首页 > 最新文献

Applied Computing Review最新文献

英文 中文
SocioPedia: Visualizing Social Knowledge over Time 社会化媒体:随着时间的推移可视化社会知识
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577660
Try My Nguyen, Jason J. Jung
In this paper, we introduce SocioPedia, which is a real-time automatic system for efficiently visualizing and analyzing the variations, characteristics, and evolutions of social knowledge following the change of time. SocioPedia has been developed to provide a full knowledge graph life cycle and combined the temporal information into each processed knowledge. To benefit different classes of users, SocioPedia provides a user-friendly and intuitive environment with different visualization types including static knowledge visualization, timeline knowledge visualization, timeline characteristic visualization, and dynamic timeline visualization.
本文介绍的SocioPedia是一个实时自动化系统,它可以有效地可视化和分析社会知识随时间变化的变化、特征和演变。SocioPedia提供了一个完整的知识图谱生命周期,并将时间信息组合到每一个被处理的知识中。为了使不同类别的用户受益,SocioPedia提供了一个用户友好、直观的环境,提供了不同的可视化类型,包括静态知识可视化、时间线知识可视化、时间线特征可视化和动态时间线可视化。
{"title":"SocioPedia: Visualizing Social Knowledge over Time","authors":"Try My Nguyen, Jason J. Jung","doi":"10.1145/3555776.3577660","DOIUrl":"https://doi.org/10.1145/3555776.3577660","url":null,"abstract":"In this paper, we introduce SocioPedia, which is a real-time automatic system for efficiently visualizing and analyzing the variations, characteristics, and evolutions of social knowledge following the change of time. SocioPedia has been developed to provide a full knowledge graph life cycle and combined the temporal information into each processed knowledge. To benefit different classes of users, SocioPedia provides a user-friendly and intuitive environment with different visualization types including static knowledge visualization, timeline knowledge visualization, timeline characteristic visualization, and dynamic timeline visualization.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78734189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Expressive and Systematic Risk Assessments with Instance-Centric Threat Models 基于实例中心威胁模型的表达性和系统性风险评估
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577668
Stef Verreydt, Dimitri Van Landuyt, W. Joosen
A threat modeling exercise involves systematically assessing the likelihood and potential impact of diverse threat scenarios. As threat modeling approaches and tools act at the level of a software architecture or design (e.g., a data flow diagram), they consider threat scenarios at the level of classes or types of system elements. More fine-grained analyses in terms of concrete instances of these elements are typically not conducted explicitly nor rigorously. This hinders (i) expressiveness, as threats that require articulation at the level of instances can not be expressed nor managed properly, and (ii) systematic risk calculation, as risk cannot be expressed and estimated with respect to instance-level properties. In this paper, we present a novel threat modeling approach that acts on two layers: (i) the design layer defines the classes and entity types in the system, and (ii) the instance layer models concrete instances and their properties. This, in turn, allows both rough risk estimates at the design-level, and more precise ones at the instance-level. Motivated by a connected vehicles application, we present the key challenges, the modeling approach and a tool prototype. The presented approach is a key enabler for more continuous and frequent threat (re-)assessment, the integration of threat analysis models in CI/CD pipelines and agile development environments on the one hand (development perspective), and in risk management approaches at run-time (operations perspective).
