检索结果-内蒙古大学图书馆

32nd International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2024

作者： Filho, Raimir Holanda Colares, Daniel University of Fortaleza Postgraduate Program in Applied Informatics Fortaleza Brazil

ISBN: (纸本)9789532901382

This paper addresses cybersecurity challenges in integrating Generative Artificial Intelligence (GenAI) into applications. It proposes a risk analysis approach that focuses on identifying threats and vulnerabilities exploited by malicious actors, which is validated through a case study on prompt injection attacks. The results demonstrated the efficacy of our approach in identifying and quantifying vulnerabilities in Large Language Models (LLMs). © 2024 university of Split, FESB.

关键词： Cyber Security Generative AI Large Language Models Risk Management

来源：评论

学校读者我要写书评

暂无评论

Hybrid model for early identification post-Covid-19 sequelae

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第11期14卷 14739-14752页

作者： de Andrade, Evandro Carvalho Pinheiro, Luana Ibiapina C. C. Pinheiro, Plácido Rogério Nunes, Luciano Comin Pinheiro, Mirian Calíope Dantas Pereira, Maria Lúcia Duarte de Abreu, Wilson Correia Filho, Raimir Holanda Simão Filho, Marum Pinheiro, Pedro Gabriel C. D. Nunes, Rafael Espíndola Comin Graduate Program in Applied Informatics University of Fortaleza Ceará Fortaleza Brazil Ceara State University Ceara Fortaleza Brazil University Center September 7 Ceara Fortaleza Brazil School of Nursing of Porto Porto Portugal

Artificial Intelligence techniques based on Machine Learning algorithms, Neural Networks and Naïve Bayes can optimise the diagnostic process of the SARS-CoV-2 or Covid-19. The most significant help of these techniques is analysing data recorded by health professionals when treating patients with this disease. Health professionals' more specific focus is due to the reduction in the number of observable signs and symptoms, ranging from an acute respiratory condition to severe pneumonia, showing an efficient form of attribute engineering. It is important to note that the clinical diagnosis can vary from asymptomatic to extremely harsh conditions. About 80% of patients with Covid-19 may be asymptomatic or have few symptoms. Approximately 20% of the detected cases require hospital care because they have difficulty breathing, of which about 5% may require ventilatory support in the Intensive Care Unit. Also, the present study proposes a hybrid approach model, structured in the composition of Artificial Intelligence techniques, using Machine Learning algorithms, associated with multicriteria methods of decision support based on the Verbal Decision Analysis methodology, aiming at the discovery of knowledge, as well as exploring the predictive power of specific data in this study, to optimise the diagnostic models of Covid-19. Thus, the model will provide greater accuracy to the diagnosis sought through clinical observation. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

***: Towards the Collection and Evaluation of Natural Causal Ladder Questions in Portuguese for AI Agents 1

***: Towards the Collection and Evaluation of Natural Causal...

引用

1st Workshop on Language Models for Low-Resource Languages, LoResLM 2025 - co-located at the 31st International Conference on Computational Linguistics, COLING 2025

作者： Lasheras, Uriel Pinheiro, Vládia Postgraduate Program in Applied Informatics University of Fortaleza Ceará Brazil

ISBN: (纸本)9798891762152

Large Language Models (LLMs) are increasingly central to the development of generative AI across diverse fields. While some anticipate these models may mark a step toward artificial general intelligence, their ability to handle complex causal reasoning remains unproven. Causal reasoning is essential for true general intelligence, particularly at Pearl’s interventional and counterfactual levels. In this work, we introduce ***, a dataset of over 8,000 natural causal questions in Portuguese, collected from real human interactions. Built upon a novel three-axis taxonomy, *** categorizes questions by causal intent, action requirements, and the level of causal reasoning needed (associational, interventional, or counterfactual). Our findings from evaluating ***’s seed questions with GPT-4o reveal that this LLM faces challenges in handling interventional and relation-seeking causal queries. These results suggest limitations in using GPT-4o for extending causal question annotations and highlight the need for improved LLM strategies in causal reasoning. *** provides a foundation for advancing LLM capabilities in causal understanding, particularly for the Portuguese-speaking world. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Methodology for Risk Management of Generative AI based Systems

A Methodology for Risk Management of Generative AI based Sys...

