检索结果-内蒙古大学图书馆

Advances in 3D fusion of multimodal medical images: 3D reconstruction of bone, muscle, and ligament structures under load from radiographs and magnetic resonance imaging

引用

Research on Biomedical Engineering 2025年第1期41卷 1-35页

作者： da Silva, Daniel S. Astolfi, Rodrigo S. Jagatheesaperumal, Senthil K. Selvaraj, Priyadharsini Russel, Newlin Shebiah de Albuquerque, Victor Hugo C. Post-Graduation Program of Medical Surgical Sciences Federal University of Ceara CE Fortaleza60455-970 Brazil Department of Teleinformatics Engineering Federal University of Ceara CE Fortaleza60455-970 Brazil Department of Electronics and Communication Engineering Mepco Schlenk Engineering College TN Sivakasi626005 India Department of Computer Science and Engineering Mepco Schlenk Engineering College TN Sivakasi626005 India

Purpose: Foot and ankle pathologies are among the most prevalent conditions within the human locomotor system. Imaging examinations are crucial for diagnosing, treating, and achieving satisfactory functional outcomes for these conditions. However, conventional imaging exams often fail to capture all the necessary details for precise analysis, necessitating the use of multiple imaging modalities to evaluate bones, ligaments, cartilage, and other structures. Objective: This research aims to explore computational technologies and algorithms for 3D reconstruction and fusion of foot and ankle images, alongside the analysis, segmentation, classification, and evaluation techniques applied to these images. Methods: The study investigates different computational approaches for 3D reconstruction and multimodal image fusion, integrating X-ray and MRI data. Advanced segmentation and classification techniques are applied to enhance the precision of structural assessment. Additionally, we assess the availability and quality of databases for training and validating these models. Results: Our findings highlight a significant gap in research concerning these specific applications, as well as a shortage of suitable databases for 3D reconstruction and fusion of images from X-rays and MRI. Conclusion: The study emphasizes the need for dedicated datasets and further research to develop effective computational solutions for multimodal foot and ankle imaging. © The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering 2025.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

CVO: Curriculum Vitae Optimization by Recommending Keywords to Undergraduate Students 11th

CVO: Curriculum Vitae Optimization by Recommending Keywords...

引用

11th and 12th EAI International Conference on Big Data Technologies and Applications, BDTA 2021 and BDTA 2022

作者： Santos, Cibele Góes, Fabrício Martins, Carlos da Cunha, Felipe Post-Graduation Program in Electrical Engineering Pontifícia Universidade Católica de Minas Gerais MG Belo Horizonte30535-901 Brazil Informatics Department University of Leicester Leicester United Kingdom Post-Graduation Program in Informatics Pontifícia Universidade Católica de Minas Gerais MG Belo Horizonte30535-901 Brazil Department of Computer Science Pontifícia Universidade Católica de Minas Gerais MG Belo Horizonte30535-901 Brazil

ISBN: (纸本)9783031336133

Candidate selection platforms have been widely used in companies that seek agility in the process of hiring. Candidates who do not meet the requirements of a job vacancy are disqualified in the first step, called screening. This stage has been automated due to the large volume of curriculum vitae (CV) of candidates per vacancy, particularly for internship vacancies. As a consequence, candidates receive little to none feedback and do not know how to improve/optimize their CVs for new applications. The goal of this paper is to realize the curriculum vitae optimization (CVO) process for internship vacancies by implementing a recommendation system that given an undergraduate student CV, it suggests the addition of relevant keywords, taking into account the student’s undergraduate course. This system is implemented based on the clustering of CVs keywords, from an internship recruitment private company database, into profile groups which are linked to internship vacancies. The experimental results showed that recommendations improved students CVs similarity (competitiveness within a specific field) from 18.83%, with 3 keywords recommendation, up to 50.67%, with 10 words. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Mitigation of Hallucinations in Language Models in Education: A New Approach of Comparative and Cross-Verification

Mitigation of Hallucinations in Language Models in Education...

