检索结果-内蒙古大学图书馆

Replay Without Saving: Prototype Derivation and Distribution Rebalance for Class-Incremental Semantic Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4699-4716页

作者： Jinpeng Chen Runmin Cong Yuxuan Luo Horace Ho Shing Ip Sam Kwong Department of Computer Science City University of Hong Kong Kowloon Hong Kong School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China Department of Computer Science and Centre for Innovative Applications of Internet and Multimedia Technologies City University of Hong Kong Kowloon Hong Kong School of Data Science Lingnan University Tuen Mun Hong Kong

The research of class-incremental semantic segmentation (CISS) seeks to enhance semantic segmentation methods by enabling the progressive learning of new classes while preserving knowledge of previously learned ones. A significant yet often neglected challenge in this domain is class imbalance. In CISS, each task focuses on different foreground classes, with the training set for each task exclusively comprising images that contain these currently focused classes. This results in an overrepresentation of these classes within the single-task training set, leading to a classification bias towards them. To address this issue, we propose a novel CISS method named STAR, whose core principle is to reintegrate the missing proportions of previous classes into current single-task training samples by replaying their prototypes. Moreover, we develop a prototype deviation technique that enables the deduction of past-class prototypes, integrating the recognition patterns of the classifiers and the extraction patterns of the feature extractor. With this technique, replay can be accomplished without using any storage to save prototypes. Complementing our method, we devise two loss functions to enforce cross-task feature constraints: the Old-Class Features Maintaining (OCFM) loss and the Similarity-Aware Discriminative (SAD) loss. The OCFM loss is designed to stabilize the feature space of old classes, thus preserving previously acquired knowledge without compromising the ability to learn new classes. The SAD loss aims to enhance feature distinctions between similar old and new class pairs, minimizing potential confusion. Our experiments on two public datasets, Pascal VOC 2012 and ADE20 K, demonstrate that our STAR achieves state-of-the-art performance.

关键词： Prototypes Training Feature extraction Semantic segmentation Continuing education Stars Semantics Vectors Transformers Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Entry-Point Adaptive Keystroke Dynamics-Based User Authentication for Evolving Passwords 6th

Entry-Point Adaptive Keystroke Dynamics-Based User Authentic...

引用

6th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2024

作者： Dutta, Sandip Roy, Soumen Mondal, Ratna Ghosh, Trisha Roy, Utpal Department of Computer and System Sciences Visva-Bharati Santiniketan West Bengal Bolpur731235 India Department of Computer Science and Engineering University of Calcutta Acharya Prafulla Chandra Roy Siksha Prangan Saltlake West Bengal Kolkata700106 India

ISBN: (纸本)9783031813351

In static Keystroke Dynamics (KD)-based user authentication, a fixed-text typing template is periodically updated with patterns for similar text, posing a challenge when users change passwords. Addressing this, we propose a dynamically generated KD template accommodating diverse password types. Leveraging Scaled Manhattan as a classifier, our system achieves a 3.01 ± 1.45% average Equal Error Rate (EER) in practical settings. This study introduces a novel hypothesis, evaluating anomaly detectors’ performance in KD with diverse password texts, ensuring adaptive templates. Utilizing a comprehensive dataset with advanced sensory features from smartphones, covering diverse user profiles, our model surpasses various anomaly detectors. Implications extend to advancing PIN- and password-based authentication, benefiting information system security for modern smartphones. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Trained LSTM Models for Household Load Profile Forecasting

Transfer Learning Trained LSTM Models for Household Load Pro...

引用

Grid Edge Technologies Conference & Exposition (Grid Edge), IEEE PES

作者： Roshan Klein-Seetharaman Xiangqi Zhu Barry Mather Department of Mathematics Yale University New Haven USA Electrical Engineering and Computer Science Oregon State University Corvallis USA National Renewable Energy Laboratory Power System Engineering Center Golden USA

ISBN: (数字)9798350352528

ISBN: (纸本)9798350352535

Grid edge renewable energy resources, such as rooftop solar photovoltaics, closely interact with consumer load profiles. Therefore, forecasting future electricity demand, ideally at the individual household level, is indispensable. In this paper, we present a transfer learning enhanced household load profile forecasting method. First, we tune a long short-term memory forecasting model to perform day-ahead prediction of household electricity load profiles. Then we improve these individualized models using transfer learning, and we use k-means clustering to create optimal source data sets. We find average improvements of 4.38% (largest improvement of 10.71%) when the entire data set was used to train the source model and 2.45% (largest improvement of 11.57%) in the mean absolute error when households were first clustered and used to train separate source models for each cluster. We find that transfer learning with clustered data can effectively boost the forecasting performance of the LSTM models. We use realistic household power measurements for 148 real residential households in Austin, Texas.