引用

International Conference on Software, Telecommunications and Computer Networks (SoftCOM)

作者： Raimir Holanda Filho Daniel Colares Postgraduate Program in Applied Informatics University of Fortaleza Fortaleza Brazil

ISBN: (数字)9789532901382

ISBN: (纸本)9798350354614

关键词： Generative AI Computational modeling Large language models Software Computer networks Telecommunications Risk management Computer crime Best practices

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of an Event-Driven Cloud-Based Architecture for a Remote Patient Monitoring System

Design and Evaluation of an Event-Driven Cloud-Based Archite...

引用

IEEE International Conference on Software Architecture Workshops (ICSAW)

作者： Pedro Fiuza Linhares Pedro H. Gaya Wanderley Marza de Sousa Zaranza Maria Andréia Formico Rodrigues Nabor C. Mendonça Post Graduate Program in Applied Informatics University of Fortaleza Fortaleza CE Brazil Center of Technological Sciences University of Fortaleza Fortaleza CE Brazil Intensive Care Unit Hospital Instituto Dr. José Frota (IJF) Fortaleza CE Brazil Post Graduate Program in Applied Informatics/GIRA Lab University of Fortaleza Fortaleza CE Brazil

ISBN: (数字)9798331533366

ISBN: (纸本)9798331533373

This paper presents an event-driven cloud-based serverless architecture for a remote patient monitoring system. The architecture is designed to be scalable, resilient, and cost-effective, and leverages managed cloud services to handle load variations and service faults. To evaluate the architecture, we conducted comprehensive capacity, scalability, and resilience tests. The test results show that the architecture can meet the performance, scalability, and reliability requirements of a remote patient monitoring system. Additionally, a detailed analysis of operational costs in the cloud confirms the cost-effectiveness of the solution and highlights practical opportunities for improvements.

关键词： Cloud computing Patient monitoring Software architecture Scalability Computer architecture Load management Performance analysis Reliability Resilience Testing

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Application for Smart Government: Dashboards for Effective Taxation of Property Taxes

A Machine Learning Application for Smart Government: Dashboa...

引用

IEEE International Smart Cities Conference (ISC2)

作者： Lara S. Furtado Virginia Queiroz Cecília Carvalho Filipe F. Damasceno Antonio A. F. Oliveira Vladia Pinheiro Masters in City Science University of Fortaleza Fortaleza Brazil Graduate Program of Applied Informatics University of Fortaleza Fortaleza Brazil Secretariat of Finance of the Municipality of Fortaleza Fortaleza Brazil

ISBN: (数字)9798350364316

ISBN: (纸本)9798350364323

Smart Government initiatives aim to enhance governmental services by strategically applying digital technologies. Property tax assessment, a crucial aspect of government revenue, often faces challenges due to outdated methods and complex evaluation models. The procedures to estimate property values are time consuming since mass estimation must evaluate dozens of building features, some of which may not completely influence market values. For government appraisers, making sense of millions of spatial data is cumbersome and prone to error. This paper proposes a comprehensive framework integrating Machine Learning (ML), dashboards, and Geographic Information Systems to address these challenges. By leveraging ML algorithms, interactive dashboards, and geospatial data, tax agencies can streamline property assessment processes, improve accuracy, and facilitate real-time decision-making. A case study in fortaleza, Brazil, demonstrates the framework's effectiveness in enhancing land value assessment and property taxation within the Smart Governance context. This paper provides insights into the benefits and challenges of implementing such a framework and underscores its potential to revolutionize property tax assessment practices.

关键词： Machine learning algorithms Smart cities Government Evaluation models Finance Machine learning Spatial databases Real-time systems Geospatial analysis Faces

来源：评论

学校读者我要写书评

暂无评论

Toc-Tum mini-games: An educational game accessible for deaf culture based on virtual reality

Toc-Tum mini-games: An educational game accessible for deaf ...