威胁建模工作包括系统地评估各种威胁情景的可能性和潜在影响。当威胁建模方法和工具在软件架构或设计(例如,数据流图)级别上工作时,它们在类或系统元素类型级别上考虑威胁场景。就这些元素的具体实例而言,更细粒度的分析通常不明确也不严格地进行。这阻碍了(i)可表达性,因为需要在实例级别上表达的威胁无法被表达或妥善管理,以及(ii)系统性风险计算,因为风险无法根据实例级别的属性来表达和估计。在本文中,我们提出了一种新的威胁建模方法,它作用于两个层:(i)设计层定义系统中的类和实体类型,(ii)实例层对具体实例及其属性建模。反过来,这既允许在设计级别进行粗略的风险估计,也允许在实例级别进行更精确的风险估计。在车联网应用的激励下,我们提出了关键挑战、建模方法和工具原型。所提出的方法是实现更持续和频繁的威胁(重新)评估的关键,一方面是在CI/CD管道和敏捷开发环境(开发角度)中集成威胁分析模型,另一方面是在运行时的风险管理方法(操作角度)中集成威胁分析模型。
{"title":"Expressive and Systematic Risk Assessments with Instance-Centric Threat Models","authors":"Stef Verreydt, Dimitri Van Landuyt, W. Joosen","doi":"10.1145/3555776.3577668","DOIUrl":"https://doi.org/10.1145/3555776.3577668","url":null,"abstract":"A threat modeling exercise involves systematically assessing the likelihood and potential impact of diverse threat scenarios. As threat modeling approaches and tools act at the level of a software architecture or design (e.g., a data flow diagram), they consider threat scenarios at the level of classes or types of system elements. More fine-grained analyses in terms of concrete instances of these elements are typically not conducted explicitly nor rigorously. This hinders (i) expressiveness, as threats that require articulation at the level of instances can not be expressed nor managed properly, and (ii) systematic risk calculation, as risk cannot be expressed and estimated with respect to instance-level properties. In this paper, we present a novel threat modeling approach that acts on two layers: (i) the design layer defines the classes and entity types in the system, and (ii) the instance layer models concrete instances and their properties. This, in turn, allows both rough risk estimates at the design-level, and more precise ones at the instance-level. Motivated by a connected vehicles application, we present the key challenges, the modeling approach and a tool prototype. The presented approach is a key enabler for more continuous and frequent threat (re-)assessment, the integration of threat analysis models in CI/CD pipelines and agile development environments on the one hand (development perspective), and in risk management approaches at run-time (operations perspective).","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78860802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Traffic Intersections as Agents: A model checking approach for analysing communicating agents 交通交叉口作为agent:一种分析通信agent的模型检验方法
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577720
Thamilselvam B, Y. Ramesh, S. Kalyanasundaram, M. Rao
The analysis of traffic policies, for instance, the duration of green and red phases at intersections, can be quite challenging. While the introduction of communication systems can potentially lead to better solutions, it is important to analyse and formulate policies in the presence of potential communication failures and delays. Given the stochastic nature of traffic, posing the problem as a model checking problem in probabilistic epistemic temporal logic seems promising. In this work, we propose an approach that uses epistemic modalities to model the effect of communication between multiple intersections and temporal modalities to model the progression of traffic volumes over time. We validate our approach in a non-stochastic setting, using the tool Model Checker for Multi-Agent Systems (MCMAS). We develop a Statistical Model Checking module and use it in conjunction with a tool chain that integrates a traffic simulator (SUMO) and a network simulator (OMNeT++/Veins) to study the impact of communications on traffic policies.
交通政策的分析,例如,十字路口的绿灯和红灯的持续时间,可能是相当具有挑战性的。虽然采用通讯系统可能导致更好的解决办法,但在可能出现通讯故障和延误的情况下分析和制订政策是很重要的。考虑到交通的随机性,将该问题作为概率认知时间逻辑中的模型检验问题似乎很有希望。在这项工作中,我们提出了一种方法,使用认知模式来模拟多个十字路口之间的通信影响,并使用时间模式来模拟交通量随时间的变化。我们在非随机设置中验证了我们的方法,使用工具模型检查器多代理系统(MCMAS)。我们开发了一个统计模型检查模块,并将其与集成了交通模拟器(SUMO)和网络模拟器(omnet++ / vein)的工具链结合使用,以研究通信对交通策略的影响。
{"title":"Traffic Intersections as Agents: A model checking approach for analysing communicating agents","authors":"Thamilselvam B, Y. Ramesh, S. Kalyanasundaram, M. Rao","doi":"10.1145/3555776.3577720","DOIUrl":"https://doi.org/10.1145/3555776.3577720","url":null,"abstract":"The analysis of traffic policies, for instance, the duration of green and red phases at intersections, can be quite challenging. While the introduction of communication systems can potentially lead to better solutions, it is important to analyse and formulate policies in the presence of potential communication failures and delays. Given the stochastic nature of traffic, posing the problem as a model checking problem in probabilistic epistemic temporal logic seems promising. In this work, we propose an approach that uses epistemic modalities to model the effect of communication between multiple intersections and temporal modalities to model the progression of traffic volumes over time. We validate our approach in a non-stochastic setting, using the tool Model Checker for Multi-Agent Systems (MCMAS). We develop a Statistical Model Checking module and use it in conjunction with a tool chain that integrates a traffic simulator (SUMO) and a network simulator (OMNeT++/Veins) to study the impact of communications on traffic policies.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87657020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deduplication vs Privacy Tradeoffs in Cloud Storage 云存储中的重复数据删除与隐私权衡
