检索结果-内蒙古大学图书馆

Fast construction and exploration of performance-cost design space for belief propagation polar decoders

Science China(Information Sciences) 2025年第3期68卷 401-402页

作者： Chao JI You YOU Weikang QIAN Yongming HUANG Chuan ZHANG Laboratory of Efficient Architectures for Digital-communication and Signal-processing (LEADS) National Mobile Communications Research Laboratory Southeast University Purple Mountain Laboratories University of Michigan-Shanghai Jiao Tong University Joint Institute Ministry of Education Key Laboratory of Artificial Intelligence Shanghai Jiao Tong University

Considering polar codes in the channel coding field, belief propagation(BP) polar decoding stands out as a potential solution for high-throughput applications due to its inherent advantage on high parallelism, and also emerging other improved BP-based decoding such as BP flip(BPF) [1, 2] and BP list(BPL) [3,4] polar decoders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bag-Level Multiple Instance Learning for Acute Stress Detection from Video Data

Bag-Level Multiple Instance Learning for Acute Stress Detect...

引用

18th International joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Brügge, Nele Sophie Korda, Alexandra Borgwardt, Stefan Andreou, Christina Giannakakis, Giorgos Handels, Heinz German Research Center for Artificial Intelligence AI in Medical Image and Signal Processing Lübeck Germany Translational Psychiatry Department of Psychiatry and Psychotherapy University of Luebeck Lübeck23562 Germany Heraklion Greece Department of Electronic Engineering Hellenic Mediterranean University Chania Greece Institute of Agri-food and Life Sciences University Research and Innovation Center Hellenic Mediterranean University Heraklion Greece Institute of Medical Informatics University of Luebeck Lübeck Germany

Stress detection is a complex challenge with implications for health and well-being. It often relies on sensors recording biomarkers and biosignals, which can be uncomfortable and alter behaviour. Video-based facial feature analysis offers a noninvasive alternative. This study explores video-level stress detection using top-k Multiple Instance Learning applied to medical videos. The approach is motivated by the assumption that subjects partly show normal behaviour while performing stressful experimental tasks. Our contributions include a tailored temporal feature network and optimised data utilisation by additionally incorporating bottom-k snippets. Leave-five-subjects-out stress detection results of 95.46% accuracy and 95.49% F1 score demonstrate the potential of our approach, outperforming the baseline methods. Additionally, through multiple instance learning, it is possible to show which temporal video segments the network pays particular attention to. © 2025 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Thermal constraint control of reversible solid oxide cell for optimal system efficiency

引用

International Journal of Hydrogen Energy 2025年 134卷 198-211页

作者： Xu, Yuanwu Yin, Jie Wang, Jingjing Wu, Xiao-long Peng, Jingxuan Tang, Ruifeng Zou, Suhang Fu, Xiaowei Li, Xi School of Artificial Intelligence and Automation Wuhan University of Science and Technology Hubei Wuhan430081 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Hubei Wuhan430074 China School of Information Engineering Nanchang University Jiangxi Nanchang330031 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore China-Poland Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China

Reversible solid oxide cell (RSOC) demonstrates considerable promise in multimodal energy conversion architectures, particularly as a technology for hydrogen-based energy storage systems. Nevertheless, under dynamic operating regimes with time-varying current inputs, realizing time-efficient and reliable transitions to steady-state operation remains difficult. This difficulty arises from the intricate coupling of thermal, electrical, and gaseous processes within the RSOC system. This study aims to address these challenges by developing a 5 kW mathematical model of the RSOC system. The proposed model enables systematic investigation of thermal safety issues arising during current switching operations while introducing a thermal constraint control strategy to enhance both system efficiency and thermal safety performance. This efficiency-driven study employs the Grid Search algorithm to identify optimal steady-state operating points for the RSOC system, ensuring strict adherence to safety constraints across varying current inputs. Furthermore, by integrating the pre-identified optimal operating points as feedforward control with Model Predictive Control (MPC)-based feedback correction, this hybrid strategy effectively mitigates stack temperature gradient overshoot while synchronously ensuring optimal system efficiency throughout current transition processes. Under simulated variable current inputs, the proposed RSOC system model and control strategy demonstrate the capability to constrain stack temperature gradient overshoot within 2.3K while enhancing transient efficiency by 5 %–8 %, achieving a peak system efficiency of 85 %. It provides a novel methodology for safe and efficient working with intermittent renewable energy. © 2025 Hydrogen Energy Publications LLC