引用

International Conference on Advanced Learning Technologies (ICALT)

作者： Wildemarkes de Almeida da Silva Luis Carlos Costa Fonseca Sofiane Labidi José Chrystian Lima Pacheco Post-Graduation Program in Computer and Systems Engineering State University of Maranhão - UEMA São Luís Brazil Bachelor of Science and Technology Program -BICT Federal University of Maranhão - UFMA São Luís Brazil Graduation in Computer and Systems Engineering State University of Maranhão - UEMA São Luís Brazil

ISBN: (数字)9798350362053

ISBN: (纸本)9798350362060

The rapid growing application of language models (LLMs) in education offers exciting prospects for personalized learning and interactive experiences. However, a critical challenge emerges - the risk of "hallucinations," where LLMs generate factually incorrect or misleading information. This paper proposes Comparative and Cross-Verification Prompting (CCVP), a novel technique specifically designed to mitigate hallucinations in educational LLMs. CCVP leverages the strengths of multiple LLMs, a Principal Language Model (PLM) and Auxiliary Language Models (ALMs), to verify the accuracy and educational relevance of the PLM's response to a prompt. Through a series of prompts and assessments, CCVP harnesses the diverse perspectives of various LLMs and incorporates human expertise for intricate cases. This method addresses the limitations of relying on a single model and fosters critical thinking skills in learners within the educational context. We detail the CCVP approach with examples specifically applicable to educational settings, such as geography. We also discuss its strengths and limitations, including computational cost, data reliance, and ethical considerations. We highlight its potential applications in educational disciplines, including fact-checking content, detecting bias, and promoting responsible LLM use. CCVP presents a promising avenue for ensuring the accuracy and trustworthiness of LLM-generated educational content. Further research and development will refine its scalability, address potential biases, and solidify its position as a vital tool for harnessing the power of LLMs while fostering responsible knowledge dissemination in education.

关键词： Geography Solid modeling Accuracy Scalability Prevention and mitigation Computational modeling Education

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence-Based Decision Making for Pest Control Against Spodoptera Frugiperda in Maize

SSRN

引用

SSRN 2023年

作者： Bertolla, Alex Bisetto Cruvinel, Paulo Estevão Embrapa Instrumentation SP São Carlos Brazil Post-Graduation Program in Computer Science Federal University of São Carlos SP São Carlos Brazil

Currently, the identification of fall armyworm (Spodoptera frugiperda) in maize (Zea mays) depends heavily on manual human effort, which could not sufficiently control the pests in a timely manner, resulting in both significant losses and negative impacts on agricultural production. This paper presents an innovative method for the pattern recognition of this species of caterpillar in its different growth stages. This method is based not only on image processing techniques but also on multivariate statistics and machine learning. Furthermore, it can allow support decision-making for pest control against fall armyworm directly in the crop area. Results have shown the effectiveness of the proposed method at recognition and classification, with both accuracy and precision higher than 70% and 80%, respectively. Thus, the proposed method makes it possible to automate mechanisms for the control of fall armyworm populations, which is of great interest to farmers who intend to promote productivity gains and pest control robustness for food security. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Band-Pass Filtering for Non-Stationary Noise in Agricultural Images to Pest Control Based On Adaptive Semantic Modeling

Band-Pass Filtering for Non-Stationary Noise in Agricultural...

引用

International Conference on Semantic Computing

作者： Alex B. Bertolla Paulo E. Cruvinel Post-Graduation Program in Computer Science Federal University of São Carlos SP Brazil

ISBN: (数字)9781728188997

ISBN: (纸本)9781728189000

Image analysis has been used in a very large scale for different purposes. When an image is captured by a digital sensor, it is usually affected by some type of noise, even the smoothest ones. Therefore, image enhancement and denoising process are important tasks of digital image processing. This paper presents an algorithm to reduce non-stationary noise with the combination of a Low-Pass Filter (LPF) and a High-Pass Filter (HPF), in conjunction with an adaptive semantic model. To simulate the usefulness of such arrangement, a non-stationary Gaussian noise has been applied to an image, which has been splitted into the four quadrants, all of them having the same dimensions. In fact, such a noise with different intensities, has been added to the image in each of its quadrants. The Peak Signal-to-Noise Ratio (PSNR) has been used to measure the best cutoff frequencies for both filters, as well as rules based on semantic concepts have been structured for decision making. Furthermore, for the validation of the algorithm we have taken into account the evaluation of the Mean Squared Error (MSE) using a typical digital image obtained from a crop of maize with the presence of the earwornm (Helicoverpa Zea). Besides, the denoising process demonstrates the efficiency and the satisfactory performance for the non-stationary noise filtering in agricultural images.