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577711
Rodrigo de Magalhães Marques dos Santos Silva, Cláudio Correia, M. Correia, Luís Rodrigues
Users often encrypt files they store on cloud storage services to ensure data privacy. Unfortunately, without additional mechanisms, encrypting files prevents the use of server-side deduplication as two identical files will be different when encrypted. Encrypted deduplication techniques combines file encryption and data deduplication. This combination usually requires some form of direct or indirect coordination between the different clients. In this paper, we address the problem of reconciling the need to encrypt data with the advantages of deduplication. In particular, we study techniques that achieve this objective while avoiding frequency analysis attacks, i.e., attacks that infer the content of an encrypted file based on how frequently the file is stored and/or accessed. We propose a new protocol for assigning encryption keys to files that leverages the use of trusted execution environments to hide the frequencies of chunks from the adversary.
用户通常会对存储在云存储服务上的文件进行加密,以确保数据隐私。不幸的是,如果没有额外的机制,加密文件会防止使用服务器端重复数据删除,因为两个相同的文件在加密后会不同。加密重复数据删除技术将文件加密和重复数据删除相结合。这种组合通常需要不同客户之间进行某种形式的直接或间接协调。在本文中,我们解决了调和数据加密需求和重复数据删除优势的问题。特别是,我们研究实现这一目标的技术,同时避免频率分析攻击,即根据文件存储和/或访问的频率推断加密文件内容的攻击。我们提出了一个为文件分配加密密钥的新协议,该协议利用可信执行环境的使用来对对手隐藏块的频率。
{"title":"Deduplication vs Privacy Tradeoffs in Cloud Storage","authors":"Rodrigo de Magalhães Marques dos Santos Silva, Cláudio Correia, M. Correia, Luís Rodrigues","doi":"10.1145/3555776.3577711","DOIUrl":"https://doi.org/10.1145/3555776.3577711","url":null,"abstract":"Users often encrypt files they store on cloud storage services to ensure data privacy. Unfortunately, without additional mechanisms, encrypting files prevents the use of server-side deduplication as two identical files will be different when encrypted. Encrypted deduplication techniques combines file encryption and data deduplication. This combination usually requires some form of direct or indirect coordination between the different clients. In this paper, we address the problem of reconciling the need to encrypt data with the advantages of deduplication. In particular, we study techniques that achieve this objective while avoiding frequency analysis attacks, i.e., attacks that infer the content of an encrypted file based on how frequently the file is stored and/or accessed. We propose a new protocol for assigning encryption keys to files that leverages the use of trusted execution environments to hide the frequencies of chunks from the adversary.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86785354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mapping Strategies for Declarative Queries over Online Heterogeneous Biological Databases for Intelligent Responses 面向智能响应的在线异构生物数据库声明性查询映射策略
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577652
H. Jamil, Kallol Naha
The emergence of Alexa and Siri, and more recently, OpenAI's Chat-GPT, raises the question whether ad hoc biological queries can also be computed without end-users' active involvement in the code writing process. While advances have been made, current querying architectures for biological databases still assume some degree of computational competence and significant structural awareness of the underlying network of databases by biologists, if not active code writing. Given that biological databases are highly distributed and heterogeneous, and most are not FAIR compliant, a significant amount of expertise in data integration is essential for a query to be accurately crafted and meaningfully executed. In this paper, we introduce a flexible and intelligent query reformulation assistant, called Needle, as a back-end query execution engine of a natural language query interface to online biological databases. Needle leverages a data model called BioStar that leverages a meta-knowledgebase, called the schema graph, to map natural language queries to relevant databases and biological concepts. The implementation of Needle using BioStar is the focus of this article.
