检索结果-内蒙古大学图书馆

Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery

IEEE Access 2025年 13卷 103880-103897页

作者： Ching-Chun Chang Kai Gao Shuying Xu Anastasia Kordoni Christopher Leckie Isao Echizen Information and Society Research Division National Institute of Informatics Tokyo Japan Department of Information Engineering and Computer Science Feng Chia University Taichung Taiwan Department of Psychology Lancaster University Lancaster U.K. Department of Computing and Information Systems University of Melbourne Melbourne VIC Australia Graduate School of Information Science and Technology University of Tokyo Tokyo Japan School of Multidisciplinary Sciences Graduate University for Advanced Studies (SOKENDAI) Kanagawa Japan

Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A backdoor attack involves the clandestine infiltration of a trigger during the learning process, metaphorically analogous to hypnopaedia, where ideas are implanted into a subject’s subconscious mind under the state of hypnosis or unconsciousness. When activated by a sensory stimulus, the trigger evokes a conditioned reflex that directs a machine to mount a predetermined response. In this study, we propose a cybernetic framework for constant surveillance of backdoor threats, driven by the dynamic nature of untrustworthy data sources. We develop a self-aware unlearning mechanism to autonomously detach a machine’s behaviour from the backdoor trigger. Through reverse engineering and statistical inference, we detect deceptive patterns and estimate the likelihood of backdoor infection. We employ model inversion to elicit artificial mental imagery, using stochastic processes to disrupt optimisation pathways and avoid convergent but potentially flawed patterns. This is followed by hypothesis analysis, which estimates the likelihood of each potentially malicious pattern as the true trigger and infers the probability of infection. The primary objective of this study is to maintain a stable state of equilibrium between knowledge fidelity and backdoor vulnerability.

关键词： Data models Soft sensors Vehicle dynamics Reverse engineering Predictive models Optimization Cyberspace Cybernetics Weapons Trojan horses

来源：评论

学校读者我要写书评

暂无评论

RadonPy:automated physical property calculation using all-atom classical molecular dynamics simulations for polymer informatics

引用

npj Computational Materials 2022年第1期8卷 2155-2169页

作者： Yoshihiro Hayashi Junichiro Shiomi Junko Morikawa Ryo Yoshida The Institute of Statistical Mathematics(ISM) Research Organization of Information and Systems10-3 Midori-choTachikawaTokyo190-8562Japan Department of Mechanical Engineering The University of Tokyo7-3-1 HongoBunkyoTokyo113-8656Japan Institute of Engineering Innovation The University of Tokyo2-11 YayoiBunkyo-kuTokyo113-0032Japan Department of Materials Science and Engineering School of Materials and Chemical TechnologyTokyo Institute of Technology2-12-1 OokayamaMeguro-kuTokyo152-8552Japan Research and Services Division of Materials Data and Integrated System(MaDIS) National Institute for Materials Science(NIMS)1-2-1 SengenTsukubaIbaraki305-0047Japan Department of Statistical Science School of Multidisciplinary ScienceThe Graduate University of Advanced Studies(SOKENDAI)10-3 Midori-choTachikawaTokyo190-8562Japan

The spread of data-driven materials research has increased the need for systematically designed materials property ***,the development of polymer databases has lagged far behind other material *** present RadonPy,an open-source library that can automate the complete process of all-atom classical molecular dynamics(MD)simulations applicable to a wide variety of polymeric ***,15 different properties were calculated for more than 1000 amorphous *** MD-calculated properties were systematically compared with experimental data to validate the calculation conditions;the bias and variance in the MD-calculated properties were successfully calibrated by a machine learning *** the high-throughput data production,we identified eight amorphous polymers with extremely high thermal conductivity(>0.4 W∙m^(–1)∙K^(–1))and their underlying *** to the advancement of materials informatics since the advent of computational property databases for inorganic crystals,database construction using RadonPy will promote the development of polymer informatics.

