检索结果-内蒙古大学图书馆

A co-evolutionary algorithm with adaptive penalty function for constrained optimization

Soft Computing 2024年第19期28卷 11343-11376页

作者： de Melo, Vinícius Veloso Nascimento, Alexandre Moreira Iacca, Giovanni Nasdaq Verafin WindsorON Canada Institute of Science and Technology Universidade Federal de São Paulo UNIFESP São José dos Campos São Paulo12231-280 Brazil Department of Information Engineering and Computer Science University of Trento Via Sommarive 9 TN Povo38123 Italy

Several constrained optimization problems have been adequately solved over the years thanks to the advances in the area of metaheuristics. Nevertheless, the question as to which search logic performs better on constrained optimization often arises. In this paper, we present Dual Search Optimization (DSO), a co-evolutionary algorithm that includes an adaptive penalty function to handle constrained problems. Compared to other self-adaptive metaheuristics, one of the main advantages of DSO is that it is able auto-construct its own perturbation logics, i.e., the ways solutions are modified to create new ones during the optimization process. This is accomplished by co-evolving the solutions (encoded as vectors of integer/real values) and perturbation strategies (encoded as Genetic Programming trees), in order to adapt the search to the problem. In addition to that, the adaptive penalty function allows the algorithm to handle constraints very effectively, yet with a minor additional algorithmic overhead. We compare DSO with several algorithms from the state-of-the-art on two sets of problems, namely: (1) seven well-known constrained engineering design problems and (2) the CEC 2017 benchmark for constrained optimization. Our results show that DSO can achieve state-of-the-art performances, being capable to automatically adjust its behavior to the problem at hand. © The Author(s) 2024.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-based Approach for WBC Classification

A Deep Learning-based Approach for WBC Classification

引用

Innovative Trends in Information Technology (ICITIIT), International Conference on

作者： K S Ramyashree B Sharada R Bhairava DoS in Computer Science Manasagangotri University of Mysore Mysuru India

ISBN: (数字)9798350386813

ISBN: (纸本)9798350386820

Human immune systems rely on white blood cells (WBCs) to fight against disease-causing pathogens. Blood cells contain vital information that can be used to determine a person’s health status. An efficient and accurate classification of blood cell types is critical due to their different features. In the domain of histopathology, WBCs hold a significant role. The analysis of these WBCs can provide valuable insights to healthcare professionals, aiding in diagnosing conditions such as tumors and infections caused by viruses. In this work, EfficientNetB0 is proposed as an advanced deep learning (DL) framework built on artificial intelligence (AI) designed for the WBC’s automatic categorization, which contains five distinct classes. These classes include basophils, eosinophils, neutrophils, lymphocytes, and monocytes. This work demonstrates the most effective efficiency, achieving WBC-type classification in significantly fewer epochs and less time than alternative methods. The approach that has been suggested is assessed using the dataset, which is available on the public Raabin Health Database, to evaluate its performance. The best performance in the assessment has been achieved through applying EfficientNetB0, with 99.17% overall efficiency and a 99.0% F1-score. In contrast to the latest DL models, the EfficientNetB0 model is designed to achieve excellent outcomes.

关键词： Pathogens Accuracy Histopathology Cells (biology) Medical services Market research Robustness

来源：评论

学校读者我要写书评

暂无评论

SYNTHETIC SIMULATED ENVIRONMENT FOR DISCRETE MANUFACTURING SYSTEMS: A DEMONSTRATOR THROUGH A COMPUTATIONAL MODELING APPROACH

SYNTHETIC SIMULATED ENVIRONMENT FOR DISCRETE MANUFACTURING S...

引用

2024 Winter Simulation Conference, WSC 2024

作者： Marti, Silvan Lopes, Paulo Victor Chen, Siyuan Rajashekarappa, Mohan Bana, Elham Rekabi Göppert, Amon Déspeisse, Mélanie Stahre, Johan Johansson, Björn Dept. of Industrial and Materials Science Chalmers University of Technology Gothenburg Sweden Dept. Computer Science Aeronautics Institute of Technology São José dos Campos Brazil RWTH Aachen University Aachen Germany

ISBN: (纸本)9798331534202

In light of the challenges posed by the often unavailability of coherent data in manufacturing for operational Artificial Intelligence (AI) decision support systems, the generation and utilization of synthetic datasets have become essential. This study introduces a simple numerical Synthetic Simulated Environment (SSE) using timed and parametrizable Petri Net (PN) modules, embedded in a Directed Acyclic Graph (DAG) structure described by an adjacency matrix to represent material flow. Implemented in PyTorch for seamless integration with AI components, our simulation framework simplifies manufacturing systems, yet remains expandable for diverse use cases. The simulation model was demonstrated displaying its capability of generating synthetic data. This approach explores the practicality and applicability of generated data. It could serve as an ideal environment to benchmark Artificial Intelligence (AI) algorithms in comparative experiments, investigating operational problems featured in the dynamic interactions of discrete manufacturing systems. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Hypoglycemia in Patients with Type 2 Diabetes Mellitus Using Data from the EHR and Patient Context 9

Classification and Prediction of Hypoglycemia in Patients wi...

