检索结果-内蒙古大学图书馆

Towards Evaluating the Robustness of Adversarial Attacks Against Image Scaling Transformation

Chinese Journal of Electronics 2023年第1期32卷 151-158页

作者： ZHENG Jiamin ZHANG Yaoyuan LI Yuanzhang WU Shangbo YU Xiao School of E-Business and Logistics Beijing Technology and Business University School of Computer Science and Technology Beijing Institute of Technology School of Computer Science and Technology Shandong University of Technology

The robustness of adversarial examples to image scaling transformation is usually ignored when most existing adversarial attacks are proposed. In contrast, image scaling is often the first step of the model to transfer various sizes of input images into fixed ones. We evaluate the impact of image scaling on the robustness of adversarial examples applied to image classification *** set up an image scaling system to provide a basis for robustness evaluation and conduct experiments in different situations to explore the relationship between image scaling and the robustness of adversarial examples. Experiment results show that various scaling algorithms have a similar impact on the robustness of adversarial examples,but the scaling ratio significantly impacts it.

关键词： Perturbation methods Solids Robustness Classification algorithms Task analysis Image classification

来源：评论

学校读者我要写书评

暂无评论

Analysis of Evolutionary Diversity Optimization for Permutation Problems

引用

ACM Transactions on Evolutionary Learning and Optimization 2022年第3期2卷 1–27页

作者： Do, Anh Guo, Mingyu Neumann, Aneta Neumann, Frank Optimisation and Logistics School of Computer Science The University of Adelaide Adelaide Australia

Generating diverse populations of high-quality solutions has gained interest as a promising extension to the traditional optimization tasks. This work contributes to this line of research with an investigation on evolutionary diversity optimization for three of the most well-studied permutation problems: the Traveling Salesperson Problem (TSP), both symmetric and asymmetric variants, and the Quadratic Assignment Problem (QAP). It includes an analysis of the worst-case performance of a simple mutation-only evolutionary algorithm with different mutation operators, using an established diversity measure. Theoretical results show that many mutation operators for these problems guarantee convergence to maximally diverse populations of sufficiently small size within cubic to quartic expected runtime. On the other hand, the results regarding QAP suggest that strong mutations give poor worst-case performance, as mutation strength contributes exponentially to the expected runtime. Additionally, experiments are carried out on QAPLIB and synthetic instances in unconstrained and constrained settings, and reveal much more optimistic practical performances while corroborating the theoretical findings regarding mutation strength. These results should serve as a baseline for future studies. © 2022 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

FERMixNet: An Occlusion Robust Facial Expression Recognition Model with Facial Mixing Augmentation and Mid-Level Representation Learning

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 639-654页

作者： Huang, Yansong Peng, Junjie Zhang, Wenqiang Zhao, Tong Chen, Gan Tan, Shuhua Yi, Fen Wang, Lu Shanghai University School of Computer Engineering and Science Shanghai China Shanghai University School of Computer Engineering and Science The Shanghai Institute for Advanced Communication and Data Science Shanghai China Fudan University Academy for Engineering and Technology School of Computer Science and Technology Shanghai China YTO Express Co. Ltd. The National Logistics Engineering Laboratory Shanghai China

Facial expressions can provide a better understanding of people's mental status and attitudes towards specific things. However, facial occlusion in real world is an unfavorable phenomenon that greatly affects the performance of facial expression recognition models. Recent works addressing the occlusion problem have primarily relied on attention mechanisms or occlusion discarding methods that focus on non-occluded regions of the face. However, these methods have not achieved a good balance between occlusion robustness and model efficiency. In this paper, we propose a simple and efficient model, called FERMixNet, for occluded facial expression recognition. The model incorporates a novel facial mixing augmentation strategy (FERMix) that generates new training samples by simulating real-world facial occlusion and preserving high expression-related semantic information. By co-training the original and newly generated samples, the model's occlusion robustness is improved without increasing its complexity during inference. Additionally, to further enhance the model's occlusion robustness, we include mid-level representation learning in the network to learn the discriminative non-occluded local features of the samples with low computational cost. Extensive experiments on four public facial occlusion datasets: Occlusion-RAF-DB, Occlusion-FERPlus and FED-RO show that the proposed model achieves state-of-the-art results which demonstrates the good robustness of our method for occluded facial expression recognition. Meanwhile, the proposed model also achieves state-of-the-art results on the in-the-wild facial expression datasets RAF-DB, AffectNet-8, and AffectNet-7. It proves that the proposed model has good application prospects in real world. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Maximum Power Point Tracking Control of Offshore Wind-Photovoltaic Hybrid Power Generation System with Crane-Assisted

引用

computer Modeling in Engineering & sciences 2025年第4期143卷 289-334页

作者： Xiangyang Cao Yaojie Zheng Hanbin Xiao Min Xiao School of Transportation and Logistics Engineering Wuhan University of TechnologyWuhan430063China Sanya Science and Education Innovation Park Wuhan University of TechnologySanya572024China School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan430063China