关键词： Photovoltaic systems Renewable energy sources Power measurement Electricity Transfer learning Predictive models Data models Forecasting Long short term memory Load modeling

来源：评论

学校读者我要写书评

暂无评论

Assessing the Impact of Homelessness on COVID-19 Hospitalization Rates in Patients with Underlying Medical Conditions Through Explainable AI

Assessing the Impact of Homelessness on COVID-19 Hospital...

引用

20th International Conference on Data science, ICDATA 2024, held as part of the World Congress in computer science, computer engineering and Applied Computing, CSCE 2024

作者： Uddin, J. M. Imtinan Hall, Hayden Long, Jessica Kimbrell, Connor Obrien, Isabel Mendiratta, Sudave Koo, Patrick Wang, Yingfeng Qin, Hong Department of Computer Science and Engineering The University of Tennessee at Chattanooga Chattanooga United States The University of Tennessee Health Science Center Chattanooga United States Erlanger Health System Chattanooga United States Department of Computer Science Old Dominion University Norfolk United States

ISBN: (纸本)9783031858550

Preexisting comorbidities like COPD and smoking history increase SARS-CoV-2 risk, but the impact of homelessness and mental health remains underexplored. This study investigates the correlation between homelessness and COVID-19 hospitalizations in patients with COPD, mental illness, smoking habit, and age using national EHR data from All of Us, including 129,524 patients, 3,547 of whom were homeless. A statistical examination using logistic regression confirmed that homelessness increases hospitalization odds, with 19.83% of homeless COVID-19 patients hospitalized, compared to 15.08% in the general population. SHAP plots, an explainable AI method highlighted significant interactions between homelessness, COPD, smoking, gender, and mental disorders on COVID-19 hospitalizations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Model for Foreign Exchange Prediction 2nd

A Machine Learning Model for Foreign Exchange Prediction

引用

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： San, Tan Jun Ajibade, Samuel-Soma M. Ajibade, Temiloluwa Iyanuoluwa Jasser, Muhammed Basheer Ayodele, Olamide Emmanuel Oyewopo, Abdulgafar Olorunleke Adediran, Anthonia Oluwatosin Majeed, Anwar P. P. Abdul Luo, Yang Department of Data Science and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Petaling Jaya Malaysia Department of Computer Engineering Istanbul Ticaret University Istanbul Turkey Department of Business Management Scholar School System Birmingham United Kingdom School of Engineering and Technology Sunway University Selangor Darul Ehsan Petaling Jaya47500 Malaysia Department of Banking and Finance Ekiti State University Ekiti State Ado Ekiti Nigeria Department of Business Administration Kwara State University Malete Nigeria Department of Real Estate Faculty of Built Environment Universiti Malaya Kuala Lumpur Malaysia Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

The rise of deep learning algorithms has sparked interest in the financial domain. The foreign exchange market (FOREX) is the globally leading financial market with millions of active stakeholders. Research in deep learning for forecasting price movements has shown its efficacy in financial markets. Notably, LSTM have empirically proven the best performance among other machine learning techniques. However, studies have shown the lack of deep learning hybrid comparisons to fortify empirical claims, especially in the FX market characterized for its high volatility and variance among currency pairs. This study develops a generalized LSTM model to forecast the major pairs and conducts a comparative analysis with a secondary hybrid deep learning model to assess and solidify the robustness of deep learning methods in forex forecasting. The empirical scenario simulates a classification problem employing cross-validation techniques to optimize the models’ generalization rigorously. Evaluation of the model utilized the accuracy, precision, recall, and f1-score metrics. Results indicated the performance of the models from best to worst were LSTM, SRNN and followed by CNN indicating the importance of testing deep learning approaches in different empirical setups. Conclusively, this study highlights the need challenges in forex forecasting and raises the need for more robust assessments on machine learning models forecasting capabilities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A comparative study of the performance of ten metaheuristic algorithms for parameter estimation of solar photovoltaic models