引用

作者： Chaves, Edilson M. Braga, Paulo Bruno de A. Montenegro, Yuri Fontenelle L. Rodrigues, Vitória B. Munguba, Marilene C. de Albuquerque, Victor Hugo C. Graduate Program in Applied Informatics University of Fortaleza Fortaleza/CE Brazil Universidade de Fortaleza Brazil

Human hearing is an important sense, which complements the other senses, and is essential for children to begin to acquire basic concepts of the world;however, in severe cases of disability, children become marginalized from these benefits. An example of this is with music, a deaf individual is to be able to perceive it. With this in mind, we developed a novel medical expert system based on virtual reality, called Toc-Tum mini-games, applying basic concepts of music in an accessible way to the deaf culture. The intelligent proposed system is validated in two different tests: (a) with the target audience to evaluate the interest in the game and (b) with professionals knowledgeable in the field of music or who have had contact with the deaf, evaluate the impact of the game teaching music to the deaf. The tests with the target audience showed that the methods of interaction allowed the children to understand most of the stages and that they were animated during the test days. Regarding the professionals, they were interested in the possibility of using the proposed system in question, even if some modifications in the design had to be made. The results showed that the Toc-Tum mini-games is an intelligent tool capable of introducing music in a playful and manageable way using a virtual environment. © 2019 John Wiley & Sons, Ltd.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Evaluating ChatGPT-4 Vision on Brazil’s National Undergraduate Computer Science Exam

arXiv

引用

arXiv 2024年

作者： Mendonça, Nabor C. Post-Graduate Program in Applied Informatics University of Fortaleza Av. Washington Soares 1321 Edson Queiroz Ceará Fortaleza60811-905 Brazil

The recent integration of visual capabilities into Large Language Models (LLMs) has the potential to play a pivotal role in science and technology education, where visual elements such as diagrams, charts, and tables are commonly used to improve the learning experience. This study investigates the performance of ChatGPT-4 Vision, OpenAI’s most advanced visual model at the time the study was conducted, on the Bachelor in Computer Science section of Brazil’s 2021 National Undergraduate Exam (ENADE). By presenting the model with the exam’s open and multiple-choice questions in their original image format and allowing for reassessment in response to differing answer keys, we were able to evaluate the model’s reasoning and self-reflecting capabilities in a large-scale academic assessment involving textual and visual content. ChatGPT-4 Vision significantly outperformed the average exam participant, positioning itself within the top 10 best score percentile. While it excelled in questions that incorporated visual elements, it also encountered challenges with question interpretation, logical reasoning, and visual acuity. A positive correlation between the model’s performance in multiple-choice questions and the performance distribution of the human participants suggests multimodal LLMs can provide a useful tool for question testing and refinement. However, the involvement of an independent expert panel to review cases of disagreement between the model and the answer key revealed some poorly constructed questions containing vague or ambiguous statements, calling attention to the critical need for improved question design in future exams. Our findings suggest that while ChatGPT-4 Vision shows promise in multimodal academic evaluations, human oversight remains crucial for verifying the model’s accuracy and ensuring the fairness of high-stakes educational exams. The paper’s research materials are publicly available at https://***/nabormendonca/gpt-4v-enade-cs-2021. © 202

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Synthesis of coral-like structures of Pr-Yb co-doped YIG: Structural,optical, magnetic and antimicrobial properties

引用

Journal of Rare Earths 2024年第3期42卷 543-554,I0004页

作者： A.Fernandez Francisca P.Araujo Y.Guerra S.Castro-Lopes J.Matilla-Arias Idglan S.de Lima Edson C.Silva-Filho Josy A.Osajima F.Guerrero R.Pena-Garcia Federal University of Piau Graduate Program in Materials Science and EngineeringTeresinaPIBrazil Federal Rural University of Pernambuco Academic Unit of Cabo de Santo AgostinhoCabo de Santo AgostinhoPEBrazil Federal University of Piaui Department of PhysicTeresinaPBrazil Federal University of Pernambuco Graduate Program in Materials ScienceRecifePEBrazil University of Granma Departmentof Basic Sciences and Applied InformaticsFaculty of Technical SciencesBayamoCuba Federal University of Amazonas Department of PhysicManausAMBrazil Federal University of Pernambuco Department of PhysicRecifePEBrazil