关键词： Thermal variables control

来源：评论

学校读者我要写书评

暂无评论

Efficient Fault Detection in Nonlinear Industrial Process: A Reduced Kernel PCA-Based Spectral Clustering Approach

Efficient Fault Detection in Nonlinear Industrial Process: A...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Khadija Attouri Majdi Mansouri Mansour Hajji Kais Bouzrara Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The challenges posed by nonlinearities in industrial systems necessitate innovative techniques that outperform the limitations of traditional methods such as principal component analysis (PCA). While Kernel Principal Component Analysis (KPCA) offers a robust solution to handle nonlinear data, its computational requirements are a significant issue, especially for large-sized datasets. In this work, we propose a novel technique, namely, reduced kernel principal component analysis-based spectral clustering (RKPCA SpC ), to monitor and detect faults in the benchmark Tennessee Eastman process. The suggested approach addresses the complexity associated with KPCA by reducing data size during the model training phase. This reduction involves retaining only the principal components, preserving informative features, and selecting pertinent samples without compromising the original data's content. The efficacy of the proposed method is evaluated through key performance metrics, including false alarm rate (FAR), missed detection rate (MDR), detection time delay (DTD), and computation time (CT). Additionally, gained execution time (GET), gained storage space (GSP), and loss function (LF) are considered, providing a comprehensive assessment of the developed paradigms' effectiveness. The results demonstrate the promising capabilities of our proposed scheme.

关键词： Training Measurement Technological innovation Fault detection Delay effects Computational modeling Complexity theory Kernel Monitoring Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Cascaded with Cross-Attention Network-Based Deformation Vector Field Estimation for Motion-Compensated 4D-CBCT Reconstruction

IEEE Transactions on Computational Imaging

引用

IEEE Transactions on Computational Imaging 2025年 11卷 717-731页

作者： Yuan, Peng Lyu, Fei Gao, Zhiqiang Yang, Chunfeng Hu, Dianlin Zhu, Jian Wu, Zhan Lyu, Tianling Zhao, Wei Dong, Jianmin Chen, Yang Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education Southeast University Nanjing210096 China Laboratory of Image Science and Technology Southeast University Nanjing210096 China Department of Computer Science Hong Kong Baptist University Hong Kong Hong Kong Academy for Advanced Interdisciplinary Science and Technology Zhejiang University of Technology Hangzhou China School of Physics Beihang University Beijing China Beihang Hangzhou Innovation Institute Zhejiang Hangzhou China School of Shandong Cancer Hospital and Institute Shandong First Medical University Shandong Academy of Medical Sciences Jinan Shandong China School of Information Engineering Xizang Minzu University Xianyang712082 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Laboratory of Image Science and Technology The School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing210096 China

