检索结果-内蒙古大学图书馆

Effective and Imperceptible Adversarial Textual Attack Via Multi-objectivization

ACM Transactions on Evolutionary Learning and Optimization 2024年第3期4卷 1-23页

作者： Liu, Shengcai Lu, Ning Hong, Wenjing Qian, Chao Tang, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen College of Engineering South Tower 1088 Xueyuan Avenue Guangdong Shenzhen518055 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong999077 Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen 10F Zhizhen Building Canghai Campus 3688 Nanhai Avenue Guangdong Shenzhen China National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University Nanjing International College Area Xianlin Campus 163 Xianlin Avenue Jiangsu Nanjing China

The field of adversarial textual attack has significantly grown over the past few years, where the commonly considered objective is to craft adversarial examples (AEs) that can successfully fool the target model. However, the imperceptibility of attacks, which is also essential for practical attackers, is often left out by previous studies. In consequence, the crafted AEs tend to have obvious structural and semantic differences from the original human-written text, making them easily perceptible. In this work, we advocate leveraging multi-objectivization to address such an issue. Specifically, we reformulate the problem of crafting AEs as a multi-objective optimization problem, where the attack imperceptibility is considered as an auxiliary objective. Then, we propose a simple yet effective evolutionary algorithm, dubbed HydraText, to solve this problem. HydraText can be effectively applied to both score-based and decision-based attack settings. Exhaustive experiments involving 44,237 instances demonstrate that HydraText consistently achieves competitive attack success rates and better attack imperceptibility than the recently proposed attack approaches. A human evaluation study also shows that the AEs crafted by HydraText are more indistinguishable from human-written text. Finally, these AEs exhibit good transferability and can bring notable robustness improvement to the target model by adversarial training. © 2024 Copyright held by the owner/author(s).

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Biogas Fermentation Monitoring Research Based on Borderline-SMOTE Algorithm and Stacking Ensemble Learning 13

Biogas Fermentation Monitoring Research Based on Borderline-...

引用

13th International Conference of Information and Communication Technology, ICTech 2024

作者： Xiu, Pengfei Fu, Lijun Sun, Yukun Wang, Hongliang Li, Xuerao Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shandong University Big Data Technology and Cognitive Intelligence Laboratory University of Chinese Academy of Sciences Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China

ISBN: (纸本)9798350376258

Anaerobic fermentation is the most important link to gas production, this paper solves the current problem with the help of the current complete machine learning technology, combining perception and intelligent processing, intelligent processing of information, and derive a decision-making basis for its control or management [1]. Aiming at the current problems of the anaerobic fermentation process in biogas engineering, the system design was carried out, and the anaerobic fermentation process of biogas and its main influencing factors were investigated, and the monitoring parameters of the system were selected to be temperature, PH value, liquid level and redox potential [2]. Previous studies are mainly based on a single prediction model, which leads to poor generalization ability of the model. In this study, unbalanced samples are handled by Borderline-SMOTE algorithm. Based on the Stacking integrated learning approach, a common single prediction model is used to construct a combined prediction model. The accuracy, precision, recall, F1 score and area under the ROC curve are used to evaluate the advantages and disadvantages of the combined prediction model over the single prediction model. ©2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

The Impact of Working From Home on Employee Collaboration, Happiness, and Career Growth: A Statistical Analysis

The Impact of Working From Home on Employee Collaboration, H...

引用

International Conference on Web Research (ICWR)

作者： Zahra Ghaderpour Majid Joudaki Mehdi Imani Department of Engineering Ayatollah Boroujerdi University Boroujerd Iran Department of Computer Engineering Faculty of Engineering Ayatollah Boroujerdi University Boroujerd Iran Department of Computer and System Sciences Stockholm University Stockholm Sweden

ISBN: (数字)9798331508913

ISBN: (纸本)9798331508920

The COVID-19 pandemic significantly accelerated the adoption of working from home, raising concerns about its impact on employee collaboration, happiness (well-being), and career growth. This study investigates the correlations between working from home and three key factors: collaboration challenges, employees' happiness about household size, and promotion opportunities. Using a publicly available dataset containing 1,512 responses from workers in New South Wales, Australia, statistical analyses, including Pearson correlation and p-values, were applied to examine these relationships. The findings indicate a statistically significant positive correlation ( $\mathrm{r}=0.23, \mathrm{p}<0.05$ ) between working from home and collaboration challenges, suggesting that remote work may introduce obstacles to teamwork. Additionally, a significant negative correlation ( $\mathrm{r}=-0.06, \mathrm{p}<0.05$ ) was found between working from home and promotion chances, implying that employees working from home may experience slightly reduced career advancement opportunities. However, no significant correlation ( $\mathrm{r}=0.04, \mathrm{p}=0.161$ ) was observed between household size and employee happiness while working from home. These results suggest that remote work offers flexibility but may challenge collaboration and career growth. The study provides empirical evidence to guide organizations in refining working from home policies that balance employee happiness, collaboration efficiency, and career growth.

