Cross-Site Scripting(XSS)remains a significant threat to web application security,exploiting vulnerabilities to hijack user sessions and steal sensitive data.Traditional detection methods often fail to keep pace with ...Cross-Site Scripting(XSS)remains a significant threat to web application security,exploiting vulnerabilities to hijack user sessions and steal sensitive data.Traditional detection methods often fail to keep pace with the evolving sophistication of cyber threats.This paper introduces a novel hybrid ensemble learning framework that leverages a combination of advanced machine learning algorithms—Logistic Regression(LR),Support Vector Machines(SVM),eXtreme Gradient Boosting(XGBoost),Categorical Boosting(CatBoost),and Deep Neural Networks(DNN).Utilizing the XSS-Attacks-2021 dataset,which comprises 460 instances across various real-world trafficrelated scenarios,this framework significantly enhances XSS attack detection.Our approach,which includes rigorous feature engineering and model tuning,not only optimizes accuracy but also effectively minimizes false positives(FP)(0.13%)and false negatives(FN)(0.19%).This comprehensive methodology has been rigorously validated,achieving an unprecedented accuracy of 99.87%.The proposed system is scalable and efficient,capable of adapting to the increasing number of web applications and user demands without a decline in performance.It demonstrates exceptional real-time capabilities,with the ability to detect XSS attacks dynamically,maintaining high accuracy and low latency even under significant loads.Furthermore,despite the computational complexity introduced by the hybrid ensemble approach,strategic use of parallel processing and algorithm tuning ensures that the system remains scalable and performs robustly in real-time applications.Designed for easy integration with existing web security systems,our framework supports adaptable Application Programming Interfaces(APIs)and a modular design,facilitating seamless augmentation of current defenses.This innovation represents a significant advancement in cybersecurity,offering a scalable and effective solution for securing modern web applications against evolving threats.展开更多
With the acceleration of network communication in the 5G era,the volume of data communication in cyberspace has increased unprecedentedly.The speed of data transmission will accelerate.Subsequently,the security of net...With the acceleration of network communication in the 5G era,the volume of data communication in cyberspace has increased unprecedentedly.The speed of data transmission will accelerate.Subsequently,the security of network communication data becomes more and more serious.Among them,malicious cross⁃site scripting leading to the leakage of user information is very serious.This article uses URL attribute analysis method and YARA rule to process data for cross⁃site scripting based on the long short⁃term memory(LSTM)characteristics of LSTM model.The results show that the LSTM classification model adopted in this paper has higher recall rate and F1⁃score than other machine learning methods,which proves that the method adopted in this paper is feasible.展开更多
Purpose: Linac quality assurance (QA) can be time consuming involving set up, execution, analysis and subject to user variability. The purpose of this study is to develop qualitative automation tools for mechanical an...Purpose: Linac quality assurance (QA) can be time consuming involving set up, execution, analysis and subject to user variability. The purpose of this study is to develop qualitative automation tools for mechanical and imaging QA to improve efficiency, consistency, and accuracy. Methods and Materials: Traditionally QA has been performed with graph paper, film, and multiple phantoms. Analysis consists of ruler and vendor provided software. We have developed a single four-phantom method for QA procedures including light-radiation coincidence, imaging quality, table motion and Isocentricity and separately cone beam computed tomography. XML scripts were developed to execute a series of tasks using Varian’s Truebeam Developer Mode. Non-phantom QA procedures have also been developed including field size, dose rate, MLC position, MLC and gantry speed, star shot, Winston-Lutz and Half Beam Block. All analysis is performed using inhouse MATLAB codes. Results: Overall time savings were 2.2 hours per Linac per month. Consistency improvements (standard deviation, STD) were observed for some tests. For example: field size improved from 0.11 mm to 0.04 mm and table motion improved from 0.17 mm to 0.12 mm. CBCT STD improved from 0.99 mm to 0.61 mm for slice thickness. No STD change was observed for Isocentricity test. We noticed an increase in STD from 0.33 mm to 0.41 mm for light-radiation coincidence test. There was a small drop in field size accuracy. Isocentricity showed an increase in measurement accuracy from 0.47 mm to 0.15 mm. Table motion increased in accuracy from 0.20 mm to 0.16 mm. Conclusion: Automation is a viable, accurate and efficient option for monthly and annual QA.展开更多
