Procedia Computer Science最新文献

英文中文

ReplaceIt: Lessons from a User-Centered Design Framework in Co-Creating an Alcohol Reduction App ReplaceIt：以用户为中心的设计框架在共同创建减酒应用程序中的启示

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.10.369

Petra K. Staiger , Paul Liknaitzky , Kate Hall , Matthew Fuller-Tyszkiewicz , Ben Richardson , Adrian Shatte , Eric O

Smartphone apps that target alcohol problems report mixed effectiveness data, which may be explained by a lack of evidence-based content and user-centred design (UCD). This paper presents the development of ReplaceIt, a smartphone application co-designed to reduce risky drinking using an evidence-based UCD framework. Initial steps included a systematic review of existing apps, interviews with end-users, and evidence-based intervention design by our multidisciplinary team, resulting in a prototype of the app. Next, the app's key components—goal setting, self-monitoring with feedback, and implementation intention strategies—were refined through co-design with end-users using a think-aloud study and iterative pilot testing. Refinement included the introduction of a module to enhance user interaction with implementation intentions, simplified instructions, and enhanced user engagement features. The resulting ReplaceIt app was then in an excellent position to undergo efficacy testing, with high usability scores and positive user reception suggesting strong potential for reducing risky drinking behaviours. Overall, the UCD framework proved essential in developing an app that aligns with user preferences and behaviours, ultimately enhancing its functionality and potential efficacy.

针对酒精问题的智能手机应用程序的效果数据参差不齐，原因可能是缺乏基于证据的内容和以用户为中心的设计（UCD）。本文介绍了 "ReplaceIt "的开发过程，这是一款采用循证用户中心设计框架共同设计的智能手机应用程序，旨在减少危险饮酒。最初的步骤包括对现有应用程序进行系统回顾、与最终用户进行访谈，以及由我们的多学科团队进行循证干预设计，最终形成应用程序的原型。接下来，通过与最终用户共同设计，并利用畅想研究和迭代试点测试，对应用程序的关键组成部分--目标设定、带反馈的自我监控和实施意图策略--进行了改进。改进包括引入一个模块，以加强用户与实施意图的互动、简化说明和增强用户参与功能。最终开发出的 ReplaceIt 应用程序在进行功效测试时表现出色，可用性得分很高，用户反应积极，这表明它在减少危险饮酒行为方面具有很大的潜力。总之，用户中心设计框架在开发符合用户偏好和行为的应用程序方面证明是至关重要的，最终增强了应用程序的功能和潜在功效。

{"title":"ReplaceIt: Lessons from a User-Centered Design Framework in Co-Creating an Alcohol Reduction App","authors":"Petra K. Staiger , Paul Liknaitzky , Kate Hall , Matthew Fuller-Tyszkiewicz , Ben Richardson , Adrian Shatte , Eric O","doi":"10.1016/j.procs.2024.10.369","DOIUrl":"10.1016/j.procs.2024.10.369","url":null,"abstract":"<div><div>Smartphone apps that target alcohol problems report mixed effectiveness data, which may be explained by a lack of evidence-based content and user-centred design (UCD). This paper presents the development of ReplaceIt, a smartphone application co-designed to reduce risky drinking using an evidence-based UCD framework. Initial steps included a systematic review of existing apps, interviews with end-users, and evidence-based intervention design by our multidisciplinary team, resulting in a prototype of the app. Next, the app's key components—goal setting, self-monitoring with feedback, and implementation intention strategies—were refined through co-design with end-users using a think-aloud study and iterative pilot testing. Refinement included the introduction of a module to enhance user interaction with implementation intentions, simplified instructions, and enhanced user engagement features. The resulting ReplaceIt app was then in an excellent position to undergo efficacy testing, with high usability scores and positive user reception suggesting strong potential for reducing risky drinking behaviours. Overall, the UCD framework proved essential in developing an app that aligns with user preferences and behaviours, ultimately enhancing its functionality and potential efficacy.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"248 ","pages":"Pages 104-111"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142697169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The power of generative AI for CRIS systems: a new paradigm for scientific information management 生成式人工智能在 CRIS 系统中的力量：科学信息管理的新范例

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.11.057

Anna Guillaumet

The paper analyses the implications of the emergence of artificial intelligence (AI), especially generative AI, on current research information systems (CRIS). It reviews the recent European regulations for high-risk AI systems, the Spanish AI strategy, and the IntelComp project as use cases. The study found that the maturity of CRIS systems, coupled with the increasing complexity due to data aggregation, sets the stage for innovative AI applications. The paper proposes key domains where AI can impact and be applied in CRIS, including data management, research assessment, and advanced analytics. It also provides examples of how generative AI can be leveraged to enhance scientific information management within CRIS. The findings highlight the need to ensure the responsible and ethical development of AI technologies in the research domain.