Alexa和Siri的出现,以及最近OpenAI的Chat-GPT的出现,提出了一个问题,即在没有最终用户积极参与代码编写过程的情况下,是否也可以计算特定的生物查询。虽然已经取得了进展,但目前的生物数据库查询体系结构仍然假设生物学家具有一定程度的计算能力和对数据库底层网络的重要结构意识,如果不是主动编写代码的话。鉴于生物数据库是高度分布式和异构的,而且大多数不符合FAIR标准,因此,要准确地编写查询并有意义地执行查询,就必须具备大量数据集成方面的专业知识。本文介绍了一种灵活智能的查询改写助手Needle,作为在线生物数据库自然语言查询接口的后端查询执行引擎。Needle利用了一个名为BioStar的数据模型,该模型利用了一个名为图式图的元知识库,将自然语言查询映射到相关数据库和生物学概念。使用BioStar实现Needle是本文的重点。
{"title":"Mapping Strategies for Declarative Queries over Online Heterogeneous Biological Databases for Intelligent Responses","authors":"H. Jamil, Kallol Naha","doi":"10.1145/3555776.3577652","DOIUrl":"https://doi.org/10.1145/3555776.3577652","url":null,"abstract":"The emergence of Alexa and Siri, and more recently, OpenAI's Chat-GPT, raises the question whether ad hoc biological queries can also be computed without end-users' active involvement in the code writing process. While advances have been made, current querying architectures for biological databases still assume some degree of computational competence and significant structural awareness of the underlying network of databases by biologists, if not active code writing. Given that biological databases are highly distributed and heterogeneous, and most are not FAIR compliant, a significant amount of expertise in data integration is essential for a query to be accurately crafted and meaningfully executed. In this paper, we introduce a flexible and intelligent query reformulation assistant, called Needle, as a back-end query execution engine of a natural language query interface to online biological databases. Needle leverages a data model called BioStar that leverages a meta-knowledgebase, called the schema graph, to map natural language queries to relevant databases and biological concepts. The implementation of Needle using BioStar is the focus of this article.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89067093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A General and NLP-based Architecture to perform Recommendation: A Use Case for Online Job Search and Skills Acquisition 执行推荐的通用和基于nlp的架构:用于在线工作搜索和技能获取的用例
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577844
Rubén Alonso, D. Dessí, Antonello Meloni, Diego Reforgiato Recupero
Natural Language Processing (NLP) is crucial to perform recommendations of items that can be only described by natural language. However, NLP usage within recommendation modules is difficult and usually requires a relevant initial effort, thus limiting its widespread adoption. To overcome this limitation, we introduce FORESEE, a novel architecture that can be instantiated with NLP and Machine Learning (ML) modules to perform recommendations of items that are described by natural language features. Furthermore, we describe an instantiation of such architecture to provide a service for the job market where applicants can verify whether their curriculum vitae (CV) is eligible for a given job position, can receive suggestions about which skills and abilities they should obtain, and finally, can obtain recommendations about online resources which might strengthen their CVs.
