检索结果-内蒙古大学图书馆

IFIP/IEEE International Symposium on Integrated Network Management

作者： Janine Kniess Julio Cezar Rutke William Alberto Cruz Castañeda Graduate Program in Applied Computing Santa Catarina State University Brazil

A smart urban mobility considers the technological-based development in transport systems, services and their use to improve the movement of people and goods inter or intra-cities. Cities increasingly face problems caused by traffic and need to find solutions to improve mobility and to reduce congestion and pollution. In this paper, we present a Passenger Counting Scheme into buses. Embedded counting algorithms based on Computer Vision are proposed to count passenger arrivals and departures in real time. Experiments in a real scenario expose that the proposed scheme achieved a high percentage of success in passenger count.

关键词： Training Computer vision Pollution Urban areas Computer architecture Cameras Real-time systems

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Bio-Scheduling Model For Emergency Networks

An Energy-Efficient Bio-Scheduling Model For Emergency Netwo...

引用

IEEE Conference on Wireless Communications and Networking

作者： Janine Kniess Marcelo Petri Rafael Stubs Parpinelli Graduate Program in Applied Computing Santa Catarina State University Brazil

The efficient management of resources after a disaster, must take place within a short time and efficiently. Therefore, resource scheduling protocol which shares resources among the victims, respecting time constraints, is decisive. In disaster scenarios, communication infrastructure is usually damaged and a commonly used solution for ensuring connectivity between victims and providers is Mobile Ad Hoc Network (MANET). Fire brigade and ambulances might be insufficient if the number of victims is high. Hence, in order to provide an efficient resource scheduling approach that cares about the energy consumption, the number of requesters attended and the processing time, we present a Scheduling Resource protocol. Thus, to reduce the provider dislocation time and increase the number of victims attended the protocol was modeled based on Genetic Algorithms. Results show that this approach maintains the trade-off between the number of victims attended, therefore, minimize the energy consumption.

关键词： Energy consumption Protocols Scheduling algorithms Biological system modeling Process control Scheduling Space exploration

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

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

Machine Learning for Prediction of Adverse Drug Reactions: Application to Neonatal Intensive Care Units

SSRN

引用

SSRN 2023年

作者： do Nascimento, Amanda Roseane Farias Greati, Victor Rodrigues Leopoldino, Ramon Weyler Duarte Martins, Rand Randall Barbosa, Euzebio Guimarães Graduate Program in Pharmaceutical Sciences Health Sciences Center Federal University of Rio Grande do Norte Rio Grande do Norte Natal Brazil Graduate Program in Systems and Computing Department of Informatics and Applied Mathematics Federal University of Rio Grande do Norte Rio Grande do Norte Natal Brazil

Introduction: The intensive care of neonates is associated with the entry of a large volume of data in their medical records. The treatment of this data can be done through Machine Learning: a tool capable of assisting in the detection and decision-making of a wide range of medical conditions, including adverse drug reactions (ADR). Objective: To train a prediction model to assist in the detection of adverse drug reactions in neonates admitted to an ICU. Methodology: observational study developed in the Neonatal Intensive Care Unit of a teaching hospital in Brazil. Clinical data were collected from daily pharmacotherapeutic follow-up, processed and analyzed by machine learning through libraries written in Python language. Results: Eight hundred and three neonates were included in the study, with a mean gestational age of 32.2 ± 4.2 weeks and mean birth weight of 1807.2 ± 936.6g. The incidence of ADR was 10.8%. Antimicrobials, especially aminoglycosides, were the most prescribed drugs for this population. An algorithm was trained and tested to predict ADR in the NICU, in which the metrics were precision (0.35) and recall (0.823), with specificity (80%) and sensitivity (67%). Conclusion: There is a high potential in the machine learning method to predict ADR in neonates admitted to an ICU. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-Instance Task in Swarm Robotics: Sorting Groups of Robots or Objects into Clusters with Minimalist Controllers

Multi-Instance Task in Swarm Robotics: Sorting Groups of Rob...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Adilson Krischanski Yuri K. Lopes Andre B. Leal Ricardo F. Martins Roberto S.U. Rosso Department of Computer Science Santa Catarina State University (UDESC) Joinville Brazil Graduate Program in Applied Computing (PPGCAP) UDESC Brazil Department of Electrical Engineering Santa Catarina State University (UDESC) Joinville Brazil