本文分析了人工智能（AI），特别是生成式人工智能的出现对当前研究信息系统（CRIS）的影响。它回顾了最近欧洲对高风险人工智能系统的规定、西班牙人工智能战略以及作为使用案例的 IntelComp 项目。研究发现，CRIS 系统的成熟度，加上数据聚合带来的日益复杂性，为人工智能的创新应用创造了条件。论文提出了人工智能可以影响和应用于 CRIS 的关键领域，包括数据管理、研究评估和高级分析。论文还举例说明了如何利用生成式人工智能来加强 CRIS 内部的科学信息管理。研究结果强调，必须确保在研究领域以负责任和合乎道德的方式开发人工智能技术。

引用次数: 0

Decentralized research data management: introducing SoVisu+ 分散式研究数据管理：引入 SoVisu+

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.11.067

Reymond David , Tabariès Alaric

This research proposes SoVisu+, a new system for managing research data in a decentralized way, building upon the foundation laid by the CRISalid consortium, a community-driven approach to research information management. Traditional, centralized systems have issues like fragmented data, unchecked and outdated information. SoVisu+ tackles these problems by giving researchers more control over their data and fostering collaboration to build a shared knowledge graph. Researchers benefit from features like self-archiving accompaniment, AI driven helpers and real-time profile views, while institutions gain access to more reliable and comprehensive data. SoVisu+ expects to employ cutting-edge technologies like Solid Pods and Linked Data to streamline data management and improve research evaluation practices. Overall, SoVisu+ aims to create a more transparent and collaborative research ecosystem that ultimately accelerates scientific progress.

这项研究提出了 SoVisu+，这是一个以分散方式管理研究数据的新系统，它建立在 CRISalid 联盟奠定的基础之上，是一种社区驱动的研究信息管理方法。传统的集中式系统存在数据零散、信息未经检查和过时等问题。SoVisu+ 通过让研究人员对其数据拥有更多控制权并促进合作以建立共享知识图谱来解决这些问题。研究人员可以从自我归档、人工智能驱动的助手和实时档案视图等功能中受益，而机构则可以获得更可靠、更全面的数据。SoVisu+ 希望采用 Solid Pods 和关联数据等尖端技术来简化数据管理和改进研究评估实践。总之，SoVisu+ 的目标是创建一个更加透明、更具协作性的研究生态系统，最终加快科学进步。

引用次数: 0

Source-Free Unsupervised Domain Adaptation Fundus Image Segmentation via Entropy Optimization and Anatomical Priors

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.11.023

Yijia Chen , Jiapeng Li , Haoze Yu , Lin Qi , Yongchun Li

This research focuses on fundus image segmentation within a source-free domain adaptation framework, where the availability of source images during the adaptation phase is limited due to privacy concerns. Although Source-Free Unsupervised Domain Adaptation (SFUDA) methods have seen significant innovative developments in recent years, they still face several challenges which include suboptimal performance due to substantial domain discrepancies, reliance on potentially noisy or inaccurate pseudo-labels during the adaptation process, and a lack of integration with domain-specific prior knowledge. To address these issues, this paper proposes a SFUDA framework via Entropy Optimization and Anatomical Priors (EOAPNet). To alleviate the influence of the divergence between the source and target domains, EOAPNet primarily evaluates the uncertainty (i.e., entropy) of predictions on target domain data and improves the model by focusing on high-entropy pixels or regions. Additionally, a weak-strong augmentation mean-teacher scheme is introduced in EOAPNet, which can enhance the accuracy of pseudo-labels and reduce error propagation. Thirdly, by integrating an anatomical knowledge-based class ratio prior into the overall loss function in the form of a Kullback–Leibler (KL) divergence, EOAPNet also incorporates expert domain knowledge. EOAPNet yields comparable results to several state-of-the-art adaptation techniques in experiments on two retinal image segmentation datasets involving the RIM-ONE-r3 and Drishti-GS datasets.