Programming and scripting can be used to activate a 3D parametric model to create a more intelligent and flexible building information model. There has been a trend in the building industry towards the use of visual s...Programming and scripting can be used to activate a 3D parametric model to create a more intelligent and flexible building information model. There has been a trend in the building industry towards the use of visual scripting that allow users to create customized, flexible, and powerful programs without having to first learn how to write traditional code. Using visual scripting, users graphically interact with program elements instead of typing lines of text-based code. Nodes are created and virtually wired together;they can be numbers, sliders for adjusting values, operators and functions, list manipulation tools, graphic creators, and other types. Text based coding programs such as Python can also be used for the creation of custom nodes when greater flexibility is desired. Examples from professional firms include scripts that help automate work in the office to increase efficiency and accuracy (e.g. create escape routes, renumber rooms by levels, create documentation), assist in form generation (e.g. parametric design of metal panels, rebar generation, coordination between Revit and Rhino), analyze BIM files (e.g. terminal airflow, visual loads and capacity), and provide analysis results (e.g. daylighting, thermal comfort, window optimization). One can learn the basic steps of learning a visual programming language through the use of Dynamo within Autodesk Revit. The example used is for a façade component that changes based on the sun’s altitude.展开更多
JShellLab is an easy to use MATLAB-like environment for the Java Virtual Machine(JVM).It implements scientific scripting based on the JShell Application Programming Interface(API)of modern Java.The paper illustrates t...JShellLab is an easy to use MATLAB-like environment for the Java Virtual Machine(JVM).It implements scientific scripting based on the JShell Application Programming Interface(API)of modern Java.The paper illustrates that JShellLab can significantly facilitate and simplify the development of complex computational demanding scientific software at the JVM.The novelty at the JShellLab is that it completely hides the complexity and the intricate dependencies of optimized scientific software.As an example,the demanded field of deep learning is exploited.Specifically,the implementation of effective practical deep learning-based systems using the JShellLab environment and the Deeplearning4j Java library is considered.展开更多
The document G21.004[20487],which is a fragment of Tangut script medical formulas held in Gansu Provincial Museum,contains 147 Tangut characters and 3 repetition marks,with the text separated by two circles.At present...The document G21.004[20487],which is a fragment of Tangut script medical formulas held in Gansu Provincial Museum,contains 147 Tangut characters and 3 repetition marks,with the text separated by two circles.At present,the academic world believes that there are three kinds of medical formulas in the fragment.Regarding the controversial line 3,for example,the text does not refer to“husked sorghum porridge”as previously translated by scholars.Instead,it means“when the rice is fully cooked,the decoction is done”.The term“Hou Luo Xin Ma(厚罗辛麻)”in line 4 should instead be translated as“Hou Lao Xi Ma(厚蓉膝麻)”.Line 5 should be translated in accordance with the writing paradigm of ancient medical books as“cure and eliminate 100 kinds of cold diseases,immortal sesame formula for longevity(神仙胡麻方)”.This study identifies seven herbs within the fragment of Tangut script medical formulas,which are related to the treatment of“cold diseases(冷疾)”,rather than cold damage(伤寒).The study of G21.004[20487]fragments involves not only the decipherment of Xixia characters and the interpretation of medical formulas,but also contributes to a deeper understanding of the medical knowledge system of the Xixia dynasty,the application of medicinal materials,and the degree of cultural exchange and integration with central plains medicine.These unearthed documents are valuable materials that fill the gaps in Chinese medical history and reconstruct the ancient medical landscape.展开更多
The phase field model can coherently address the relatively complex fracture phenomenon,such as crack nucleation,branching,deflection,etc.The model has been extensively implemented in the finite element package Abaqus...The phase field model can coherently address the relatively complex fracture phenomenon,such as crack nucleation,branching,deflection,etc.The model has been extensively implemented in the finite element package Abaqus to solve brittle fracture problems in recent studies.However,accurate numerical analysis typically requires fine meshes to model the evolving crack path effectively.A broad region must be discretized without prior knowledge of the crack path,further augmenting the computational expenses.In this proposed work,we present an automated framework utilizing a posteriori error-indicator(MISESERI)to demarcate and sufficiently refine the mesh along the anticipated crack path.This eliminates the need for manual mesh refinement based on previous experimental/computational results or heuristic judgment.The proposed Python-based framework integrates the preanalysis,sufficient mesh refinement,and subsequent phase-field model-based numerical analysis with user-defined subroutines in a single streamlined pass.The novelty of the proposed work lies in integrating Abaqus’s native error estimation and mesh refinement capability,tailored explicitly for phase-field simulations.The proposed methodology aims to reduce the computational resource requirement,thereby enhancing the efficiency of the phase-field simulations while preserving the solution accuracy,making the framework particularly advantageous for complex fracture problems where the computational/experimental results are limited or unavailable.Several benchmark numerical problems are solved to showcase the effectiveness and accuracy of the proposed approach.The numerical examples present the proposed approach’s efficacy in the case of a complex mixed-mode fracture problem.The results show significant reductions in computational resources compared to traditional phase-field methods,which is promising.