检索结果-内蒙古大学图书馆

19th IEEE International Conference on Networking, Sensing and Control, ICNSC 2022

作者： Bai, Xiang-En An, Jing Yu, Zi-Bo Bao, Han-Qiu Wang, Ke-Fan School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai China College of Applied Mathematics Xi'an Jiaotong-Liverpool University Suzhou China College of Electronic and Information Engineering Tongji University Shanghai China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China

ISBN: (纸本)9781665472432

As an important research topic in graph learning, the performance of node classification has been improved with the development of some new methods, among which graph neural networks (GNNs) have achieved state-of-the-art node classification performance. However, the existing GNN-based methods mainly address the classification problem with balanced distribution of node samples. However, many real application scenarios of graph data usually have a highly skewed class distribution, i.e., the majority classes occupy most of the samples while the minority classes contain only a few samples. When the nodes exhibit an imbalanced class distribution, existing GNN-based methods favor the majority class and under-represent the minority class. Therefore, we propose a novel Kernel Propagation-based model for Imbalanced Node Classification in Graph Convolutional Networks (KINC-GCN). First, we introduce a kernel propagation method as a preprocessing step to exploit higher-order structural features. The node features are enhanced by concatenating the higher-order structural feature matrix with the node feature matrix. Node embeddings are obtained from the enhanced feature and adjacency matrices by a two-layer GCN, and then a self-optimizing cluster analysis and graph reconstruction module are introduced. The self-optimizing cluster analysis module performs cluster analysis on the node embeddings to enhance the representativeness of the node embeddings. The graph reconstruction module uses an inner product decoder to reconstruct the graph structure and minimize the differences between the reconstructed graph and the original graph. The effectiveness of KINC-GCN in node classification is demonstrated by experiments on three real-world imbalanced graph datasets. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners

arXiv

引用

arXiv 2023年

作者： Yadav, Sarthak Theodoridis, Sergios Hansen, Lars Kai Tan, Zheng-Hua Department of Electronic Systems Aalborg University Denmark Pioneer Centre for Artificial Intelligence Denmark Department of Applied Mathematics and Computer Science DTU Denmark Department of Informatics and Telecommunications National and Kapodistrian University of Athens Greece

In this work, we propose a Multi-Window Masked Autoencoder (MW-MAE) fitted with a novel Multi-Window Multi-Head Attention (MW-MHA) module that facilitates the modelling of local-global interactions in every decoder transformer block through attention heads of several distinct local and global windows. Empirical results on ten downstream audio tasks show that MW-MAEs consistently outperform standard MAEs in overall performance and learn better general-purpose audio representations, along with demonstrating considerably better scaling characteristics. Investigating attention distances and entropies reveals that MW-MAE encoders learn heads with broader local and global attention. Analyzing attention head feature representations through Projection Weighted Canonical Correlation Analysis (PWCCA) shows that attention heads with the same window sizes across the decoder layers of the MW-MAE learn correlated feature representations which enables each block to independently capture local and global information, leading to a decoupled decoder feature hierarchy. Code for feature extraction and downstream experiments along with pre-trained models will be released publically. © 2023, CC BY.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees

arXiv

引用

arXiv 2025年

作者： Zhou, Yuhao Xu, Jintao Bao, Chenglong Ding, Chao Zhu, Jun Department of Computer Science and Technology Tsinghua AI Insitute BNList Lab Tsinghua-Bosch Joint Center for ML Tsinghua University China Department of Applied Mathematics The Hong Kong Polytechnic University Hong Kong Yau Mathematical Sciences Center Tsinghua University Beijing Institute of Mathematical Sciences and Applications China Academy of Mathematics and Systems Science Chinese Academy of Sciences China

