检索结果-内蒙古大学图书馆

Improving Critical Node Detection Using Neural Network-based Initialization in a Genetic Algorithm

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Chanjuan Ge, Shike Chen, Zhihan Pei, Wenbin Zhu, Enqiang Mei, Yi Ishibuchi, Hisao The School of Computer Science and Technology Dalian University of Technology 116024 China The Institute of Software Chinese Academy of Science Beijing100190 China The Institute of Computing Science and Technology Guangzhou University Guangzhou510006 China The School of Engineering and Computer Science Victoria University of Wellington Wellington6012 New Zealand The Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

The Critical Node Problem (CNP) is concerned with identifying the critical nodes in a complex network. These nodes play a significant role in maintaining the connectivity of the network, and removing them can negatively impact network performance. CNP has been studied extensively due to its numerous real-world applications. Among the different versions of CNP, CNP-1a has gained the most popularity. The primary objective of CNP-1a is to minimize the pair-wise connectivity in the remaining network after deleting a limited number of nodes from a network. Due to the NP-hard nature of CNP-1a, many heuristic/metaheuristic algorithms have been proposed to solve this problem. However, most existing algorithms start with a random initialization, leading to a high cost of obtaining an optimal solution. To improve the efficiency of solving CNP-1a, a knowledge-guided genetic algorithm named K2GA has been proposed. Unlike the standard genetic algorithm framework, K2GA has two main components: a pretrained neural network to obtain prior knowledge on possible critical nodes, and a hybrid genetic algorithm with local search for finding an optimal set of critical nodes based on the knowledge given by the trained neural network. The local search process utilizes a cut node-based greedy strategy. The effectiveness of the proposed knowledge-guided genetic algorithm is verified by experiments on 26 real-world instances of complex networks. Experimental results show that K2GA outperforms the state-of-the-art algorithms regarding the best, median, and average objective values, and improves the best upper bounds on the best objective values for eight real-world instances. Copyright © 2024, The Authors. All rights reserved.

关键词： Combinatorial optimization

A multi-features fusion support vector machine method (MF-SVM) for classification of mangrove remote sensing image

学校读者我要写书评

暂无评论

Journal of Computational Information Systems 2012年第1期8卷 323-334页

作者： Luo, Yanmin Liao, Minghong Yan, Jing Zhang, Caiyun Cognitive Science Department Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen University Xiamen 361005 China College of Computer Science and Technology Huaqiao University Xiamen 361005 China Software School of Xiamen University Xiamen 361005 China College of Oceanography and Environmental Science Xiamen University Xiamen 361005 China

Remote sensing technology has been the major monitoring and analysing technologies of the mangrove ecosystem. Because of the similar spectral features between mangroves and other types of land cover such as agricultural land and forests, serious confusion in mangrove classification using conventional methods can develop. As one of the popular and advanced statistical learning algorithms, Support Vector Machine (SVM) has been the important study area of pattern recognition and machine learning in recent years. SVM is the useful technique for data classification which based on structural risk minimization (SRM) principle. SVM has such advantages as suitableness to high dimensional data, requirement of few samples and robustness to uncertainty, so it can be used to remote sensing image classification effectively. In order to improve the accuracy of mangrove remote sensing images classification, this paper discusses the SVM models including kernel functions and multi-class methods, and proposes a Multi-features fusion support vector machine classification method (MF-SVM) for classification of mangrove remote sensing image using multi-temporal Landsat TM data, ancillary GIS data and image information. The SVM with the RBF kernel function and one against one multiclass method is used in the MF-SVM. Experiments are performed on the remote sensing image of Zhangjiangkou Mangrove Forestry National Nature Reserve which is located in Yunxiao, Fujian, China. The result shows that the proposed method can improve the extraction accuracy of mangroves. © 2012 Binary Information Press January 2012.

关键词： Classification (of information)

The Implantable Electrode Co-Deposited with Iron Oxide Nanoparticles and Pedot:Pss

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Liu, Yiyang Wang, Sheng Yang, Quanwei Zhang, Baolin Key Laboratory of New Processing Technology for Nonferrous Metal & Materials Ministry of Education Guangxi Key Laboratory of Optical and Electronic Materials and Devices College of Materials Science and Engineering Guilin University of Technology Jian Gan Road 12 Guilin541004 China Kedou（Suzhou）Brain-Computer Technology Co. Ltd Suzhou215152 China