Four-Dimensional Cone Beam Computed Tomography (4D-CBCT) imaging technology offers enhanced image quality and spatial resolution for intraoperative guidance, facilitating real-time tracking of tumor position changes during radiotherapy. However, this is still a task of great challenges due to insufficient projections at each respiratory phase after phase-sorting, and the image phases reconstructed directly from phase-sorted data are discrete and discontinuous. To generate high-quality 4D-CBCT deformation vector fields (DVFs), this paper leverages the preoperative static prior image to guide intraoperative dynamic sparse-view reconstruction images for reducing anatomical structure differences, ultimately achieving continuous and dynamic 4D-CBCT imaging. In this paper, we propose a Multi-scale Cascaded residual deformable vector field estimation framework based on Cross-attention in Motioncompensated 4D-CBCT reconstruction (MCCM), which combines Multi-Scale Cascaded residual registration network (MSCNet), Cross-Attention Enhanced feature Fusion (CAEF) module and Structure-Enhanced Motion-Compensated (SEMC) module: 1) the MCCM employs a multi-scale cascaded residual network strategy, merging multi-receptive fields and multi-resolution feature maps for large-scale internal changes. 2) the CAEF is embedded into MSC-Net to facilitate effective communication and learning between features and promote the flow of information. 3) the SEMC is developed to reduce artifacts after intraoperative CBCT sparse-view reconstruction, restore global lung motion changes and local details, and enhance structural information through image fusion. The proposed method has been evaluated using simulated and clinical datasets and has shown promising results by comparative experiment. Our approach exhibits significant improvements across various evaluation metrics. © 2024 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

MOBILE ROBOT POSITION DETERMINATION USING VISUAL LANDMARKS

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 1994年第6期41卷 654-662页

作者： DORAZIO, T LOVERGINE, FP IANIGRO, M STELLA, E DISTANTE, A National Research Council-Institute of Signal and Image Processing Bari Italy

This paper is concerned with the problem of determining the position of a mobile vehicle during navigation. In order to achieve this objective a multisensor navigation system for self location of the robot has been developed. By tracking a few known landmarks with a vision module, the system is able to monitor continuously its position and to integrate these estimates with the measures provided by the vehicle odometers. This paper describes in detail the vision module used by the navigation system.

关键词： Mobile robots Vehicles Navigation Infrared sensors Robot sensing systems Cameras Monitoring Position measurement Layout Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

Short-Term Photovoltaic Power Forecasting-Based Kernel Ridge Regression

Short-Term Photovoltaic Power Forecasting-Based Kernel Ridge...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Manel Marweni Majdi Mansouri Mansour Hajji Mohamed Faouzi Mimouni Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The modern energy landscape is undergoing a seismic change from traditional, finite energy sources and toward cleaner, renewable alternatives. The restrictions faced by traditional sources, which are not only finite but increasingly shrink in the face of burgeoning global energy demands driven by population increase and industrial expansion, are driving this change. Although promising, renewable energy poses complications, particularly the reliance on climatic conditions. An important aspect of addressing these difficulties is effective energy management within distribution systems, which includes forecasting and optimization phases. This research focuses on forecasting using an advanced machine learning (ML) approach. Accurately forecasting renewable energy generation over time is critical for improving energy management. This technique is evaluated using a variety of performance indicators, including Mean Error (ME), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R 2 ). Empirical studies support the method's usefulness, demonstrating noteworthy performance with low error rates.

关键词： Photovoltaic systems Renewable energy sources Technological innovation Accuracy Machine learning Predictive models Forecasting Kernel Energy management Optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Photoacoustic Imaging of CAR-T Cells in Cancer Immunotherapy

Deep Learning for Photoacoustic Imaging of CAR-T Cells in Ca...

引用

Medical Imaging 2025: Ultrasonic Imaging and Tomography

作者： Vale, William Bamber, Jeffrey Koruk, Hasan Carneiro, Gustavo Florescu, Lucia Centre for Vision Speech & Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom Joint Department of Physics Division of Radiotherapy and Imaging The Institute of Cancer Research Sutton LondonSM2 5NG United Kingdom Ultrasound and Underwater Acoustics Group Department of Medical Marine and Nuclear National Physical Laboratory TeddingtonTW11 0LW United Kingdom