We consider the problem of finding an ϵ-stationary point of a nonconvex function with a Lipschitz continuous Hessian and propose a quadratic regularized Newton method incorporating a new class of regularizers constructed from the current and previous gradients. The method leverages a recently developed linear conjugate gradient approach with a negative curvature monitor to solve the regularized Newton equation. Notably, our algorithm is adaptive, requiring no prior knowledge of the Lipschitz constant of the Hessian, and achieves a global complexity of O(ϵ−3 2 ) + Õ(1) in terms of the second-order oracle calls, and Õ(ϵ−7 4 ) for Hessian-vector products, respectively. Moreover, when the iterates converge to a point where the Hessian is positive definite, the method exhibits quadratic local convergence. Preliminary numerical results illustrate the competitiveness of our algorithm. Copyright © 2025, The Authors. All rights reserved.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Theory of phase reduction for systems with higher-order interactions: a route to Kuramoto models on hypergraphs

arXiv

引用

arXiv 2025年

作者： León, Iván Muolo, Riccardo Hata, Shigefumi Nakao, Hiroya Department of Applied Mathematics and Computer Science Universidad de Cantabria Santander39005 Spain Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo152-8552 Japan Graduate School of Science and Engineering Kagoshima University Kagoshima890-0065 Japan Research Center for Autonomous Systems Materialogy Institute of Innovative Research Tokyo Institute of Technology Yokohama226-8501 Japan

Phase reduction is a powerful technique in the study of nonlinear oscillatory systems. Under certain assumptions, it allows us to describe each multidimensional oscillator by a single phase variable, giving rise to simple phase models such as the Kuramoto model. Classically, the method has been applied in the case where the interactions are only pairwise (two-body). However, increasing evidence shows that interactions in real-world systems are not pairwise but higher-order, i.e., many-body. Although synchronization in higher-order systems has received much attention, analytical results are scarce because of the highly nonlinear nature of the framework. In this paper, we fill the gap by presenting a general theory of phase reduction for the case of higher-order interactions. We show that the higher-order topology is preserved in the phase reduced model at the first order and that only odd couplings have an effect on the dynamics when certain symmetries are present. Additionally, we show the power and ductility of the phase reduction approach by applying it to a population of Stuart-Landau oscillators with an all-to-all configuration and with a ring-like hypergraph topology;in both cases, only the analysis of the phase model can provide insights and analytical results. © 2025, CC BY-NC-ND.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Multi-facet Classification of Individual Logs in Wooden Piles 18th

Segmentation and Multi-facet Classification of Individual Lo...

引用

18th International Conference on computer Aided systems Theory, EUROCAST 2022

作者： Praschl, Christoph Auersperg-Castell, Philipp Forster-Heinlein, Brigitte Zwettler, Gerald Adam Research Group Advanced Information Systems and Technology Research and Development Department University of Applied Sciences Upper Austria Hagenberg Austria Department of Software Engineering School of Informatics Communications and Media University of Applied Sciences Upper Austria Hagenberg Austria Bluedynamics Auersperg-Castell KG Kritzing 31 Freinberg Austria Faculty of Computer Science and Mathematics University of Passau Passau Germany

ISBN: (纸本)9783031253119

The inspection of products and assessment of quality is connected with high costs and time effort in many industrial domains. This also applies to the forestry industry. Utilizing state-of-the-art deep learning models allows automizing the analysis of wooden piles in a vision-based manner. In this work, a parallel two-step approach is presented for the segmentation and multi-facet classification of individual logs, according to the wood type and quality. The present approach is based on a preliminary log localization step and like this allows determining the quality, volume and also the value of individual logs, respectively the whole wooden pile. Using a YOLOv4 model for wood species classification for douglas firs, pines and larches results in an accuracy of 74.53%, while a quality classification model for spruce logs reaches 86.58%. In addition to that, the trained U-NET segmentation model reaches an accuracy of 93%. In the future, the underlying data set and models will be further improved and integrated to a mobile application for the on site analysis of wooden piles by foresters. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning and Convex Mean-Variance Optimisation for Portfolio Management

arXiv

引用

arXiv 2022年

作者： Pretorius, Ruan Van Zyl, Terence L. The School Of Computer Science And Applied Mathematics University Of The Witwatersrand South Africa South Africa The Institute For Intelligent Systems Unversity Of Johannesburg Johannesburg South Africa

