检索结果-内蒙古大学图书馆

ComMatch: A semi-supervised learning classification algorithm based on model calibration

Journal of Intelligent and Fuzzy Systems 2025年第6期48卷 811-822页

作者： Li, Ye Zhou, Jingkang School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai China

Semi-supervised learning (SSL) aims to reduce reliance on labeled data. Achieving high performance often requires more complex algorithms, therefore, generic SSL algorithms are less effective when it comes to image classification tasks. In this study, we propose ComMatch, a simpler and more effective algorithm that combines negative learning, dynamic thresholding, and predictive stability discriminations into the consistency regularization approach. The introduction of negative learning is to help facilitate training by selecting negative pseudo-labels during stages when the network has low confidence. And ComMatch filters positive and negative pseudo-labels more accurately as training progresses by dynamic thresholds. Since high confidence does not always mean high accuracy due to network calibration issues, we also introduce network predictive stability, which filters out samples by comparing the standard deviation of the network output with a set threshold, thus largely reducing the influence of noise in the training process. ComMatch significantly outperforms existing algorithms over several datasets, especially when there is less labeled data available. For example, ComMatch achieves 1.82% and 3.6% error rate reduction over FlexMatch and FixMatch on CIFAR-10 with 40 labels respectively. And with 4000 labeled samples, ComMatch achieves 0.54% and 2.65% lower error rates than FixMatch and MixMatch, respectively. © 2025 – IOS Press. All rights reserved.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

The ChatGPT After: Building Knowledge Factories for Knowledge Workers with Knowledge Automation

引用

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2041-2044页

作者： Yutong Wang Xiao Wang Xingxia Wang Jing Yang Oliver Kwan Lingxi Li Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China School of Artificial Intelligence Anhui UniversityHefei 230039China Motion G Inc068898Singapore Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University IndianapolisIndiana 46202-5132 USA IEEE

Briefing: This perspective introduces the concept and framework of knowledge factories with knowledge machines for knowledge workers to achieve knowledge automation for Industry 5.0 and intelligent *** The big hit of Chat GPT makes it imperative to contemplate the practical applications of big or foundation models [1]-[5]. However, as compared to conventional models, there is now an increasingly urgent need for foundation intelligence of foundation models for real-world industrial applications.

关键词： Automation template Chat GPT

来源：评论

学校读者我要写书评

暂无评论

A Novel Conv-Mamba-Hybrid Network for Medical Image Segmentation

A Novel Conv-Mamba-Hybrid Network for Medical Image Segmenta...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Qiao, Sibo Zhao, Zhiyuan Xie, Pengfei Yin, Wenjing Wang, Min Zhang, Yuanyuan Pang, Shanchen Tiangong University The College of Software Tianjin China China University of Petroleum The College of Computer Science and Technology Qingdao China Khalifa University of Science and Technology The Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Tiangong University The College of Life Sciences Tianjin China Qingdao University of Technology The College of Information and Control Engineering Qingdao China

ISBN: (纸本)9798350386226

In the rapidly advancing landscape of intelligent medical technology, high-precision and widely applicable medical image segmentation techniques are pivotal in advancing personalized treatment plans and enhancing patient experiences. To address inherent obstacles, such as complex structures and features that are difficult to capture in segmentation tasks, we first propose a CMH module that merges convolutional neural networks (CNNs) with state space models (e.g., Mamba). This module hierarchically integrates CNN's local priors into the Mamba layer, adeptly capturing specific details of target objects and broader contextual information from different perspectives. Subsequently, we introduce an information fusion module based on Mamba (MIH), aimed at dynamically fusing feature information from different paths and levels to enhance feature expression and discrimination. Building upon the abovementioned modules, we develop an unexplored segmentation model, CMHNet, capable of flexibly capturing feature maps of varying scales and angles from medical images. In the experiments, we present CMHNet's distinguished performance in segmentation tasks through massive experiments on four medical datasets. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Retinal disorder diagnosis based on hybrid deep learning models

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Efficient data-driven occupancy detection in office environments and feature impact analysis

引用

International Journal of Information technology (Singapore) 2024年 1-11页

作者： Fouzi, Harrou Ramakrishna, Kini K. Madakyaru, Muddu Ying, Sun Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Computer Thuwal 23955-6900 Saudi Arabia Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India Department of Chemical Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India

Occupancy detection is crucial in optimizing building energy efficiency and enhancing occupant comfort. This study introduces an innovative data-driven approach for accurate occupancy detection in an office room environment. Specifically, the methodology combines the advantages of Independent Component Analysis (ICA) to extract essential features from multivariate data and Kantorovitch distance (KD)-based schemes for detection sensitivity. The KD scheme’s detection threshold is computed nonparametrically using kernel density estimation to enhance the sensitivity of occupancy detection. The efficacy of this strategy is evaluated utilizing publicly available data recorded during winter in Mons, Belgium, capturing vital environmental parameters such as temperature, humidity, light, and CO2 levels through specialized sensors. Results demonstrate that the ICA-KD approach achieves an averaged accuracy of 98.355%, surpassing conventional approaches like Principal Component Analysis (PCA)-based, ICA-based, and other state-of-the-art methods. Additionally, the study uses Shapley Additive exPlanations (SHAP) with XGBoost to explore the impact of input variables on occupancy detection, highlighting the influence of various factors under different testing conditions. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Building occupancy Data-driven Environmental data Occupancy detection Semi-supervised detection

来源：评论

学校读者我要写书评

暂无评论

A distributed algorithm with network-independent step-size and event-triggered mechanism for economic dispatch problem

A distributed algorithm with network-independent step-size a...

引用

作者： Chen, Baitong Yang, Jianhua Lu, Wei Pedrycz, Witold Sun, Changhai School of Control Science and Engineering Dalian University of Technology Dalian China Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Institute of Systems Engineering Macau University of Science and Technology SARTaipa 999078 China Research Center of Performance and Productivity Analysis Istinye University Istanbul Turkey School of Electrical Engineering Dalian University of Technology Dalian China

The economic dispatch problem (EDP) poses a significant challenge in energy management for modern power systems, particularly as these systems undergo expansion. This growth escalates the demand for communication resources and increases the risk of communication failures. To address this challenge, we propose a distributed algorithm with network-independent step sizes and an event-triggered mechanism, which reduces communication requirements and enhances adaptability. Unlike traditional methods, our algorithm uses network-independent step sizes derived from each agent's local cost functions, thus eliminating the need for detailed network topology knowledge. The theoretical derivation identifies a range of step size values that depend solely on the objective function's strong convexity and the gradient's Lipschitz continuity. Furthermore, the proposed algorithm is shown to achieve a linear convergence rate, assuming the event triggering threshold criteria are met for linear convergence. Numerical experiments further validate the effectiveness and advantages of our proposed distributed algorithm by demonstrating its ability to maintain good convergence characteristics while reducing communication frequency. © 2024 John Wiley & Sons Ltd.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Efficient multimodal cancelable biometric system based on steganography and cryptography

引用

Iran Journal of computer Science 2023年第2期6卷 109-121页

作者： Salama, Gerges M. El-Gazar, Safaa Nassar, Rana M. El-Shafai, Walid Khalaf, Ashraf A. M. El-Banby, Ghada M. Hamed, Hesham F. A. El-Samie, Fathi E. Abd Department of Electrical Engineering Faculty of Engineering Minia University Minia 61111 Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Security Engineering Laboratory Department of Computer Science Prince Sultan University Riyadh 11586 Saudi Arabia Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electrical Engineering Faculty of Engineering Egyptian-Russian University Cairo Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh 84428 Saudi Arabia

Due to the development of hacking programs, it has become easy to penetrate systems. Hence, there is a need for strong security mechanisms. The use of traditional passwords has become insufficient to secure systems. Biometric authentication is now widely used for security applications, and it has proven to be superior compared to traditional authentication methods. However, two issues need to be considered in biometric systems. The first is not to keep biometric data in its original form in the database. If biometric traits are hacked, they will no longer be of use. Biometric data should be kept in cancelable forms for reuse. The second issue is the reliance on a single biometric, which limits the verification accuracy. This can be solved by using a multimodal biometric system. Using steganography and cryptography, this paper introduces a cancelable multimodal biometric system. As voiceprints, facial images, and fingerprint images are used. In this paper, the verification is performed through the Mel frequency cepstral coefficients (MFCCs) of the voiceprints. Steganography is used as a tool to secure features extracted from voiceprints by embedding them into the facial image using block-based singular value decomposition (BSVD). Double random phase encoding (DRPE) is utilized as an encryption algorithm to generate the final cancelable templates. To increase the level of system security, fingerprint images are used as random phase masks (RPMs). Verification is performed by estimating the correlation between registered and test MFCCs. The correlation value is then compared with a threshold value, which is calculated using the distribution curves for the genuine and imposter correlations. Equal error rate (EER) values close to zero and an area under the receiver operator characteristic curve (AROC) that is close to one are obtained from the simulation results, demonstrating the outstanding performance of the suggested system. The proposed system achieves good performan

关键词： BSVD Cancelable biometrics DRPE MFCCs

来源：评论

学校读者我要写书评

暂无评论

Personalized Privacy Protection Incentive Mechanism for Mobile Crowdsourcing Based on Homomorphic Encryption and Edge Computing

Personalized Privacy Protection Incentive Mechanism for Mobi...

引用

IEEE International Conference on Web Services (ICWS)

作者： Yingxin Li Weilong Wang Yingjie Wang Tong Xiangrong Peiyong Duan Zhipeng Cai Department of Computer and Control Engineering Yantai University Department of Computer Science and Engineering Southeast University Department of Electrical and Control Qilu University of Technology Department of Computer Science Georgia State University

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

With the rapid development of crowd sensing computing, Mobile crowdsourcing (MCS) has become an indispensable part of today’s society. While MCS brings convenience to people, it also exposes them to the risk of privacy leakage. In addition, the demand for data is increasing, and the personalized privacy requirements of crowd workers may affect the service quality. In order to address these problems, this paper proposes a personalized privacy protection incentive mechanism (PPPIM) for MCS based on homomorphic encryption and edge computing. Firstly, this paper designs a personalized privacy metric, using social attributes and private attributes of crowd workers to calculate the privacy level required by crowd workers. Then, based on homomorphic encryption and edge computing, a personalized residual federated security learning scheme (PRFSL) is proposed to ensure the security, timeliness, integrity of task data and the privacy of crowd workers’ needs to improve encryption efficiency. Finally, based on the evolutionary game, a personalized privacy incentive mechanism is proposed to improve the overall service utility. Experimental comparisons based on real datasets show that the proposed scheme can not only ensure the security, timeliness, and integrity of task data more effectively. It can also effectively reduce data processing time, improve the probability of crowd workers actively completing tasks and the overall service quality utility.

关键词： Crowdsourcing Measurement Privacy Data privacy Web services Sensors Homomorphic encryption Protection Mobile computing Edge computing

来源：评论

学校读者我要写书评

暂无评论

Semantic Feature Division Multiple Access for Digital Semantic Broadcast Channels

引用

IEEE Internet of Things Journal 2025年第11期12卷 17123-17136页

作者： Ma, Shuai Sun, Zhiye Shen, Bin Wu, Youlong Li, Hang Shi, Guangming Li, Shiyin Al-Dhahir, Naofal Peng Cheng Laboratory Shenzhen518066 China China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China Xidian University School of Artificial Intelligence Shaanxi Xi'an710071 China The University of Texas at Dallas Department of Electrical and Computer Engineering RichardsonTX75080 United States

In this paper, we propose a digital semantic feature division multiple access (SFDMA) paradigm in multi-user broadcast (BC) networks for the inference and the image reconstruction tasks. In this SFDMA scheme, the multi-user semantic information is encoded into discrete approximately orthogonal representations, and the encoded semantic features of multiple users can be simultaneously transmitted in the same time-frequency resource. Specifically, for inference tasks, we design a SFDMA digital BC network based on robust information bottleneck (RIB), which can achieve a tradeoff between inference performance, data compression and multi-user interference. Moreover, for image reconstruction tasks, we develop a SFDMA digital BC network by utilizing a Swin Transformer, which significantly reduces multi-user interference. More importantly, SFDMA can protect the privacy of users' semantic information, in which each receiver can only decode its own semantic information. Furthermore, we establish a relationship between performance and signal to interference plus noise ratio (SINR), which is fitted by an Alpha-Beta-Gamma (ABG) function. Furthermore, an optimal power allocation method is developed for the inference and reconstruction tasks. Extensive simulations verify the effectiveness and superiority of our proposed SFDMA scheme. © 2014 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

MulDoor: A Multi-target Backdoor Attack Against Federated Learning System

MulDoor: A Multi-target Backdoor Attack Against Federated Le...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Li, Xuan Wu, Longfei Guan, Zhitao Du, Xiaojiang Aitsaadi, Nadjib Guizani, Mohsen North China Electric Power University School of Control and Computer Engineering China Fayetteville State University Department of Mathematics and Computer Science Fayetteville United States Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ United States Université Paris-Saclay Uvsq David Versailles France Machine Learning Department United Arab Emirates

ISBN: (纸本)9798350351255

In recent years, with the development of wireless communication networks, federated learning (FL) has been widely deployed in distributed scenarios as a privacy-preserving machine learning paradigm. Due to its inherent features, FL shows vulnerability to backdoor attacks. In a backdoor attack, an adversary manipulates the global model's output by compromising the model of one or multiple participants. Existing backdoor attacks are constrained to outputting a single specified target label during the inference phase, limiting the adversary's flexibility to alter the model's output when different target labels are required. In this paper, we study the multi-target attack scenario within the federated learning context, where the adversary aims to manipulate the global model to output various specified labels by inserting different types of triggers. To effectively insert multiple backdoors simultaneously without reducing the attack's effectiveness, we propose MulDoor, a novel multi-target backdoor attack scheme. MulDoor incorporates the concept of supervised contrastive learning to learn the discrepancies among different types of triggers and mitigate interference between them. The experimental results demonstrate that MulDoor achieves better attack effectiveness compared to existing backdoor attacks in a multi-target backdoor attack setting. © 2024 IEEE.

关键词： Contrastive 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：