检索结果-内蒙古大学图书馆

IEEE Symposium Series on computational intelligence (SScI)

作者： Javier Del Ser Eneko Osaba Aritz D. Martinez Miren Nekane Bilbao Javier Poyatos Daniel Molina Francisco Herrera TECNALIA Basque Research and Technology Alliance (BRTA) Derio Bizkaia Spain University of the Basque Country (UPV/EHU) Bilbao Bizkaia Spain Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain

ISBN: (纸本)9781728190495

Much controversy has been lately risen around the design and performance of modern bio-inspired optimization methods, in particular due to the alleged lack of algorithmic novelty in their definition with respect to traditional heuristic solvers. In this work we present a first attempt at shedding empirical evidence over this debate, for which results of a benchmark with unprecedented scales in terms of problems and algorithms are reported and discussed. Specifically, informed conclusions are held in what refers to the claimed superior performance of these bio-inspired solvers and their competitiveness when compared to competition-winning alternatives. Finally, we prove that the tailored selection of a subset of problems and techniques can unfairly bias the comparisons favoring any of such algorithms, ultimately arriving at illusory conclusions about their comparative performance.

关键词： Heuristic algorithms Optimization methods Benchmark testing computational intelligence

来源：评论

学校读者我要写书评

暂无评论

An Approach to Prevent Weight Manipulation by Minimum Adjustment and Maximum Entropy Method in Large-Scale Group Decision Making

SSRN

引用

SSRN 2022年

作者： Sun, Qi Wu, Jian chiclana, Francisco Wang, Sha Herrera-Viedma, Enrique School of Economics and Management Shanghai Maritime University Shanghai201306 China Center for Artificial Intelligence and Decision Sciences Shanghai Maritime University Shanghai201306 China Institute of Artificial Intelligence Faculty of Computing Engineering and Media De Montfort University Leicester United Kingdom Andalusian Research Institute in Data Science and Computational Intelligence Dept. of Computer Science and AI University of Granada Granada18071 Spain Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia

This paper proposes a theoretical framework to prevent weight manipulation in large-scale group decision making (LSGDM). Firstly, a community detection based method is used to cluster the large group. The power relations of subgroups are measured by the rights index (RI), which depends on the subgroups size and cohesion. Then, a minimum adjustment feedback model with maximum entropy is proposed to prevent subgroups’manipulation behavior. The minimum adjustment rule aims for ‘effificiency’ while the maximum entropy rule aims for ‘justice’. consequently, by keeping a balance between ‘effificiency’ and ‘justice’ in the mechanism of assigning weights, the rationality of weight allocation to reach consensus effificiently can be ensured. Detailed numerical and simulation analyses are carried out to verify the validity of the proposed method. © 2022, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of lung nodule in cT scan slices using cNN segmentation schemes: A study

引用

Procedia computer science 2023年 218卷 2786-2794页

作者： Seifedine Kadry Enrique Herrera-Viedma Rubén González crespo Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Research Institute in Data Science and Computational Intelligence University of Granada Granada Andalusian Spain Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The lung is one of the prime respiratory organs in human physiology, and its abnormality will severely disrupt the respiratory system. Lung Nodule (LN) is one of the abnormalities, and early screening and treatment are necessary to reduce its harshness. The proposed work aims to implement the convolutional-Neural-Network (cNN) segmentation methodology to extract the LN in various lung cT slices, such as axial, coronal, and sagittal planes. This work consists of the following phases; (i) Image collection and pre-processing, (ii) Ground-truth generation, (iii) cNN-supported segmentation, and (iv) Performance evaluation and validation. In this work, the merit of pre-trained cNN segmentation schemes is verified using (i) One-fold training and (ii) Two-fold training methods. The test images for this study are collected from The cancer Imaging Archive (TcIA) database. The experimental investigation is executed using Python®, and the outcome of this study confirms that the VGG-SegNet helps to get better values of Jaccard (>88%), Dice (>93%), and Accuracy (>96%) compared to other cNN methods.