引用

9th International Conference on Internet of Things, Big Data and Security, IoTBDS 2024

作者： Gubert, Luis Claudio Zeiser, Felipe André André da Costa, Cristiano Kunst, Rafael Software Innovation Laboratory SOFTWARELAB Universidade do Vale do Rio dos Sinos Unisinos São Leopoldo Brazil Department of Computer Science IFRS RS Ibirubá Brazil

ISBN: (纸本)9789897586996

The increase in obesity, a sedentary lifestyle, and population aging are considered the main factors for the increase in Type 2 Diabetes Mellitus (T2DM) worldwide. Global estimates indicate that around 400 million people live with T2DM, reaching 600 million in 2035. This scenario generates a high social and financial cost for the patient and the healthcare system. In this context, this work evaluates machine learning models to classify and predict hypoglycemic crises in patients with T2DM. A dataset with data from a clinical center in southern Brazil is constructed. Patient data involves Electronic Health Records (EHR) and data collected in the patient context through Internet of Things (IoT). This dataset is used to run classification and prediction models. Results show that the proposed approach is promising, achieving an AUC of 0.8200 and a sensitivity of 90.00% for classifying hypoglycemia. In addition, the Clarke Error Grid plot demonstrates an assertiveness of prediction for high blood glucose in clinical terms. These results demonstrate that the proposed method achieves comparable or superior results to related works in the literature. The combined use of EHR, IoT, and Machine Learning can be a promising alternative to improve the monitoring of chronic and long-term diseases, such as T2DM, contributing to a more accurate and effective diagnosis. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Time-referenced wavelet spatio-temporal change detection on multi-temporal SAR images

Time-referenced wavelet spatio-temporal change detection on ...

引用

2024 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024

作者： Fonseca, Rodney Negri, Rogerio Pinheiro, Aluisio Weizmann Institute of Science Department of Computer Science And Applied Mathematics Rehovot7610001 Israel São Paulo State University Science And Technology Institute São José dos Campos Brazil Campinas Departamento De Estatística Imecc Brazil

ISBN: (纸本)9798350389678

We discuss here an unsupervised method to detect spatio-temporal changes on multitemporal SAR images. We name it TR-WECS (Time-Referenced Wavelet Energies Correlation Screening). We have a series of SAR images taken over time on the same region. We establish the first image as our time reference against which changes will be studied. We employ wavelet smoothing in each image, so that detected changes are not speckle-related. We then analyze temporal changes on discontiguous blocks of various sizes through wavelet energy apportionment, and ultra-high dimensional correlation screening. We illlustrate TR-WECS on a time series of Sentinel-1 images on the border of Brazil and French Guiana. The proposal's performance is favorably compared to traditional change detection methods. © 2024 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

MUSICAL TIMBRE CLASSIFICATION USING FFT-ACOUSTIC DESCRIPTORS AND MACHINE LEARNING 10

MUSICAL TIMBRE CLASSIFICATION USING FFT-ACOUSTIC DESCRIPTORS...

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： González, Yubiry Prati, Ronaldo Center of Mathematics Computer Science and Cognition Federal University of ABC Av. Dos Estados 5001 SP Santo André09210-580 Brazil

ISBN: (纸本)9788888942674

Musical timbre is a complex multidimensional attribute of auditory perception, which allows discriminating between musical instruments when they have the same sound, intensity, and duration. One of the challenges in discriminating between musical timbres is that there are some sounds that appear to have very close timbral similarity, even when the instruments have different acoustic characteristics. This fact can make classifying musical instruments by timbres difficult. In the present study, we explore a 7-dimensional abstract space, formed by the fundamental frequency and acoustic descriptors extracted from Fourier Transform in five musical instruments: Trumpet, Violin, Cello, Transverse Flute, and Clarinet, of a monophonic audio record, from the Tinysol and Good-Sounds databases, corresponding to the fourth octave. This approach makes it possible to define points in timbral space uniquely and allows differentiating monophonic sounds played in ordinary style on any type of musical instrument. Through geometric distance between musical sounds in the abstract space, we explore Unsupervised Machine Learning techniques to establish categories of similarities between musical sounds, instruments, and family of musical instruments. The analysis showed that timbral similarity can be quantified geometrically, making it possible to identify groups of musical timbre. © 2023 European Acoustics Association, EAA. 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

System Identification of an Advanced Geared Turbofan Model Using Neural Networks

System Identification of an Advanced Geared Turbofan Model U...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Dias, Joaquim N. Melo, Gabriel A. Department of Aerospace Engineering Auburn University AuburnAL United States Computer Science Division Instituto Tecnológico de Aeronáutica SP São José dos Campos Brazil