{"title":"Source-Free Unsupervised Domain Adaptation Fundus Image Segmentation via Entropy Optimization and Anatomical Priors","authors":"Yijia Chen , Jiapeng Li , Haoze Yu , Lin Qi , Yongchun Li","doi":"10.1016/j.procs.2024.11.023","DOIUrl":"10.1016/j.procs.2024.11.023","url":null,"abstract":"<div><div>This research focuses on fundus image segmentation within a source-free domain adaptation framework, where the availability of source images during the adaptation phase is limited due to privacy concerns. Although Source-Free Unsupervised Domain Adaptation (SFUDA) methods have seen significant innovative developments in recent years, they still face several challenges which include suboptimal performance due to substantial domain discrepancies, reliance on potentially noisy or inaccurate pseudo-labels during the adaptation process, and a lack of integration with domain-specific prior knowledge. To address these issues, this paper proposes a SFUDA framework via Entropy Optimization and Anatomical Priors (EOAPNet). To alleviate the influence of the divergence between the source and target domains, EOAPNet primarily evaluates the uncertainty (i.e., entropy) of predictions on target domain data and improves the model by focusing on high-entropy pixels or regions. Additionally, a weak-strong augmentation mean-teacher scheme is introduced in EOAPNet, which can enhance the accuracy of pseudo-labels and reduce error propagation. Thirdly, by integrating an anatomical knowledge-based class ratio prior into the overall loss function in the form of a Kullback–Leibler (KL) divergence, EOAPNet also incorporates expert domain knowledge. EOAPNet yields comparable results to several state-of-the-art adaptation techniques in experiments on two retinal image segmentation datasets involving the RIM-ONE-r3 and Drishti-GS datasets.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"250 ","pages":"Pages 182-187"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A SLAM framework based spinal endoscopic localization method

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.11.012

Yang Yang , Li Guoliang , Qianqian Li , Rui Song

Percutaneous endoscopy has become an important part of spinal surgery. During endoscopic operation, image navigation is an important technique to ensure accuracy and reliability. Optical navigation is the most widely used technique for endoscopic surgery, but it has some limitations such as inability to locate the non-rigid end of the instrument and limiting the operating space of the doctor. In order to solve these problems, a navigation strategy based on the idea of Simultaneous Localization And Mapping (SLAM) algorithm is proposed in this paper. In this novel navigation strategy, the 3D reconstruction CT image was used to be the global point cloud map of the surgical environment, while the local point cloud was reconstructed using the endoscopic image, and a Structure From Motion(SFM) algorithm was adopted to locate the endoscope in the local space. Then, the position and pose of the endoscope in the global space was calculated via the registration of the local and global point clouds. The feasibility and effectiveness of the proposed method are verified by comparative experiments on the experimental platform of robot-assisted endoscopic spine surgery.

{"title":"A SLAM framework based spinal endoscopic localization method","authors":"Yang Yang , Li Guoliang , Qianqian Li , Rui Song","doi":"10.1016/j.procs.2024.11.012","DOIUrl":"10.1016/j.procs.2024.11.012","url":null,"abstract":"<div><div>Percutaneous endoscopy has become an important part of spinal surgery. During endoscopic operation, image navigation is an important technique to ensure accuracy and reliability. Optical navigation is the most widely used technique for endoscopic surgery, but it has some limitations such as inability to locate the non-rigid end of the instrument and limiting the operating space of the doctor. In order to solve these problems, a navigation strategy based on the idea of Simultaneous Localization And Mapping (SLAM) algorithm is proposed in this paper. In this novel navigation strategy, the 3D reconstruction CT image was used to be the global point cloud map of the surgical environment, while the local point cloud was reconstructed using the endoscopic image, and a Structure From Motion(SFM) algorithm was adopted to locate the endoscope in the local space. Then, the position and pose of the endoscope in the global space was calculated via the registration of the local and global point clouds. The feasibility and effectiveness of the proposed method are verified by comparative experiments on the experimental platform of robot-assisted endoscopic spine surgery.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"250 ","pages":"Pages 81-87"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Disturbance Rejection Control for Autonomous Trolley Collection Robots with Prescribed Performance

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.11.003

Rui-Dong Xi , Tie-Nan Ma , Bingyi Xia , Xue Zhang , Yixuan Yuan , Jiankun Wang , Max Q.-H. Meng

Trajectory tracking control of autonomous trolley collection robots (ATCR) is a challenging task due to the complex environment, significant noise, and external disturbances. To address these challenges, this work investigates a control scheme for ATCRs subject to severe environmental interference. A fast-convergent, kinematics model-based adaptive sliding mode disturbance observer (ASMDOB) is first proposed to estimate lumped disturbances. Building upon this, a robust controller with prescribed performance is designed using the backstepping technique, improving transient performance and guaranteeing fast convergence. Simulation results have been given to illustrate the effectiveness of the proposed control scheme.