关键词： Lung nodule cT scan cNN segmentation VGG-SegNet Accuracy Detection

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

引用

Procedia computer science 2023年 218卷 2675-2683页

作者： Seifedine Kadry Rubén González crespo Enrique Herrera-Viedma Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Andalusian Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes; (i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database.

关键词： Eye abnormality Diabetic retinopathy Fundus imaging Deep-Learning classification

来源：评论

学校读者我要写书评

暂无评论

Federated Learning and Differential Privacy: Software tools analysis, the *** FL framework and methodological guidelines for preserving data privacy

arXiv

引用

arXiv 2020年

作者： Rodríguez-Barroso, Nuria Stipcich, Goran Jiménez-López, Daniel Ruiz-Millán, José Antonio Martínez-cámara, Eugenio González-Seco, Gerardo Luzón, M. Victoria Veganzones, Miguel Ángel Herrera, Francisco Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Spain Sherpa.ai Bilbao Spain

The high demand of artificial intelligence services at the edges that also preserve data privacy has pushed the research on novel machine learning paradigms that fit those requirements. Federated learning has the ambition to protect data privacy through distributed learning methods that keep the data in their data silos. Likewise, differential privacy attains to improve the protection of data privacy by measuring the privacy loss in the communication among the elements of federated learning. The prospective matching of federated learning and differential privacy to the challenges of data privacy protection has caused the release of several software tools that support their functionalities, but they lack of the needed unified vision for those techniques, and a methodological workflow that support their use. Hence, we present the *** Federated Learning framework that is built upon an holistic view of federated learning and differential privacy. It results from the study of how to adapt the machine learning paradigm to federated learning, and the definition of methodological guidelines for developing artificial intelligence services based on federated learning and differential privacy. We show how to follow the methodological guidelines with the *** Federated Learning framework by means of a classification and a regression use cases. copyright © 2020, The Authors. All rights reserved.

关键词： computer programming

来源：评论

学校读者我要写书评

暂无评论

correction: Medical health resources allocation evaluation in public health emergencies by an improved ORESTE method with linguistic preference orderings

引用

Fuzzy Optimization and Decision Making 2023年第1期23卷 29-29页

作者： Gou, Xunjie Xu, Xinru Deng, Fumin Zhou, Wei Herrera-Viedma, Enrique Business School Sichuan University Chengdu China School of Finance Yunnan University of Finance and Economics Kunming China Andalusian Research Institute in Data Science and Computational Intelligence Granada Spain

来源：评论

学校读者我要写书评

暂无评论

Learning Visual Voice Activity Detection with an Automatically Annotated dataset

Learning Visual Voice Activity Detection with an Automatical...

引用

International conference on Pattern Recognition

作者： Sylvain Guy Stéphane Lathuilière Pablo Mesejo Radu Horaud Inria Grenoble Rhône-Alpes and Univ. Grenoble Alpes France LTCI Télécom Paris Institut Polytechnique de Paris France Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Spain

Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not. V-VAD is useful whenever audio VAD (A-VAD) is inefficient either because the acoustic signal is difficult to analyze or because it is simply missing. We propose two deep architectures for V-VAD, one based on facial landmarks and one based on optical flow. Moreover, available datasets, used for learning and for testing V-VAD, lack content variability. We introduce a novel methodology to automatically create and annotate very large datasets in-the-wild - WildVVAD - based on combining A-VAD with face detection and tracking. A thorough empirical evaluation shows the advantage of training the proposed deep V-VAD models with this dataset¹.