关键词： COVID-19 Correlation engineering profession Statistical analysis Pandemics Collaboration Organizations Remote working Teamwork Sustainable development

来源：评论

学校读者我要写书评

暂无评论

LSTM & MACD Approach: Prediction and Analysis of Stock Market

LSTM & MACD Approach: Prediction and Analysis of Stock Marke...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： L. Jerart Julus S.N. Syed Naweed D. Aadhavan S. Sudhakara Sankar R.S. Rampriya T. Kavitha Department of IT School of Computer Science Engineering and Information System Vellore Institute of Technology Vellore India School of Computer Science Engineering and Information System Vellore Institute of Technology Vellore India Department of ECE Vel Tech University Chennai Tamilnadu India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Investing and researchers alike have long been fascinated by the volatile and dynamic nature of financial markets. For the prediction and analysis of stock market movements, we present a hybrid approach that combines Long Short-Term Memory (LSTM) and Moving Average Convergence Divergence (MACD). Leveraging the power of deep learning and technical analysis, this hybrid model offers a comprehensive solution for forecasting and understanding market trends. The LSTM component, a type of recurrent neural network, provides the model with the ability to capture and learn intricate patterns in historical stock price data, thus enabling accurate short and long-term predictions. The MACD indicator, a widely used tool in technical analysis, supplements the LSTM by identifying potential reversal points and providing valuable insights into market momentum. A hybrid approach will provide a stronger and more reliable forecasting framework by combining both LSTM and MACD. To validate the model's efficacy, we apply it to historical stock market data and conduct a thorough analysis of its predictive performance. Our findings suggest that the Hybrid LSTM-MACD approach outperforms traditional methods and offers a promising solution for investors, traders, and financial analysts seeking to navigate the complex world of stock market trading.

关键词： Analytical models Accuracy Predictive models Market research Data models Internet Stock markets Forecasting Long short term memory Convergence

来源：评论

学校读者我要写书评

暂无评论

Evaluation of an Intelligent Controller for Electric Vehicle Charging with Vienna Rectifier Topology

Evaluation of an Intelligent Controller for Electric Vehicle...

引用

International Conference on Power Electronic Drives

作者： Adithya Lingadahalli Nima Tashakor Hans-Joerg Wiehoff Hui Wang Stefan Goetz System Engineering Power Electronics Vitesco Technologies Regensburg Germany Electrical and Computer Engineering Department Duke University Durham USA Electrical and Computer Engineering Duke University Durham USA

ISBN: (数字)9798350372472

ISBN: (纸本)9798350372489

The Vienna rectifier is a widely used topology in a variety of industrial applications, including electric vehicle (EV) charging. Although conventional control approaches exist, the nonlinear and highly dynamic nature of the Vienna rectifier as well as many existing uncertainties within the system hinder the development of a performant controller based on classic control theory. This paper proposes a model-free controller based on reinforcement learning (RL) to optimize the performance of the DC-link voltage control loop with concurrent regulation of the power factor. We developed a state-space model of the Vienna rectifier in MATLAB/Simulink and a classical proportional-integral (PI) controller for quantitative comparison. The RL controller's ability to handle system nonlinearities and component uncertainties, such as inductor and capacitor tolerances, enables it to outperform classical control strategies. Furthermore, this paper benchmarks multiple RL-based algorithms including deep deterministic policy gradient (DDPG) as well as twin delayed DDPG (TD3) in the voltage control loop. The results demonstrate that TD3 can reduce 2.5 percent voltage ripple and has a shorter settling time of 0.75 s at the cost of higher computational requirements.

关键词： Reactive power PI control Uncertainty Rectifiers Reinforcement learning Electric vehicle charging Regulation Topology Voltage control Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Detecting Rises in SBP from PPG for Identifying Autonomic Dysreflexia

Detecting Rises in SBP from PPG for Identifying Autonomic Dy...

