检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yu, Xiaoyan Zhou, Shen Li, Huafeng Zhu, Liehuang School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing100081 China

The use of a single image restoration framework to achieve multi-task image restoration has garnered significant attention from researchers. However, several practical challenges remain, including meeting the specific and simultaneous demands of different tasks, balancing relationships between tasks, and effectively utilizing task correlations in model design. To address these challenges, this paper explores a multi-expert adaptive selection mechanism. We begin by designing a feature representation method that accounts for both the pixel channel level and the global level, encompassing low-frequency and high-frequency components of the image. Based on this method, we construct a multi-expert selection and ensemble scheme. This scheme adaptively selects the most suitable expert from the expert library according to the content of the input image and the prompts of the current task. It not only meets the individualized needs of different tasks but also achieves balance and optimization across tasks. By sharing experts, our design promotes interconnections between different tasks, thereby enhancing overall performance and resource utilization. Additionally, the multi-expert mechanism effectively eliminates irrelevant experts, reducing interference from them and further improving the effectiveness and accuracy of image restoration. Experimental results demonstrate that our proposed method is both effective and superior to existing approaches, highlighting its potential for practical applications in multi-task image restoration. The source code of the proposed method is available at https://***/zhoushen1/MEASNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

A multi-view comparative learning method for spatial transcriptomics data clustering

A multi-view comparative learning method for spatial transcr...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Wei Peng Zhihao Zhang Wei Dai Xiaodong Fu Li Liu Lijun Liu Ning Yu Faculty of Information Engineering and Automation Kunming University of Science and Technology Computer Technology Application Key Lab of Yunnan Province Kunming University of Science and Technology Kunming China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Department of Computing Sciences The College at Brockport State University of New York Brockport NY

Clustering individual cells or spots based on their gene expression profiles in a spatial context is a powerful approach to uncovering the underlying biological diversity and relationships among cells. The intricate information within spatial transcriptomics data demands sophisticated algorithms that effectively integrate gene expression, cell position, and tissue image data for accurate cell or spot clustering. This work proposes a Multi-View Comparative Learning method for clustering Spatial Transcriptomics data (MVCLST). MVCLST first builds on two data views using gene expression profiles, cell space coordinates, and image features. Then it employs four different encoders to capture the common and private features of the two views. The model employs a contrastive learning loss to encourage effective interaction between the two views and ensure feature consistency. The shared and private features from both views are fused using corresponding decoders. Finally, the model employs the Leiden algorithm for downstream clustering of the learned features. We test the MVCLST method on a human dorsolateral prefrontal cortex dataset. The results show that MVCLST outperforms other state-of-the-art methods in most cases. Additionally, the clusters identified by MVCLST align closely with manual annotations and established neuroscience definitions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online B-Spline Based Trajectory Planning for Swarm of Agents Using Distributed Model Predictive Control

Online B-Spline Based Trajectory Planning for Swarm of Agent...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Cong Khanh Dinh Ionela Prodan Florin Stoican Univ. Grenoble Alpes Grenoble INP† LCIS Valence France The Faculty of Automation Control and Computer Science Institute of Engineering and Management Univ. Grenoble Alpes University Politehnica of Bucharest Romania

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

This paper deals with the motion planing in real-time for swarm of agents using distributed Model Predictive Control (DMPC). Optimization-based control helps both to stabilize the motion dynamics of the robots and to enforce the system's constraints. However, the price is a significant increase in complexity as the scale of the system surges. To improve the scalability for a large formation, we propose a DMPC framework that considers B-spline parameterizations for the agents' trajectories. The proposed approach has great promise for multi-drones system, as illustrated with simulation examples using a state of the art quadcopter model.