Iron oxide nanoparticles (IONs) are confirmed with good biocompatibility, easy modification for drug loading, the ability to generate forces and heat in an external magnetic field, and the potential to enhance imaging effects in magnetic resonance imaging (MRI). In this work, a method was proposed to coat IONs as interface-modifying materials onto the electrode surface to improve the performance of the implantable electrodes and their ability to bond with neuronal cells. IONs were synthesized using a solvent thermal decomposition method, and chondroitin sulfate (CS) was physically grafted onto the surface of IONs to modify the surface charge and functional groups of IONs. The modified IONs were then co-deposited with the conductive polymer PEDOT: PSS onto the surface of metal wire electrodes using the electrochemistry method. In vitro electrochemical experiments showed that the coated materials (CS-IONs/PEDOT/PSS) reduced the impedance of the implantable electrodes and increased charge storage capacity (CSC). In vivo implantation experiments demonstrated that the electrodes with the coated materials recorded local field potential (LFP) and spike signals with higher amplitudes, higher power spectral density (PSD), as well as higher signal-to-noise ratio (SNR) which can be attributed to the binding ability of CS to neurons and effects of PEDOT/PSS. The use of iron oxide nanoparticle composites as a coating to enhance the performance of implant electrodes is rarely reported. This approach holds promise for improving neuron binding, enabling neuron modulation under a magnetic field, facilitating drug loading and targeted delivery, and enhancing magnetic resonance imaging (MRI) of the electrodes. © 2024, The Authors. All rights reserved.

关键词： Iron oxides

Data Augmentation for Enhancing EEG-based Emotion Recognition with Deep Generative Models

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Luo, Yun Zhu, Li-Zhen Wan, Zi-Yu Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai200240 China

The data scarcity problem in emotion recognition from electroencephalography (EEG) leads to difficulty in building an affective model with high accuracy using machine learning algorithms or deep neural networks. Inspired by emerging deep generative models, we propose three methods for augmenting EEG training data to enhance the performance of emotion recognition models. Our proposed methods are based on two deep generative models, variational autoencoder (VAE) and generative adversarial network (GAN), and two data augmentation strategies. For the full usage strategy, all of the generated data are augmented to the training dataset without judging the quality of the generated data, while for partial usage, only high-quality data are selected and appended to the training dataset. These three methods are called conditional Wasserstein GAN (cWGAN), selective VAE (sVAE), and selective WGAN (sWGAN). To evaluate the effectiveness of these methods, we perform a systematic experimental study on two public EEG datasets for emotion recognition, namely, SEED and DEAP. We first generate realistic-like EEG training data in two forms: power spectral density and differential entropy. Then, we augment the original training datasets with a different number of generated realistic-like EEG data. Finally, we train support vector machines and deep neural networks with shortcut layers to build affective models using the original and augmented training datasets. The experimental results demonstrate that the augmented training datasets produced by our methods enhance the performance of EEG-based emotion recognition models and outperform the existing data augmentation methods such as conditional VAE, Gaussian noise, and rotational data augmentation. Copyright © 2020, The Authors. All rights reserved.

关键词： Electrophysiology

ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System for Image Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lei, Chunyu Chen, C.L. Philip Guo, Jifeng Zhang, Tong The Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Brain and Affective Cognitive Research Center Pazhou Lab Guangzhou510335 China

Deep learning generally suffers from enormous computational resources and time-consuming training processes. Broad Learning System (BLS) and its convolutional variants have been proposed to mitigate these issues and have achieved superb performance in image classification. However, the existing convolutional-based broad learning system (C-BLS) either lacks an efficient training method and incremental learning capability or suffers from poor performance. To this end, we propose a convolutional broad learning system (ConvBLS) based on the spherical K-means (SKM) algorithm and two-stage multi-scale (TSMS) feature fusion, which consists of the convolutional feature (CF) layer, convolutional enhancement (CE) layer, TSMS feature fusion layer, and output layer. First, unlike the current C-BLS, the simple yet efficient SKM algorithm is utilized to learn the weights of CF layers. Compared with random filters, the SKM algorithm makes the CF layer learn more comprehensive spatial features. Second, similar to the vanilla BLS, CE layers are established to expand the feature space. Third, the TSMS feature fusion layer is proposed to extract more effective multi-scale features through the integration of CF layers and CE layers. Thanks to the above design and the pseudo-inverse calculation of the output layer weights, our proposed ConvBLS method is unprecedentedly efficient and effective. Finally, the corresponding incremental learning algorithms are presented for rapid remodeling if the model deems to expand. Experiments and comparisons demonstrate the superiority of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning systems

On the Normalization in Evolutionary Multi-Modal Multi-Objective Optimization

学校读者我要写书评

暂无评论

On the Normalization in Evolutionary Multi-Modal Multi-Objec...

Congress on Evolutionary Computation

作者： Yiping Liu Hisao Ishibuchi Gary G. Yen Yusuke Nojima Naoki Masuyama Yuyan Han Department of Computer Science and Intelligent Systems Osaka Prefecture University Sakai Osaka Japan Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China School of Electrical and Computer Engineering Oklahoma State University Stillwater OK USA School of Computer Science Liaocheng University Liaocheng China

ISBN: (数字)9781728169293

ISBN: (纸本)9781728169309

Multi-modal multi-objective optimization problems may have different Pareto optimal solutions with the same objective vector. A number of evolutionary multi-modal multiobjective algorithms have been developed to solve these problems. They aim to search for a Pareto optimal solution set with good diversity in both the objective and decision spaces. Although the normalization in both the objective and decision spaces is very important for these algorithms, there are few studies on this topic. In this paper, we investigate the effect of four normalization methods on two evolutionary multi-modal multiobjective algorithms. Six distance minimization problems are chosen as test problems. The experimental results show that the effect of normalization in evolutionary multi-modal multiobjective optimization is algorithm- and problem-dependent.

