Emergency medical services (EMS) are a vital element of the public healthcare system in China,^([1])providing an opportunity to respond to critical medical conditions and save people’s lives.^([2])The accessibility o...Emergency medical services (EMS) are a vital element of the public healthcare system in China,^([1])providing an opportunity to respond to critical medical conditions and save people’s lives.^([2])The accessibility of EMS has received considerable attention in health and transport geography studies.^([3])One of the optimal gauges for evaluating the accessibility of EMS is the response time,which is defined as the time from receiving an emergency call to the arrival of an ambulance.^([4])Beijing has already reduced the response time to approximately12 min,and the next goal is to ensure that the response time across Beijing does not exceed 12 min (the information comes from the Beijing Emergency Medical Center).展开更多
在万物互联的云时代,云应用程序编程接口(API)是数字经济建设和服务化软件开发的关键数字基础设施。然而,云API数量的持续增长给用户决策和推广带来挑战,设计有效的推荐方法成为亟待解决的重要问题。现有研究多利用调用偏好、搜索关键...在万物互联的云时代,云应用程序编程接口(API)是数字经济建设和服务化软件开发的关键数字基础设施。然而,云API数量的持续增长给用户决策和推广带来挑战,设计有效的推荐方法成为亟待解决的重要问题。现有研究多利用调用偏好、搜索关键词或二者结合进行建模,主要解决为给定Mashup推荐合适云API的问题,未考虑开发者对个性化高阶互补云API的实际需求。该文提出一种基于个性化张量分解的高阶互补云API推荐方法(Personalized Tensor Decomposition based High-order Complementary cloud API Recommendation,PTDHCR)。首先,将Mashup与云API之间的调用关系,以及云API与云API之间的互补关系建模为三维张量,并利用RECAL张量分解技术对这两种关系进行共同学习,以挖掘云API之间的个性化非对称互补关系。然后,考虑到不同互补关系对推荐结果的影响程度不同,构建个性化高阶互补感知网络,充分利用Mashup、查询云API以及候选云API的多模态特征,动态计算Mashup对不同查询和候选云API之间互补关系的关注程度。在此基础上,将个性化互补关系拓展到高阶,得到候选云API与查询云API集合的整体个性化互补性。最后,利用两个真实云API数据集进行实验,结果表明,相较于传统方法,PTDHCR在挖掘个性化互补关系和推荐方面具有较大的优势。展开更多
Ransomware,particularly crypto-ransomware,remains a significant cybersecurity challenge,encrypting victim data and demanding a ransom,often leaving the data irretrievable even if payment is made.This study proposes an...Ransomware,particularly crypto-ransomware,remains a significant cybersecurity challenge,encrypting victim data and demanding a ransom,often leaving the data irretrievable even if payment is made.This study proposes an early detection approach to mitigate such threats by identifying ransomware activity before the encryption process begins.The approach employs a two-tiered approach:a signature-based method using hashing techniques to match known threats and a dynamic behavior-based analysis leveraging Cuckoo Sandbox and machine learning algorithms.A critical feature is the integration of the most effective Application Programming Interface call monitoring,which analyzes system-level interactions such as file encryption,key generation,and registry modifications.This enables the detection of both known and zero-day ransomware variants,overcoming limitations of traditional methods.The proposed technique was evaluated using classifiers such as Random Forest,Support Vector Machine,and K-Nearest Neighbors,achieving a detection accuracy of 98%based on 26 key ransomware attributes with an 80:20 training-to-testing ratio and 10-fold cross-validation.By combining minimal feature sets with robust behavioral analysis,the proposed method outperforms existing solutions and addresses current challenges in ransomware detection,thereby enhancing cybersecurity resilience.展开更多
针对恶意软件利用环境感知能力来逃避分析系统检测的现状,深入研究基于系统应用程序接口(Application Program Interface,API)的环境感知技术,并实现全面检测环境感知API的自动化工具EAFinder(Environment-Aware API Finder)。EAFinder...针对恶意软件利用环境感知能力来逃避分析系统检测的现状,深入研究基于系统应用程序接口(Application Program Interface,API)的环境感知技术,并实现全面检测环境感知API的自动化工具EAFinder(Environment-Aware API Finder)。EAFinder能够枚举所有的系统API,并在真机和模拟器中进行自动化调用,最终通过比较API在不同环境中的可访问性和返回值的差异,检测出环境感知API。实验结果显示EAFinder在Android 9至13上共检测出344个API,排除误报后得到323个可用于环境感知的API。将其按使用方式分为独立使用、基于阈值使用和组合使用三类,并抽样测试了各类API的有效性,结果显示利用这些API能以97%的准确率区分真实设备和模拟器。展开更多
