检索结果-内蒙古大学图书馆

Boosting Adversarial Training with Learnable Distribution

Computers, Materials & Continua 2024年第3期78卷 3247-3265页

作者： Kai Chen Jinwei Wang James Msughter Adeke Guangjie Liu Yuewei Dai School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Intelligent Support Technology for Complex Environments Ministry of EducationNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Nanjing Center for Applied Mathematics Nanjing211135China

In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural *** training is one of the most potent methods to defend against adversarial ***,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial *** paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture *** distribution centroid is built to classify samples and constrain the distribution of the sample *** natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the *** proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial *** algorithm gradually increases the accuracy and robustness of the model by scaling ***,the proposed method outputs the predicted labels and the distance between the sample and the distribution *** distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model *** effectiveness of the proposed method is demonstrated through comprehensive experiments.

关键词： Adversarial training feature space learnable distribution distribution centroid

来源：评论

学校读者我要写书评

暂无评论

Evaluating Public Sentiments of Covid-19 Vaccine Tweets Using Machine Learning Techniques

引用

Informatica (Slovenia) 2022年第1期46卷 69-75页

作者： Akpatsa, Samuel Kofi Lei, Hang Li, Xiaoyu Obeng, Victor-Hillary Kofi Setornyo School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Province Chengdu610054 China

The quest to create a vaccine for covid-19 has rekindled hope for most people worldwide, with the anticipation that a vaccine breakthrough would be one step closer to the end of the deadly Covid-19. The pandemic has had a bearing on the use of Twitter as a communication medium to reach a wider audience. This study examines Covid-19 vaccine-related discussions, concerns, and Twitter-emerged sentiments about the Covid-19 vaccine rollout program. Natural Language Processing (NLP) techniques were applied to analyze Covid-19 vaccine-related tweets. Our analysis identified popular n-grams and salient themes such as "vaccine health information," "vaccine distribution and administration," "vaccine doses required for immunity," and "vaccine availability." We apply machine learning algorithms and evaluate their performance using the standard metrics, namely accuracy, precision, recall, and f1-score. Support Vector Machine (SVM) classifier proves to be the best fit on the dataset with 84.32% accuracy. The research demonstrates how Twitter data and machine learning methods can study the evolving public discussions and sentiments concerning the Covid-19 vaccine rollout program. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Breaking the energy-eficiency barriers for smart sensing applications with “Sensing with Computing” architectures

引用

science China(information sciences) 2023年第10期66卷 162-177页

作者： Xinghua YANG Zheyu LIU Kechao TANG Xunzhao YIN Cheng ZHUO Qi WEI Fei QIAO Department of Electronic Engineering Tsinghua University College of Science Beijing Forestry University Make Sens AI Technology (Beijing) Co. Ltd. School of Integrated Circuits Peking University College of Information Science and Electronic Engineering Zhejiang University

With the developing technologies of artificial intelligence and the Internet of Things, intelligent IoT(iIoT) is prevailing currently. Design and implementation of integrated IoT nodes with continuous perception capability are indispensable to realize various smart terminal devices, which would also be vital to reduce the power consumption, improve the real-time performance, and enhance the security/privacy of the IoT system. In this paper, we present the architecture of “Sensing with Computing” and its chip design for smart sensing applications, which would support multi-modal perception signal processing with multi-dimension extension ability. Specially, we explore the analog/mixed-signal circuit designs and algorithm-hardware codesign methodologies for perception signal processing, and we also study the multi-modal integration of novel sensors and their interface technologies. Additionally, some multi-modal smart sensing systems with “Sensing+Computing in Memory” mixed-signal chips would be fabricated, which would support typical always-on smart sensing tasks.

关键词： low power consumption circuit design sensing with computing smart sensors edge computing multi-modal sensing

来源：评论

学校读者我要写书评

暂无评论

Remote Charging for Cardiac Pacemakers Using Transcutaneous Optical Energy Transmission System

引用

Sensors and Materials 2024年第8期36卷 3335-3350页

作者： Yang, Shang-Kuo Chen, Chia-Hong Zhu, Yong-Jun Chen, Kai-Jung Department of Mechanical Engineering National Chin Yi University of Technology Taichung41170 Taiwan School of Electronic and Information Engineering Suzhou University of Science and Technology Jiangsu Suzhou215009 China

For cardiopathy patients with an implanted cardiac pacemaker, supplying power to the pacemaker is a challenging problem. In this study, we aim to design a transcutaneous optical energy transmission system that transmits optical energy from an optical-energy-generating circuit to a receiving circuit in a human body through the skin to charge the pacemaker’s battery such that the battery supplies power to the pacemaker continuously. We use 0.5-mm-thick pigskin to imitate human skin tissue. The light source of the system is a halogen lamp and the receiver is a solar cell. The beam emitted by a the halogen lamp is transmitted to the solar cell through the skin generating a photovoltaic effect so as to charge the rechargeable button battery. As optical energy is received by a four-solar-cell module, we adopt a Zener voltage regulation circuit and a pure resistance circuit to charge the battery. Experimental data show that if a four-solar-cell module is used to charge a battery with the voltage regulation circuit, the battery after 62 h of charging stores enough power to operate the pacemaker for 20–35 days. On the other hand, charging the battery using the pure resistor circuit can reduce the charging time from 62 h to 14 h for the same number of operation days. If the number of solar cells in parallel is increased to 12, the charging time for the same number of operation days can be shortened from 14 h to 12 h with the pure resistance circuit. As a result, transcutaneous remote charging is achieved. Approaches to shorten the charging time and future works are proposed as well. © MYU K.K.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