Traditional portfolio management methods can incorporate specific investor preferences but rely on accurate forecasts of asset returns and covariances. Reinforcement learning (RL) methods do not rely on these explicit forecasts and are better suited for multi-stage decision processes. To address limitations of the evaluated research, experiments were conducted on three markets in different economies with different overall trends. By incorporating specific investor preferences into our RL models' reward functions, a more comprehensive comparison could be made to traditional methods in risk-return space. Transaction costs were also modelled more realistically by including nonlinear changes introduced by market volatility and trading volume. The results of this study suggest that there can be an advantage to using RL methods compared to traditional convex mean-variance optimisation methods under certain market conditions. Our RL models could significantly outperform traditional single-period optimisation (SPO) and multi-period optimisation (MPO) models in upward trending markets, but only up to specific risk limits. In sideways trending markets, the performance of SPO and MPO models can be closely matched by our RL models for the majority of the excess risk range tested. The specific market conditions under which these models could outperform each other highlight the importance of a more comprehensive comparison of Pareto optimal frontiers in riskreturn space. These frontiers give investors a more granular view of which models might provide better performance for their specific risk tolerance or return targets. © 2022, CC BY-SA.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

The Role of Predictive Maintenance Optimization Techniques in Enhancing Industrial Productivity

The Role of Predictive Maintenance Optimization Techniques i...

引用

International Conference on Optimization and Applications (ICOA)

作者： Mohamed Er-Ratby Abdessamad Kobi Youssef Sadraoui Moulay Saddik Kadiri LASTI Laboratory of Science and Engineering Techniques National School of Applied Sciences Sultan Moulay Slimane University Khouribga Morocco LARIS Angevin Laboratory for Systems Engineering Research Polytech Angers University of Angers Angers France LIPIM Laboratory of Process Engineering Computer Science and Mathematics National School of Applied Sciences Sultan Moulay Slimane University Khouribga Morocco

ISBN: (数字)9798350387353

ISBN: (纸本)9798350387360

The convergence between advanced technology and industrial production holds significant potential to enhance operational efficiency, reduce maintenance costs, and minimize unexpected disruptions. Artificial intelligence, in particular, plays a crucial role in predicting machine failures, thereby contributing to the optimization of operational performance and maximizing overall company output. However, current challenges in maintenance and production are numerous. High maintenance costs are often a major concern for companies, as they can significantly eat into profit margins. Unexpected downtime, caused by sudden machine failures, leads to substantial production losses, affecting not only revenue but also customer satisfaction and the company's reputation. Furthermore, the increasing complexity of industrial systems makes the management of maintenance and production even more difficult, necessitating more advanced and integrated solutions. This article explores the various applications of artificial intelligence in the manufacturing industry, highlighting its impact on business performance. It also examines the steps necessary for implementing predictive maintenance, from data collection and processing to the establishment of predictive models. The ultimate goal is to improve equipment availability, optimize operational performance, and maximize overall company output.

关键词： Productivity Manufacturing industries Costs Focusing Companies Predictive models Maintenance Artificial intelligence Optimization Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Towards a methodology for addressing missingness in datasets, with an application to demographic health datasets

arXiv

引用

arXiv 2022年

作者： Khangamwa, Gift van Zyl, Terence L. van Alten, Clint J. University of the Witwatersrand Johannesburg School of Computer Science and Applied Mathematics Johanneburg South Africa University of Johannesburg Institute for Intelligent Systems Johannesburg South Africa