展开更多
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2024R513),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
摘要Cross-Site Scripting(XSS)remains a significant threat to web application security,exploiting vulnerabilities to hijack user sessions and steal sensitive data.Traditional detection methods often fail to keep pace with the evolving sophistication of cyber threats.This paper introduces a novel hybrid ensemble learning framework that leverages a combination of advanced machine learning algorithms—Logistic Regression(LR),Support Vector Machines(SVM),eXtreme Gradient Boosting(XGBoost),Categorical Boosting(CatBoost),and Deep Neural Networks(DNN).Utilizing the XSS-Attacks-2021 dataset,which comprises 460 instances across various real-world trafficrelated scenarios,this framework significantly enhances XSS attack detection.Our approach,which includes rigorous feature engineering and model tuning,not only optimizes accuracy but also effectively minimizes false positives(FP)(0.13%)and false negatives(FN)(0.19%).This comprehensive methodology has been rigorously validated,achieving an unprecedented accuracy of 99.87%.The proposed system is scalable and efficient,capable of adapting to the increasing number of web applications and user demands without a decline in performance.It demonstrates exceptional real-time capabilities,with the ability to detect XSS attacks dynamically,maintaining high accuracy and low latency even under significant loads.Furthermore,despite the computational complexity introduced by the hybrid ensemble approach,strategic use of parallel processing and algorithm tuning ensures that the system remains scalable and performs robustly in real-time applications.Designed for easy integration with existing web security systems,our framework supports adaptable Application Programming Interfaces(APIs)and a modular design,facilitating seamless augmentation of current defenses.This innovation represents a significant advancement in cybersecurity,offering a scalable and effective solution for securing modern web applications against evolving threats.
摘要With the acceleration of network communication in the 5G era,the volume of data communication in cyberspace has increased unprecedentedly.The speed of data transmission will accelerate.Subsequently,the security of network communication data becomes more and more serious.Among them,malicious cross⁃site scripting leading to the leakage of user information is very serious.This article uses URL attribute analysis method and YARA rule to process data for cross⁃site scripting based on the long short⁃term memory(LSTM)characteristics of LSTM model.The results show that the LSTM classification model adopted in this paper has higher recall rate and F1⁃score than other machine learning methods,which proves that the method adopted in this paper is feasible.
摘要Purpose: Linac quality assurance (QA) can be time consuming involving set up, execution, analysis and subject to user variability. The purpose of this study is to develop qualitative automation tools for mechanical and imaging QA to improve efficiency, consistency, and accuracy. Methods and Materials: Traditionally QA has been performed with graph paper, film, and multiple phantoms. Analysis consists of ruler and vendor provided software. We have developed a single four-phantom method for QA procedures including light-radiation coincidence, imaging quality, table motion and Isocentricity and separately cone beam computed tomography. XML scripts were developed to execute a series of tasks using Varian’s Truebeam Developer Mode. Non-phantom QA procedures have also been developed including field size, dose rate, MLC position, MLC and gantry speed, star shot, Winston-Lutz and Half Beam Block. All analysis is performed using inhouse MATLAB codes. Results: Overall time savings were 2.2 hours per Linac per month. Consistency improvements (standard deviation, STD) were observed for some tests. For example: field size improved from 0.11 mm to 0.04 mm and table motion improved from 0.17 mm to 0.12 mm. CBCT STD improved from 0.99 mm to 0.61 mm for slice thickness. No STD change was observed for Isocentricity test. We noticed an increase in STD from 0.33 mm to 0.41 mm for light-radiation coincidence test. There was a small drop in field size accuracy. Isocentricity showed an increase in measurement accuracy from 0.47 mm to 0.15 mm. Table motion increased in accuracy from 0.20 mm to 0.16 mm. Conclusion: Automation is a viable, accurate and efficient option for monthly and annual QA.
