检索结果-内蒙古大学图书馆

Knowledge Transfer Learning via Dual Density Sampling for Resource-Limited Domain Adaptation

IEEE/CAA Journal of Automatica Sinica 2023年第12期10卷 2269-2291页

作者： Zefeng Zheng Luyao Teng Wei Zhang Naiqi Wu Shaohua Teng the School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510006China the School of Information Engineering Guangzhou Panyu PolytechicGuangzhou 511483China the Faculty of Information Technology Monash University20 Exhibition Walk ClaytonVIC 3800Australia IEEE the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems Macao University of Science and TechnologyMacao 999078China

Most existing domain adaptation(DA) methods aim to explore favorable performance under complicated environments by ***,there are three unsolved problems that limit their efficiencies:ⅰ) they adopt global sampling but neglect to exploit global and local sampling simultaneously;ⅱ)they either transfer knowledge from a global perspective or a local perspective,while overlooking transmission of confident knowledge from both perspectives;and ⅲ) they apply repeated sampling during iteration,which takes a lot of *** address these problems,knowledge transfer learning via dual density sampling(KTL-DDS) is proposed in this study,which consists of three parts:ⅰ) Dual density sampling(DDS) that jointly leverages two sampling methods associated with different views,i.e.,global density sampling that extracts representative samples with the most common features and local density sampling that selects representative samples with critical boundary information;ⅱ)Consistent maximum mean discrepancy(CMMD) that reduces intra-and cross-domain risks and guarantees high consistency of knowledge by shortening the distances of every two subsets among the four subsets collected by DDS;and ⅲ) Knowledge dissemination(KD) that transmits confident and consistent knowledge from the representative target samples with global and local properties to the whole target domain by preserving the neighboring relationships of the target *** analyses show that DDS avoids repeated sampling during the *** the above three actions,confident knowledge with both global and local properties is transferred,and the memory and running time are greatly *** addition,a general framework named dual density sampling approximation(DDSA) is extended,which can be easily applied to other DA *** experiments on five datasets in clean,label corruption(LC),feature missing(FM),and LC&FM environments demonstrate the encouraging performance of KTL-DDS.

关键词： Cross-domain risk dual density sampling intra-domain risk maximum mean discrepancy knowledge transfer learning resource-limited domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Graph Embedding With Consistency and Specificity for Domain Adaptation

引用

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2094-2107页

作者： Shaohua Teng Zefeng Zheng Naiqi Wu Luyao Teng Wei Zhang School of Computer Science and Technology Guangdong University of TechnologyGuangzhou 510006China Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and Systems Macao University of Science and TechnologyMacao 999078China School of Information Engineering Guangzhou Panyu PolytechicGuangzhou 511483China Faculty of Information Technology Monash University20 Exhibition Walk ClaytonVIC 3800Australia IEEE

Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabeled target samples *** approaches leverage Graph Embedding Learning to explore such a subspace. Unfortunately, due to 1) the interaction of the consistency and specificity between samples, and 2) the joint impact of the degenerated features and incorrect labels in the samples, the existing approaches might assign unsuitable similarity, which restricts their performance. In this paper, we propose an approach called adaptive graph embedding with consistency and specificity(AGE-CS) to cope with these issues. AGE-CS consists of two methods, i.e., graph embedding with consistency and specificity(GECS), and adaptive graph embedding(AGE).GECS jointly learns the similarity of samples under the geometric distance and semantic similarity metrics, while AGE adaptively adjusts the relative importance between the geometric distance and semantic similarity during the iterations. By AGE-CS,the neighborhood samples with the same label are rewarded,while the neighborhood samples with different labels are punished. As a result, compact structures are preserved, and advanced performance is achieved. Extensive experiments on five benchmark datasets demonstrate that the proposed method performs better than other Graph Embedding methods.