引用次数: 0

Creating virtual worlds and designing games

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.09.419

Dana M. Barry , Hideyuki Kanematsu

This paper provides a general and interesting presentation for connecting virtual worlds to game design. It defines virtual worlds as computer-based environments where users can interact by using an avatar or playable characters that are included in video games. Individuals can make a virtual world by joining a virtual world platform like Second Life and creating their own space. To create a virtual world from scratch, a game engine is needed. Virtual worlds serve as the setting for games. Game design is the creation and shaping of the rules and content of the game. It includes the preparation of stories, characters, goals, and challenges. Games can be used for entertainment, education, and for other purposes. The authors visited a class at SUNY Canton to observe an introductory course about building virtual worlds for game design. They gave survey forms to the new college students who were in the initial stage of designing virtual worlds for their games. This paper includes some preliminary and general information obtained by analyzing the results of the surveys completed by the class participants. It also provides a general description of the steps necessary for planning and creating a video game.

{"title":"Creating virtual worlds and designing games","authors":"Dana M. Barry , Hideyuki Kanematsu","doi":"10.1016/j.procs.2024.09.419","DOIUrl":"10.1016/j.procs.2024.09.419","url":null,"abstract":"<div><div>This paper provides a general and interesting presentation for connecting virtual worlds to game design. It defines virtual worlds as computer-based environments where users can interact by using an avatar or playable characters that are included in video games. Individuals can make a virtual world by joining a virtual world platform like Second Life and creating their own space. To create a virtual world from scratch, a game engine is needed. Virtual worlds serve as the setting for games. Game design is the creation and shaping of the rules and content of the game. It includes the preparation of stories, characters, goals, and challenges. Games can be used for entertainment, education, and for other purposes. The authors visited a class at SUNY Canton to observe an introductory course about building virtual worlds for game design. They gave survey forms to the new college students who were in the initial stage of designing virtual worlds for their games. This paper includes some preliminary and general information obtained by analyzing the results of the surveys completed by the class participants. It also provides a general description of the steps necessary for planning and creating a video game.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"246 ","pages":"Pages 403-412"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An End-to-End OCR-Free Solution For Identity Document Information Extraction

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.09.425

Salvatore Carta , Alessandro Giuliani , Leonardo Piano , Sandro Gabriele Tiddia

Efficiently verifying the customer’s identity is essential for ensuring the security of online transactions. Such verification is mainly accomplished according to the widespread Know Your Client (KYC) protocol, which relies on a self-identification handled by the user, typically providing personal data from their identification document (ID). In the current digital communication generation, such a task is usually performed by uploading a digital copy of the document by scanning or taking a real-time picture from a personal device such as a smartphone or tablet. Such activity, which usually involves manual data entry, is time-consuming and prone to human errors. Document Understanding (DU) has emerged as a crucial factor for automating data extraction in this scenario. One of its main challenges is the scarcity of data, which is barely available for security and privacy concerns. To this end, this paper proposes a solution that takes advantage of recent advances in DU to devise an innovative strategy for Identity Document Recognition (IDR), i.e., the task aimed at automatically understanding, extracting, and transcribing the fields of an ID card. We devised a two-stage approach based on fine-tuning a pre-trained model on synthetic and real-world data. We also developed a dedicated synthetic data generation tool to support the IDR process. Experimental results demonstrated the effectiveness of our methodology.

{"title":"An End-to-End OCR-Free Solution For Identity Document Information Extraction","authors":"Salvatore Carta , Alessandro Giuliani , Leonardo Piano , Sandro Gabriele Tiddia","doi":"10.1016/j.procs.2024.09.425","DOIUrl":"10.1016/j.procs.2024.09.425","url":null,"abstract":"<div><div>Efficiently verifying the customer’s identity is essential for ensuring the security of online transactions. Such verification is mainly accomplished according to the widespread Know Your Client (KYC) protocol, which relies on a self-identification handled by the user, typically providing personal data from their identification document (ID). In the current digital communication generation, such a task is usually performed by uploading a digital copy of the document by scanning or taking a real-time picture from a personal device such as a smartphone or tablet. Such activity, which usually involves manual data entry, is time-consuming and prone to human errors. Document Understanding (DU) has emerged as a crucial factor for automating data extraction in this scenario. One of its main challenges is the scarcity of data, which is barely available for security and privacy concerns. To this end, this paper proposes a solution that takes advantage of recent advances in DU to devise an innovative strategy for Identity Document Recognition (IDR), i.e., the task aimed at automatically understanding, extracting, and transcribing the fields of an ID card. We devised a two-stage approach based on fine-tuning a pre-trained model on synthetic and real-world data. We also developed a dedicated synthetic data generation tool to support the IDR process. Experimental results demonstrated the effectiveness of our methodology.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"246 ","pages":"Pages 453-462"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development and Evaluation of an Urban-Scale Traffic Simulation for Reducing the Number of Traffic Accidents