摘要Programming and scripting can be used to activate a 3D parametric model to create a more intelligent and flexible building information model. There has been a trend in the building industry towards the use of visual scripting that allow users to create customized, flexible, and powerful programs without having to first learn how to write traditional code. Using visual scripting, users graphically interact with program elements instead of typing lines of text-based code. Nodes are created and virtually wired together;they can be numbers, sliders for adjusting values, operators and functions, list manipulation tools, graphic creators, and other types. Text based coding programs such as Python can also be used for the creation of custom nodes when greater flexibility is desired. Examples from professional firms include scripts that help automate work in the office to increase efficiency and accuracy (e.g. create escape routes, renumber rooms by levels, create documentation), assist in form generation (e.g. parametric design of metal panels, rebar generation, coordination between Revit and Rhino), analyze BIM files (e.g. terminal airflow, visual loads and capacity), and provide analysis results (e.g. daylighting, thermal comfort, window optimization). One can learn the basic steps of learning a visual programming language through the use of Dynamo within Autodesk Revit. The example used is for a façade component that changes based on the sun’s altitude.
摘要JShellLab is an easy to use MATLAB-like environment for the Java Virtual Machine(JVM).It implements scientific scripting based on the JShell Application Programming Interface(API)of modern Java.The paper illustrates that JShellLab can significantly facilitate and simplify the development of complex computational demanding scientific software at the JVM.The novelty at the JShellLab is that it completely hides the complexity and the intricate dependencies of optimized scientific software.As an example,the demanded field of deep learning is exploited.Specifically,the implementation of effective practical deep learning-based systems using the JShellLab environment and the Deeplearning4j Java library is considered.
基金financed by Major Project of the National Language Commission’s“14th Five-Year Plan”Scientific Research Planning for 2024(No.ZDA145-21)Special Project for Cultivating Rising Talents in Scientific Research at Beijing University of Chinese Medicine(No.K2023D02)Basic Scientific Research Business Expense Scientific Research Platform Construction Project at Beijing University of Chinese Medicine(No.2026-JYB-KYPT-12).
摘要The document G21.004[20487],which is a fragment of Tangut script medical formulas held in Gansu Provincial Museum,contains 147 Tangut characters and 3 repetition marks,with the text separated by two circles.At present,the academic world believes that there are three kinds of medical formulas in the fragment.Regarding the controversial line 3,for example,the text does not refer to“husked sorghum porridge”as previously translated by scholars.Instead,it means“when the rice is fully cooked,the decoction is done”.The term“Hou Luo Xin Ma(厚罗辛麻)”in line 4 should instead be translated as“Hou Lao Xi Ma(厚蓉膝麻)”.Line 5 should be translated in accordance with the writing paradigm of ancient medical books as“cure and eliminate 100 kinds of cold diseases,immortal sesame formula for longevity(神仙胡麻方)”.This study identifies seven herbs within the fragment of Tangut script medical formulas,which are related to the treatment of“cold diseases(冷疾)”,rather than cold damage(伤寒).The study of G21.004[20487]fragments involves not only the decipherment of Xixia characters and the interpretation of medical formulas,but also contributes to a deeper understanding of the medical knowledge system of the Xixia dynasty,the application of medicinal materials,and the degree of cultural exchange and integration with central plains medicine.These unearthed documents are valuable materials that fill the gaps in Chinese medical history and reconstruct the ancient medical landscape.
摘要The phase field model can coherently address the relatively complex fracture phenomenon,such as crack nucleation,branching,deflection,etc.The model has been extensively implemented in the finite element package Abaqus to solve brittle fracture problems in recent studies.However,accurate numerical analysis typically requires fine meshes to model the evolving crack path effectively.A broad region must be discretized without prior knowledge of the crack path,further augmenting the computational expenses.In this proposed work,we present an automated framework utilizing a posteriori error-indicator(MISESERI)to demarcate and sufficiently refine the mesh along the anticipated crack path.This eliminates the need for manual mesh refinement based on previous experimental/computational results or heuristic judgment.The proposed Python-based framework integrates the preanalysis,sufficient mesh refinement,and subsequent phase-field model-based numerical analysis with user-defined subroutines in a single streamlined pass.The novelty of the proposed work lies in integrating Abaqus’s native error estimation and mesh refinement capability,tailored explicitly for phase-field simulations.The proposed methodology aims to reduce the computational resource requirement,thereby enhancing the efficiency of the phase-field simulations while preserving the solution accuracy,making the framework particularly advantageous for complex fracture problems where the computational/experimental results are limited or unavailable.Several benchmark numerical problems are solved to showcase the effectiveness and accuracy of the proposed approach.The numerical examples present the proposed approach’s efficacy in the case of a complex mixed-mode fracture problem.The results show significant reductions in computational resources compared to traditional phase-field methods,which is promising.