检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Giuri, Humberto Krohling, Renato A. Labcin - Nature-inspired computing Lab. Federal University of Espírito Santo ES Vitória Brazil Graduate Program in Computer Science PPGI UFES Federal University of Espírito Santo ES Vitória Brazil

Content-Based Image Retrieval (CBIR) have shown promising results in the field of medical diagnosis, which aims to provide support to medical professionals (doctor or pathologist). However, the ultimate decision regarding the diagnosis is made by the medical professional, drawing upon their accumulated experience. In this context, we believe that artificial intelligence can play a pivotal role in addressing the challenges in medical diagnosis not by making the final decision but by assisting in the diagnosis process with the most relevant information. The CBIR methods use similarity metrics to compare feature vectors generated from images using Convolutional Neural Networks (CNNs). In addition to the information contained in medical images, clinical data about the patient is often available and is also relevant in the final decision-making process by medical professionals. In this paper, we propose a novel method named CBIDR, which leverage both medical images and clinical data of patient, combining them through the ranking algorithm TOPSIS. The goal is to aid medical professionals in their final diagnosis by retrieving images and clinical data of patient that are most similar to query data from the database. As a case study, we illustrate our CBIDR for diagnostic of oral cancer including histopathological images and clinical data of patient. Experimental results in terms of accuracy achieved 97.44% in Top-1 and 100% in Top-5 showing the effectiveness of the proposed approach. © 2024, CC BY-NC-ND.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Methods for Addressing Imbalanced Datasets in Predicting Medical Appointment No-Shows

Comparative Methods for Addressing Imbalanced Datasets in Pr...

引用

Conferencia Latinoamericana En Informatica (CLEI)

作者： Marcelo Ardizzon Lovatte Leandro Colombi Resendo Karin Satie Komati Instituto Federal do Espírito Santo PPComp IFES Campus Serra Serra-ES Brazil Graduate Program in Applied Computing Instituto Federal do Espírito Santo PPComp IFES Campus Serra Serra-ES Brazil

ISBN: (数字)9798331540975

ISBN: (纸本)9798331540982

The efficiency and accessibility of healthcare delivery systems can be enhanced through solutions that minimize the impact of patient No-Shows for medical exams and appointments. The significant disparity between the “Show” and “No-Show” categories within the dataset can impair the efficacy of predictive models, necessitating the employment of dataset balancing techniques before classifier training. This study evaluated various methods to address imbalances in datasets for predicting patient No-Shows. Techniques such as undersampling (Random Removal - RR, Remove Similar - RS, Remove Farthest - RF) and oversampling (Adaptive Synthetic Sampling - ADASYN) were applied to adjust the balance between Show and No-Show categories to ratios of 80–20%, 70–30%, 60–40%, and 50–50%, alongside a cost-sensitive learning approach. Four classifiers were deployed: Support Vector Machine (SVM), Naive Bayes, k-Nearest Neighbors (k-NN), and Random Forests. Additionally, a decision tree produced by the C4.5 algorithm was utilized for the cost-sensitive learning approach. The classifiers were evaluated using metrics such as Precision, Recall, F-measure, and AUC/ROC. Among the various methods tested, the RR combined with the k-NN classifier achieved the highest AUC/ROC value. However, due to the longer computational time of k-NN, the Random Forest classifier emerged as a more pragmatic choice when processing time is a critical consideration.

关键词： Measurement Training Support vector machines Accuracy Databases Training data Predictive models Classification algorithms Random forests Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

TASC4RE: a data-driven context model to support the elicitation of context-aware functionalities

TASC4RE: a data-driven context model to support the elicitat...