关键词： property calculation dynamics

来源：评论

学校读者我要写书评

暂无评论

A Highly-Precise Digital Wind Tunnel

A Highly-Precise Digital Wind Tunnel

引用

Consumer technology (ICCT-Pacific), International Conference on

作者： Wei-Hsin Hung Meng-Hsiun Tsai Ying-Hsuan Huang Guu-Chang Yang dept. of Electrical Engineering National Chung Hsing University Taichung Taiwan dept. of Management Information Systems National Chung Hsing University Taichung Taiwan Aeronautical Systems Research Division National Chung-Shan Institute of Science and Technology Taichung Taiwan

ISBN: (数字)9798331504120

ISBN: (纸本)9798331504137

A digital wind tunnel (WT) can learn from historical aerodynamic coefficients derived from experiments and simulations to build a prediction model. This model enables the prediction of aerodynamic coefficients without requiring additional experiments or simulations, significantly reducing their overall frequency and cost. In 2020, Huang et al. adopts multi-output back-propagation neural network (BPNN) to simultaneously predict lift coefficient and drag coefficient. However, Huang et al. does not investigate about the following issues, (1) abnormal data detection, (2) other aerodynamic coefficients, (3) overfitting problem. In order to solve these problems, this paper proposed a data-validate strategy and re-designed the single-output BPNN. Experimental results showed that both the mean square error and maximum absolute error of the proposed method is smaller than those of Huang et al. 's method.

关键词： Technological innovation Costs Wind tunnels Neural networks Mean square error methods Predictive models Aerodynamics Data models Overfitting

来源：评论

学校读者我要写书评

暂无评论

Relip: Reliable in-Band Parallel Communication for Magnetic MIMO Wireless Power Transfer System

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Xinyu Zhou, Wangqiu Zhou, Hao Jiang, Shenyao Liu, Zhi Wang, Xiaoyan Ji, Yusheng Song, Qi City University of Hong Kong Department of Computer Science Hong Kong University of Science and Technology of China School of Computer Science and Technology Hefei230027 China The University of Electro-Communications Graduate School of Informatics and Engineering Tokyo182-8585 Japan Ibaraki University Graduate School of Science and Engineering Ibaraki310-8512 Japan National Institute of Informatics Information Systems Architecture Science Research Division Tokyo101-0003 Japan

In magnetic resonant coupling (MRC) based wireless power transfer (WPT) systems, receiver (RX) feedback communication is promising to enhance the capability and efficiency of the system. Although some studies have explored in-band implementations with low overhead costs, it has not been comprehensively investigated. In this paper, we propose Relip, a Reliable layer-level in-band parallel feedback communication mechanism for MIMO MRC-WPT systems, which addresses the impact of RX-RX couplings (i.e., non-negligible interference from strong couplings and positive effects of relay phenomenon), and provides a theoretical analysis of communication reliability. Technically, we first devise an On-Off based two-phase modulation mechanism to achieve RX identification and dependency detection under relay phenomenon. Then, we utilize observed channel decomposability to collect group-level power transfer channel conditions for eliminating the interference caused by strong RX-RX couplings. Furthermore, we perform RX selection to optimize the trade-off between communication reliability and time overhead. We design and implement the Relip prototype and conduct extensive experiments. The results validate the effectiveness of our mechanism, i.e., Relip can provide ≥99% average decoding accuracy for concurrent feedback communication of 14 devices, achieving an 18.31% improvement compared to the state-of-the-art solution. © 2002-2012 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphs

arXiv

引用

arXiv 2024年

作者： Zhang, Tianyu Hou, Chengbin Jiang, Rui Zhang, Xuegong Zhou, Chenghu Tang, Ke Lv, Hairong The Ministry of Education Key Laboratory of Bioinformatics Bioinformatics Division Beijing National Research Center for Information Science and Technology Department of Automation Tsinghua University Beijing100084 China The School of Computer Science and Engineering Fuyao Institute of Technology Fuzhou350109 China The State Key Laboratory of Resources and Environmental Information Systems Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China The Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Fuzhou Institute of Data Technology Fuzhou350200 China

Node Importance Estimation (NIE) is a task of inferring importance scores of the nodes in a graph. Due to the availability of richer data and knowledge, recent research interests of NIE have been dedicating to knowledge graphs for predicting future or missing node importance scores. Existing state-of-the-art NIE methods train the model by available labels, and they consider every interested node equally before training. However, the nodes with higher importance often require or receive more attention in real-world scenarios, e.g., people may care more about the movies or webpages with higher importance. To this end, we introduce Label Informed ContrAstive Pretraining (LICAP) to the NIE problem for being better aware of the nodes with high importance scores. Specifically, LICAP is a novel type of contrastive learning framework that aims to fully utilize the continuous labels to generate contrastive samples for pretraining embeddings. Considering the NIE problem, LICAP adopts a novel sampling strategy called top nodes preferred hierarchical sampling to first group all interested nodes into a top bin and a non-top bin based on node importance scores, and then divide the nodes within top bin into several finer bins also based on the scores. The contrastive samples are generated from those bins, and are then used to pretrain node embeddings of knowledge graphs via a newly proposed Predicate-aware Graph Attention Networks (PreGAT), so as to better separate the top nodes from non-top nodes, and distinguish the top nodes within top bin by keeping the relative order among finer bins. Extensive experiments demonstrate that the LICAP pretrained embeddings can further boost the performance of existing NIE methods and achieve the new state-of-the-art performance regarding both regression and ranking metrics. The source code for reproducibility is available at https://***/zhangtia16/LICAP Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Revisiting At-a-Station Hydraulic Geometry Using Discharge Observations and Satellite-Derived River Widths