引用

2023 IEEE Biomedical Circuits and systems Conference, BioCAS 2023

作者： Wang, Weinan Kilgore, Kevin L. Mohseni, Pedram Najafizadeh, Laleh Rutgers University Department of Electrical and Computer Engineering PiscatawayNJ United States Case Western Reserve University and the MetroHealth System Department of Physical Medicine & Rehabilitation ClevelandOH United States Case Western Reserve University Department of Electrical Computer and Systems Engineering ClevelandOH United States

ISBN: (纸本)9798350300260

Autonomic dysreflexia (AD) is a life-threatening and prevalent post-secondary health condition affecting individuals with spinal cord injury (SCI). Reliable and timely identification of AD requires continuous monitoring of changes in the blood pressure (BP), and alarming the patient of rapid BP elevations. However, conventional methods for identifying AD, including clinical observation and patient's self-report, lack timeliness in addressing the immediate threat of acute hypertension, leading to cardiovascular damages in SCI patients. To address this issue, we target the problem of detecting onsets of rapid systolic BP (SBP) elevations from photoplethysmogram (PPG) signals, and present a batched Residual Network-Long Short Term Memory (ResNet-LSTM) deep learning model as a solution. Results indicate that the model achieves an accuracy of 74.38% and F-1 score of 72.99% on 356 leave-out testing subjects. With only one sensor required for providing input signals, the proposed method holds promise for implementing low-cost continuous monitoring systems, for the timely detection of onsets of AD in SCI patients. © 2023 IEEE.

关键词： Autonomic Dysreflexia Blood Pressure Convolutional Neural Networks (CNN) Cuffless Blood Pressure Monitoring Photo-plethysmography (PPG) Spinal Cord Injury

来源：评论

学校读者我要写书评

暂无评论

GNN-Assisted BiG-AMP: Joint Channel Estimation and Data Detection for Massive MIMO Receiver

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 4631-4646页

作者： Liu, Zishen Wu, Nan He, Dongxuan Yuan, Weijie Li, Yonghui Quek, Tony Q. S. School of Information and Electronics Beijing Institute of Technology Beijing100081 China School of System Design and Intelligent Manufacturing Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China School of Electrical and Information Engineering The University of Sydney SydneyNSW2008 Australia Singapore University of Technology and Design 487372 Singapore Department of Electronic Engineering Kyung Hee University Yongin17104 Korea Republic of

In this paper, we develop a graph neural network (GNN)-assisted bilinear inference approach to enhance the receiver performance of the MIMO system through message passing-based joint channel estimation and data detection (JCD). Specifically, based on the bilinear generalized approximate message passing (BiG-AMP) framework and conditional correlation of signal, we propose a GNN-assisted BiG-AMP (GNN-BiGAMP) approach, which integrates a GNN module into the data-detection-loop to compensate the inaccurate marginal likelihood approximation. By leveraging the coupling between the channel and received symbols, a bilinear GNN-assisted BiG-AMP (BiGNN-BiGAMP) JCD receiver is further proposed. This method incorporates two GNNs with similar graph representation into the bilinear posterior estimation loops, which not only compensates for approximation errors but also alleviates performance loss due to premature variance convergence, thereby enhancing the receiver performance significantly. To fully exploit the supervised information from channel estimation and data detection, we propose a multitask learning based training scheme, which coordinates GNNs with different tasks in two loops. Simulation results show that our proposed GNN-assisted JCD receivers significantly outperform other JCD counterparts in terms of both channel estimation and data detection. © 2025 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Coarse to Fine Detection Method for Prohibited Object in X-ray Images Based on Progressive Transformer Decoder 24

A Coarse to Fine Detection Method for Prohibited Object in X...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ma, Chunjie Du, Lina Gao, Zan Zhuo, Li Wang, Meng Shandong Jinan China School of Computer Science and Technology Shandong Jianzhu University Shandong Jinan China Faculty of Information Technology Beijing University Of Technology Beijing China School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9798400706868