关键词： Trajectory planning Scalability Prediction algorithms Real-time systems Trajectory Splines (mathematics) Surges

来源：评论

学校读者我要写书评

暂无评论

Attack-Agnostic Deep Face Anti-Spoofing

Attack-Agnostic Deep Face Anti-Spoofing

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Ajian Liu Zichang Tan Yanyan Liang Jun Wan MAIS Institute of Automation Chinese Academy of Sciences Beijing China Institute of Deep Learning Baidu Research Beijing China School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology Macau

The task of face anti-spoofing (FAS) is to determine whether the captured face from a face recognition system is live or fake. Current methods which are trained with existing fake faces ignore the generalization and perform poorly on unseen attacks. To tackle this problem, a novel Attack-agnostic Face Anti-spoofing framework is proposed. Different from previous methods that can be treated as a defense system, we regard face anti-spoofing as a unified framework with the attack and defense systems and optimize the defense system against unseen attacks via adversarial training with the attack system. Concretely, the attack system consists of two modules: an Adversarial learning-based Attack Pattern Generation (Adv-APG) module and a Supervised learning-based Attack Pattern Drift (Sup-APD) module. The Adv-APG module generates a series of spoofing samples by recombining a live face with known attack patterns in a generative way. The Sup-APD module pulls the generated spoofing samples in a supervised way to an unknown domain that makes the defense system ineffective. The defense system is free to choose and compatible with our attack system. Extensive experiments are conducted by using three different defense architectures to verify that the proposed attack system can improve the performance on both seen- and unseen attacks on multiple datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EEG Classification Using Contrastive Learning and Riemannian Tangent Space Representations

EEG Classification Using Contrastive Learning and Riemannian...

引用

Telecommunications and Intelligent Systems (ICTIS), International Conference on

作者： Ahmed Tibermacine Imad Eddine Tibermacine Meftah Zouai Abdelaziz Rabehi Department of Computer Science University of Biskra Biskra Algeria Department of Computer Automation and Management Engineering Sapienza University of Rome Rome Italy Laboratory of Telecommunications and Smart Systems Faculty of Sciences and Technology Zian Achour University of Djelfa Djelfa Algeria

ISBN: (数字)9798331527396

ISBN: (纸本)9798331527402

This paper introduces a novel advanced framework for the classification of Electroencephalography (EEG) signals through the integration of Riemannian geometry and a bespoke contrastive learning framework. Initially, the EEG signals are segmented and converted into covariance matrices, which are regularized to ensure positive definiteness, thus enabling their interpretation as Symmetric Positive Definite (SPD) matrices. These SPD matrices are then projected onto the Riemannian manifold, facilitating the extraction of discriminative features by utilizing Euclidean geometric operations within the tangent space. A specialized neural network architecture, TangentSpaceNet, is devised to map these features into a lower-dimensional space. In this space, a customized contrastive loss function, predicated on Euclidean distance, is implemented to enhance class separability. This approach substantially improves the robustness and accuracy of EEG signal classification. Empirical assessments highlight the effectiveness of the suggested approach, showcasing significant improvements in classifying performance 93% accuracy, 94%precision, 94% recall, and 94% F1-score. The novel fusion of Riemannian geometry and contrastive learning presents a sturdy and adaptable structure for analyzing EEG signals, presenting considerable prospects for utilization in brain-computer interfaces, cognitive neuroscience, and the identification of neurological conditions.

关键词： Geometry Training Accuracy Computational modeling Contrastive learning Brain modeling Feature extraction Electroencephalography Covariance matrices Matrix converters

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Prediction with Decomposition and Multi-Scale Autocorrelation in Large-Scale Cloud Data Centers

Network Traffic Prediction with Decomposition and Multi-Scal...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Meijia Wang Haitao Yuan Zhenwei Kuang Hanbo Ma Jing Bi Jia Zhang MengChu Zhou School of Automation Science and Electrical Engineering Beihang University Beijing China Faculty of Information Technology Beijing University of Technology Beijing China Dept. of Computer Science Southern Methodist University Dallas TX USA Dept. of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9798350365221

