,recall,F-measure,pvalue,MCC and so on.The proposed SILF enhances network intrusion detection and offers a novel research methodology for intrusion detection.Here,the simulation is done with a MATLAB environment where the proposed model shows a better trade-off compared to prevailing approaches.