The evolution of technology in 1990s resulted in the enormous growth of smartphones and the propagation of mobile applications (App) that marked new opportunities for healthcare centers and medical education. Apps hav...The evolution of technology in 1990s resulted in the enormous growth of smartphones and the propagation of mobile applications (App) that marked new opportunities for healthcare centers and medical education. Apps have altered health services from patient’s health monitoring to specialist’s appointments and consultations from specialized health facilities. It can be argued that a healthy society can bring forth sustainable economic development to its full potential while an unhealthy society cannot. However, a free movement of people, labour and right to residence which was built across East Africa (EA) borders enabled Tanzania and Kenya borders to have enormous interactions. Subsequently, increase the risk of highly communicable diseases such as Tuberculosis and Sexually transmitted infections in such a way that medical attention is unavoidable along the borders. Statistically, Android Operating System (OS) owns 83% of Africa’s mobile OS market. In addition, 25,794,560 internet users reported by Tanzania Communications Regulatory Authority (TCRA) together with the 22.86 million internet users provided by Kenya Digital which is equivalent to 46% and 43% of internet penetration in year 2020, disclose the need for Android mobile application for mapping health facilities both online and offline using Google map API, which will solve residents’ need to healthcare services on the presence or shortage of internet connections;using either Swahili or English language via Smartphone devices. The App incorporates Monitoring and Evaluation (M & E) tool for tracking application usage which will ease Admin’s task to generate daily and monthly reports in Excel and Comma-Separated Values (CSV) formats. The developed system received positive feedback from EA citizens and residents in the Arusha region and Namanga border crossing where 90.2% of the system evaluation conducted between Dec 2020 and Apr 2021 agreed upon App usage.展开更多
针对目前恶意软件检测分类方法在特征提取、检测准确率等方面面临的挑战,提出一种基于API分组重构与图像表示的恶意软件检测分类方法。首先,对恶意软件调用的API类别统一编号,将API指令序列中相同编号的API聚合为同一API组,根据恶意软...针对目前恶意软件检测分类方法在特征提取、检测准确率等方面面临的挑战,提出一种基于API分组重构与图像表示的恶意软件检测分类方法。首先,对恶意软件调用的API类别统一编号,将API指令序列中相同编号的API聚合为同一API组,根据恶意软件运行时各类API的首次调用顺序对API组重排序,将各API组的条目数记录为该类API对软件样本的贡献度。经分组重构后,各API组按序组织,其顺序为软件样本调用各类API的顺序。各API组内部有序,其内部各API的排列顺序即为软件样本对单个API的调用顺序。有序化的API分组有助于API指令序列信息的图像化表达。基于重组的API指令序列提取API编号作为全局特征列表、API贡献度作为局部特征列表、API顺序索引作为时序特征列表,对特征列表进行标准化与零填充,转化为统一尺寸的特征数组。其中,API编号能清晰地标识API类别,API贡献度可以表征该API的调用频繁程度,API顺序索引可区分各API被调用的顺序。然后,分别用3类特征数组填充RGB图像的3个通道,生成3通道的API编号贡献度及顺序索引特征图像(Feature image of API code devotion and sequential index,FimgCDS)。最后,将Fimg CDS特征图像输入自主构建的轻量型恶意软件特征图像卷积神经网络(malware feature image convolutional neural network,MficNN)分类器,实现对恶意软件的检测与分类。实验结果表明,本文方法在两类数据集上的检测分类准确率分别为98.66%和98.35%,具有较高的恶意软件检测分类性能指标和检测分类速度。展开更多
基金supported by National Key Research & Development Program of China (2022YFC3006201)。
文摘Emergency medical services (EMS) are a vital element of the public healthcare system in China,^([1])providing an opportunity to respond to critical medical conditions and save people’s lives.^([2])The accessibility of EMS has received considerable attention in health and transport geography studies.^([3])One of the optimal gauges for evaluating the accessibility of EMS is the response time,which is defined as the time from receiving an emergency call to the arrival of an ambulance.^([4])Beijing has already reduced the response time to approximately12 min,and the next goal is to ensure that the response time across Beijing does not exceed 12 min (the information comes from the Beijing Emergency Medical Center).
文摘在万物互联的云时代,云应用程序编程接口(API)是数字经济建设和服务化软件开发的关键数字基础设施。然而,云API数量的持续增长给用户决策和推广带来挑战,设计有效的推荐方法成为亟待解决的重要问题。现有研究多利用调用偏好、搜索关键词或二者结合进行建模,主要解决为给定Mashup推荐合适云API的问题,未考虑开发者对个性化高阶互补云API的实际需求。该文提出一种基于个性化张量分解的高阶互补云API推荐方法(Personalized Tensor Decomposition based High-order Complementary cloud API Recommendation,PTDHCR)。首先,将Mashup与云API之间的调用关系,以及云API与云API之间的互补关系建模为三维张量,并利用RECAL张量分解技术对这两种关系进行共同学习,以挖掘云API之间的个性化非对称互补关系。然后,考虑到不同互补关系对推荐结果的影响程度不同,构建个性化高阶互补感知网络,充分利用Mashup、查询云API以及候选云API的多模态特征,动态计算Mashup对不同查询和候选云API之间互补关系的关注程度。在此基础上,将个性化互补关系拓展到高阶,得到候选云API与查询云API集合的整体个性化互补性。最后,利用两个真实云API数据集进行实验,结果表明,相较于传统方法,PTDHCR在挖掘个性化互补关系和推荐方面具有较大的优势。
基金funded by the National University of Sciences and Technology(NUST)supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(2021R1IIA3049788).
