检索结果-内蒙古大学图书馆

European signal processing Conference (EUSIPCO)

作者： Anam Hashmi Julia Dietlmeier Kathleen M. Curran Noel E. O'Connor ML-Labs Dublin City University Ireland Insight SFI Research Centre for Data Analytics Dublin City University Ireland School of Medicine University College Dublin Ireland

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

Cine cardiac magnetic resonance (CMR) imaging is recognised as the benchmark modality for the comprehensive assessment of cardiac function. Nevertheless, the acquisition process of cine CMR is considered as an impediment due to its prolonged scanning time. One commonly used strategy to expedite the acquisition process is through k-space undersampling, though it comes with a drawback of introducing aliasing effects in the reconstructed image. Lately, deep learning-based methods have shown remarkable results over traditional approaches in rapidly achieving precise CMR reconstructed images. This study aims to explore the untapped potential of attention mechanisms incorporated with a deep learning model within the context of the CMR reconstruction problem. We are motivated by the fact that attention has proven beneficial in downstream tasks such as image classification and segmentation, but has not been systematically analysed in the context of CMR reconstruction. Our primary goal is to identify the strengths and potential limitations of attention algorithms when integrated with a convolutional backbone model such as a U-Net. To achieve this, we benchmark different state-of-the-art spatial and channel attention mechanisms on the CMRxRecon dataset and quantitatively evaluate the quality of reconstruction using objective metrics. Furthermore, inspired by the best performing attention mechanism, we propose a new, simple yet effective, attention pipeline specifically optimised for the task of cardiac image reconstruction that outperforms other state-of-the-art attention methods. Our code is publicly available at https://***/Hashmi360/CMR_Attention

关键词： Measurement Learning systems Image segmentation Attention mechanisms Magnetic resonance imaging Pipelines signal processing algorithms Magnetic resonance Benchmark testing Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Impact of the CMOS Pixel Clock on Optical Camera Communication Using Rolling Shutter Mode

Impact of the CMOS Pixel Clock on Optical Camera Communicati...

引用

International Symposium on Communication Systems, Networks and Digital signal processing, CNSDSP

作者： Raul Zamorano-Illanes Zabih Ghassemlooy Othman Younus Xicong Li Stanislav Zvánovec Ismael Soto Sebastian Gutierrez Physics and Electrical Engineering Department Optical Wireless Communications Group Photonics Laboratory Mathematics Northumbria University Newcastle upon Tyne Department of Electromagnetic Field Czech Technical University in Prague Prague Czech Republic Electrical Engineering Department CIMTT University of Santiago Chile Facultad de Ingeniería Universidad Autonoma de Chile Chile

ISBN: (数字)9798350348743

ISBN: (纸本)9798350348750

This study delves into the impact of the pixel clock $(p_{\text{clk}})$ on the frequency response of Optical Camera Communication (OCC) systems utilizing rolling shutter mode. Employing an experimental approach, we examine how variations in the $p_{\text{clk}}$ influence the frequency response of a complementary metal-oxide-semiconductor (CMOS) image sensor within OCC links. Our setup incorporates an algorithmic methodology to manipulate and assess internal camera parameters, focusing on the minimum exposure times to optimize signal capture and processing. The findings reveal a direct relation between the $p_{\text{clk}}$ and the achievable frame rate. It is a first approach to delineating its effect on the temporal resolution and bandwidth of the communication channel, showing the importance of these insights for enhancing the design and efficiency of OCC systems. Our research contributes to understanding the hardware limitations and opens future explorations into maximizing the communication performance.

关键词： signal processing algorithms Cameras Optical imaging Frequency response Optical fiber communication Hardware Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Topological Data Analysis for Unsupervised Anomaly Detection in Time Series

Topological Data Analysis for Unsupervised Anomaly Detection...

引用

European signal processing Conference (EUSIPCO)

作者： Alexandre Bois Brian Tervil Laurent Oudre Université Paris Saclay Université Paris Cité ENS Paris Saclay CNRS SSA INSERM Centre Borelli Gif-sur-Yvette France

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

In this article, we propose a new algorithm for unsupervised anomaly detection in univariate time series, based on topological data analysis. It relies on delay embeddings and on the extraction of persistent cycles from the I-dimensional persistent homology module constructed from the distance to measure Rips filtration. This filtration makes it possible to identify 1-cycles (i.e. loops) corresponding to recurrent patterns by leveraging density information. Points in those cycles are considered as normal, and the algorithm can then assign an anomaly score to any point which is its distance to the normal set. In this paper, we describe the algorithm and test it on several real-world datasets, showing that it is competitive with state-of-the-art anomaly detection methods.

