检索结果-内蒙古大学图书馆

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

作者： Margarido, Solange Roque, Licínio Machado, Penousal Martins, Pedro CISUC/LASI Department of Informatics Engineering University of Coimbra Coimbra Portugal

ISBN: (纸本)9783031734960

The study of creative collaboration between humans and computational systems is a recurring topic in the area of computational creativity. With the rapid developments of Generative AI systems with increasingly improved performance and greater agency, this topic assumes growing importance. In this paper, we explore a specific paradigm of human-AI collaboration where the participants in the creative process work as colleagues – mixed-initiative co-creativity (MI-CCy). We investigate parameters that can serve as guidelines for the implementation of AI systems that have both a high level of mixed-initiative and a high level of co-creativity. To this end, we introduce the MI-CCy Quantifier, a framework that researchers and practitioners can use for assessing co-creative tools on their degree of MI-CCy through scales of gradable criteria presented in an intuitive visual layout. We reflect on the applicability of the MI-CCy Quantifier by demonstrating its usage in the analysis of a co-creative system, and we conclude by proposing future directions for mutually beneficial collaborations between humans and AI. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Co-creative systems Framework Human-AI co-creativity Mixed-initiative

来源：评论

学校读者我要写书评

暂无评论

Shaping the Digital Content of Mentoring Programs for Women in informatics: Insights from an Exploratory Study

Shaping the Digital Content of Mentoring Programs for Women ...

引用

17th International Conference on Computer Supported Education, CSEDU 2025

作者： Sousa, Francisca Tejo, Leonor Miranda, Sunny Silva, Paula Alexandra Department of Informatics Engineering University of Coimbra Portugal Department of Informatics Engineering University of Coimbra CISUC/LASI - Centre for Informatics and Systems of the University of Coimbra Portugal

ISBN: (纸本)9789897587467

Gender disparities in informatics persist as a significant issue, with women facing barriers to entry, retention, and advancement. Mentoring programs hold the potential to improve this issue. Because change demands a collective response, this study explores how to shape the digital content of mentoring programs to support the students, women and men, in an informatics department. This work builds upon the findings of a focus group study, complementing them by applying a questionnaire to gain insight into students' academic experiences, perceptions of the benefits of a mentoring program, and preferences concerning digital communication platforms. Findings indicate that the digital content of mentoring programs can help in three keyways: providing insights into the job market, shedding light on career and recruitment processes, and offering real-life content. These findings are valuable to departments and mentoring programs that wish to support women in informatics through the digital content of their websites and social media platforms. Copyright © 2025 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Self-organising Approach to Anomaly Mitigation in the Cloud-to-Edge Continuum 30th

Self-organising Approach to Anomaly Mitigation in the Clo...

引用

30th International Conference on Cooperative Information Systems, CoopIS 2024

作者： Faria, Bruno Abreu, David Perez Velasquez, Karima Curado, Marília Laboratory for Informatics and Systems Pedro Nunes Institute Coimbra Portugal CISUC Department of Informatics Engineering University of Coimbra Coimbra Portugal

ISBN: (纸本)9783031813740

The cloud-to-edge continuum paradigm has permeated various application domains, including critical urban-city safety systems. In these contexts, anomalies can compromise public safety, for example, by disrupting the communication between smart city infrastructure and vehicles, which aims to prevent accidents at pedestrian crossings. Given these environments’ heterogeneous and large-scale nature, manual recovery from anomalies is not feasible. Machine Learning techniques have emerged as an alternative, supporting a zero-touch approach that enables self-organising and self-healing solutions for anomaly prediction, detection, and mitigation. This paper proposes an Artificial Intelligence-driven, self-organising approach for anomaly management in the cloud-to-edge continuum, integrating both reactive and proactive mechanisms. We evaluate different Machine Learning models, including Random Forest Classifiers, Neural Networks, and Convolutional Neural Networks, to predict node performance anomalies. The simulation results obtained using the COSCO framework showcase the effectiveness of our method. It achieves an F1 score of 73% for multiclass classification, predicting different levels of anomaly severity, and 87% for binary classification, distinguishing between normal and abnormal states. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Anomaly management Cloud-to-edge continuum Machine learning Self-X Time-series classification Zero-touch

来源：评论

学校读者我要写书评

暂无评论

Introduction to the "Best of GECCO 2023" Special Issue

引用

ACM Transactions on Evolutionary Learning and Optimization 2025年第1期5卷 1-2页

作者： Paquete, Luís Silva, Sara University of Coimbra CISUC - Centre for Informatics and Systems LASI The University of Coimbra Department of Informatics Engineering Coimbra60106440 Portugal LASIGE Faculdade de Ciências Universidade de Lisboa Lisboa60106051 Portugal

来源：评论

学校读者我要写书评

暂无评论

What is the Role of GIS in Shaping Marketing Approaches? A Systematic Review

What is the Role of GIS in Shaping Marketing Approaches? A S...