Coral-like structures of the Y_(3-x)Pr_(x)Fe_(5-y)Yb_(y)O_(12),(0.00 ≤ x ≤ 0.04, 0.00 ≤ y ≤ 0.02) compound were synthesized using the sol-gel method. Structural investigation certified the YIG cubic crystal structure formation, without any secondary phase. It is shown that, the relatively large ionic radius of the dopant cations results in an expansion of the lattice parameter, variations in the Iona-O-Iondangle, Iona-O,Iond-O and Ionc-O bond distances and decrease in the average crystallite size. Fourier transform infrared(FTIR) and Raman measurements are essential to testify the single-phase formation of YIG crystal structure and are observed changes in the stretching and vibrational modes, respectively. The morphological study, energy dispersive spectroscopy(EDS) spectra and textural properties show corallike structures, peaks associated with Pr^(3+) and Yb^(3+) atoms and the effect of dopants on surface area,diameter, and pore volume, respectively. The optical analysis from diffuse reflectance spectra witnessed an increase in the optical gap band, a decrease in Urbach energy and blue shift in the charge transfer,correlated with the expansion of the unit cell due to the dopant's insertion in the YIG structure. A typical ferrimagnetic behavior is exhibited by the Y_(3-x)Pr_(x)Fe_(5-y)Yb_(y)O_(12)compound. The saturation magnetization(M_(s)), cubic anisotropy constant(K_(1)) and coercive field(H_(c)) increase with the Pr^(3+)cations content, as consequence of their magnetic nature and distribution around of Fe^(3+)ions due to the coexistence with the Yb^(3+). Finally, for the first time, antibacterial tests by mean of the direct contact method were performed for YIG co-doped with Pr^(3+)and Yb^(3+)and it is shown that, relatively high dosages of Pr^(3+) cations favored the activity against S. aureus, therefore, a new biological property for YIG doped with rare earths is presented.

关键词： Yttrium iron garnet(YIG) Coral-like structures Rare earths Band gap energy Magnetic properties Antimicrobial properties

来源：评论

学校读者我要写书评

暂无评论

Software Quality Practices in Growing Startups: A Qualitative Study 20

Software Quality Practices in Growing Startups: A Qualitativ...

引用

20th Brazilian Symposium on Software Quality, SBQS 2021

作者： Pizzini, Adriano Bortolo Vieira, Ricardo Deda Gomes, Rhodrigo Santos, Gleison Malucelli, Andreia Reinehr, Sheila Graduate Program in Informatics Pontifical Catholic University of Paraná Paran Curitiba Brazil Department of Applied Informatics Federal University of the State of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)9781450395533

Startups arise in environments of extreme uncertainty, with few resources and the need to scale quickly. In the growth phase, they still need agility, but they tend to concern more with software quality and the development process by having more human and financial resources. Studying the factors that lead startups in the growth phase to seek quality in their processes can help new startups anticipate implementing quality practices. In this paper, we aim to identify how startups adopt quality practices in the growth phase. We carried out a multiple case study with four growth phase startups. We applied qualitative analysis techniques to summarize the findings. The studied startups adopt limited quality practices and are influenced by the development team's maturity level, organizational culture, and experience. Furthermore, they tend to be reactive towards quality, solving the problems when they impact their product, business, customer, or when technical debt can no longer be managed. The findings are relevant to support stabilizing and growing startups to define actions to improve the quality of their processes and products. Besides, they suggest that growth phase startups begin a process of change in the organizational culture concerning quality, adopting the behavior of mature companies as soon as they get more human and financial resources. © 2021 ACM.

关键词： Quality control

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：