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Gas turbine modeling exhibits nonlinearities in both steady-state and transient operations, with additional complexity introduced by varying ambient conditions, making it difficult to obtain accurate gas turbine models. In the present work, we examine classical system identification methods and deep learning approaches for modeling of an advanced geared turbofan engine using high-fidelity simulation data across multiple flight conditions. First, we implement a Hammerstein model through conventional nonlinear system identification, deriving static gains from quasi-steady states and estimating dynamic parameters from throttle inputs. The second approach was based on black-box modeling using neural networks. A number of different deep learning architectures were tested, namely feed-forward layers, long-short term memory architecture, and neural differential architecture. Model performance is quantified through prediction accuracy of five engine parameters (fuel flow, thrust, turbine temperature, shaft rotational speeds N1 and N2) using only altitude, Mach number and throttle as inputs across distinct flight conditions. The results demonstrate that the Neural Differential architecture significantly outperformed both classical and other neural approaches, reducing the standard deviations of residuals by 82% up to 92%, when compared with the conventional system identification method, across all engine parameters. This work advances the understanding of classical and deep learning methodologies for gas turbine modeling in flight simulation applications. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Gas turbines

来源：评论

学校读者我要写书评

暂无评论

A High-Level Synthesis Approach Applicable to Autonomous Embedded Systems 29

A High-Level Synthesis Approach Applicable to Autonomous Emb...

引用

29th IEEE International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2022

作者： Loubach, Denis S. Aeronautics Institute of Technology - ITA Computer Science Division Department of Computer Systems São Paulo São José dos Campos Brazil

ISBN: (数字)9781665486361

ISBN: (纸本)9781665486361

This paper proposes a high-level synthesis approach applicable to future autonomous systems, i.e. embedded systems, in the context of domain-specific architectures (DSA) along with domain-specific languages (DSL). That enables the system's design and specification to focus on the functions and requirements that such a system must provide and, at the same time, obtain an executable model. We show an illustrative example to demonstrate the potential and applicability of our approach down to automatic hardware description language generation and synthesis. © 2022 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Roadmap for Implementing Business Intelligence Systems in Higher Education Institutions: Validation of a Case Study at the University of Trás-os-Montes and Alto Douro 21

Roadmap for Implementing Business Intelligence Systems in Hi...

引用

21st International Conference on Smart Business Technologies, ICSBT 2024

作者： Sequeira, Romeu Reis, Arsénio Branco, Frederico Alves, Paulo School of Science and Technology University of Trás-os-Montes and Alto Douro Quinta dos Prados Vila Real Portugal Instituto Politécnico de Bragança Bragança Portugal INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal

ISBN: (纸本)9789897587108

The adoption of effective policies and access to relevant information are critical to improving strategic management and performance monitoring in Higher Education Institutions (HEIs), which is essential to promote data-driven decision-making. This article describes how an HEI can carry out the validation process when implementing a Business Intelligence (BI) system, and provides a detailed guide to doing so. Through a case study at the University of Trás-os-Montes and Alto Douro, a structured roadmap is validated, which acts as a visual and sequential guide to facilitate the effective implementation of BI solutions. The validation carried out through semi-structured interviews with experts and evaluation of dashboards by user groups, not only confirms the applicability and efficiency of the proposed model but also emphasises its practical relevance, providing valuable insights for the adaptation and use of BI in different educational contexts. Copyright © 2024 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Competitive intelligence

来源：评论

学校读者我要写书评

暂无评论

Ransomware Detection: Ensemble Machine Learning Models Using Disjoint Data

Ransomware Detection: Ensemble Machine Learning Models Using...

引用

Cyber Security and Resilience (CSR), IEEE International Conference on

作者： Charles M. R. Da Silva Paulo André L. De Castro Cecilia De A. C. Cesar Computer Science Division Aeronautics Institute of Technology São Josédos Campos Brazil

ISBN: (数字)9798350375367

ISBN: (纸本)9798350375374

The ransomware attack has become a lucrative business for cybercriminals and has impacted several companies, as data hijacking interrupts business continuity. Several Machine Learning models have been developed that capture some techniques used by malware. However, these models limit the scope of detection to features observed in individual data sets, which can reduce the detection rate of ransomware families and variants. This research aimed to develop a strategy to increase the spectrum of ransomware detection through the ensemble technique that combines machine learning models to achieve superior results compared to isolated models. Furthermore, we introduce a data set combination strategy, aiming to observe a broader range of features that mirror the real-world behavior of ransomware. Open datasets were collected to train previously selected machine learning models, and this data was combined. The results indicated that the combination of models produced better results than applying the models alone.

关键词： Measurement Accuracy Predictive models Feature extraction Data models Filling Ransomware

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：