引用

International Conference on Marketing and Technologies, ICMarkTech 2023

作者： Estima, Jacinto Estima, Ana University of Coimbra CISUC Department of Informatics Engineering Coimbra Portugal GOVCOPP ISCA—University of Aveiro Aveiro Portugal

ISBN: (纸本)9789819736973

In today’s data-driven world, Geographic Information Systems (GIS) have emerged as a powerful tool with significant implications for marketing strategies. This article presents a systematic literature review focused on the intersection of GIS and marketing, aiming to highlight the pivotal role of location-based methods and tools in shaping modern marketing approaches. Our investigation involved the retrieval of a curated selection of scholarly papers from the Scopus database, encompassing publications from the past decade within scientific journals, conference proceedings, and book chapters. Subsequently, we meticulously scrutinized 24 pertinent studies through a comprehensive analysis of their full texts. Through the examination of these selected papers, we identified prevailing themes and emerging trends across diverse applications of GIS within marketing contexts. These findings underscore the pivotal role that GIS can assume in optimizing marketing activities. Furthermore, this review engages in a thorough discussion, offering valuable guidance to both researchers and practitioners on how to harness the full potential of GIS, which can inform and inspire future research endeavor’s in this dynamic and ever-evolving field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Information use

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Code Pattern Reuse and Pattern Preference Consistency in Novice Programmers 23rd

An Empirical Study of Code Pattern Reuse and Pattern Prefe...

引用

23rd International Conference on Web-Based Learning, ICWL 2024 was held in conjunction with the 9th International Symposium on Emerging Technologies for Education, SETE 2024

作者： Lei, Philip I. S. Mendes, António José Lam, Chan-Tong CISUC Department of Informatics Engineering University of Coimbra Coimbra Portugal Computing Program Macao Polytechnic University Macao SAR China

ISBN: (纸本)9789819644063

After learning the basic features of a programming language, such as expressions and control statements, novice programmers need to combine these features to solve programming questions. Some of these combined code snippets are reusable constructs useful to solve future questions. They are referred to as plans, schemas, or patterns in the literature. An example of such a pattern is determining the equality of three values using the ‘equal and logical and operators. Previous research has investigated the acquisition of these patterns by observing and interviewing novice programmers as they solve programming problems. In this paper, we test the hypothesis that students tend to reuse acquired patterns to solve subsequent problems by analyzing a computer science education dataset called CodeWorkout, which contains students’ code submissions for introductory-level programming questions. We employed directed labeled tree to represent the Abstract Syntax Tree (AST) of the submitted code and the patterns. To search for a pattern, we first applied the subgraph isomorphism algorithm VF2 with wildcard node labels to identify candidate matches, followed by enforcing the proper ordering of descendant nodes between the pattern and the candidate matches. Experimental results demonstrate that our approach effectively identifies common usage of patterns. Moreover, the findings indicate that if a student employs a pattern in one question, they are likely to reuse the same pattern in a subsequent question. This paper also reveals that when multiple alternative patterns exist for the same function, students tend to maintain their preference for a particular alternative while solving different questions. These insights can inform future curriculum design and instructional strategies in programming education. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Unmanned Aerial Vehicles for Healthcare and Emergency Services

arXiv

引用

arXiv 2025年

作者： Habibi, Sara Ivaki, Naghmeh Barata, João CISUC Department of Informatics Engineering University of Coimbra Coimbra Portugal

Unmanned aerial vehicles (UAVs), initially developed for military applications, are now used in various fields. As UAVs become more common across multiple industries, it is crucial to understand how to adopt them effectively, efficiently, and safely. The utilization of UAVs in healthcare and emergency services has evolved significantly in recent years, with these aerial vehicles potentially contributing to increased survival rates and enhanced healthcare services. This paper presents a two-stage systematic literature review, including a tertiary study of 15 review papers and an in-depth assessment of 136 primary publications focused on using UAVs in healthcare and emergency services. The research demonstrates how civilian UAVs have been used in numerous applications, such as healthcare emergencies, medical supply delivery, and disaster management, for diverse use cases such as Automated External Defibrillator (AED) delivery, blood delivery, and search and rescue. The studies indicate that UAVs significantly improve response times in emergency situations, enhance survival rates by ensuring the timely delivery of critical medical supplies such as AEDs, and prove to be cost-effective alternatives to traditional delivery methods, especially in remote or inaccessible areas. The studies also highlight the need for ongoing research and development to address existing challenges, such as regulatory frameworks, security, privacy and safety concerns, infrastructure development, and ethical and social issues. Effectively understanding and tackling these challenges is essential for maximizing the benefits of UAV technology in healthcare and emergency services, ultimately leading to safer, more resilient, and responsive systems that can better serve public health needs. © 2025, CC BY-NC-ND.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