Missing data is a common concern in health datasets, and its impact on good decision-making processes is well documented. Our study’s contribution is a methodology for tackling missing data problems using a combination of synthetic dataset generation, missing data imputation and deep learning methods to resolve missing data challenges. Specifically, we conducted a series of experiments with these objectives;a) generating a realistic synthetic dataset, b) simulating data missingness, c) recovering the missing data, and d) analyzing imputation performance. Our methodology used a gaussian mixture model whose parameters were learned from a cleaned subset of a real demographic and health dataset to generate the synthetic data. We simulated various missingness degrees ranging from 10%, 20%, 30%, and 40% under the missing completely at random scheme MCAR. We used an integrated performance analysis framework involving clustering, classification and direct imputation analysis. Our results show that models trained on synthetic and imputed datasets could make predictions with an accuracy of 83% and 80% on a) an unseen real dataset and b) an unseen reserved synthetic test dataset, respectively. Moreover, the models that used the DAE method for imputation yielded the lowest log loss an indication of good performance, even though the accuracy measures were slightly lower. In conclusion, our work demonstrates that using our methodology, one can reverse engineer a solution to resolve missingness on an unseen dataset with missingness. Moreover, though we used a health dataset, our methodology can be utilized in other contexts. © 2022, CC BY-NC-SA.

关键词： Health

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on the Efficiency of the Modified COMET in Decision-Making

引用

Procedia computer science 2024年 246卷 103-112页

作者： Bartosz Paradowski Paweł Olender Wojciech Sałabun Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology Szczecin ul. Żołnierska 49 71-210 Szczecin Poland National Institute of Telecommunications ul. Szachowa 1 04-894 Warsaw Poland

Decision-making is a high-risk area and, simultaneously, a process that cannot be ignored. Risks often arise under challenging situations where ranking the options under consideration is a complex problem. For such purposes, multi-criteria decision-making methods are resorted to, which, despite continuous improvement, still have some weaknesses, often due to their characteristics. One such method that has seen many modifications in the literature is the Characteristic Objects METhod (COMET). It allows a simplified comparison of alternatives considered in a given problem, compared to the Analytic Hierarchy Process (AHP), but has a relatively high computational complexity. In this study, we present a modification of the COMET method that simplifies the procedure for assigning preference values to characteristic objects. Furthermore, a comparison with the classical approach is given regarding the obtained preference values, rankings, and criteria weights, which occur implicitly in this method. The study showed that the proposed modification has grounds for broader use and offers similar results to classical COMET while reducing the number of required operations to obtain preference values.

关键词： COMET analysis MCDA MCDM weights decision making

来源：评论

学校读者我要写书评

暂无评论

CONSUMER TRANSACTIONS SIMULATION THROUGH GENERATIVE ADVERSARIAL NETWORKS UNDER STOCKS CONSTRAINTS IN LARGE-SCALE RETAIL

arXiv

引用

arXiv 2024年

作者： Tkachuk, Sergiy Lukasik, Szymon Wróblewska, Anna Systems Research Institute Polish Academy of Sciences ul. Newelska 6 Warsaw01-447 Poland Faculty of Mathematics and Information Science Warsaw University of Technology Warsaw Poland Faculty of Physics and Applied Computer Science AGH University of Science and Technology al. Mickiewicza 30 Kraków30-059 Poland

In the rapidly evolving domain of large-scale retail data systems, envisioning and simulating future consumer transactions has become a crucial area of interest. It offers significant potential to fortify demand forecasting and fine-tune inventory management. This paper presents an innovative application of Generative Adversarial Networks (GANs) to generate synthetic retail transaction data, specifically focusing on a novel system architecture that combines consumer behavior modeling with stock-keeping unit (SKU) availability constraints to address real-world assortment optimization challenges. We diverge from conventional methodologies by integrating SKU data into our GAN architecture and using more sophisticated embedding methods (e.g., hyper-graphs). This design choice enables our system to generate not only simulated consumer purchase behaviors but also reflects the dynamic interplay between consumer behavior and SKU availability – an aspect often overlooked, among others, because of data scarcity in legacy retail simulation models. Our GAN model generates transactions under stock constraints, pioneering a resourceful experimental system with practical implications for real-world retail operation and strategy. Preliminary results demonstrate enhanced realism in simulated transactions measured by comparing generated items with real ones using methods employed earlier in related studies. This underscores the potential for more accurate predictive modeling. © 2024, CC BY-NC-ND.

关键词： Generative adversarial networks

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：