关键词： Adaptive adjustment consistency and specificity domain adaptation graph embedding geometrical and semantic metrics

来源：评论

学校读者我要写书评

暂无评论

Why Should I Trust Your Explanation? An Evaluation Approach for XAI Methods Applied to Predictive Process Monitoring Results

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1458-1472页

作者： Elkhawaga, Ghada Elzeki, Omar M. Abu-Elkheir, Mervat Reichert, Manfred Ulm University Institute of Databases and Information Systems Ulm89081 Germany Mansoura University Faculty of Computers and Information Mansoura35516 Egypt New Mansoura University Faculty of Computer Science and Engineering Mansoura35516 Egypt German University in Cairo Faculty of Media Engineering and Technology New Cairo11835 Egypt

As a use case of process mining, predictive process monitoring (PPM) aims to provide information on the future course of running business process instances. A large number of available PPM approaches adopt predictive models based on machine learning (ML). With the improved efficiency and accuracy of ML models usually being coupled with increasing complexity, their understandability becomes compromised. Having the user at the center of attention, various eXplainable artificial intelligence (XAI) methods emerged to provide users with explanations of the reasoning process of an ML model. Though there is a growing interest in applying XAI methods to PPM results, various proposals have been made to evaluate explanations according to different criteria. In this article, we propose an approach to quantitatively evaluate XAI methods concerning their ability to reflect the facts learned from the underlying stores of business-related data, i.e., event logs. Our approach includes procedures to extract features that are crucial for generating predictions. Moreover, it computes ratios that have proven to be useful in differentiating XAI methods. We conduct experiments that produce useful insights into the effects of the various choices made through a PPM workflow. We can show that underlying data and model issues can be highlighted using the applied XAI methods. Furthermore, we could penalize and reward XAI methods for achieving certain levels of consistency with the facts learned about the underlying data. Our approach has been applied to different real-life event logs using different configurations of the PPM workflow. © 2020 IEEE.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

So Far Yet So Near: Time Series Data Augmentation with Exploring non-Semantic Boundaries based on Reinforcement Learning

So Far Yet So Near: Time Series Data Augmentation with Explo...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Haoran Zhang, Zhibo Kang, Jiarong Jiang, Xun Gong, Xiaoli Zhang, Jin Sun, Zhe Cichocki, Andrzej College of Computer Science Nankai University Tianjin China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Medicine Faculty of Health Data Science Juntendo University Japan Systems Research Institute Polish Academy of Science Warsaw Poland

ISBN: (纸本)9798350368741

Data augmentation effectively expands feature distribution in time series classification, enhancing downstream task performance. However, existing techniques often fail to maintain semantic consistency between augmented and original time series data, causing label noise and thereby degrading downstream task performance. We argue that data augmentation should preserve time series semantic consistency and expand the non-semantic information space. In this paper, we reformulate data augmentation as a semantic path planning problem between original data and augmented data, modeled as a Markov Decision Process (MDP). We propose a reinforcement learning-based algorithm (RL) named FreqSYN, where the action space is defined by a set of learnable Gaussian kernels that perturbs the frequency domain of the original data to generate augmented samples. The confidence coefficients of augmented data in semantically relevant classification tasks are used as a reward to iteratively refine the FreqSYN. Our method is validated across four datasets, achieving state-of-the-art performance, with a 2% improvement in F1 score over the SimPSI method. The code and models are available at https://***/NKU-EmbeddedSystem/FreqSYN. © 2025 IEEE.

关键词： Data argumentation frequency domain augmentation Gaussian kernel prediction time series

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of the Invasive Weed Optimization K-Means Algorithm With Particle Swarm Optimization K-Means for Banking Data 6

Performance Comparison of the Invasive Weed Optimization K-M...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Suwirmayanti, Ni Luh Gede Pivin Putra, I. Ketut Gede Darma Sudarma, Made Sukarsa, I. Made Setyaningsih, Emy Department of Computer Systems Faculty of Informatics and Computer Institut Teknologi dan Bisnis STIKOM Bali Bali Indonesia Department of Information Technology Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Electrical Engineering Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Computer Systems Engineering Faculty of Applied Science Universitas AKPRIND Indonesia Yogyakarta Indonesia

ISBN: (纸本)9798331539603

Banking produces extensive and diverse data, so a clustering process is needed to understand customer behavior patterns and transactions more effectively. This clustering has been widely utilized with the K-Means algorithm due to its simplicity and efficiency. However, this algorithm is limited in determining the optimal cluster center, affecting the accuracy of the clustering results. This study proposes applying two metaheuristic algorithms, Invasive Weed Optimization (IWO) and Particle Swarm Optimization (PSO), as additional solutions combined with K-Means. These two algorithms were chosen because of their ability to find global solutions and convergence speed to handle large and complex banking data. The results show the superiority of IWOKM compared to PSOKM in terms of SSE and DBI. From the SSE value, IWOKM produces a lower value (3029.77), which indicates that this method is better at minimizing clustering errors and producing more accurate clustering than PSOKM (80007.09). From the DBI value, IWOKM also produces a better value (1.6684) than PSOKM (1.6782), which shows that the clusters produced by IWOKM are more compact and more separated. However, in terms of computation time, PSOKM is more efficient, with a faster average computation time. Although IWOKM produces better clustering quality, PSOKM offers advantages in terms of processing speed. This finding confirms that the selection of the IWO algorithm is more appropriate for use on datasets with characteristics such as the German Credit Dataset. © 2024 IEEE.