自然语言处理(NLP)对于执行只能用自然语言描述的项目的推荐至关重要。然而,在推荐模块中使用NLP是困难的,通常需要相关的初始努力,从而限制了它的广泛采用。为了克服这一限制,我们引入了FORESEE,这是一种新颖的架构,可以用NLP和机器学习(ML)模块实例化,以执行由自然语言特征描述的项目的推荐。此外,我们描述了这种架构的一个实例,为就业市场提供服务,申请人可以验证他们的简历(CV)是否符合给定的工作职位,可以收到关于他们应该获得哪些技能和能力的建议,最后可以获得有关在线资源的建议,这可能会加强他们的简历。
{"title":"A General and NLP-based Architecture to perform Recommendation: A Use Case for Online Job Search and Skills Acquisition","authors":"Rubén Alonso, D. Dessí, Antonello Meloni, Diego Reforgiato Recupero","doi":"10.1145/3555776.3577844","DOIUrl":"https://doi.org/10.1145/3555776.3577844","url":null,"abstract":"Natural Language Processing (NLP) is crucial to perform recommendations of items that can be only described by natural language. However, NLP usage within recommendation modules is difficult and usually requires a relevant initial effort, thus limiting its widespread adoption. To overcome this limitation, we introduce FORESEE, a novel architecture that can be instantiated with NLP and Machine Learning (ML) modules to perform recommendations of items that are described by natural language features. Furthermore, we describe an instantiation of such architecture to provide a service for the job market where applicants can verify whether their curriculum vitae (CV) is eligible for a given job position, can receive suggestions about which skills and abilities they should obtain, and finally, can obtain recommendations about online resources which might strengthen their CVs.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80721294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Prediction of readmissions in hospitalized children and adolescents by machine learning 利用机器学习预测住院儿童和青少年的再入院情况
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577592
Nayara Cristina da Silva, M. Albertini, A. R. Backes, G. Pena
Pediatric hospital readmission involves greater burdens for the patient and their family network, and for the health system. Machine learning can be a good strategy to expand knowledge in this area and to assist in the identification of patients at readmission risk. The objective of the study was to develop a predictive model to identify children and adolescents at high risk of potentially avoidable 30-day readmission using a machine learning approach. Retrospective cohort study with patients under 18 years old admitted to a tertiary university hospital. We collected demographic, clinical, and nutritional data from electronic databases. We apply machine learning techniques to build the predictive models. The 30-day hospital readmissions rate was 9.50%. The accuracy for CART model with bagging was 0.79, the sensitivity, and specificity were 76.30% and 64.40%, respectively. Machine learning approaches can predict avoidable 30-day pediatric hospital readmission into tertiary assistance.
儿科医院再入院给患者及其家庭网络以及卫生系统带来了更大的负担。机器学习可以是一个很好的策略来扩展这一领域的知识,并帮助识别有再入院风险的患者。该研究的目的是开发一种预测模型,以识别使用机器学习方法可能避免30天再入院的高风险儿童和青少年。回顾性队列研究在18岁以下的患者入院的第三大学医院。我们从电子数据库中收集了人口统计、临床和营养数据。我们运用机器学习技术来建立预测模型。30天再入院率为9.50%。带套袋的CART模型准确率为0.79,敏感性为76.30%,特异性为64.40%。机器学习方法可以预测可避免的30天儿科医院三级辅助再入院情况。
{"title":"Prediction of readmissions in hospitalized children and adolescents by machine learning","authors":"Nayara Cristina da Silva, M. Albertini, A. R. Backes, G. Pena","doi":"10.1145/3555776.3577592","DOIUrl":"https://doi.org/10.1145/3555776.3577592","url":null,"abstract":"Pediatric hospital readmission involves greater burdens for the patient and their family network, and for the health system. Machine learning can be a good strategy to expand knowledge in this area and to assist in the identification of patients at readmission risk. The objective of the study was to develop a predictive model to identify children and adolescents at high risk of potentially avoidable 30-day readmission using a machine learning approach. Retrospective cohort study with patients under 18 years old admitted to a tertiary university hospital. We collected demographic, clinical, and nutritional data from electronic databases. We apply machine learning techniques to build the predictive models. The 30-day hospital readmissions rate was 9.50%. The accuracy for CART model with bagging was 0.79, the sensitivity, and specificity were 76.30% and 64.40%, respectively. Machine learning approaches can predict avoidable 30-day pediatric hospital readmission into tertiary assistance.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91138581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Analysis of active semi-supervised learning 主动半监督学习分析
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577621
Lilian Berton, Felipe Mitsuishi, Didier Vega Oliveros
In many real-world applications, labeled instances are costly and infeasible to obtain large training sets. This way, learning strategies that do the most with fewer labels are calling attention, such as semi-supervised learning (SSL) and active learning (AL). Active learning allows querying instance to be labeled in the uncertain region and semi-supervised learning classify with a small set of labeled data. We combine both strategies to investigate how AL improves SSL performance, considering both classification results and computational cost. We present experimental results comparing five AL strategies on seven benchmark datasets encompassing synthetic data, handwritten digit and image recognition, and brain-computing interaction tasks. The best single AL strategy was the ranked batch mode, but it has the highest computational cost. On the other hand, using a consensus committee approach leads to the highest results and low-processing footprints.