FairCoRe: Fairness-Aware Recommendation Through Counterfactual Representation Learning

引用

IEEE Transactions on Knowledge and Data engineering 2025年第7期37卷 4049-4062页

作者： Bin, Chenzhong Liu, Wenqiang Zhang, Feng Chang, Liang Gu, Tianlong Guilin University of Electronic Technology School of Computer Science and Information Security Guilin541004 China Guilin University of Electronic Technology School of Business Guilin541004 China Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software Guilin541004 China Jinan University College of Cyber Security Engineering Research Center of Trustworthy AI Ministry of Education Guangzhou510632 China

Eliminating bias from data representations is crucial to ensure fairness in recommendation. Existing studies primarily focus on weakening the correlation between data representations and sensitive attributes, yet may inadvertently steer the user representations toward another potential bias direction of the target attribute. Furthermore, they often overlook the impact of user preferences on capturing sensitive information, incurring inadequate bias elimination. In this paper, we propose a Fair Counterfactual Representations (FairCoRe) learning framework, which aims to ensure the neutrality of representations among all bias directions. First, we intervene on sensitive attributes to construct a counterfactual scenario. Then, two opposing attribute prediction tasks are respectively performed in ground-truth and counterfactual scenarios to encode sensitive information along different bias directions. Second, we design a bias-aware enhancement learning method that quantifies the respective correlation of user preferences and sensitive attributes to enhance sensitive information encoding. Finally, we introduce two mutual information optimization methods that optimize the representations to capture users’ interests and disentangle sensitive factors. Moreover, we propose an attribute neutralization strategy that refines the learned representations, ensuring sensitive attribute neutrality. Extensive experiments demonstrate that our method achieves the optimal fairness and competitive accuracy compared to state-of-the-art methods. © 1989-2012 IEEE.

关键词： Accuracy Mutual information Correlation Data Visualization Medical Services Training Measurement Disentangled Representation Learning Semantics Recommender Systems Recommender System Recommendation Fairness Representation Learning Counterfactual Representations Potential Bias Mutual information User Preferences Sensitive Attributes Counterfactual Scenario User Representation Time Complexity Generative Adversarial Networks Learning Objectives Demographic Groups Baseline Methods Recommender Systems Minimum Method Prediction Loss Preference information Graph Convolution User Side Recommendation Model Counterfactual Thinking Maximum Mutual information Representation Learning Methods Maximization Method Recommendation Accuracy Recommendation Method Recommendation Task Notions Of Fairness Negative Samples Mutual information Estimation

来源：评论

学校读者我要写书评

暂无评论

RM-CSTV:An effective high-resolution method of non-line-of-sight millimeter-wave radar 3-D imaging

引用

National science Open 2024年第5期3卷 36-52页

作者： Xinyuan Liu Shunjun Wei Wei Pu Xiang Cai Yanbo Wen Shisheng Guo Lingjiang Kong Xiaoling Zhang School of Information and Communication Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Non-line-of-sight(NLOS)imaging is a novel radar sensing technology that enables the reconstruction of hidden ***,it may suffer from synthetic aperture length reduction caused by ambient *** this study,a complex total variation(CTV)regularization-based sparse reconstruction method for NLOS three-dimensional(3-D)imaging by millimeter-wave(mm W)radar,named RM-CSTV method,is proposed to improve imaging quality and *** this scheme,the NLOS imaging model is first introduced,and associated geometric constraints for NLOS objects are ***,an effective high-resolution NLOS imaging method based on the range migration(RM)kernel and complex sparse joint total variation constraint,dubbed as modified RM-CSTV,is proposed for 3-D high-resolution imaging with edge *** experiments with multi-type NLOS targets show that the proposed RM-CSTV method can provide effective and high-resolution NLOS targets 3-D imaging.

关键词： NLOS imaging 3-D-SAR 3-D imaging sparse reconstruction

来源：评论

学校读者我要写书评

暂无评论

Flexible Inverse Design of Microwave Filter Customized on Demand With Wavelet Transform Deep Learning

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 806-817页

作者： Xu, Kuiwen Wang, Jianguo Cai, Jialin Ma, Xuetiao Lv, Qinyi Chen, Shichang Liu, Jie Liu, Jun Hangzhou Dianzi University Innovation Center for Electronic Design Automation Technology The Key Laboratory of RF Circuits and Systems Ministry of Education Hangzhou310018 China Chang'an Campus Northwestern Polytechnical University School of Electronic Information Xi'an710060 China University of Electronic Science and Technology of China School of Electronic Science and Engineering Chengdu610054 China Information Science Academy China Electronics Technology Group Corporation Beijing100846 China