引用

2022 ER Forum and PhD Symposium, ER-Forum-PhD 2022

作者： Falcão, Rodrigo Pestana, Maria Clara Vieira, Vaninha Fraunhofer IESE Fraunhofer-Platz 1 Kaiserslautern67663 Germany Computer Science Graduate Program UFBA Av. Milton Santos s/n Salvador40170-110 Brazil Institute of Computing UFBA Av. Milton Santos s/n Salvador40170-110 Brazil

In requirements elicitation for context-aware systems, context modeling is an essential early step. However, it has been overlooked by practitioners due to its perceived high complexity, in particular when it comes to the analysis of how different contexts may influence a user task of interest. To change this situation, data-driven context modeling approaches appear to be promising: Based on contextual data, algorithms can identify how contextual elements may, in combination with each other, influence user tasks. In this paper, we contribute the Task-specific Context Model for Requirements Elicitation (TASC4RE). TASC4RE is a context model representation aimed at supporting data-driven context modeling approaches. It combines the expressiveness of natural language, which is appreciated by human readers, with formality. TASC4RE was preliminarily evaluated in a controlled experiment with professionals in the context of a software development project. The results showed a positive trend towards the acceptance of the model. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Influence of land-sea breeze on PM _2.5 prediction in central and southern Taiwan using composite neural network

引用

Scientific Reports 2023年第1期13卷 1-9页

作者： Kibirige, George William Huang, Chiao Cheng Liu, Chao Lin Chen, Meng Chang Institute of Information Science Academia Sinica New Taipei Taiwan Social Networks and Human Centered Computing Program Taiwan International Graduate Program New Taipei Taiwan National Chengchi University New Taipei Taiwan

PM2.5 prediction plays an important role for governments in establishing policies to control the emission of excessive atmospheric pollutants to protect the health of citizens. However, traditional machine learning me...

PM_2.5 prediction plays an important role for governments in establishing policies to control the emission of excessive atmospheric pollutants to protect the health of citizens. However, traditional machine learning methods that use data collected from ground-level monitoring stations have reached their limit with poor model generalization and insufficient data. We propose a composite neural network trained with aerosol optical depth (AOD) and weather data collected from satellites, as well as interpolated ocean wind features. We investigate the model outputs of different components of the composite neural network, concluding that the proposed composite neural network architecture yields significant improvements in overall performance compared to each component and the ensemble model benchmarks. The monthly analysis also demonstrates the superiority of the proposed architecture for stations where land-sea breezes frequently occur in the southern and central Taiwan in the months when land-sea breeze dominates the accumulation of PM_2.5. © 2023, The Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Steady-state phases and interaction-induced depletion in a driven-dissipative chirally-coupled dissimilar atomic array

引用

Physical Review Research 2024年第2期6卷 023232-023232页

作者： Shao-Hong Chung I Gusti Ngurah Yudi Handayana Yi-Lin Tsao Chun-Chi Wu G.-D. Lin H. H. Jen Department of Physics and Center for Quantum Science and Engineering Taipei 10617 Taiwan Molecular Science and Technology Program Taiwan International Graduate Program Department of Physics Physics Division National Center for Theoretical Sciences Taipei 10617 Taiwan Trapped-Ion Quantum Computing Laboratory Hon Hai Research Institute Taipei 11492 Taiwan

A nanophotonic waveguide coupled with an atomic array forms one of the strongly coupled quantum interfaces to showcase many fascinating collective features of quantum dynamics. In particular, for a dissimilar array of two different interparticle spacings with competing photon-mediated dipole-dipole interactions and directionality of couplings, we study the steady-state phases of atomic excitations under a weakly driven condition of laser field. We identify a partial set of steady-state phases of the driven system composed of combinations of steady-state solutions in a homogeneous array. We also reveal the intricate role of the atom at the interface of the dissimilar array in determining the steady-state phases and find an alteration in the dichotomy of the phases strongly associated with steady-state distributions with crystalline orders. We further investigate in detail the interaction-induced depletion in half of the dissimilar array, where the blockaded region results from two contrasting interparticle spacings near the reciprocal coupling regime. This can be further evidenced from the analytical solutions under the reciprocal coupling. Our results can provide insights in the driven-dissipative quantum phases of atomic excitations with nonreciprocal couplings and pave the avenues toward quantum simulations of exotic many-body states essential for quantum information applications.

关键词： Collective behavior Dissipative dynamics Nanophotonics Phase diagrams Dipole approximation Two-level models

来源：评论

学校读者我要写书评

暂无评论

Modelling IF Steels Using Artificial Neural Networks and Automated Machine Learning 20th

Modelling IF Steels Using Artificial Neural Networks and Aut...