引用

PeerJ computer science 2025年 11卷 e2646-e2646页

作者： Zga, Adel Zitouni, Farouq Harous, Saad Sallam, Karam Almazyad, Abdulaziz S. Xiong, Guojiang Mohamed, Ali Wagdy Department of Computer Science and Information Technology Laboratory of Artificial Intelligence and Information Technology Kasdi Merbah University Ouargla Algeria Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Guizhou Key Laboratory of Intelligent Technology in Power System College of Electrical Engineering Guizhou University Guiyang China Operations Research Department Faculty of Graduate Studies for Statistical Research Cairo University Giza Egypt Applied Science Research Center Applied Science Private University Amman Jordan

This study conducts a comparative analysis of the performance of ten novel and wellperforming metaheuristic algorithms for parameter estimation of solar photovoltaic models. This optimization problem involves accurately identifying parameters that reflect the complex and nonlinear behaviours of photovoltaic cells affected by changing environmental conditions and material inconsistencies. This estimation is challenging due to computational complexity and the risk of optimization errors, which can hinder reliable performance predictions. The algorithms evaluated include the Crayfish Optimization Algorithm, the Golf Optimization Algorithm, the Coati Optimization Algorithm, the Crested Porcupine Optimizer, the Growth Optimizer, the Artificial Protozoa Optimizer, the Secretary Bird Optimization Algorithm, the Mother Optimization Algorithm, the Election Optimizer Algorithm, and the Technical and Vocational Education and Training-Based Optimizer. These algorithms are applied to solve four well-established photovoltaic models: the singlediode model, the double-diode model, the triple-diode model, and different photovoltaic module models. The study focuses on key performance metrics such as execution time, number of function evaluations, and solution optimality. The results reveal significant differences in the efficiency and accuracy of the algorithms, with some algorithms demonstrating superior performance in specific models. The Friedman test was utilized to rank the performance of the various algorithms, revealing the Growth Optimizer as the top performer across all the considered models. This optimizer achieved a root mean square error of 9.8602187789E−04 for the single-diode model, 9.8248487610E−04 for both the double-diode and triplediode models and 1.2307306856E−02 for the photovoltaic module model. This consistent success indicates that the Growth Optimizer is a strong contender for future enhancements aimed at further boosting its efficiency and effectiveness. Its

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Concept-Level Semantic Transfer and Context-Level Distribution Modeling for Few-Shot Segmentation

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Luo, Yuxuan Chen, Jinpeng Cong, Runmin Ip, Horace Ho Shing Kwong, Sam City University of Hong Kong Department of Computer Science Hong Kong Shandong University School of Control Science and Engineering Jinan250061 China Ministry of Education Key Laboratory of Machine Intelligence and System Control Jinan250061 China Lingnan University Hong Kong

Few-shot segmentation (FSS) methods aim to segment objects using only a few pixel-level annotated samples. Current approaches either derive a generalized class representation from support samples to guide the segmentation of query samples, which often discards crucial spatial contextual information, or rely heavily on spatial affinity between support and query samples, without adequately summarizing and utilizing the core information of the target class. Consequently, the former struggles with fine detail accuracy, while the latter tends to produce errors in overall localization. To address these issues, we propose a novel FSS framework, CCFormer, which balances the transmission of core semantic concepts with the modeling of spatial context, improving both macro and micro-level segmentation accuracy. Our approach introduces three key modules: (1) the Concept Perception Generation (CPG) module, which leverages pre-trained category perception capabilities to capture high-quality core representations of the target class;(2) the Concept-Feature Integration (CFI) module, which injects the core class information into both support and query features during feature extraction;and (3) the Contextual Distribution Mining (CDM) module, which utilizes a Brownian Distance Covariance matrix to model the spatial-channel distribution between support and query samples, preserving the fine-grained integrity of the target. Experimental results on the PASCAL-5i and COCO-20i datasets demonstrate that CCFormer achieves state-of-the-art performance, with visualizations further validating its effectiveness. Our code is available at ***/lourise/ccformer. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Secure-by-Construction Synthesis for Control systems

引用

IEEE Transactions on Automatic Control 2025年

作者： Zhong, Bingzhuo Liu, Siyuan Caccamo, Marco Zamani, Majid Thrust of Artificial Intelligence Information Hub The Thrust of Intelligent Transportation System Hub China KTH Royal Institute of Technology Division of Decision and Control Systems Stockholm Sweden Technical University of Munich TUM School of Engineering and Design Germany University of Colorado Boulder Department of Computer Science United States Ludwig Maximilian University Department of Computer Science Munich Germany