Artificial intelligence (AI) techniques are increasingly being used for the inverse design of microwave devices. However, several challenges, including intensive computation costs for training samples, high-dimensional data, nonuniformity, and low-quality samples in the design space, can negatively impact the final modeling performance. To alleviate these issues, a high-quality sampling inverse design scheme incorporating wavelet transform deep learning (HQS-WTDL) is proposed to achieve customized, automated microwave filter design. In the forward simulation-based sampling, particle swarm optimization (PSO) is used to tentatively select rule-defined samples. Multilabel synthetic minority over-sampling technique (MLSMOTE) is then applied to enlarge the training samples and improve their uniformity in the design space. An inverse modeling approach using neural networks to map the nonlinear relationship between a given set of S-parameters and required filter structural parameters is presented. Given that the dimension of the S-parameters is much higher than that of the structure parameters, the corresponding neural network used in this approach is deep and complex, with multiple layers and neurons. To reduce the number of input variables, the S-parameters are subjected to wavelet transformation, allowing for more efficient representation by the neural network. The proposed method is validated using a band-pass microstrip hairpin filter as an example. Results demonstrate that the proposed approach achieves better modeling effectiveness and inverse design efficiency than conventional methods. In addition, the proposed method allows for fast customization of device parameters, such as center frequencies and bandwidths with good prediction accuracy. © 1982-2012 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

LPT-One and BFD-One Search Algorithms for Load Balance and Bin-Packing of Cloud Computing 9

LPT-One and BFD-One Search Algorithms for Load Balance and B...

引用

9th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2023

作者： Zhou, Guangyao Tian, Wenhong Buyya, Rajkumar University of Electronic Science and Technology of China School of Information and Software Engineering China The University of Melbourne School of Computing and Information Systems Australia

ISBN: (纸本)9798350304428

Cloud computing contains large-scale tasks and resources. Currently, the local search is a considerable choice in ensuring both computational complexity and optimization. Based on our previous research on multi-route search algorithm to reduce makespan, we apply BFDO and LPTO algorithms to address load balancing and bin-packing problems. Through abundant experiments, we validate the superiority of our proposed BFDO and LPTO. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Adversarial Domain Adaptation for Non-Intrusive LOAD Monitoring 20

Adversarial Domain Adaptation for Non-Intrusive LOAD Monitor...

引用

20th International Computer Conference on Wavelet Active Media technology and information Processing, ICCWAMTIP 2023

作者： Bongyi, Gao Bei, Hui School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9798350318982

Non-Intrusive Load Monitoring (NILM), known as energy disaggregation, is a method for determining the usage of separated devices by analyzing the overall energy consumption of an entire household. Understanding individual appliance energy consumption is crucial for customers to effectively manage usage and plan demand response programs. Recent advancements in data-driven methods have demonstrated promising performance in NILM. However, these methods rely on massive labeled data and would be dramatically degraded in novel environments. This paper presents ADAED, an energy disaggregation algorithm based on adversarial domain adaptation to monitor the loads of an unlabeled target domain by learning shared representations from a related source domain. Through the application of a sequence-to-point architecture and shared representations, ADAED can achieve more accurate predictions. Extensive experiments on three open benchmarks verify that our method can achieve better results than existing methods. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Revealing Security Flaws in Cross-Modal Retrieval Models through Video Poisoning

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 6184-6194页

作者： Jin, Ming Hu, Wenbo Hong, Richang Zhu, Lei Hefei University of Technology School of Computer and Information Hefei China Data Space Research Institute Hefei Comprehensive National Science Center China Tongji University School of Electronic and Information Engineering Shanghai China

Video-text cross-modal retrieval is widely studied to improve retrieval accuracy. However, the security of video-text cross-modal retrieval models receives little attention. If attackers exploit the security vulnerabilities in these models, it poses a significant threat to the retrieval models. Thus, identifying security flaws in video-text cross-modal retrieval models becomes the focus of our research. We are the first to design a video poisoning model to uncover security vulnerabilities in retrieval models. Existing poisoning models have certain limitations when it comes to exploiting vulnerabilities in retrieval models. These include failing to comprehensively embed malicious information into the original video and being unable to maintain visual consistency between the original and poisoned videos. These limitations can result in unsuccessful attacks on retrieval models and an inability to effectively identify security flaws within them. To address these shortcomings, we design an efficient poisoning model that embeds malicious information thoroughly into the original clean data to attack video-text cross-modal retrieval models. We are the first to use a poisoning model to attack retrieval models, thereby uncovering their security vulnerabilities. Second, we introduce a bi-level poisoning module to ensure that malicious information is thoroughly embedded into the original video, thereby enhancing the attack capability of the poisoning model. Finally, we design an adversarial module to improve visual consistency between the original and poisoned videos, thus enhancing the concealment of malicious information within the training data of retrieval models. Our poisoning model can identify security flaws in video-text cross-modal retrieval models, providing insights into improving the security of retrieval models. The effectiveness of our model is validated on the MSR-VTT, LSMDC, and MSVD datasets. © 1991-2012 IEEE.

关键词： Content based retrieval

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：