引用

20th International Conference on Hybrid Intelligent Systems, HIS 2020 and 12th World Congress on Nature and Biologically Inspired computing, NaBIC 2020

作者： Sgrott, Douglas Macedo Cerqueira, Fabricio Moreira Miranda, Fabiano J. F. Filho, José F. S. Parpinelli, Rafael S. UDESC Graduate Program in Applied Computing Santa Catarina State University JoinvilleSC Brazil Global Research and Development Group ArcelorMittal São Francisco do SulSC Brazil

ISBN: (纸本)9783030730499

The development of steels requires multiples manufacturing steps and involves a high number of variables and non-linear processes. Although there are data-driven models used to predict such steels’ mechanical properties, their design often requires specialized Machine Learning knowledge, hampering the application of such models. In this paper, an Automated Machine Learning (AutoML) framework, namely Auto-Keras, was employed to generate and train a data-driven model on a steel data-set through Neural Architecture Search. This paper proposes predicting the mechanical properties of steels applying Artificial Neural Networks (ANN) as a multivariate regression problem using AutoML. The results show that even with a vast parameter search space, it is possible to generate ANNs with different architectures that provide high performance with free and open-source AutoML. Three ANNs with different activation functions were optimized using Auto-Keras and compared. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Synthetic Well Logs with PCA-Based GAN Models

Enhancing Synthetic Well Logs with PCA-Based GAN Models

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Luciano Garim Garcia Gabriel De Oliveira Ramos José Manuel Marques Teixeira de Oliveira Ariane Santos Da Silveira Applied Computing Graduate Program Universidade do Vale do Rio dos Sinos São Leopoldo Brazil Center of Excellence in Geological and Numerical Modeling Universidade do Vale do Rio dos Sinos São Leopoldo Brazil

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

The generation of synthetic well log data is crucial for enhancing the understanding and exploration of subsurface reservoirs. This paper introduces a novel Generative Adversarial Network (GAN) model that incorporates a Principal Component Analysis (PCA)-based loss function to improve the quality of synthetic well log data. The proposed method is distinguished by its ability to generate complete well log datasets, rather than just individual logs or completing partial logs. Traditional GANs utilize cross-entropy loss but often fail to capture the complex structural patterns inherent in well logs. By integrating PCA into the loss function, our model not only distinguishes real from synthetic data but also ensures that the synthetic data retains the intrinsic variability and relationships observed in real logs. We validate our approach using histograms, correlation heatmaps, dimensionality reduction techniques (PCA and t-SNE), and a discriminative task. Results show that synthetic data generated with PCA-based loss aligns closely with real data, demonstrating superior preservation of statistical and structural characteristics. This advancement in synthetic data generation holds promise for enriching subsurface data analysis and exploration.

关键词： Training Analytical models Data analysis Correlation Scalability Generative adversarial networks Transformers Data models Synthetic data Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

ICD-10 - ORPHA: An Interactive Complex Network Model for Brazilian Rare Diseases

引用

Procedia Computer Science 2024年 239卷 634-642页

作者： Mariane Barros Neiva Bibiana Mello de Oliveira Amanda Maria Schmidt Victória Machado Scheibe Júlia Cordeiro Milke Mariana Lopes dos Santos Diego Bettiol Yamada Márcio Eloi Colombo Filho Giovane Thomazini Soares Yasmin de Araújo Ribeiro Odemir Martinez Bruno Têmis Maria Félix Domingos Alves RARAS Network group Scientific Computing Group University of São Paulo São Carlos SP Brazil Ribeirão Preto Faculty of Medicine University of São Paulo São Paulo Brazil Medical Genetics Service Porto Alegre Clinical Hospital Porto Alegre RS Brazil Graduate Program in Genetics and Molecular Biology Federal University of Rio Grande do Sul Porto Alegre RS Brazil Graduate Program in Medicine: Medical Sciences Federal University of Rio Grande do Sul Porto Alegre RS Brazil