关键词： Voice activity detection Training Visualization Face recognition Deep architecture Human-robot interaction Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Array relocation approach for radial scanning algorithms on multi-GPU systems: Total viewshed problem as a case study

arXiv

引用

arXiv 2020年

作者： Sanchez, A.J. Romero, L.F. Bandera, G. Tabik, S. Department of Computer Architecture University of Malaga Malaga Spain Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain

In geographic information systems, Digital Elevation Models (DEMs) are commonly processed using radial scanning based algorithms. These algorithms are particularly popular when calculating parameters whose magnitudes decrease with the distance squared such as those related to radio signals, sound waves, and human eyesight. However, radial scanning algorithms imply a large number of accesses to 2D arrays, which despite being regular, results in poor data locality. This paper proposes a new methodology, termed sDEM, which substantially improves the locality of memory accesses and largely increases the inherent parallelism involved in the computation of radial scanning algorithms. In particular, sDEM applies a data restructuring technique prior to accessing the memory and performing the computation. In order to demonstrate the high efficiency of sDEM, we use the problem of total viewshed computation as a case study. Sequential, parallel, single-GPU and multi-GPU implementations are analyzed and compared with the state-of-the-art total viewshed computation algorithm. Experiments show that sDEM achieves an acceleration rate of up to 827.3 times for the best multi-GPU execution approach with respect to the best multi-core implementation. copyright © 2020, The Authors. All rights reserved.

关键词： Surveying

来源：评论

学校读者我要写书评

暂无评论

A showcase of the use of autoencoders in feature learning applications?

arXiv

引用

arXiv 2020年

作者： charte, David charte, Francisco del Jesus, María J. Herrera, Francisco Andalusian Research Institute in Data Science and Computational Intelligence Dept. of Computer Science and Artificial Intelligence Universidad de Granada Periodista Daniel Saucedo Aranda s/n Granada18071 Spain Andalusian Research Institute in Data Science and Computational Intelligence Computer Science Dept. Universidad de Jaén Campus Las Lagunillas s/n Jaén23071 Spain

Autoencoders are techniques for data representation learning based on artificial neural networks. Differently to other feature learning methods which may be focused on finding specific transformations of the feature space, they can be adapted to fulfill many purposes, such as data visualization, denoising, anomaly detection and semantic hashing. This work presents these applications and provides details on how autoencoders can perform them, including code samples making use of an R package with an easy-to-use interface for autoencoder design and training, ruta. Along the way, the explanations on how each learning task has been achieved are provided with the aim to help the reader design their own autoencoders for these or other objectives. This manuscript was accepted as conference paper in IWINAc 2019. The final authenticated publication is available online at https://***/10. 1007/978-3-030-19651-6 40. copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial optimization

Simultaneously Evolving Deep Reinforcement Learning Models u...

引用

congress on Evolutionary computation

作者： Aritz D. Martinez Eneko Osaba Javier Del Sery Francisco Herrera TECNALIA Basque Research and Technology Alliance (BRTA) Bizkaia Spain DaSCI Andalusian Institute of Data Science and Computational Intelligence University of Granada Granada Spain

ISBN: (数字)9781728169293

ISBN: (纸本)9781728169309

In recent years, Multifactorial optimization (MFO) has gained a notable momentum in the research community. MFO is known for its inherent capability to efficiently address multiple optimization tasks at the same time, while transferring information among such tasks to improve their convergence speed. On the other hand, the quantum leap made by Deep Q Learning (DQL) in the Machine Learning field has allowed facing Reinforcement Learning (RL) problems of unprecedented complexity. Unfortunately, complex DQL models usually find it difficult to converge to optimal policies due to the lack of exploration or sparse rewards. In order to overcome these drawbacks, pre-trained models are widely harnessed via Transfer Learning, extrapolating knowledge acquired in a source task to the target task. Besides, meta-heuristic optimization has been shown to reduce the lack of exploration of DQL models. This work proposes a MFO framework capable of simultaneously evolving several DQL models towards solving interrelated RL tasks. Specifically, our proposed framework blends together the benefits of meta-heuristic optimization, Transfer Learning and DQL to automate the process of knowledge transfer and policy learning of distributed RL agents. A thorough experimentation is presented and discussed so as to assess the performance of the framework, its comparison to the traditional methodology for Transfer Learning in terms of convergence, speed and policy quality, and the intertask relationships found and exploited over the search process.

关键词： Task analysis Optimization Search problems Sociology Statistics Evolutionary computation Machine learning

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：