关键词： Band-pass filters PSNR Semantics Cutoff frequency Low-pass filters Filtering algorithms Digital filters

来源：评论

学校读者我要写书评

暂无评论

The Arquive of Tatuoca Magnetic Observatory Brazil: from paper to intelligent bytes

The Arquive of Tatuoca Magnetic Observatory Brazil: from pap...

引用

IEEE International Conference on Big Data

作者： Cristian Berrío-Zapata Ester Ferreira da Silva Mayara Costa Pinheiro Vinicius Augusto Carvalho de Abreu Cristiano Mendel Martins Mario Augusto Góngora Kelso Dunman Faculty of Archival Science Information Science Post Graduation Program (PPGCI) Universidade Federal do Pará (UFPA) Belém Brazil Archives and Libraries in the Digital Environment Universidad Carlos III (UC3M) Madrid Spain Post Graduation Program (PPGCI) Universidade Federal do Pará (UFPA) Belém Brazil Faculty of Computer Science Information Science Post graduation Program (PPGCI) Universidade Federal do Pará (UFPA) Belém Brazil Faculty of Geology Geoscience Post graduation Program (PPGGF) Universidade Federal do Pará (UFPA) Belém Brazil Faculty of Computing Engineering and Media De Montfort University Leicester UK School of Information MAS/LIS program University of British Columbia Canada

ISBN: (纸本)9781665480468

The Magnetic Observatory of Tatuoca (TTB) was installed by Observatório Nacional (ON) in 1957, near Belém city in the state of Pará, Brazilian Amazon. Its history goes back to 1933, when a Danish mission used this location to collect data, due to its privileged position near the terrestrial equator. Between 1957 and 2007, TTB produced 18,000 magnetograms on paper using photographic variometers, and other associated documents like absolute value forms and yearbooks. Data was obtained manually from these graphs with rulers and grids, taking 24 average readings per day, that is, one per hour. In 2017, the Federal University of Pará (UFPA in the Portuguese acronym) and ON collaborated to rescue this physical archive. In 2022 UFPA took a step forward and proposed not only digitizing the documents but also developing an intelligent agent capable of reading and extracting the information of the curves with a resolution better than an hour, being this the central goal of the project. If the project succeeds, it will rescue 50 years of data imprisoned in paper, increasing measurement sensitivity far beyond what these sources used to give. This will also open the possibility of applying the same AI to similar documents in other observatories or disciplines like seismography. This article recaps the project, and the complex challenges faced in articulating Archival science principles with AI and Geoscience.

关键词： Deep learning Observatories Magnetic resonance imaging Urban areas Collaboration Big Data Data mining

来源：评论

学校读者我要写书评

暂无评论

Algorithm For the Countering Maize Plants Based On UAV, Digital Image Processing and Semantic Modeling

Algorithm For the Countering Maize Plants Based On UAV, Digi...

引用

International Conference on Semantic Computing

作者： Wilbur N. Chiuyari Veramendi Paulo E. Cruvinel Federal University of Sao Carlos - Post Graduation Program in Computer Science São Carlos SP Brazil

ISBN: (数字)9781728188997

ISBN: (纸本)9781728189000

With the need to increase agricultural production and to avoid loss, this paper presents the development of a new method for counting plants of maize in an agricultural field using spectral images obtained by an UAV, as well as digital processing and semantic modeling techniques. The method is based on the use of the Circular Hough Transform (CHT) in conjunction with the techniques of Backmapping, neighborhood analysis, and a classification of patterns. Both the supper vector machines (SVM) and the neural networks (NN) methods have been evaluated for the classification procedure. Besides, using a computational environment for simulation, previous results have been obtained, i.e., showing not only the usefulness of the direct measures but also an automatic way for the plants identification, counting and height determination of the planted maize. Also, the establishment of a friendly interface has been carried out, which allows the monitoring of the phenological phases involved in the stages of the maize cultivation.