ISBN: (纸本)9781510686021

CAR-T cell immunotherapy is a promising technique for cancer treatment. To better understand and improve its efficacy for solid tumours, methods for in-vivo imaging and quantifying the CAR-T cell distribution are necessary. One approach involves inserting a reporter gene into the CAR-T cells, causing them to express photochromic proteins that provide strong near-infrared (NIR) optical contrast. NIR photoacoustic (PA) imaging is then used to image these proteins, and implicitly the CAR-T cells. The laser pulse in PA imaging causes a systematic and repeatable variation in the contrast provided by the photochromic proteins between successive scans that is distinguishable from the constant background contrast. In this study, machine learning (ML) techniques are used to classify and predict the spatial concentration of the proteins by analysing time-series PA images. To address the need for large training datasets, we developed a novel 3D simulation framework, which generates labelled PA images of CAR-T cells expressing the reporter gene. The framework was used to procedurally generate, and simulate imaging of, 629 digital samples, each of these was scanned sequentially by 32 laser pulses, resulting in 20,128 images. Neural networks, specifically a Multi-Layer Perception (MLP) and U-Net, were applied for the pixel-wise binary classification and regression of the reporter protein. These exceeded the performance of a Random Forest (RF) algorithm which was previously applied in another study using a small (n=3) in-vivo dataset. The U-Net achieved a coefficient of determination (R2) of 0.96 and a root mean squared error (RMSE) of 4.3 × 10−9 M, which represents a significant improvement when compared with the R2 of 0.72 and RMSE of 1.1 × 10−8 M achieved by the RF. This study proposes a potential advancement in the accurate non-invasive image detection and quantification of CAR-T cells, with the goal of accelerating preclinical research in cancer immunotherapy for solid tumour

关键词： T-cells

来源：评论

学校读者我要写书评

暂无评论

5G green cellular networks considering power allocation schemes

引用

Science China(Information Sciences) 2016年第2期59卷 112-125页

作者： Xiaohu GE Jiaqi CHEN Cheng-Xiang WANG John THOMPSON Jing ZHANG School of Electronics Information and Communications Huazhong University of Science and Technology Joint Research Institute for Signal and Image Processing School of Engineering & Physical SciencesHeriot-Watt University

It is important to assess the effect of transmit power allocation schemes on the energy consumption on random cellular networks. The energy efficiency of 5G green cellular networks with average and water-filling power allocation schemes is studied in this paper. Based on the proposed interference and achievable rate model,an energy efficiency model is proposed for MIMO random cellular networks. Furthermore, the energy efficiency with average and water-filling power allocation schemes are presented, respectively. Numerical results indicate that the maximum limits of energy efficiency are always there for MIMO random cellular networks with different intensity ratios of mobile stations(MSs) to base stations(BSs) and channel conditions. Compared with the average power allocation scheme, the water-filling scheme is shown to improve the energy efficiency of MIMO random cellular networks when channel state information(CSI) is attainable for both transmitters and receivers.

关键词： energy efficiency cellular networks MIMO achievable rate model power allocation scheme

来源：评论

学校读者我要写书评

暂无评论

Parallel Markov chain Monte Carlo computation for varying-dimension signal analysis

Parallel Markov chain Monte Carlo computation for varying-di...

引用

17th European signal processing Conference, EUSIPCO 2009

作者： Ye, Jing Wallace, Andrew Thompson, John Edinburgh Joint Research Institute in Signal and Image Processing Heriot-Watt University United Kingdom Edinburgh Joint Research Institute in Signal and Image Processing University of Edinburgh United Kingdom

Parallel implementation of Markov Chain Monte Carlo (MCMC) algorithms for Bayesian inference has been effective but is usually restricted to the case where the dimension of the parameter vector is fixed. We propose an efficient parallel solution for the varying-dimension problem by constructing multiple within-model MCMC chains and then combining the separate results to analyze the posterior distribution of dimensionality. We aim for parallel speed-up by reducing the length of the burn-in period and the individual chains in comparison with a serial, reversible jump MCMC (RJMCMC) algorithm. The parallel methodology is illustrated with application to a benchmarking, change point problem. © EURASIP, 2009.

关键词： Chains

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：