Relying only on behaviors that emerge from simple responsive controllers; swarms of robots have been shown capable of autonomously aggregate themselves or objects into clusters without any form of communication. We push these controllers to the limit, requiring robots to sort themselves or objects into different clusters. Based on a responsive controller that maps the current reading of a line-of-sight sensor to a pair of speeds for the robots' differential wheels, we demonstrate how multiple tasks instances can be accomplished by a robotic swarm. Using the dividing rectangles approach and physics simulation, a training step optimizes the parameters of the controller guided by a fitness function. We conducted a series of systematic trials in physics-based simulation and evaluate the performance in terms of dispersion and the ratio of clustered robots/objects. Across 20 trials where 30 robots cluster themselves into 3 groups, an average of 99.83% of them were correctly clustered into their group after 300 s. Across 50 trials where 15 robots cluster 30 objects into 3 groups, an average of 61.20%, 82.87%, and 97.73% of objects were correctly clustered into their group after 600 s, 900 s, and 1800 s, respectively. The object cluster behavior scales well while the aggregation does not, the latter due to the requirement of control tuning based on the number of robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mineralogical Classification of Sedimentary Rocks by Spectral Matching Techniques Based on Library and Field-Work References

Mineralogical Classification of Sedimentary Rocks by Spectra...

引用

Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS

作者： Daniel C. Zanotta Lais V. De Souza Marcelo K. De Souza Alysson S. Ayres Vinícius F. Sales Graciela R. Racolte Delano M. Ibanez Luiz G. Silveira Maurício R. Veronez Vizlab — X-Reality and GeoInformatics Lab UNISINOS São Leopoldo RS Brazil Graduate Program in Applied Computing at Vale do Rio dos Sinos University São Leopoldo RS Brazil PETROBRAS - Petrobras Research and Development Center (CENPES) RJ Brazil

ISBN: (数字)9798331513139

ISBN: (纸本)9798331513146

Sedimentary rocks are of great importance for the oil and gas industry. Spectral matching using known references made on hyperspectral images is one of the most rapid and cost effective alternatives for the detailed analysis in these areas, since they can adequately catch the specific absorption features of the multiple minerals available. In many initiatives, scientists run the methods with standard spectral references, usually from spectral libraries or samples from other places. However, for the success of their application, they must be used along with spectral references that accurately describe the actual constituents of the surface. In this paper we scrutinize three different ways for mineralogical mapping performed by spectral matching techniques. The results showed that using reference spectra from samples collected directly on the surveyed environment can considerably improve the results, reaching high scores, pointing out that many places share common substances, but each specific material has particular differences that cannot be generalized.

关键词： Costs Systematics Signal processing Rocks Gas industry Libraries Minerals Petroleum industry Standards Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Indirect Calibration of Hyperspectral Images Using Rock Samples

Indirect Calibration of Hyperspectral Images Using Rock Samp...

引用

Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS

作者： Daniel C. Zanotta Leonardo D. Araújo Marcelo K. De Souza Delano M. Ibanez Luiz G. Silveira Maurício R. Veronez Vizlab — X-Reality and GeoInformatics Lab UNISINOS São Leopoldo RS Brazil Graduate Program in Applied Computing at Vale do Rio dos Sinos University São Leopoldo RS Brazil PETROBRAS - Petrobras Research and Development Center (CENPES) RJ Brazil

ISBN: (数字)9798331513139

ISBN: (纸本)9798331513146

This paper presents a methodology for the indirect calibration of hyperspectral images using radiometric measurements from field samples. While hyperspectral imaging (HSI) is essential in remote sensing, its accuracy depends on precise calibration, which is often challenging in the field. Most approaches rely on a single standard panel used as absolute reference and the empirical line method. This often leads to mistakes and uncertainties in the analysis. In this paper we propose an alternative that utilizes radiometric data from rock samples with known spectral properties to indirectly calibrate hyperspectral images. The results show specific improvements in accuracy, particularly in the shape of the curves, compared to standard calibration method. The calibrated images offer better material differentiation and more reliable spectral signatures, which are crucial for geological mapping and mineral exploration. This approach can enhance the reliability of hyperspectral data analysis in geological and environmental studies, especially in situations where time and logistics are challenging.

关键词： Accuracy Uncertainty Coal Signal processing Rocks Radiometry Calibration Minerals Standards Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Approach to the Protein Structure Prediction Problem using the Biased Random-Key Genetic Algorithm

A Multi-objective Approach to the Protein Structure Predicti...

引用

Congress on Evolutionary Computation

作者： Felipe Marchi Rafael Stubs Parpinelli Graduate Program in Applied Computing Santa Catarina State University Joinville Santa Catarina Brazil

Proteins are base molecules present in live organisms. The study of their structures and functions is of considerable importance for many application fields, particularly for the pharmaceutical area. This paper presents a multi-objective model to the Protein Structure Prediction problem, using three objectives: energy score, secondary structure information, and contact maps information. A BRKGA method is used as a global optimizer and adapted to work with multiple objective problems. Also, the MUFOLD-CL clustering method is applied to select a single predicted structure. Experiments were carried out to analyze the proposed model performance using state-of-the-art ab initio algorithms for comparison. Results obtained indicate that the proposed approach is competitive in terms of RMSD and GDT metrics.

关键词： Proteins Measurement Adaptation models Evolutionary computation Predictive models Prediction algorithms Organisms

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：