EDCA - An Evolutionary Data-Centric AutoML Framework for Efficient Pipelines

arXiv

引用

arXiv 2025年

作者： Simões, Joana Correia, João University of Coimbra CISUC LASI Department of Informatics Engineering Portugal

Automated Machine Learning (AutoML) gained popularity due to the increased demand for Machine Learning (ML) specialists, allowing them to apply ML techniques effortlessly and quickly. AutoML implementations use optimisation methods to identify the most effective ML solution for a given dataset, aiming to improve one or more predefined metrics. However, most implementations focus on model selection and hyperparameter tuning. Despite being an important factor in obtaining high-performance ML systems, data quality is usually an overlooked part of AutoML and continues to be a manual and time-consuming task. This work presents EDCA, an Evolutionary Data Centric AutoML framework. In addition to the traditional tasks such as selecting the best models and hyperparameters, EDCA enhances the given data by optimising data processing tasks such as data reduction and cleaning according to the problems’ needs. All these steps create an ML pipeline that is optimised by an evolutionary algorithm. To assess its effectiveness, EDCA was compared to FLAML and TPOT, two frameworks at the top of the AutoML benchmarks. The frameworks were evaluated in the same conditions using datasets from AMLB classification benchmarks. EDCA achieved statistically similar results in performance to FLAML and TPOT but used significantly less data to train the final solutions. Moreover, EDCA experimental results reveal that a good performance can be achieved using less data and efficient ML algorithm aspects that align with Green AutoML guidelines. Copyright © 2025, The Authors. All rights reserved.

关键词： Data reduction

来源：评论

学校读者我要写书评

暂无评论

From Waterfallish Aerospace Certification onto Agile Certifiable Iterations

arXiv

引用

arXiv 2025年

作者： Ribeiro, J. Eduardo Ferreira Zenha-Rela, Mário Silva, João Gabriel Department of Informatics Engineering Faculty of Engineering University of Porto Porto4200-465 Portugal CISUC Department of Informatics Engineering Coimbra3030-290 Portugal

MSC Codes N/AAgile software development is becoming increasingly popular in the aerospace industry because of its capability to accommodate requirement changes. However, safety-critical domains require compliance with strict regulations such as the DO-178C avionics standard, which demands thorough documentation. The main challenge of this constraint is not the content itself, but rather the comprehensive traceability from system-level requirements to all sorts of testing and verification evidence, including who did what, when, and to which artifact. Currently, this is mostly a manual activity performed at the end of the project, which blocks efforts to agilize the development of software for aerospace applications. In this paper, we present a strategy and tools that support the generation of continuous documentation complying with DO-178C requirements. By iteratively creating the DO-178C documentation associated with each software component and seamlessly merging it with the previously generated documentation, we open the way to truly continuous certifiable iterations, an evolution from the current Waterfallish industry practice. The proposed mechanisms and tools were co-designed and validated with aerospace industry professionals, thereby confirming its applicability and usefulness. The generated artifacts show that document automation is feasible in the aerospace industry, opening the way for more widespread adoption of Agile practices in this highly regulated sector. © 2025, CC BY.

关键词： Aerospace industry

来源：评论

学校读者我要写书评

暂无评论

EDCA – An Evolutionary Data-Centric AutoML Framework for Efficient Pipelines

EDCA – An Evolutionary Data-Centric AutoML Framework for E...

引用

28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025

作者： Simões, Joana Correia, João Department of Informatics Engineering University of Coimbra CISUC/LASI - Centre for Informatics and Systems of the University of Coimbra Coimbra Portugal

ISBN: (纸本)9783031900648

Automated Machine Learning (AutoML) gained popularity due to the increased demand for Machine Learning (ML) specialists, allowing them to apply ML techniques effortlessly and quickly. AutoML implementations use optimisation methods to identify the most effective ML solution for a given dataset, aiming to improve one or more predefined metrics. However, most implementations focus on model selection and hyperparameter tuning. Despite being an important factor in obtaining high-performance ML systems, data quality is usually an overlooked part of AutoML and continues to be a manual and time-consuming task. This work presents EDCA, an Evolutionary Data Centric AutoML framework. In addition to the traditional tasks such as selecting the best models and hyperparameters, EDCA enhances the given data by optimising data processing tasks such as data reduction and cleaning according to the problems’ needs. All these steps create an ML pipeline that is optimised by an evolutionary algorithm. To assess its effectiveness, EDCA was compared to FLAML and TPOT, two frameworks at the top of the AutoML benchmarks. The frameworks were evaluated in the same conditions using datasets from AMLB classification benchmarks. EDCA achieved statistically similar results in performance to FLAML and TPOT but used significantly less data to train the final solutions. Moreover, EDCA experimental results reveal that a good performance can be achieved using less data and efficient ML algorithm aspects that align with Green AutoML guidelines. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data reduction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：