Journal of Remote Sensing

引用

Journal of Remote Sensing 2024年第1期4卷 178-190页

作者： Zimin Yuan Peirong Lin Xiwei Guo Kai Zhang Hylke E.Beck Institute of Remote Sensing and Geographic Information Systems School of Earth and Space SciencesPeking UniversityBeijingChina Department of Geosciences The Pennsylvania State UniversityUniversity ParkPA 16802USA Geovis Environment Technology Co.Ltd. BeijingChina Physical Science and Engineering Division King Abdullah University of Science and TechnologyThuwalSaudi Arabia

The power-function exponent b of at-a-station hydraulic geometry(AHG)depicts the temporal response of river hydraulic parameters to changing discharge and is crucial for hydraulic modeling,habitat assessment,and river ***,previous research,limited by field measurements,offers only a fragmentary understanding of the AHG exponent b in confined ***,it remains challenging to establish the correlation between b and the climatic regime of a *** offer a more comprehensive scope of AHG,this study assesses the width-discharge AHG exponents of 1,568 river reaches by pairing multi-temporal river width data from 1.19 million Landsat images with discharge observations from>17,000 gauge stations *** results show that b has a median value of 0.213,consistent with values reported in previous regional studies,but it exhibits complex relationships with 3 spatial dimensions-latitude,elevation,and drainage *** further analyze the spatial variations in b against>200 physiographic and climatic factors,and find that reaches characterized by cohesive soil,high forest coverage,and less anthropogenic influences typically exhibit lower values of b,indicating a weaker response of width to discharge *** labeling 4 planimetric river morphologic types globally,we show that braided reaches exhibit the highest median of b,followed by straight,anabranching,and meandering *** differences can be well explained by the climatic conditions of the river reaches as shown on the Budyko *** study lays the foundation for AHG research in ungauged regions using satellite remote sensing,expanding global hydraulic data and enhancing the understanding of the spatial variability and influencing factors of hydraulic geometry worldwide.

关键词： field measurementsoffers satellite derived river widths hydraulic modelinghabitat assessmentand spatial variability discharge power function exponent b river hydraulic parameters hydraulic geometry

来源：评论

学校读者我要写书评

暂无评论

Toward efficient resource utilization at edge nodes in federated learning

arXiv

引用

arXiv 2023年

作者： Alawadi, Sadi Ait-Mlouk, Addi Toor, Salman Hellander, Andreas Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden School of Informatics University of Skövde Skövde Sweden Department of Information Technology Division of Scientific Computing Uppsala University Sweden Scaleout Systems Sweden

Federated learning (FL) enables edge nodes to collaboratively contribute to constructing a global model without sharing their data. This is accomplished by devices computing local, private model updates that are then aggregated by a server. However, computational resource constraints and network communication can become a severe bottleneck for larger model sizes typical for deep learning (DL) applications. Edge nodes tend to have limited hardware resources (RAM, CPU), and the network bandwidth and reliability at the edge is a concern for scaling federated fleet applications. In this paper, we propose and evaluate a FL strategy inspired by transfer learning in order to reduce resource utilization on devices, as well as the load on the server and network in each global training round. For each local model update, we randomly select layers to train, freezing the remaining part of the model. In doing so, we can reduce both server load and communication costs per round by excluding all untrained layer weights from being transferred to the server. The goal of this study is to empirically explore the potential trade-off between resource utilization on devices and global model convergence under the proposed strategy. We implement the approach using the FL framework FEDn. A number of experiments were carried out over different datasets (CIFAR-10, CASA, and IMDB), performing different tasks using different DL model architectures. Our results show that training the model partially can accelerate the training process, efficiently utilizes resources on-device, and reduce the data transmission by around 75% and 53% when we train 25%, and 50% of the model layers, respectively, without harming the resulting global model accuracy. Furthermore, our results demonstrate a negative correlation between the number of participating clients in the training process and the number of layers that need to be trained on each client’s side. As the number of clients increases, there is a decrease

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Characterization of Systematic Bias in ALOS-2 Multilooked Interferograms