关键词： Visualization Plants (biology) Digital images Semantics Two dimensional displays Process control Production

来源：评论

学校读者我要写书评

暂无评论

A Differential Evolution Algorithm for Contrast Optimization 9th

A Differential Evolution Algorithm for Contrast Optimization

引用

9th Brazilian Conference on Intelligent Systems, BRACIS 2020

作者： da Costa Oliveira, Artur Leandro Britto, André Post-Graduation Program in Computer Science Federal University of Sergipe Sergipe Brazil Departament of Computing Federal University of Sergipe Sergipe Brazil

ISBN: (纸本)9783030613761

Image Enhancement is one of the most important phases of the image processing system. Contrast Enhancement plays a key role in this step. Histogram Equalization (HE) is one of the main tools used to improve the contrast of an image. However, the use of HE causes an increase in the natural brightness of the image, which is not desirable in many types of applications such as consumer electronics products. To solve these limitations, it is proposed in this paper a variation of the Differential Evolution metaheuristic algorithm for Contrast Optimization called DECO. The results obtained were statistically compared with other techniques and metaheuristic algorithms. The results showed that DECO is competitive compared with other techniques. © 2020, Springer Nature Switzerland AG.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

New Surrogate Approaches Applied to Meta-Heuristic Algorithms 19th

New Surrogate Approaches Applied to Meta-Heuristic Algorithm...

引用

19th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2020

作者： Oliveira, Joel A. Almeida, Matheus Santos Santos, Reneilson Y. C. de Gusmão, Rene Pereira Britto, André Post-Graduation Program on Computer Science Federal University of Sergipe São Cristóvão Brazil Computation Departament Federal University of Sergipe São Cristóvão Brazil

ISBN: (纸本)9783030615338

Surrogate can be defined as a mechanism capable of learning the behavior of a given objective function. As it is a regression problem, machine learning (ML) models are natural candidates to solve it. However, there is a lack of works comparing different machine learning techniques employed as surrogates. Thus, this paper proposes new surrogate approaches applied to meta-heuristic algorithms, as well as evaluate different machine learning models. It is proposed a new framework that embodies different ML models as surrogates, like decision trees, random forest, and SVR, and explores different mechanisms to train the models. An experiment set is performed to evaluate the framework. © 2020, Springer Nature Switzerland AG.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Ontology for Structuring a Digital Databases for Decision Making in Grain Production

Ontology for Structuring a Digital Databases for Decision Ma...

引用

International Conference on Semantic Computing

作者： Ricardo A. Neves Paulo E. Cruvinel Federal Institute of São Paulo São João da Boa Vista SP Brazil Post-Graduation Program in Computer Science - Federal University of São Carlos SP Brazil

ISBN: (数字)9781728188997

ISBN: (纸本)9781728189000

This paper presents an ontology for the structuring of digital databases with the objective of acting in a cloud environment and meeting big data sources in the agricultural context of grain production. Its conception is structured in three stages: the first stage presents an ontological architecture aimed at public and private cloud environments, the second stage deals with a semantic model at process level, and a pseudocode for ontological application is elaborated in the third stage, considering the technologies applied to the cloud. This work combines advanced features to support decision making from Data Lake storage solutions, semantic treatment of big data, as well as the presentation of strategies based on machine learning and data quality analysis to obtain data and metadata organized for application in a decision model. The configuration of the ontology presented meets the diversity of big data projects in the grain production context, the characteristics of which are based on interoperability in the use of heterogeneous data and its integration, elasticity of computational resources, and high availability of cloud access.

关键词： Cloud computing Databases Semantics Decision making Production Ontologies Big Data

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：