Currently, Transformer-based prohibited object detection methods in X-ray images appear constantly, but there are still some shortcomings such as poor performance and high computational complexity for prohibited object detection with heavily occlusion. Therefore, a coarse to fine detection method for prohibited object in X-ray images based on progressive Transformer decoder is proposed in this paper. Firstly, a coarse to fine framework is proposed, which includes two stages: coarse detection and fine detection. Through adaptive inference in stages, the computational efficiency of the model is effectively improved. Then, a position and class object queries method is proposed, which improves the convergence speed and detection accuracy of the model by fusing the position and class information of prohibited object with object queries. Finally, a progressive Transformer decoder is proposed, which distinguishes high and low score queries by decreasing confidence thresholds, so that high-score queries are not affected by low-score queries in the decoding stage, and the model can focus more on decoding low-score queries, which usually correspond to prohibited object with severe occlusion. The experimental results on three public benchmark datasets (SIXray, OPIXray, HiXray) demonstrate that compared with the baseline DETR, the proposed method achieves the state-of-the-art detection accuracy with a 21.6% reduction in model computational complexity. Especially for prohibited objects with heavily occlusion, accurate detection can be carried out. © 2024 ACM.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Improved Density Peaking Algorithm for Community Detection Based on Graph Representation Learning

引用

computer systems Science & engineering 2022年第12期43卷 997-1008页

作者： Jiaming Wang Xiaolan Xie Xiaochun Cheng Yuhan Wang Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin541006GuangxiChina School of Information Science and Engineering Guilin University of TechnologyGuilin541006GuangxiChina Department of Computer Science Middlesex UniversityLondon

There is a large amount of information in the network data that we canexploit. It is difficult for classical community detection algorithms to handle network data with sparse topology. Representation learning of network data is usually paired with clustering algorithms to solve the community detection ***, there is always an unpredictable distribution of class clusters outputby graph representation learning. Therefore, we propose an improved densitypeak clustering algorithm (ILDPC) for the community detection problem, whichimproves the local density mechanism in the original algorithm and can betteraccommodate class clusters of different shapes. And we study the communitydetection in network data. The algorithm is paired with the benchmark modelGraph sample and aggregate (GraphSAGE) to show the adaptability of ILDPCfor community detection. The plotted decision diagram shows that the ILDPCalgorithm is more discriminative in selecting density peak points compared tothe original algorithm. Finally, the performance of K-means and other clusteringalgorithms on this benchmark model is compared, and the algorithm is proved tobe more suitable for community detection in sparse networks with the benchmarkmodel on the evaluation criterion F1-score. The sensitivity of the parameters ofthe ILDPC algorithm to the low-dimensional vector set output by the benchmarkmodel GraphSAGE is also analyzed.

关键词： Representation learning data mining low-dimensional embedding community detection density peaking algorithm

来源：评论

学校读者我要写书评

暂无评论

Impact of Feature Selection Towards Short Text Classification

Impact of Feature Selection Towards Short Text Classificatio...

引用

2023 International Research Conference on Smart Computing and systems engineering, SCSE 2023

作者： Jayakody, Jrkc Vidanagama, Vgtn Perera, Indika Herath, Hmlk University of Wayamba Department of Computing and Information System Sri Lanka University of Moratuwa Department of Computer Science and Engineering Sri Lanka University of Wayamba Department of Agribusiness Management Sri Lanka

ISBN: (纸本)9798350341454

feature selection technique is used in text classification pipeline to reduce the number of redundant or irrelevant features. Moreover, feature selection algorithms help to decrease the overfitting, reduce training time and improve the accuracy of the build models. Similarly, feature reduction techniques based on frequencies support eliminating unwanted features. Most of the existing work related to feature selection was based on general text and the behavior of feature selection was not evaluated properly with short text type dataset. Therefore this research was conducted to investigate how performance varied with selected features from feature selection algorithms with short text type datasets. Three publicly available datasets were selected for the experiment. Chi square, info gain and f measure were examined as those algorithms were identified as the best algorithms to select features for text classification. Moreover, we examined the impact of those algorithms when selecting different types of features such as 1gram and 2-gram. Finally, we look at the impact of frequency based feature reduction techniques with the selected dataset. Our results showed that info gain algorithm outperform other two algorithms. Moreover, selection of best 20% feature set with info gain algorithm provide the same performance level as with the entire feature set. Further we observed the higher number of dimensions was due to bigrams and the impact of n grams towards feature selection algorithms. Moreover, it is worth noting that removing the features which occur twice in a document would be ideal before moving to apply feature selection techniques with different algorithms. © 2023 IEEE.

关键词： Classification (of information)

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：