在许多实际应用中,标记实例是昂贵的,并且不可能获得大型训练集。这样,用更少的标签做得最多的学习策略引起了人们的注意,比如半监督学习(SSL)和主动学习(AL)。主动学习允许在不确定区域对查询实例进行标记,半监督学习允许使用少量标记数据进行分类。我们结合这两种策略来研究人工智能如何提高SSL性能,同时考虑分类结果和计算成本。我们在七个基准数据集上比较了五种人工智能策略的实验结果,这些数据集包括合成数据、手写数字和图像识别以及脑计算交互任务。排名批处理模式是最佳的单人工智能策略,但它的计算成本最高。另一方面,使用共识委员会方法可以获得最高的结果和较低的处理足迹。
{"title":"Analysis of active semi-supervised learning","authors":"Lilian Berton, Felipe Mitsuishi, Didier Vega Oliveros","doi":"10.1145/3555776.3577621","DOIUrl":"https://doi.org/10.1145/3555776.3577621","url":null,"abstract":"In many real-world applications, labeled instances are costly and infeasible to obtain large training sets. This way, learning strategies that do the most with fewer labels are calling attention, such as semi-supervised learning (SSL) and active learning (AL). Active learning allows querying instance to be labeled in the uncertain region and semi-supervised learning classify with a small set of labeled data. We combine both strategies to investigate how AL improves SSL performance, considering both classification results and computational cost. We present experimental results comparing five AL strategies on seven benchmark datasets encompassing synthetic data, handwritten digit and image recognition, and brain-computing interaction tasks. The best single AL strategy was the ranked batch mode, but it has the highest computational cost. On the other hand, using a consensus committee approach leads to the highest results and low-processing footprints.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89748429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Detecting Suspicious Conditional Statement using App Execution Log 使用应用程序执行日志检测可疑条件语句
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577722
Sumin Lee, Minho Park, Jiman Hong
Because1 the logic bomb performs malicious behaviors only within the branch that triggers the malicious behaviors, if the branch can be easily found, malicious behaviors can be detected efficiently. Existing malicious app analysis tools look for branches that trigger malicious behaviors based on static analysis, so if reflection is used in the app, this branch statement cannot be found properly. Therefore, in this paper, we propose an app execution log-based suspicious conditional statement detection tool that can detect suspicious conditional statements even when reflection is used. The proposed detection tool which is implemented on the android-10.0.0_r47 version of AOSP(Android Open Source Project) can check the branch statement and information about called method while the app is executing, including the method called by reflection. Also, since suspicious conditional statements are detected by checking the method call flow related to branch statements in the execution log, there is no need to examine all branch statements in the app. Experimental results show that the proposed detection tool can detect suspicious conditional statements regardless of the use of reflection.