关键词： Invasive weed optimization

来源：评论

学校读者我要写书评

暂无评论

A New Cybersecurity Approach Enhanced by xAI-Derived Rules to Improve Network Intrusion Detection and SIEM

引用

computers, Materials & Continua 2025年第5期83卷 1607-1621页

作者： Federica Uccello Marek Pawlicki Salvatore D'Antonio RafałKozik MichałChoras Centro Direzionale Department of EngineeringUniversity of Naples‘Parthenope’Isola C4Napoli80133Italy Department of Computer and Information Science Software and SystemsLinköping UniversityLinköping58183Sweden ITTI Sp.z o.o. Pozna´n61-612Poland Faculty of Telecommunications Computer Science and Electrical EngineeringBydgoszcz University of Science and TechnologyBydgoszcz85-796Poland

The growing sophistication of cyberthreats,among others the Distributed Denial of Service attacks,has exposed limitations in traditional rule-based Security Information and Event Management *** machine learning–based intrusion detection systems can capture complex network behaviours,their“black-box”nature often limits trust and actionable insight for security *** study introduces a novel approach that integrates Explainable Artificial Intelligence—xAI—with the Random Forest classifier to derive human-interpretable rules,thereby enhancing the detection of Distributed Denial of Service(DDoS)*** proposed framework combines traditional static rule formulation with advanced xAI techniques—SHapley Additive exPlanations and Scoped Rules-to extract decision criteria from a fully trained *** methodology was validated on two benchmark datasets,CICIDS2017 and *** rules were evaluated against conventional Security Information and Event Management systems rules with metrics such as precision,recall,accuracy,balanced accuracy,and Matthews Correlation *** results demonstrate that xAI-derived rules consistently outperform traditional static ***,the most refined xAI-generated rule achieved near-perfect performance with significantly improved detection of DDoS traffic while maintaining high accuracy in classifying benign traffic across both datasets.

关键词： Cybersecurity explainable artificial intelligence intrusion detection system rule-based SIEM distributed denial of service

来源：评论

学校读者我要写书评

暂无评论

Metaheuristics for Financial Investment Strategies: Applications Survey

Metaheuristics for Financial Investment Strategies: Applicat...

引用

2023 International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Bousbaa, Zineb Bencharef, Omar Cady Ayyad University Computer and Systems Engineering Laboratory Faculty of Sciences and Technology Computer Science Department Marrakesh Morocco

ISBN: (纸本)9798350322972

Machine learning has been widely used as part of financial markets investment strategies, whether for forecasting the financial assets exchange rate, managing market volatility, or solving different classification problems that help with decision-making. Building an investment strategy using a scientific approach requires a massive amount of data, good computational power, and some expertise in the finance industry. Machine learning applications to the financial field, such as price exchange rate prediction, market pattern recognition, or other trading strategy tasks, are considered optimization problems. As they require an efficient algorithm dedicated to finding a global optimum, they can be solved using metaheuristics. In this survey, we study how metaheuristic optimization techniques contribute to building a robust learning model dedicated to financial investment strategy applications. © 2023 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Photonics Applications and Web engineering – WILGA 2024

Photonics Applications and Web Engineering – WILGA 2024

引用

Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2024

作者： Romaniuk, Ryszard S. Smolarz, Andrzej Wójcik, Waldemar Warsaw University of Technology Institute of Electronic Systems Poland Lublin University of Technology Faculty of Electrical Engineering and Computer Science Poland

