检索结果-内蒙古大学图书馆

10th International Conference on engineering and Emerging Technologies, ICEET 2024

作者： Wadood, Hamid Haris, Muhammad Hassan, Aqib Malik, Muhammad Osama Yousaf, Hamza Ullah, Kaleem University of Alabama at Birmingham Department of Computer Science Alabama United States Institute for Insight - J Mack Robinson College of Business Georgia State University AtlantaGA United States School of Computing and Mathematical Sciences University of Greenwich London United Kingdom University of Tulsa Department of Business Analytics Oklahoma United States Stetson-Hatcher School of Business Mercer University GA30341 United States University of Engineering and Technology Department of Energy System Engineering Peshawar Pakistan

ISBN: (纸本)9798331532895

Driven by the pressing need for sustainable and reliable energy sources, this paper critically evaluates deep learning's role in advancing wind energy forecasting, highlighting its potential to address current energy demands through improved prediction accuracy. Due to the inherent unpredictability of wind, conventional forecasting models often fall short;however, deep learning models offer enhanced reliability by effectively identifying complex, embedded patterns within wind data. The paper examines techniques such as time-series recurrent neural networks, restricted Boltzmann machines, convolutional neural networks, and autoencoders, each targeting distinct challenges in wind forecasting to strengthen grid integration and ensure energy reliability. Future directions-including hybrid model approaches and model interpretability-are discussed, underscoring deep learning's promise as a powerful tool for optimizing wind energy utilization and supporting a more sustainable, low-carbon energy infrastructure. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

Robin: A Novel Method to Produce Robust Interpreters for Dee...

引用

IEEE International Conference on Automated Software engineering (ASE)

作者： Zhen Li Ruqian Zhang Deqing Zou Ning Wang Yating Li Shouhuai Xu Chen Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security Department of Computer Science University of Colorado Colorado Springs USA Center for Research in Computer Vision University of Central Florida USA School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

引用

IEEE Transactions on Multimedia 2025年

作者： Fu, Congrui Yuan, Hui Jiang, Shiqi Zhang, Guanghui Shen, Liquan Hamzaoui, Raouf Center of Experimental Teaching China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China Shandong University School of software Shandong Jinan China Shandong University School of Computer Science and Technology China Shanghai University School of Communication and Information Engineering Shanghai China De Montfort University School of Engineering and Sustainable Development LeicesterLE1 9BH United Kingdom

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. Our method combines long-term global information and short-term local information from the video to better extract complete and accurate spatial-temporal information. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This provides a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms open source state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.2 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectiv

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Estimation of load factors of trains using multi-source data for complex metro systems 7

Estimation of load factors of trains using multi-source data...

引用

7th International Conference on Big Data Computing and Communications, BigCom 2021

作者： Wu, Hexiang Liu, Tong Li, Chengfan Tong, Weiqin Feng, Zhenni Zhao, Shimin Shanghai University School of Computer Engineering and Science China Shanghai Engineering Research Center of Intelligent Computing System China Donghua University School of Computer Science and Technology China Shanghai Shentong Metro Co. Ltd. China

ISBN: (纸本)9781665442527

Metro systems play a significant role of urban transportation in large cities. It is critical for metro system managers to understand load factors of trains. Although the wide deployment of automated fare collection (AFC) system brings us a lot of convenience, only the information likes tap-in and tap-out time stamp and stations of each trip can be directly obtained from AFC records, the train and the route chosen by the passengers are uncertain. The information is necessary for achieving the load factors of trains. Considering that AFC records contain the no-transfer trips, one-transfer trips and multi-transfer trips, the problem becomes particularly complicated. Benefiting from machine learning, we propose an effective data-mining method to better understand the train and route chosen by a passenger with considering the impacts of time and space. We also classify passengers based on the similarity of passenger travel characteristics, which can automatically select the initial cluster centres in data. We validate our approach using a large-scale dataset collected from the Shanghai Metro system, and results demonstrate that our approach works effectively. © 2021 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

arXiv

引用

arXiv 2023年

作者： Zhou, Ziqi Hu, Shengshan Zhao, Ruizhi Wang, Qian Zhang, Leo Yu Hou, Junhui Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Wuhan University China School of Information and Communication Technology Griffith University Australia Department of Computer Science City University of Hong Kong Hong Kong National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial use. In this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://github. com/CGCL-codes/AdvEncoder. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Restoration of Defective Cloud Images from Meteorological Satellites

Restoration of Defective Cloud Images from Meteorological Sa...