A disease is considered rare if it has a low prevalence. It is estimated that around 400 million people worldwide have a rare disease, including 15 million in Brazil. Consequently, it became a public health priority for the World Health Organization and the Brazilian Health Ministry. In 2014, the Brazilian government launched a national policy regarding the care for rare patients’, the Ordinance nº199. The national politic defines guidelines, procedures, and descriptions of rare disease codes to provide access and diagnosis in the public health system to reduce mortality and improve patient’s quality of life. Diseases are identified according to the International Classification of Diseases 10th Revision, a widely used terminology in this context. However, there are also different terminologies to codify a rare disease, such as the ORPHAcode provided by Orphanet. This paper proposes a complex network model using the terminologies’ relationship to show that the International Classification of Diseases 10th Revision may be generic for diagnosing rare Brazilian patients. Moreover, there is no perfect nomenclature to define rare diseases, but each context has a better application. So, mapping the relationship between each terminology is fundamental for creating consistent semantic relationships in biomedical ontologies, providing a functional environment for carrying out tasks involving more than one terminology.

关键词： Rare Disease Complex Network Biomedical Ontology Graph Modeling

来源：评论

学校读者我要写书评

暂无评论

The Influence of Feature Selection on Job Clustering for an E-recruitment Recommender System 19th

The Influence of Feature Selection on Job Clustering for an ...

引用

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

作者： Junior, Joel J. S. Vilasbôas, Fabricio G. de Castro, Leandro N. Graduate Program in Electrical Engineering and Computing Mackenzie Presbyterian University São Paulo Brazil

ISBN: (纸本)9783030615338

Recommender systems aim to effectively recommend items to the user based on their profile. An online recruitment system recommends jobs for a candidate according to his profile and can also act in reverse, recommending more qualified candidates for a particular job. Defining which variables will be used impacts directly the recommendation quality so that, when using the most important variables, we have a better assertiveness in the process. The goal of this work is to select the most important features of an online recruitment database using feature selection techniques. More specifically, we used the algorithms of Mitra, SUD and ACA to perform feature selection. The datasets used were derived from the original dataset assuming three distinct scenarios: the dataset containing the attributes related with the jobs' features;the dataset containing the bag of words of the description feature of the jobs;and the dataset resulting from the union of the two previous ones. The features' subsets selected in each of the above scenarios had their performance evaluated in a clustering task. The results obtained in each scenario show a performance gain of the clustering process when feature selection is made over the original data. Also, it was observed that the jobs' features result in better performance than the other two cases. © 2020, Springer Nature Switzerland AG.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Determining environmental indicators related to the propagation of contagious diseases and health issues: A Systematic Literature Review

Determining environmental indicators related to the propagat...

引用

Iberian Conference on Information Systems and Technologies (CISTI)

作者： Janeth Domínguez Portillo Laura M. Rodríguez Peralta Paulo N. M. Sampaio Eldman de Oliveira Nunes Faculty of Information Technologies and Data Science Universidad Popular Autónoma del Estado de Puebla (UPAEP) México Graduate Program in Computing and Systems University of Salvador (UNIFACS) Salvador Bahia Brazil

The environmental indicators provide significant information in order to describe the state of a phenomenon, environment or area [1]. This paper addresses the indicators present in the air and their relationship in the accommodation and transmission of viruses, as well as how these environmental indicators can lead to health problems. Therefore, the main goal of this work is to review the scientific contributions in the literature in order to determine and select the potential environmental indicators present in indoor environments which have an impact on the health of people who work and live within these spaces. For this purpose, we carried out a Systematic Literature Review (SLR) related to environmental monitoring, COVID-19, Internet of things, air pollution and environmental indicators within indoor spaces. This SLR allowed us to identify indicators that according to their level of presence can represent a high risk for people’s health. Therefore, the process of planning, conducting and reporting the Systematic Literature Review enabled us not only to identify some environmental indicators, but also their corresponding monitoring advantages and disadvantages, and multiple perspectives and approaches of each contribution in the literature. Further on, this study will be the basis for the proposal of an automatic and intelligent platform based on Internet of Things for monitoring indoor environments in order to detect high risk levels for the contamination of contagious diseases.

关键词：

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：