ISBN: (纸本)9798350365238

As the Internet and big data technologies advance, a tremendous amount of data is generated daily. Efficient network operations are essential for handling such data. Accurately predicting future network traffic in real-time enables prompt response from cloud infrastructure and efficient traffic scheduling and allocation, ultimately reducing costs, preventing economic losses, and optimizing the performance of downstream facilities. However, predicting network traffic in large-scale data centers is challenging due to the multidimensional, nonlinear, and high-volatility nature of the time series. Traditional prediction methods, e.g., regression algorithms, struggle to capture non-linear features effectively. Many deep learning models face issues such as gradient explosion or vanishing during their training. Current commonly used prediction methods fail to fully uncover vital information about the frequency domain features in the time series. To do so, this work proposes a novel network traffic prediction model that combines a Savitzky Golay filter, sequence decomposition, multi-scale attention, a temporal convolutional network, an autocorrelation mechanism, and bidirectional long short-term memory. It can accurately predict future network traffic by adaptively extracting important features without requiring excessive feature engineering of the original data. It performs end-to-end sequence prediction, feature selection, and automatic learning of data features and temporal dependencies to achieve accurate time series prediction and avoid redundant data processing. Experiments involving ablation studies and comparisons with advanced prediction models are performed with the Google cluster trace. Experimental results show that the proposed model improves the prediction accuracy by at least 38.52% over the state-of-the-art models.

关键词： Data centers Biological system modeling Time series analysis Telecommunication traffic Predictive models Feature extraction Prediction algorithms Autocorrelation Data mining Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of SVM and CNN Classifiers for EEG Signal Classification in Response to Different Auditory Stimuli

Comparative Analysis of SVM and CNN Classifiers for EEG Sign...

引用

Telecommunications and Intelligent Systems (ICTIS), International Conference on

作者： Ahmed Tibermacine Djouher Akrour Rofeida Khamar Imad Eddine Tibermacine Abdelaziz Rabehi Department of Computer Science University of Biskra Biskra Algeria Department of Computer Automation and Management Engineering Sapienza University of Rome Rome Italy Laboratory of Telecommunications and Smart Systems Faculty of Sciences and Technology Zian Achour University of Djelfa Djelfa Algeria

ISBN: (数字)9798331527396

ISBN: (纸本)9798331527402

This study aims to classify brainwave patterns using electroencephalogram (EEG) signals in response to various auditory stimuli, specifically Quran recitation, participants’ favorite music, and Interstellar’s main theme. By analyzing the unique EEG responses elicited by these stimuli, the study explores cognitive and emotional processing differences. Two prominent classifiers, Support Vector Machine (SVM) and Convolutional Neural Networks (CNN), were utilized. SVM, combined with Power Spectral Density (PSD) features, achieved the highest accuracy of 95% when distinguishing Quran recitation from rest. CNN, particularly with Kernel Density Estimation (KDE) features, exhibited strong performance in distinguishing between different auditory stimuli, with an average accuracy exceeding 90%. These results highlight the critical role of feature extraction techniques, such as PSD and KDE, in improving classification performance and deepening our understanding of EEG-based emotional and cognitive responses to auditory stimuli.

关键词： Support vector machines Accuracy Recurrent neural networks Pattern classification Brain modeling Feature extraction Electroencephalography Telecommunications Convolutional neural networks Object recognition

来源：评论

学校读者我要写书评

暂无评论

A review of Implementation and Challenges of Unmanned Aerial Vehicles for Spraying Applications and Crop Monitoring in Indonesia

arXiv

引用

arXiv 2023年

作者： Fikri, Muhamad Rausyan Candra, Taufiq Saptaji, Kushendarsyah Noviarini, Ajeng Nindi Wardani, Dilla Ayu Automation Technology and Mechanical Engineering Faculty of Engineering and Science Tampere University Tampere33720 Finland Information Systems Faculty of Engineering and Technology Sampoerna University Jakarta12780 Indonesia Industrial Engineering Faculty of Engineering and Technology Sampoerna University Jakarta12780 Indonesia Mechanical Engineering Faculty of Engineering and Technology Sampoerna University Jakarta12780 Indonesia Computer Science Faculty of Engineering and Technology Sampoerna University Jakarta12780 Indonesia