This study investigates the Maximum Power Point Tracking(MPPT)control method of offshore windphotovoltaic hybrid power generation system with offshore crane-assisted.A new algorithm of Global Fast Integral Sliding Mode Control(GFISMC)is proposed based on the tip speed ratio method and sliding mode *** algorithm uses fast integral sliding mode surface and fuzzy fast switching control items to ensure that the offshore wind power generation system can track the maximum power point quickly and with low *** offshore wind power generation system model is presented to verify the algorithm *** offshore off-grid wind-solar hybrid power generation systemis built in MATLAB/*** with other MPPT algorithms,this study has specific quantitative improvements in terms of convergence speed,tracking accuracy or computational ***,the improved algorithm is further analyzed and carried out by using Yuankuan Energy’s ModelingTech semi-physical simulation *** results verify the feasibility and effectiveness of the improved algorithm in the offshore wind-solar hybrid power generation system.

关键词： Offshore wind power generation efficiency maximum power point tracking(MPPT) integral sliding mode control grey wolf optimization algorithm offshore photovoltaic cells

来源：评论

学校读者我要写书评

暂无评论

One-Shot Learning for MIPs with SOS1 Constraints

引用

Operations Research Forum 2024年第3期5卷 57页

作者： Robinson La Rocca, Charly Cordeau, Jean-Franã§Ois Frejinger, Emma Department of Computer Science and Operations Research Université de Montréal Department of Logistics and Operations Management HEC Montréal

Efficient algorithms and solvers are required to provide optimal or near-optimal solutions quickly and enable organizations to react promptly to dynamic situations such as supply chain disruptions or changing customer demands. State-of-the-art mixed-integer programming (MIP) solvers are crafted to tackle a wide variety of problems, yet many real-world situations are characterized by problem instances that originate from a narrow distribution. This has inspired the creation of tailored approaches that exploit historical data to inform heuristic design. Deep learning (DL) methods are typically used in this context to extract patterns from data, but they require large datasets and comprehensive hyperparameter tuning for strong performance. This article describes a one-shot learning heuristic that leverages solutions discovered within the branch-and-bound tree to construct a model with minimal overhead. We evaluate our method on the locomotive assignment problem (LAP) and sets of MIPLIB instances that contain constraints based on special ordered sets of type 1. Experimental results include a comparison with multiple primal heuristics and state-of-the-art MIP solvers. We show that the method is most effective with CPLEX in terms of the average primal gap. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Fleet management problem Learning heuristics Machine learning MIPLIB Mixed-integer programming

来源：评论

学校读者我要写书评

暂无评论

Average reward adjusted discounted reinforcement learning

引用

Neural Computing and Applications 2025年 1-32页

作者： Schneckenreither, Manuel Moser, Georg Department of Information Systems Production and Logistics Management University of Innsbruck Universitaetsstrasse 15 Innsbruck6020 Austria Computer Science University of Innsbruck Technikerstrasse 21a Innsbruck6020 Austria

In this paper, we provide a novel view upon reinforcement learning (RL for short). In particular, we are interested in applications of RL in use cases, where average rewards may be nonzero. While RL methodologies have been extensively researched upon, this particular application area has only received scarce attention in the Literature. In part, our motivation stems from applications in Operation Research (OR for short), where it is typically the case that rewards are profit derived. Similar use cases can be found in more general applications in economics. Based on a principled study of the mathematical background of discounted reinforcement learning we establish a novel adaptation of standard RL, dubbed Average Reward Adjusted Discounted Reinforcement Learning (ARAL for short). Our approach stems from revisiting the Laurent Series expansion of the discounted state value and a subsequent reformulation of the target function guiding the learning process. While the theoretical advance is arguably incremental, we provide ample experimental evidence that the thus obtained novel RL methodology compares favorable to well-established techniques like Q-learning or R-learning. © The Author(s) 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-scale feature fusion for facial expression recognition

引用

Neural Computing and Applications 2025年第17期37卷 11399-11420页

作者： Guo, Jiatao Peng, Junjie Huang, Yansong Chen, Gan Cai, Zesu Tan, Shuhua School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China School of Computer Science and Technology Harbin Institute of Technology Harbin China National Engineering Laboratory for Logistics Information Technology YTO Express Co. Ltd. Shanghai China

As an important computer vision task that can be used in many areas, facial expression recognition (FER) has been widely studied which much progress has been obtained especially when deep learning (DL) approaches have been introduced in FER. However, existing methods are restricted to extracting localized information or utilizing attention mechanism to focus on the region most relevant to the emotion, possibly resulting in errors in facial expression interpretation. Moreover, the inconsistency of image sizes in the wild FER datasets further increases the difficulty of the FER task. To address these issues, we propose a multi-scale feature fusion (MSFF) for FER. Specifically, our method first extracts features from facial images using multi-scale feature extraction to obtain rich multi-dimensional information. Meanwhile, extensive feature extraction at different scales is achieved by expanding the receptive field of the model, which provides the basis for more detailed analysis of facial expressions. Eventually, features at different scales are fused to enhance their synergistic effect. Subsequently, the adaptive extraction of comprehensive and valuable information from the fused features is performed, optimizing the performance of expression recognition. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on in-the-wild datasets. It is promising for FER in realistic and complex scenarios. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

AI generated route data pre-processing for faster decision making 8

AI generated route data pre-processing for faster decision m...