文摘Ransomware,particularly crypto-ransomware,remains a significant cybersecurity challenge,encrypting victim data and demanding a ransom,often leaving the data irretrievable even if payment is made.This study proposes an early detection approach to mitigate such threats by identifying ransomware activity before the encryption process begins.The approach employs a two-tiered approach:a signature-based method using hashing techniques to match known threats and a dynamic behavior-based analysis leveraging Cuckoo Sandbox and machine learning algorithms.A critical feature is the integration of the most effective Application Programming Interface call monitoring,which analyzes system-level interactions such as file encryption,key generation,and registry modifications.This enables the detection of both known and zero-day ransomware variants,overcoming limitations of traditional methods.The proposed technique was evaluated using classifiers such as Random Forest,Support Vector Machine,and K-Nearest Neighbors,achieving a detection accuracy of 98%based on 26 key ransomware attributes with an 80:20 training-to-testing ratio and 10-fold cross-validation.By combining minimal feature sets with robust behavioral analysis,the proposed method outperforms existing solutions and addresses current challenges in ransomware detection,thereby enhancing cybersecurity resilience.
文摘针对恶意软件利用环境感知能力来逃避分析系统检测的现状,深入研究基于系统应用程序接口(Application Program Interface,API)的环境感知技术,并实现全面检测环境感知API的自动化工具EAFinder(Environment-Aware API Finder)。EAFinder能够枚举所有的系统API,并在真机和模拟器中进行自动化调用,最终通过比较API在不同环境中的可访问性和返回值的差异,检测出环境感知API。实验结果显示EAFinder在Android 9至13上共检测出344个API,排除误报后得到323个可用于环境感知的API。将其按使用方式分为独立使用、基于阈值使用和组合使用三类,并抽样测试了各类API的有效性,结果显示利用这些API能以97%的准确率区分真实设备和模拟器。
文摘The evolution of technology in 1990s resulted in the enormous growth of smartphones and the propagation of mobile applications (App) that marked new opportunities for healthcare centers and medical education. Apps have altered health services from patient’s health monitoring to specialist’s appointments and consultations from specialized health facilities. It can be argued that a healthy society can bring forth sustainable economic development to its full potential while an unhealthy society cannot. However, a free movement of people, labour and right to residence which was built across East Africa (EA) borders enabled Tanzania and Kenya borders to have enormous interactions. Subsequently, increase the risk of highly communicable diseases such as Tuberculosis and Sexually transmitted infections in such a way that medical attention is unavoidable along the borders. Statistically, Android Operating System (OS) owns 83% of Africa’s mobile OS market. In addition, 25,794,560 internet users reported by Tanzania Communications Regulatory Authority (TCRA) together with the 22.86 million internet users provided by Kenya Digital which is equivalent to 46% and 43% of internet penetration in year 2020, disclose the need for Android mobile application for mapping health facilities both online and offline using Google map API, which will solve residents’ need to healthcare services on the presence or shortage of internet connections;using either Swahili or English language via Smartphone devices. The App incorporates Monitoring and Evaluation (M & E) tool for tracking application usage which will ease Admin’s task to generate daily and monthly reports in Excel and Comma-Separated Values (CSV) formats. The developed system received positive feedback from EA citizens and residents in the Arusha region and Namanga border crossing where 90.2% of the system evaluation conducted between Dec 2020 and Apr 2021 agreed upon App usage.
文摘针对目前恶意软件检测分类方法在特征提取、检测准确率等方面面临的挑战,提出一种基于API分组重构与图像表示的恶意软件检测分类方法。首先,对恶意软件调用的API类别统一编号,将API指令序列中相同编号的API聚合为同一API组,根据恶意软件运行时各类API的首次调用顺序对API组重排序,将各API组的条目数记录为该类API对软件样本的贡献度。经分组重构后,各API组按序组织,其顺序为软件样本调用各类API的顺序。各API组内部有序,其内部各API的排列顺序即为软件样本对单个API的调用顺序。有序化的API分组有助于API指令序列信息的图像化表达。基于重组的API指令序列提取API编号作为全局特征列表、API贡献度作为局部特征列表、API顺序索引作为时序特征列表,对特征列表进行标准化与零填充,转化为统一尺寸的特征数组。其中,API编号能清晰地标识API类别,API贡献度可以表征该API的调用频繁程度,API顺序索引可区分各API被调用的顺序。然后,分别用3类特征数组填充RGB图像的3个通道,生成3通道的API编号贡献度及顺序索引特征图像(Feature image of API code devotion and sequential index,FimgCDS)。最后,将Fimg CDS特征图像输入自主构建的轻量型恶意软件特征图像卷积神经网络(malware feature image convolutional neural network,MficNN)分类器,实现对恶意软件的检测与分类。实验结果表明,本文方法在两类数据集上的检测分类准确率分别为98.66%和98.35%,具有较高的恶意软件检测分类性能指标和检测分类速度。