引用

2023 China Automation Congress, CAC 2023

作者： Xu, Ruiyao Zhou, Zhixuan Zhao, Xintong Wang, Congcong Liu, Ding School of Mechano-Electronic Engineering Xidian University Xi'an710071 China Hangzhou Institute of Technology Xidian University Intelligent Robot Laboratory Hangzhou311231 China Beijing Global Metroute Technology Co. Ltd Huafeng Weather Media Group Beijing10081 China Ministry of Education Engineering Research Center of Learning-Based Intelligent System School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9798350303759

Meteorological satellites are inevitably disturbed in information transmission, which leads to missing bars on the cloud images and thus makes it impossible for meteorologists to give accurate weather predictions. The UNet-like networks have a hierarchical feature map to obtain rich multi-scale contextual features. In addition, they can enhance the image reconstruction process using jump connections between the encoder and decoder. Therefore, based on deep learning theory, this paper proposes a method to restore defective satellite images using UNet and Swin-U'Net, which are both in shape of 'U'. Moreover, the work selects the infrared satellite cloud image ir107 in the SEVIR dataset as the base dataset, from which the defective dataset is artificially generated. By comparing the restoration results of the two networks, the work concludes that the UNet network performs better than the Swin-UNet network in the image restoration function, which verifies the effectiveness of the network in the image restoration function. © 2023 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

arXiv

引用

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Method for Removing Complex Visible Watermarks of Electronic Map Based on Conditional Generative Adversarial Nets 29

A Method for Removing Complex Visible Watermarks of Electron...

引用

29th International Conference on Geoinformatics, Geoinformatics 2022

作者： Baode, Jiang Shaofen, Xu Liufeng, Tao Zhong, Xie National Engineering Research Center of Geographic Information System China University of Geosciences Wuhan430074 China School of Computer Science China University of Geosciences Wuhan430074 China State Key Laboratory of Geo-information Engineering Xi'an710054 China

ISBN: (数字)9798350309881

ISBN: (纸本)9798350309881

With the rapid development and extensive application of the electronic map technology, complex visible watermarks have been widely used in e-maps and map tiles delivered by map service providers to protect copyright. To evaluate the robustness and effectiveness of visible watermarks, many researches on watermark removal have attracted much attention in recent years. However, most of the existing watermark removal methods have the problems of watermark residue or repaired area being indistinct and unreal. To address these difficulties, this paper presented a deep neural network model based on conditional generative adversarial networks (cGANs) to remove complex visible watermark for electronic map tiles. The model is mainly consisted of a generator and a discriminator. The generator adopts a U-Net structure with jump connections to generate watermark-free maps based on watermarked maps, and the discriminator uses a full convolutional network based on region discrimination model to distinguish the differences between the generated watermark-free maps and real watermark-free ones. Specifically, a perceptual loss function was introduced to enhance the structural details of the generated maps. The experiments show that the proposed method can remove not only simple textual watermarks, but also colorful graphic watermarks with complex structures as well, and it does not need manual intervention and can achieve fast batch removal of a wide variety of watermarks for electronic maps. In addition, the detailed information contained in map tiles can be effectively preserved while acquiring high-quality watermark-free electronic map tiles. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Q-learning Sampling Based on Advantages 5

Deep Q-learning Sampling Based on Advantages

引用

5th International Conference on Intelligent Robotics and Control engineering, IRCE 2022

作者： Xie, Ming Ren, Xinrui Yu, Jianbo Shu, Feng Shanghai Engineering Research Center of Ultra-Precision Motion Control and Measurement Academy for Engineering and Technology Fudan University Shanghai China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China School of Microelectronics Fudan University State Key Laboratory of ASIC and System Shanghai200433 China

ISBN: (数字)9781665469951

ISBN: (纸本)9781665469951

Deep Q-learning (DQN) has shown recent success on a wide range of complicated sequential decision-making issues, especially in the classic control area. However, in most DQN training, the sampling policies, particularly the ϵ-greedy policy and its derivation rules, produce noise erroneously due to the unsteadiness and unreliability of Q values utilized for searching for optimum actions. We begin with a fundamental hypothesis: complete advantages-based exploitation may be employed to help in successful exploration, and the gap between advantages on outstanding and poor actions tends to extend during the early phases of training before stabilizing. We then present a novel DQN architecture with a superior sampling policy that is totally and directly based on advantage values. This new DQN is named A-sampling DQN, and it requires minor code changes based on the original DQN codes. In most cases, A-sampling DQN and its derivatives outperformed the traditional DQN method. © 2022 IEEE.

关键词： Deep learning

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：