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.09.429

Kaede Suzuki , Takeshi Uchitane , Naoto Mukai , Kazunori Iwata , Nobuhiro Ito , Yong Jiang

Realizing urban-scale traffic simulations and utilizing the results of traffic analysis provide valuable insights for society. This study focused on cities in Aichi Prefecture, which has relatively high rates of traffic accident fatalities compared to other prefectures in Japan and aimed to achieve an urban-scale vehicle traffic simulation for traffic analysis. We used Simulation of Urban MObility (SUMO) as the simulator and got appropriate results for the entire area of Aichi Prefecture. This paper also details the simulation results and discusses how these results can be applied to analyze and reduce the number of traffic accidents.

引用次数: 0

Privacy-Oriented Feature Selection for Multivariate Time Series Classification

Procedia Computer Science

Pub Date : 2024-01-01 DOI: 10.1016/j.procs.2024.09.430

Adrian-Silviu Roman , Béla Genge , Roland Bolboacă

The widespread use of sensors in various domains such as automotive or healthcare has greatly increased the amount of collected data, leading to important privacy issues. Although the sensor data does not directly identify individuals, it can still reveal sensitive information. Addressing privacy in the context of Time Series Classification (TSC) presents challenges, including the need to balance data utility and privacy protection. The current study introduces a novel privacy-oriented feature selection methodology for TSC, aiming to improve data privacy while preserving utility. We propose a dual-model approach, leveraging two classifiers with opposing objectives: a Utility-Focused Classifier (UFC) and a Privacy-Breaking Classifier (PBC). The methodology introduces the Importance Difference Score (IDS) for feature ranking with the objective of selecting features important for the UFC while removing the features essential for the PBC. The approach includes two feature clustering techniques, one based on IDS and the other on K-means clustering, to optimize the feature selection process. The experiments performed on two driving datasets and two Human Activity Recognition (HAR) datasets, evaluate the effectiveness in reducing the accuracy of potential adversarial classifiers while maintaining appropriate levels of utility. We contribute to the state-of-the-art by offering a configurable framework for feature selection to balance the privacy and utility of the data in TSC.

{"title":"Privacy-Oriented Feature Selection for Multivariate Time Series Classification","authors":"Adrian-Silviu Roman , Béla Genge , Roland Bolboacă","doi":"10.1016/j.procs.2024.09.430","DOIUrl":"10.1016/j.procs.2024.09.430","url":null,"abstract":"<div><div>The widespread use of sensors in various domains such as automotive or healthcare has greatly increased the amount of collected data, leading to important privacy issues. Although the sensor data does not directly identify individuals, it can still reveal sensitive information. Addressing privacy in the context of Time Series Classification (TSC) presents challenges, including the need to balance data utility and privacy protection. The current study introduces a novel privacy-oriented feature selection methodology for TSC, aiming to improve data privacy while preserving utility. We propose a dual-model approach, leveraging two classifiers with opposing objectives: a Utility-Focused Classifier (UFC) and a Privacy-Breaking Classifier (PBC). The methodology introduces the Importance Difference Score (IDS) for feature ranking with the objective of selecting features important for the UFC while removing the features essential for the PBC. The approach includes two feature clustering techniques, one based on IDS and the other on K-means clustering, to optimize the feature selection process. The experiments performed on two driving datasets and two Human Activity Recognition (HAR) datasets, evaluate the effectiveness in reducing the accuracy of potential adversarial classifiers while maintaining appropriate levels of utility. We contribute to the state-of-the-art by offering a configurable framework for feature selection to balance the privacy and utility of the data in TSC.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"246 ","pages":"Pages 500-509"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Procedia Computer Science

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.

﹀