引用

8th International Young Engineers Forum on Electrical and computer Engineering, YEF-ECE 2024

作者： Maas, Rene Shevtshenko, Eduard Karaulova, Tatjana TTK University of Applied Sciences Institute of Logistics Faculty of Science and Technology University of Tartu Institute of Computer Science Tallinn Estonia Tallinn University of Technology TTK University of Applied Sciences Department of Mechanical and Industrial Engineering Institute of Logistics Tallinn Estonia

ISBN: (纸本)9798350387643

The industry is constantly generating new data, allowing take advantage of their use to increase manufacturing efficiency through the reutilisation of operational *** such possibility is to use Artificial Intelligence (AI). While AI is heralded as a solution for industry efficiency and accuracy quandaries through process automation, its implementation grapples with the issue of inaccurate production data used for training, giving an erroneous *** article introduces a framework to facilitate the integration of AI tools within companies. The focus is on the accuracy of predicting normative times and selecting alternative routes when accuracy is low. This approach improves the price quotation prediction process, where using AI is practical due to time constraints. Making quick and accurate decisions is crucial for maintaining efficiency in *** elucidate the functionality, the authors have performed a case study in production for the framework's validation. The wood production sector was selected due to its lower operational complexity than machinery construction, resulting in time savings in the planning *** study revealed that the prediction accuracy of AI was 70% on average for operations normative times. To improve this accuracy, the t-Test method to classify operations was used. This approach eliminates operations with low AI prediction accuracy when making price quotations. Through the case study, AI module accuracy reached 80%, while the additional data collection volume decreased by one-Third. © 2024 IEEE.

关键词： Machine Learning Normative Times Wood Industry

来源：评论

学校读者我要写书评

暂无评论

Identification of the Mathematical Model of the pH Environment in the Biogas Plant based on the Application of the Swarm Intelligence Method 14

Identification of the Mathematical Model of the pH Environme...

引用

14th International Conference on Advanced computer Information Technologies, ACIT 2024

作者： Dyvak, Mykola Krepych, Svitlana Manzhula, Volodymyr Tsovka, Yurii Popovych, Pavlo Zabchuk, Vadym West Ukrainian National University Department of Computer Science Ternopil Ukraine West Ukrainian National University Department of Transport and Logistics Ternopil Ukraine

ISBN: (纸本)9798350350036

The article deals with the task of developing a mathematical model and its computer implementation, which connects the pH (acidity of the environment) with the factors on which it depends based on the analysis of interval data obtained during the study of the biogas plant. In the course of research, it was established that the pH of the substrate depends on the volume and structure of the raw material, as well as on the temperature in the bioreactor and the humidity of the bio-raw material. To construct this mathematical model, the suggested approach involves utilizing interval data analysis alongside parameter identification methods employing computational algorithms inspired by swarm intelligence in bee colonies. The results of experimental studies for a specific type of biogas plant are presented, and an interval model with guaranteed prognostic properties is obtained, which characterizes the pH of the environment depending on the specific type of dry and liquid part of bio-raw material and temperature. The obtained mathematical model is an algebraic nonlinear equation that can be used to determine the optimal volumes of raw materials of each type during the loading period depending on the temperature of the substrate in the bioreactor. © 2024 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Intelligent reflecting surface-assisted cognitive radio-inspired rate-splitting multiple access systems

引用

Digital Communications and Networks 2023年第3期9卷 655-666页

作者： Peixu Liu Gang Jing Hongwu Liu Liang Yang Theodoros A.Tsiftsis School of Information Science and Electrical Engineering Shandong Jiaotong UniversityJinan250357China School of Transportation and Logistics Engineering Shandong Jiaotong UniversityJinan250357China College of Computer Science and Electronic Engineering Hunan UniversityChangsha410082China School of Intelligent Systems Science and Engineering Jinan UniversityZhuhai519070China

Intelligent reflecting surface(IRS)has been widely regarded as a promising technology for configuring wireless propagation *** this paper,we utilize IRS to assist transmission of a secondary user(SU)in a cognitive radio-inspired rate-splitting multiple access(CR-RSMA)system in which a primary user's(PU's)quality of service(QoS)requirements must be *** introducing intolerable interference to deteriorate the PU's outage performance,the SU conducts rate-splitting to transmit its signal to the base-station through the direct link and IRS reflecting *** the IRS-assisted CR-RSMA(IRS-CR-RSMA)scheme,we derive the optimal transmit power allocation,target rate allocation,and successive interference cancellation decoding order to enhance the outage performance of the *** closed-form expression for the SU's outage probability achieved by the IRS-CR-RSMA scheme is *** simulation results are presented to clarify the enhanced outage performance achieved by the proposed IRS-CR-RSMA scheme over the CR-RSMA scheme.

关键词： Rate-splitting multiple access(RSMA) Intelligent reflecting surface(IRS) Successive interference cancellation(SIC) Cognitive radio

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：