In this note, we present the synthesis of secure-by-construction controllers that address safety and security properties simultaneously in cyber-physical systems. Our focus is on studying a specific security property called opacity, which characterizes the system's ability to maintain plausible deniability of its secret behavior in the presence of an intruder. These controllers are synthesized based on a concept of so-called (augmented) control barrier functions. We propose conditions that facilitate the construction of the desired (augmented) control barrier functions and their corresponding secure-by-construction controllers. To compute these functions, we propose an iterative scheme that leverages iterative sum-of-square programming techniques. This approach enables efficient computation of these functions, particularly for polynomial systems. Finally, we validate the effectiveness of our results through a case study of a vehicle. © 1963-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

CONCRETIZER: MODEL INVERSION ATTACK VIA OCCUPANCY CLASSIFICATION AND DISPERSION CONTROL FOR 3D POINT CLOUD RESTORATION

arXiv

引用

arXiv 2025年

作者： Kim, Youngseok Hwang, Sunwook Kim, Hyung-Sin Bahk, Saewoong Department of Electrical and Computer Engineering Seoul National University Korea Republic of System LSI Samsung Electronics Korea Republic of Graduate School of Data Science Seoul National University Korea Republic of

The growing use of 3D point cloud data in autonomous vehicles (AVs) has raised serious privacy concerns, particularly due to the sensitive information that can be extracted from 3D data. While model inversion attacks have been widely studied in the context of 2D data, their application to 3D point clouds remains largely unexplored. To fill this gap, we present the first in-depth study of model inversion attacks aimed at restoring 3D point cloud scenes. Our analysis reveals the unique challenges, the inherent sparsity of 3D point clouds and the ambiguity between empty and non-empty voxels after voxelization, which are further exacerbated by the dispersion of non-empty voxels across feature extractor layers. To address these challenges, we introduce ConcreTizer, a simple yet effective model inversion attack designed specifically for voxel-based 3D point cloud data. ConcreTizer incorporates Voxel Occupancy Classification to distinguish between empty and non-empty voxels and Dispersion-Controlled Supervision to mitigate non-empty voxel dispersion. Extensive experiments on widely used 3D feature extractors and benchmark datasets, such as KITTI and Waymo, demonstrate that ConcreTizer concretely restores the original 3D point cloud scene from disrupted 3D feature data. Our findings highlight both the vulnerability of 3D data to inversion attacks and the urgent need for robust defense strategies. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Line-of-Sight Multipath Classification Method for BDS Using Convolutional Sparse Autoencoder with LSTM

引用

Tsinghua science and Technology 2025年第1期30卷 68-86页

作者： Yahang Qin Zhenni Li Shengli Xie Bo Li Ming Liu Victor Kuzin School of Automation Guangdong University of Technologyand also with Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete ManufacturingGuangzhou 510006China School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Information Processing and System Integration of IoTMinistry of EducationGuangzhou 510006China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologHong Kong 999077China Academician of Russian Engineering Academy Moscow Moscow 125009Russia

Multipath signal recognition is crucial to the ability to provide high-precision absolute-position services by the BeiDou Navigation Satellite system(BDS).However,most existing approaches to this issue involve supervised machine learning(ML)methods,and it is difficult to move to unsupervised multipath signal recognition because of the limitations in signal *** by an autoencoder with powerful unsupervised feature extraction,we propose a new deep learning(DL)model for BDS signal recognition that places a long short-term memory(LSTM)module in series with a convolutional sparse autoencoder to create a new autoencoder ***,we propose to capture the temporal correlations in long-duration BeiDou satellite time-series signals by using the LSTM module to mine the temporal change patterns in the time ***,we develop a convolutional sparse autoencoder method that learns a compressed representation of the input data,which then enables downscaled and unsupervised feature extraction from long-duration BeiDou satellite series ***,we add an l_(1/2) regularizer to the objective function of our DL model to remove redundant neurons from the neural network while ensuring recognition *** tested our proposed approach on a real urban canyon dataset,and the results demonstrated that our algorithm could achieve better classification performance than two ML-based methods(e.g.,11%better than a support vector machine)and two existing DL-based methods(e.g.,7.26%better than convolutional neural networks).

关键词： convolutional sparse autoencoder BeiDou Navigation Satellite system(BDS) long short-term memory(LSTM) multipath classification

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：