因为逻辑炸弹只在触发恶意行为的分支内执行恶意行为,所以如果分支很容易被找到,就可以有效地检测出恶意行为。现有的恶意应用分析工具会根据静态分析来查找触发恶意行为的分支,所以如果在应用中使用了反射,则无法正确找到该分支语句。因此,在本文中,我们提出了一种基于应用执行日志的可疑条件语句检测工具,即使使用反射也可以检测到可疑条件语句。本文提出的检测工具在Android -10.0.0_r47版本的AOSP(Android开源项目)上实现,可以在应用程序执行时检查分支语句和被调用方法的信息,包括反射调用的方法。此外,由于可疑条件语句是通过检查执行日志中与分支语句相关的方法调用流来检测的,因此不需要检查应用程序中的所有分支语句。实验结果表明,无论是否使用反射,所提出的检测工具都可以检测到可疑条件语句。
{"title":"Detecting Suspicious Conditional Statement using App Execution Log","authors":"Sumin Lee, Minho Park, Jiman Hong","doi":"10.1145/3555776.3577722","DOIUrl":"https://doi.org/10.1145/3555776.3577722","url":null,"abstract":"Because1 the logic bomb performs malicious behaviors only within the branch that triggers the malicious behaviors, if the branch can be easily found, malicious behaviors can be detected efficiently. Existing malicious app analysis tools look for branches that trigger malicious behaviors based on static analysis, so if reflection is used in the app, this branch statement cannot be found properly. Therefore, in this paper, we propose an app execution log-based suspicious conditional statement detection tool that can detect suspicious conditional statements even when reflection is used. The proposed detection tool which is implemented on the android-10.0.0_r47 version of AOSP(Android Open Source Project) can check the branch statement and information about called method while the app is executing, including the method called by reflection. Also, since suspicious conditional statements are detected by checking the method call flow related to branch statements in the execution log, there is no need to examine all branch statements in the app. Experimental results show that the proposed detection tool can detect suspicious conditional statements regardless of the use of reflection.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90075158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Graph Convolutional Neural Network for Multimodal Movie Recommendation 多模态电影推荐的图卷积神经网络
IF 1 Pub Date : 2023-03-27 DOI: 10.1145/3555776.3577853
Prabir Mondal, Daipayan Chakder, Subham Raj, S. Saha, N. Onoe
The Recommendation System (RS) development and recommending customers' preferred products to the customer are highly desirable motives in today's digital market. Most of the RSs are mainly based on textual information of the engaged entities in the platform and the ratings provided by the users to the products. This paper develops a movie recommendation system where the cold-start problem relating to rating information dependency has been dealt with and the multi-modality approach is introduced. The proposed method differs from existing approaches in three main aspects: (a) implementation of knowledge graph for text embedding, (b) besides textual information, other modalities of movies like video, and audio are employed rather than rating information for generating movie/user representation and this approach deals with the cold-start problem effectively, (c) utilization of graph convolutional network (GCN) for generating some further hidden features and also for developing regression system.
在当今的数字市场中,推荐系统(RS)的开发和向客户推荐客户喜欢的产品是非常可取的动机。大多数RSs主要基于平台中参与实体的文本信息和用户对产品的评分。本文开发了一个电影推荐系统,解决了评级信息依赖的冷启动问题,并引入了多模态方法。所提出的方法与现有方法的不同之处主要有三个方面:(a)实现用于文本嵌入的知识图;(b)除了文本信息,还使用视频和音频等其他电影形式而不是评级信息来生成电影/用户表示,这种方法有效地处理了冷启动问题;(c)利用图卷积网络(GCN)来生成一些进一步的隐藏特征,并用于开发回归系统。
{"title":"Graph Convolutional Neural Network for Multimodal Movie Recommendation","authors":"Prabir Mondal, Daipayan Chakder, Subham Raj, S. Saha, N. Onoe","doi":"10.1145/3555776.3577853","DOIUrl":"https://doi.org/10.1145/3555776.3577853","url":null,"abstract":"The Recommendation System (RS) development and recommending customers' preferred products to the customer are highly desirable motives in today's digital market. Most of the RSs are mainly based on textual information of the engaged entities in the platform and the ratings provided by the users to the products. This paper develops a movie recommendation system where the cold-start problem relating to rating information dependency has been dealt with and the multi-modality approach is introduced. The proposed method differs from existing approaches in three main aspects: (a) implementation of knowledge graph for text embedding, (b) besides textual information, other modalities of movies like video, and audio are employed rather than rating information for generating movie/user representation and this approach deals with the cold-start problem effectively, (c) utilization of graph convolutional network (GCN) for generating some further hidden features and also for developing regression system.","PeriodicalId":42971,"journal":{"name":"Applied Computing Review","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76865314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
期刊
Applied Computing Review
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1