ISBN: (数字)9781510685796

ISBN: (纸本)9781510685789

Wilga 2024 Summer Symposium on Photonics Applications and Web engineering was the 52th edition of the research and technical meetings series. Traditionally, the annual series of technical conferences and topical sessions lasted the whole week. They usually were split to one winter meeting in January and one or two summer events in May/June, and in September. The Covid epidemic and the war in Ukraine has changed a lot. The hybrid meetings were held in Wilga resort near Warsaw, owned by the Warsaw University of Technology. Now the meetings since 2022 were shifted to Lublin. Nearly 100 participants took part in all of the Wilga 2022 events, most of them being young researchers active in all aspects of photonics, electronics and ICT science and technology. Over 60 participants took part in Wilga 2024 meetings. Wilga Symposium embraces hardware and software technologies associated with photonics like optics, optical engineering, optoelectronics, electronics and electrical engineering, mechatronics, chemical and material engineering, applied physics, industrial solutions and applications. Around 50 papers were presented during Wilga 2024, oral and poster. Out of this number, some papers chosen by authors are published in this volume of Proc. SPIE mostly related to photonics. The major change was that during Wilga 2020, 2021, 2022 and 2024 Symposia, during summer editions, no traditional large young researcher sessions at large were possible to be organized. We hope that this will change and Wilga 2025 will return to a good tradition to organize concurrent social research sessions full of young researchers like was during Wilga 2019 and earlier. © 2024 SPIE.

关键词： Photonic devices

来源：评论

学校读者我要写书评

暂无评论

DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution 40

DistriBlock: Identifying adversarial audio samples by levera...

引用

40th Conference on Uncertainty in Artificial Intelligence, UAI 2024

作者： Pizarro, Matías B.P. Kolossa, Dorothea Fischer, Asja Faculty of Computer Science Ruhr University Bochum Germany Electronic Systems of Medical Engineering Technische Universität Berlin Germany

Adversarial attacks can mislead automatic speech recognition (ASR) systems into predicting an arbitrary target text, thus posing a clear security threat. To prevent such attacks, we propose DistriBlock, an efficient detection strategy applicable to any ASR system that predicts a probability distribution over output tokens in each time step. We measure a set of characteristics of this distribution: the median, maximum, and minimum over the output probabilities, the entropy of the distribution, as well as the Kullback-Leibler and the Jensen-Shannon divergence with respect to the distributions of the subsequent time step. Then, by leveraging the characteristics observed for both benign and adversarial data, we apply binary classifiers, including simple threshold-based classification, ensembles of such classifiers, and neural networks. Through extensive analysis across different state-of-the-art ASR systems and language data sets, we demonstrate the supreme performance of this approach, with a mean area under the receiver operating characteristic curve for distinguishing target adversarial examples against clean and noisy data of 99% and 97%, respectively. To assess the robustness of our method, we show that adaptive adversarial examples that can circumvent DistriBlock are much noisier, which makes them easier to detect through filtering and creates another avenue for preserving the system’s robustness. © 2024 Proceedings of Machine Learning Research. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Quantum Q-Learning Model for the Capacitated Vehicle Routing Problem 17

A Quantum Q-Learning Model for the Capacitated Vehicle Routi...

引用

17th IEEE International Symposium on Embedded Multicore/Many-core systems-on-Chip, MCSoC 2024

作者： Xu, Jiahua Xie, Ningyi Lee, Xinwei Saito, Yoshiyuki Asai, Nobuyoshi Cai, Dongsheng University of Tsukuba Graduate School of Science and Technology Japan Singapore Management University School of Computing and Information Systems Singapore University of Aizu Graduate School of Computer Science and Engineering Japan University of Aizu School of Computer Science and Engineering Japan University of Tsukuba Faculty of Engineering Information and Systems Japan

ISBN: (纸本)9798331530471

The research on Variational Quantum Algorithms (VQAs) has gained significant momentum because of their promising practicality in the noisy intermediate-scale quantum (NISQ) era. Recent studies highlight the potential of VQAs in reinforcement learning (RL) by replacing classical components with parameterized quantum circuits (PQCs). Building on this, we propose a quantum Q-learning model for the Capacitated Vehicle Routing Problem (CVRP), combining a PQC with an RL training process. We present a PQC for embedding both static and dynamic states in RL environments. The proposed PQC approximates the Q-value function by using the expectation values of different observables. Experimental results demonstrate that the proposed PQC outperforms the existing PQC for the CVRP with fewer quantum resources. Furthermore, our method shows competitive performance compared to the classical counterpart. © 2024 IEEE.

关键词： Vehicle routing

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：