关键词： Pareto optimization Sociology Evolutionary computation computer science Search problems

Residual Networks for Light Field Image Super-Resolution

学校读者我要写书评

暂无评论

Residual Networks for Light Field Image Super-Resolution

IEEE/CVF Conference on computer Vision and Pattern Recognition

作者： Shuo Zhang Youfang Lin Hao Sheng Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Key Laboratory of Intelligent Passenger Service of Civil Aviation CAAC State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

Light field cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial resolution has brought lots of difficulties in developing related applications and becomes the main bottleneck of light field cameras. In this paper, a learning-based method using residual convolutional networks is proposed to reconstruct light fields with higher spatial resolution. The view images in one light field are first grouped into different image stacks with consistent sub-pixel offsets and fed into different network branches to implicitly learn inherent corresponding relations. The residual information in different spatial directions is then calculated from each branch and further integrated to supplement high-frequency details for the view image. Finally, a flexible solution is proposed to super-resolve entire light field images with various angular resolutions. Experimental results on synthetic and real-world datasets demonstrate that the proposed method outperforms other state-of-the-art methods by a large margin in both visual and numerical evaluations. Furthermore, the proposed method shows good performances in preserving the inherent epipolar property in light field images.

关键词：

ECG-DPM: Electrocardiogram Generation via a Spectrogram-based Diffusion Probabilistic Model 10

学校读者我要写书评

暂无评论

ECG-DPM: Electrocardiogram Generation via a Spectrogram-base...

10th IEEE Smart World Congress, SWC 2024

作者： Li, Lujundong Xia, Tong Zhang, Haojie He, Dongchen Qian, Kun Hu, Bin Yamamoto, Yoshiharu Schuller, Bjorn W. Mascolo, Cecilia Beijing Institute of Technology Key Laboratory of Brain Health Intelligent Evaluation and Intervention Ministry of Education Beijing China Beijing Institute of Technology School of Medical Technology Beijing China The Hong Kong University of Science and Technology Info Hub Ai Thrust Guangzhou China University of Cambridge Department of Computer Science and Technology United Kingdom Peking University School of Life Sciences Beijing China The University of Tokyo Guaduate School of Frontier Sciences Computational Biology and Medical Sciences Japan The University of Tokyo Educational Physiology Laboratory Graduate School of Education Japan Glam - the Group on Language Audio & Music Imperial College London United Kingdom Mri Technical University of Munich Chi - Chair of Health Informatics Germany

ISBN: (纸本)9798331520861

An electrocardiogram (ECG) records the electrical signals from the heart to assess various cardiovascular conditions. Deep learning methods have been proposed to model ECGs, but the insufficient availability of ECG data and annotations often hinders their performance. To address this challenge, this paper explores the latest data synthesis technique, i.e., diffusion probabilistic models (DPMs), to enable the generation of an unlimited number of ECGs representing various cardiovascular conditions. In contrast to previous approaches that treat ECGs as time series data or convert them into power spectrograms, we introduce a novel multi-channel spectrogram-based diffusion framework. In our method, the diffusion model enhances generation diversity, while the multi-channel spectrogram preserves both magnitude and phase information, ensuring high fidelity in the reconstructed ECGs. Extensive experiments conducted on real-world ECG data demonstrate the superiority of our approach. Notably, our ECG-DPM outperforms the best baseline by a margin ranging from 1 2. 5 % to 6 2. 5 % when generating ECGs for 30 seconds. © 2024 IEEE.

关键词： Spectrographs

MetaUE: Model-based Meta-learning for Underwater Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhenwei Yan, Haorui Tang, Ke Duan, Yuping Center for Applied Mathematics Tianjin University Tianjin300072 China The Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China

The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be used to overcome the problem of inadequately observing data, it may result in over-fitting and enhancement degradation. This paper proposes a model-based deep learning method for restoring clean images under various underwater scenarios, which exhibits good interpretability and generalization ability. More specifically, we build up a multi-variable convolutional neural network model to estimate the clean image, background light and transmission map, respectively. An efficient loss function is also designed to closely integrate the variables based on the underwater image model. The meta-learning strategy is used to obtain a pre-trained model on the synthetic underwater dataset, which contains different types of degradation to cover the various underwater environments. The pre-trained model is then fine-tuned on real underwater datasets to obtain a reliable underwater image enhancement model, called MetaUE. Numerical experiments demonstrate that the pre-trained model has good generalization ability, allowing it to remove the color degradation for various underwater attenuation images such as blue, green and yellow, etc. The fine-tuning makes the model able to adapt to different underwater datasets, the enhancement results of which outperform the state-of-the-art underwater image restoration methods. All our codes and data are available at https://***/Duanlab123/MetaUE. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement