检索结果-内蒙古大学图书馆

CSMViT: A Lightweight Transformer and CNN fusion Network for Lymph Node Pathological Images Diagnosis

IEEE ACCESS 2024年 12卷 155365-155378页

作者： Jiang, Peihe Xu, Yukun Wang, Chunni Zhang, Wei Lu, Ning Yantai Univ Sch Phys & Elect Informat Yantai 264005 Peoples R China Shandong First Med Univ & Shandong Acad Med Sci Shandong Canc Hosp & Inst Dept Radiat Oncol Jinan 250117 Peoples R China Yantaishan Hosp Dept Pathol Yantai 264003 Peoples R China

To address the burdensome and time-consuming nature of manual diagnosis of pathological sections, this study proposes an automated pathological image detection system. This system can directly detect pathological images and accurately locate lesion tissues, providing a reference for pathological diagnosis. We propose an improved MobileViT model for feature extraction in the system, which we have named CSMViT. Considering the complexity and multi-scale characteristics of pathological images, we made three significant modifications to the MobileViT model. First, the original MV2 module was replaced with an improved Ghost module to reduce the model's parameter count, enhance detection accuracy, and accelerate inference speed. Second, we improved the backbone structure of the network to achieve multi-scale feature learning, which not only further reduces the parameter count but also allows for more effective capture of features at different scales. Lastly, we introduced a new CSA module that can simultaneously accept two feature maps of different sizes as input. Through internal attention mechanisms and feature fusion, this module achieves cross-scale feature learning. Experimental results indicate that the CSMViT model achieved accuracy, F1-score, and specificity of 99.42%, 99.4%, and 99.6%, respectively. Additionally, the detection accuracy of CSMViT for the entire pathological image is 84%, representing an 8% improvement over the original network. Notably, the FLOPs of CSMViT is 1.461G, which is a 72.19% reduction compared to the original network, significantly decreasing the model's complexity. These results thoroughly demonstrate the effectiveness and substantial value of CSMViT in pathological image detection.

关键词： Pathology Feature extraction Computational modeling Transformers Computer vision Accuracy Lymph nodes Image segmentation Convolutional neural networks Metastasis classification algorithms Biomedical imaging classification lightweight network lymph node transformer pathological images

来源：评论

学校读者我要写书评

暂无评论

Combing Multiple Visual Stimuli to Enhance the Performance of VEP-Based Biometrics

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 7982-7993页

作者： Qu, Haomin Zhao, Hongze Wei, Qingguo Pei, Weihua Gao, Xiaorong Wang, Yijun Nanchang Univ Dept Elect Engn Nanchang 330031 Peoples R China Tsinghua Univ Sch Biomed Engn Dept Biomed Engn Beijing 100084 Peoples R China Chinese Acad Sci Inst Semicond Key Lab Solid State Optoelect Informat Technol Beijing 100083 Peoples R China Univ Chinese Acad Sci Sch Future Technol Beijing 100049 Peoples R China

In recent years, electroencephalography (EEG) has received increasing attention in the field of biometrics because of its unique advantages such as covertness, resistance to spoofing, sensitivity to emotional and mental states, and continuous nature. Visual evoked potentials (VEPs) have been widely used in EEG-based biometrics owing to fast recognition speed and high accuracy. This study proposes a new method to combine multiple visual stimuli for VEP-based individual identification. Correct recognition rate (CRR) was estimated using steady-state VEPs (ss-VEPs), and code modulated VEPs (c-VEPs) recorded from a group of 35 subjects. c-VEPs achieved a 100% CRR using 3.1-s of VEP data (a 10.8-s duration, including 7.7-s intervals) in the cross-session condition. An online system based on the combination of stimuli optimized from the data of 35 subjects was further developed and validated with an additional group of 22 subjects. A cross-session CRR of 99.55% was achieved using the same parameters. These results indicate that the proposed VEP-based individual identification method using multiple visual stimuli shows great potential for practical applications.

关键词： Electroencephalography Biometrics Visualization Identification of persons classification algorithms Authentication Feature extraction electroencephalography person identification visual evoked potentials cross-session performance

来源：评论

学校读者我要写书评

暂无评论

A Novel Instruction Gesture Set Determination Scheme for Robust Myoelectric Control Applications

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2025年第3期72卷 909-920页

作者： Ruan, Yuwen Chen, Xiang Zhang, Xu Univ Sci & Technol China Sch Informat Sci & Technol Hefei Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei Peoples R China

Objective: Myoelectric control technology has important application value in rehabilitation medicine, prosthesis control, human-computer interaction (HCI) and other fields. However, the user dependence of electromyography (EMG) pattern recognition is one of the key problems hindering the implementation of robust myoelectric control applications. Aimed at solving the user dependence problem, this paper proposed a novel instruction gesture set determination scheme for EMG pattern recognition in user-independent mode. Methods: The scheme uses T-distributed stochastic neighbor embedding (T-SNE) dimensionality reduction to analyze high-dimensional surface EMG data from multiple users and gestures. This process can identify gesture combinations with minimal individual differences and high separability. Results: The proposed scheme was validated using two large-scale EMG gesture databases with different acquisition devices, subjects, and gestures. Optimal and inferior gesture sets of varying sizes were identified. In recognition experiments conducted in both user-independent and electrode-offset modes, the optimal gesture sets demonstrated significantly higher recognition accuracies compared to the inferior sets, with improvements ranging from 12.57% to 36.92%. Conclusion: The results demonstrated that the separability of the obtained optimal gesture sets was significantly superior to that of the inferior sets, confirming the effectiveness of the proposed scheme in reducing user dependence in EMG pattern recognition. Significance: The study has certain application value to promote the development of myoelectric control technology. Specifically, the scheme proposed can be used to determine instruction gesture sets with low user dependence and high separability for myoelectric control applications.

关键词： Electromyography Muscles Databases Wrist Feature extraction Electrodes Accuracy Thumb Gesture recognition classification algorithms EMG pattern recognition gesture set myoelectric control T-SNE user dependence

来源：评论

学校读者我要写书评

暂无评论

A Novel Multitouch Recognition Algorithm for Infrared Touch Screens Based on Geometric Construction and Clustering

引用

IEEE SENSORS JOURNAL 2025年第10期25卷 17671-17682页

作者： Zuo, Jiancun Ji, Zhangyuan Sun, Jingguo Li, Hewei Wang, Haowei Peng, Yue Shanghai Polytech Univ Sch Comp & Informat Engn Shanghai 201209 Peoples R China

Both sensor layout and sensor number determine the scan line density and limit the performance of modern infrared touchscreens in terms of recognition accuracy, positioning error, minimum touch object size, response time, and maximum number of touch points. This article explores methods to optimize the multitouch recognition algorithm, improving touchscreen performance without increasing hardware costs. To efficiently and accurately calculate touch point locations, a multitouch recognition algorithm based on geometric construction and clustering is proposed. The algorithm divides the set of intersection points into core, noncore, and noise regions by optimizing the median of blocked scan lines. A K-d tree is constructed for the intersection set using fast library for approximate nearest neighbor (FLANN), followed by the application of the KNN-BLOCK-DBSCAN clustering algorithm. Touch point coordinates are determined by merging and splitting clusters based on their density reachability. Experimental results show that our algorithm outperforms the polygon-cutting method in recognition accuracy, minimum touch object size, and response time. The response time is reduced by over 50%, with a minimum touch object diameter of 4 mm in the center and 5 mm in the corners, while eliminating touch-insensitive areas across the entire touch area.

关键词： Clustering algorithms Touch sensitive screens Accuracy Hardware Costs classification algorithms Tactile sensors Time factors Intelligent sensors Optical transmitters Clustering geometric construction infrared touch screen multitouch recognition

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based direct estimation of remaining useful life (RUL) of IGBT using multi-precursor prognostics

引用

ELECTRICAL ENGINEERING 2025年第3期107卷 3435-3449页

作者： Prathiba, R. V. Saravanan, M. David, Prince Winston Thangaraj, Hariharasudhan Thiagarajar Coll Engn Dept EEE Madurai 625015 Tamil Nadu India Kamaraj Coll Engn & Technol Dept EEE Vellakulam 625701 Tamilnadu India

The reliability of motor drives plays a crucial role in all motion control applications. Due to circuit overstresses, the IGBTs used in motor drives are prone to degradation and aging, which may result in motor drives failure. The RUL prediction of IGBT gives early warning of the unexpected IGBT failures, by predicting the useful life of IGBT while it is in operating condition. The existing methods for RUL prediction of IGBT focus on the use of a single precursor which cannot effectively determine the level of degradation of IGBT, and the methods are too laborious and have prediction errors. This work employs three precursors VCE(ON), IC and VGE, and uses a simple yet effective method to predict the RUL of IGBT by machine learning techniques, and the results are tested using online-accelerated IGBT aging data from the NASA's Ames Research Centre. The data preprocessing and feature selection are carried out using MATLAB toolboxes, namely Data Cleaner and Diagnostic Feature Designer. Then, the MATLAB classification Learner toolbox is used to train the various machine learning classifiers, and a comparison is made for various cases involving single, double and multi-precursor parameters in predicting RUL of IGBT. Hyperparameter tuning of the machine learning classifiers is also done, and evaluation metrics such as Precision, Recall, F1 score and ROC-AUC are used to validate the performance of the different ML classifiers. Highest classification accuracy of 99.6% is obtained with ensemble, neural networks and KNN model classifiers after hyperparameters were optimized.

关键词： Insulated-gate bipolar transistor (IGBT) Remaining useful life (RUL) Multi-precursor prognostics Machine learning classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Extended Zero-Gradient-Sum Approach for Constrained Distributed Optimization With Free Initialization

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2025年第6期55卷 3824-3834页

作者： Shi, Xinli Yu, Xinghuo Wen, Guanghui Xu, Xiangping Southeast Univ Sch Cyber Sci & Engn Nanjing 210096 Peoples R China RMIT Univ Sch Engn Melbourne Vic 3001 Australia Southeast Univ Sch Automat Nanjing 210096 Peoples R China Southeast Univ Sch Math Nanjing 210096 Peoples R China

This article proposes an extended zero-gradient-sum (EZGS) approach for solving constrained distributed optimization with free initialization and desired convergence properties. A Newton-based continuous-time algorithm is first designed for general constrained optimization, which is adapted to handle inequality constraints by using log-barrier penalty functions. Then, a general class of EZGS dynamics is developed to address equation-constrained distributed optimization, where an auxiliary dynamics is introduced to ensure the final ZGS property from any initialization. It is demonstrated that for typical consensus protocols and auxiliary dynamics, the proposed EZGS dynamics can achieve the performance with exponential/finite/fixed/prescribed-time (PT) convergence. Particularly, the nonlinear consensus protocols for finite-time EZGS algorithms allow for heterogeneous power coefficients. Significantly, the proposed PT EZGS dynamics is continuous, uniformly bounded, and capable of reaching the optimal solution in a single stage. Furthermore, the barrier method is employed to handle the inequality constraints effectively. Finally, the efficiency and performance of the proposed algorithms are validated through numerical examples, highlighting their superiority over existing methods. In particular, by selecting appropriate protocols, the proposed EZGS dynamics can achieve desired convergence performance.

关键词： Optimization Convergence Heuristic algorithms Consensus protocol Estimation Couplings Resource management classification algorithms Vehicle dynamics Vectors Barrier method constrained distributed optimization convergence rate finite-time (FT) stability zero-gradient-sum (ZGS) method

来源：评论

学校读者我要写书评

暂无评论

A Flexible Framework for Design and Validation of rPPG Methods

引用

IEEE ACCESS 2025年 13卷 50059-50076页

作者： Dawoodjee, Ilyas Ghahramani, Ali Natl Univ Singapore Dept Built Environm Singapore 117565 Singapore Univ Manitoba Mech Engn Dept Winnipeg MB R3T 2N2 Canada

Over the past decade, Remote Photoplethysmography (rPPG) has emerged as an unobtrusive alternative to wearable sensors for measuring physiological signals, such as heart rate. Despite advancements, its real-world scalability remains limited due to the absence of standardized benchmark methods for validation. This lack of standardization complicates proper comparisons between different approaches, creating inconsistencies in performance evaluation. To address this, we conducted a comprehensive review of recent rPPG methods, analyzing their pre- and post-processing algorithms, validation procedures, benchmark algorithms, datasets, evaluation metrics, data segmentation, and reported results. Our findings demonstrate significant variability in the reported Mean Absolute Error (MAE) of benchmark rPPG methods applied to the same public datasets, confirming the challenge of inconsistent evaluation. By examining the original implementations of established benchmark methods, we developed a flexible framework that optimally selects pre- and post-processing algorithms through an exhaustive search. Applying this framework to benchmark algorithms across three public datasets, we found that 80% of the refined methods ranked within the top 25th percentile in MAE, RMSE, and PCC, with 60% surpassing the highest reported accuracies. These refined methods provide a more rigorous foundation for evaluating novel rPPG techniques, addressing the standardization gap in the field. The codebase for this framework (frPPG) is available at [https://***/Building-Robotics-Lab/flexible_rPPG], offering a valuable tool for designing and benchmarking rPPG methods against the best-performing algorithms on a given dataset.

关键词： Benchmark testing classification algorithms Systematic literature review Accuracy Systematics Measurement Software algorithms Photoplethysmography Blood Skin Benchmark rPPG methods error variability heart rate monitoring open-source code pre- and post- processing stages and algorithms remote photoplethysmography (rPPG)

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Localization of Mixed Near-Field and Far-Field Sources Based on a Unified Exact Propagation Model

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2025年 73卷 245-258页

作者： Fang, Jiaxiong Chen, Hua Liu, Wei Yang, Songjie Yuen, Chau So, Hing Cheung Ningbo Univ Fac Elect Engn & Comp Sci Ningbo 315211 Peoples R China Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China Univ Elect Sci & Technol China Natl Key Lab Wireless Commun Chengdu 610054 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Singapore 639798 Singapore City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

In applications like speaker localization using a microphone array, the collected signals are typically a mixture of far-field (FF) and near-field (NF) sources. To find the positions of both NF and FF sources, a three-dimensional spatial-temporal localization algorithm based on a unified exact propagation geometry is developed in this paper, which avoids approximating the spatial phase difference with the first-order and second-order Taylor expansions applied to FF and NF sources, respectively. Our scheme utilizes cross-correlation to produce virtual observations for establishing a third-order parallel factor data model with the use of spatial and temporal information. The array's steering vectors can be extracted by trilinear decomposition. The amplitude and phase information of the whole array elements is jointly exploited to classify the source types and obtain the location estimates via a least squares method. Moreover, the proposed algorithm is computationally efficient since no spectral searches, high-order statistics calculations or parameter pairing procedures are required. The deterministic Cram & eacute;r-Rao bound is also derived as a performance benchmark, and numerical results are provided to demonstrate the effectiveness of the developed method.

关键词： Noise measurement Location awareness classification algorithms Geometry Three-dimensional displays Signal processing algorithms Phased arrays Multiple signal classification Apertures Microphone arrays Array signal processing source localization spatial-temporal near-field far-field

来源：评论

学校读者我要写书评

暂无评论

Deep Label Propagation With Nuclear Norm Maximization for Visual Domain Adaptation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2025年 34卷 1246-1258页

作者： Wang, Wei Li, Hanyang Wang, Cong Huang, Chao Ding, Zhengming Nie, Feiping Cao, Xiaochun Sun Yat Sen Univ Sch Cyber Sci & Technol Shenzhen Campus Shenzhen 518107 Peoples R China Ctr Adv Reliabil & Safety Hong Kong Peoples R China Tulane Univ Dept Comp Sci New Orleans LA 70118 USA Northwestern Polytech Univ Ctr Opt Imagery Anal & Learning OPTIMAL Sch Comp Sci Xian 710000 Peoples R China

Domain adaptation aims to leverage abundant label information from a source domain to an unlabeled target domain with two different distributions. Existing methods usually rely on a classifier to generate high-quality pseudo-labels for the target domain, facilitating the learning of discriminative features. Label propagation (LP), as an effective classifier, propagates labels from the source domain to the target domain by designing a smooth function over a similarity graph, which represents structural relationships among data points in feature space. However, LP has not been thoroughly explored in deep neural network-based domain adaptation approaches. Additionally, the probability labels generated by LP are low-confident and LP is sensitive to class imbalance problem. To address these problems, we propose a novel approach for domain adaptation named deep label propagation with nuclear norm maximization (DLP-NNM). Specifically, we employ the constraint of nuclear norm maximization to enhance both label confidence and class diversity in LP and propose an efficient algorithm to solve the corresponding optimization problem. Subsequently, we utilize the proposed LP to guide the classifier layer in a deep discriminative adaptation network using the cross-entropy loss. As such, the network could produce more reliable predictions for the target domain, thereby facilitating more effective discriminative feature learning. Extensive experimental results on three cross-domain benchmark datasets demonstrate that the proposed DLP-NNM surpasses existing state-of-the-art domain adaptation approaches.

关键词： Prototypes Reliability Representation learning Optimization Feature extraction Adaptation models Propagation losses classification algorithms Artificial neural networks Training Domain adaptation deep label propagation nuclear norm maximization discriminative feature learning

来源：评论

学校读者我要写书评

暂无评论

Quantum Support Vector Machine for Classifying Noisy Data

引用

IEEE TRANSACTIONS ON COMPUTERS 2024年第9期73卷 2233-2247页

作者： Li, Jiaye Li, Yangding Song, Jiagang Zhang, Jian Zhang, Shichao Zhejiang Univ State Key Lab Blockchain & Data Secur Hangzhou 310027 Peoples R China Hunan Normal Univ Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha 410081 Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China

Noisy data is ubiquitous in quantum computer, greatly affecting the performance of various algorithms. However, existing quantum support vector machine models are not equipped with anti-noise ability, and often deliver low performance when learning accurate hyperplane normal vectors from noisy data. To attack this issue, an anti-noise quantum support vector machine algorithm is developed in this paper. Specifically, a weight factor is first embedded into the hinge loss, so as to construct the objective function of anti-noise support vector machine. And then, an alternative iterative optimization strategy and a quantum circuit are designed for solving the objective function, aiming to obtain the normal vector and intercept of the hyperplane that finally divides the data. Finally, the classification and anti-noise effect of the algorithm are verified on artificial dataset and public dataset. Experimental results show that the proposed algorithm is efficient, yet maintains stable accuracy in noisy data.

关键词： Support vector machines Quantum computing classification algorithms Accuracy Quantum entanglement Computers Vectors Quantum support vector machine quantum computer noisy data 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：