Characterization of Systematic Bias in ALOS-2 Multilooked In...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Ryu Sugimoto Yu Morishita Masanobu Shimada Ryo Natsuaki Chiaki Tsutsumi Ryosuke Nakamura Toru Kouyama Digital Architecture Research Center National Institute of Advanced Industrial Science and Technology Japan Division of Architectural Civil and Environmental Engineering School of Science and Engineering Tokyo Denki University Japan Department of Electrical Engineering and Information Systems The University of Tokyo Japan

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Interferometric SAR time series analysis using multilooked interferograms has measured ground deformation with high accuracy over large areas, but is known to be contaminated by a systematic bias when using only short-term interferograms. This bias, also referred to as a "fading signal", has been investigated using the abundant time series data from Sentinel-1 C-band SAR, and soil moisture and biomass changes have been suggested as two possible causes for the observed bias. Several correction methods have been proposed to mitigate the phase bias, assuming a periodic observation strategy. The phase bias is supposed to increase with the wavelength, but the bias in ALOS-2 L-band SAR has not been investigated in detail because the data distribution policy restricts its users. In addition, these correction methods are not suitable for the infrequently observed data such as ALOS-2. In this paper, we investigated the systematic bias in ALOS-2 multilooked interferograms with respect to various interferometric pairs. We also corrected the phase bias using the noise-filtering technique. The bias in ALOS-2 multilooked interferograms showed >3 mm/year with an average temporal baseline of 144 days, which is equivalent to that of Sentinel-1 with the temporal baseline of 78 days. That is, the bias effect toward the temporal baseline was larger in ALOS-2 than in Sentinel-1. The noise-filtering technique could mitigate the bias with less pairs regardless of land-use.

关键词： Fading channels Systematics Soil measurements Time series analysis Soil moisture Sentinel-1 Geoscience and remote sensing

来源：评论

学校读者我要写书评

暂无评论

POSSIBILITIES AND LIMITS OF DIAGNOSTIC METHODS FOR POWER TRANSFORMERS IN SERVICE 23

POSSIBILITIES AND LIMITS OF DIAGNOSTIC METHODS FOR POWER TRA...

引用

23rd International Symposium on High Voltage Engineering, ISH 2023

作者： Schreiter, Sebastian Lohmeyer, Holger Werle, Peter HTWK Leipzig Leipzig University of Applied Science Faculty of Electrical Engineering and Information Technology Department of Electric Power Systems Germany FTZ Leipzig e. V. Research and Transfer Centre The HTWK Leipzig Germany Hitachi Energy Transformer Service Centre Halle Oil Lab. Halle Germany Leibniz University Hannover Institute of Electric Power Systems Division of High Voltage Engineering and Asset Management Schering-Institute Hannover Germany

ISBN: (纸本)9781839539954

The detection of possible faults in an early state is of elementary interest to operators of transformers in order to avoid unplanned outages. Such unplanned failures lead to the interruption of energy supply or even loss of production. Therefore, a large number of diagnostic methods are available such as oil analysis and electrical measurements up to high-voltage tests on site. For this reason, it is necessary for operators to select the meaningful diagnostic procedures in each case. In this contribution investigation are discussed concerning the question which diagnostic procedures or which combination of procedures can be used to detect faults reliable. This was done based on a large population of transformers in service. © The Institution of Engineering & technology 2023.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Risk-Averse Learning with Non-Stationary Distributions

arXiv

引用

arXiv 2024年

作者： Wang, Siyi Wang, Zifan Yi, Xinlei Zavlanos, Michael M. Johansson, Karl H. Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich80333 Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Lab for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States Mechanical Engineering and Material Science Duke University DurhamNC27708 United States

Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time. In such cases, it is favorable to adopt a strategy that minimizes the negative impact of change to avoid potentially risky situations. In this paper, we investigate risk-averse online optimization where the distribution of the random cost changes over time. We minimize risk-averse objective function using the Conditional Value at Risk (CVaR) as risk measure. Due to the difficulty in obtaining the exact CVaR gradient, we employ a zeroth-order optimization approach that queries the cost function values multiple times at each iteration and estimates the CVaR gradient using the sampled values. To facilitate the regret analysis, we use a variation metric based on Wasserstein distance to capture time-varying distributions. Given that the distribution variation is sub-linear in the total number of episodes, we show that our designed learning algorithm achieves sub-linear dynamic regret with high probability for both convex and strongly convex functions. Moreover, theoretical results suggest that increasing the number of samples leads to a reduction in the dynamic regret bounds until the sampling number reaches a specific limit. Finally, we provide numerical experiments of dynamic pricing in a parking lot to illustrate the efficacy of the designed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

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：