The rapid development of technology has brought unmanned aerial vehicles (UAVs) to become widely known in the current era. The market of UAVs is also predicted to continue growing with related technologies in the future. UAVs have been used in various sectors, including livestock, forestry, and agriculture. In agricultural applications, UAVs are highly capable of increasing the productivity of the farm and reducing farmers' workload. This paper discusses the application of UAVs in agriculture, particularly in spraying and crop monitoring. This study examines the urgency of UAV implementation in the agriculture sector. A short history of UAVs is provided in this paper to portray the development of UAVs from time to time. The classification of UAVs is also discussed to differentiate various types of UAVs. The application of UAVs in spraying and crop monitoring is based on the previous studies that have been done by many scientific groups and researchers who are working closely to propose solutions for agriculture-related issues. Furthermore, the limitations of UAV applications are also identified. The challenges in implementing agricultural UAVs in Indonesia are also presented. Copyright © 2023, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Improved harris hawks optimization algorithm based on collaborative quantization 6

Improved harris hawks optimization algorithm based on collab...

引用

6th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2022

作者： Li, Yan Zhang, Xiang Qian, Qian Pan, Jiawen Feng, Yong Fu, Yunfa Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan650500 China Yunnan Key Laboratory of Computer Technology Applications Kunming University of Science and Technology Kunming Yunnan650500 China Logistic Service Group Yunnan University Kunming Yunnan650500 China

ISBN: (纸本)9781510656635

Harris hawk optimization algorithm (HHO) is one of the population-based algorithms proposed by in *** has received great attention from researchers. However, HHO algorithm still has some problems, such as the exploitation ability is too large compared with the exploration ability, which leads to low optimization accuracy, slow convergence speed and so on. Therefore, the collaborative strategy and quantization strategy are introduced. With the support of the two strategies, the algorithm can avoid falling into local extremum in the early phase of iteration and improve its optimization accuracy at the late phase of iteration. Through the test of four representative functions, compared with the other three basic algorithms, the proposed algorithm greatly improves the optimization accuracy and convergence speed of the optimal solution, and the ability to find global extremum is greatly improved. © 2022 SPIE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Surface Electric Field Measurement of Composite Insulator Using an Optical Waveguide Sensor

SSRN

引用

SSRN 2023年

作者： Zhang, Jiahong Li, Weichang Shi, Jiali Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650000 China Yunnan Key Laboratory of Computer Technology Applications Kunming University of Science and Technology Kunming650000 China

In this paper, an integrated optical waveguide sensor is designed and developed to comprehensively analyze the surface electric field distribution characteristics of composite insulators. Based on the optical waveguide electric field sensor, a measuring system for the surface axial and radial electric fields of composite insulators is built, and the axial and radial electric fields along the surface of composite insulator is measured under normal, damaged and internally defects. Based on the optical waveguide electric field sensor, an experimental system is setup for measuring the axial and radial electric fields along surface of composite insulators under normal, damaged and internally defective conditions. The experimental results showed that when a 10 kV power frequency voltage is connected, the radial and axial electric fields at the low and high voltage ends of the normal insulator are 21.53 kV/m, 53.07 kV/m and 47.55 kV/m, 105.12 kV/m respectively. When the insulator surface is damaged, the radial and axial electric field intensities at the damaged locations increased by 37.59%-204.85% and 12.89%-32.69%, respectively. When an internal defect occurred, the radial and axial electric field along the defect area increased by 18% and decreased by 127.72%, respectively. The radial electric field is more affected by the defect. The comparison with the calculated results shows that the integrated optical waveguide electric field sensor has great potential capability to be used for measuring the surface electric field of insulators. © 2023, The Authors. All rights reserved.

关键词： Electric fields

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：