关键词： Point cloud compression Data analysis Filtration Time series analysis signal processing algorithms Europe signal processing Delays Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Improving Radar-Camera Fusion Network for Distance Estimation

Improving Radar-Camera Fusion Network for Distance Estimatio...

引用

International Conference on Computer and Automation Engineering, ICCAE

作者： Samuktha V. Hershita Shukla Nitish Kumar Tejasri N. D Santhosh Reddy P Rajalakshmi Department of Artificial Intelligence IIT Hyderabad India Integrated Sensor System Centre for Interdisciplinary Programs IIT Hyderabad India Department of Electrical Engineering IIT Hyderabad India Department of Electrical Engineering NM-ICPS TiHAN IIT Hyderabad India

ISBN: (数字)9798350370058

ISBN: (纸本)9798350370164

In today's world, a sensor-based autonomous industry needs a range of sensors to understand its environment and decide how to function safely and productively. The precise and trustworthy assessment of the surroundings around a vehicle has made a variety of autonomous or assisted driving approaches possible. Hence, we provide a novel radar camera fusion technique based on deep learning that greatly enhances object identification performance. The combination of radar and camera data in particular has emerged as a promising strategy for improving the precision and dependability of object identification systems. However, the performance of current fusion algorithms is frequently constrained by issues with occlusion, variable illumination, and sensor noise. With enhancing capabilities of autonomous vehicles through different algorithms and perception methodologies, it has become important to look into the importance of computationally lighter algorithms which work efficiently as well. Based on the knowledge gleaned from analyzing several deep learning models, we came up with a modified fusion algorithm by adding a number of new operations. The processes of this algorithm consist of improved object identification techniques, feature extraction, and feature fusion. Our approach successfully addresses the issues posed by occlusion, varying illumination, and sensor noise by utilizing the complementary nature of radar and camera technologies, resulting in enhanced object detection performance. In conclusion, this study offers a cutting-edge deep learning-based radar camera fusion technique that surpasses current methods for object detection. Our approach provides improved accuracy, robustness, and real-time performance by using insights from several deep-learning models and including extra processes. The suggested approach provides a sizable improvement in sensor fusion methods, opening the door for more improvements to perception system enhancement.

关键词： Noise signal processing algorithms Radar detection Lighting Radar Object detection Sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Subsample Time Delay Estimation Based on Weighted Straight Line Fitting to Cross-Spectrum Phase

引用

Chinese Journal of Electronics 2023年第3期19卷 553-556页

作者： Yechao Bai Xinggan Zhang Xiaojun Qiu School of Electronic Science and Engineering Nanjing University Nanjing China Institute of Acoustics Nanjing University Nanjing China

Time delay estimation (TDE) lies at the heart of signal processing algorithms, however, the accuracy of conventional TDE algorithms is limited by the sampling interval. An algorithm for TDE with accuracy less than one sampling period is presented in this paper. This algorithm estimates the integral time delay (taking sampling period as a unit) by locating the maximum of Cross-correlation function (CCF), and the fractional part by calculating the slope of the straight line obtained by applying weighted fitting to the cross-spectrum phase. The weight is deduced from Best linear unbiased estimator (BLUE). Estimating the integral part first can avoid phase wrapping. The simulations show that the algorithm outperforms other algorithms for wideband signals.

关键词： Heart Passive radar Delay effects Fitting signal processing algorithms Estimation Delays

来源：评论

学校读者我要写书评

暂无评论

Harmony Search-Based Quantization Bit Allocation on Cell-Free Massive MIMO Systems

Harmony Search-Based Quantization Bit Allocation on Cell-Fre...

引用

European signal processing Conference (EUSIPCO)

作者： Minje Kim In-Soo Kim Junil Choi School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Wireless Research & Development Qualcomm Technologies Inc. San Diego CA USA

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

In this paper, we propose a novel harmony search (HS)-based algorithm for optimizing bit allocation in cell-free massive multiple-input multiple-output (CF-mMIMO) systems, addressing the challenge of quantization errors due to fronthaul capacity limitations. By employing the quantizer, we analyze the impact of bit allocation on quantization noise and formulate an optimization problem focused on sum-rate maximization. Our algorithm, designed to tackle a non-convex combinatorial problem, dynamically updates bit configurations using exploration and exploitation strategies. Simulation results demonstrate that the proposed algorithm significantly improves sum-rate over uniform bit allocation while reducing computational complexity.

关键词： Quantization (signal) Heuristic algorithms Simulation Bit rate signal processing algorithms Open RAN Reliability Computational complexity Optimization signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral imaging using deep learning in wheat diseases: (Review)

Hyperspectral imaging using deep learning in wheat diseases:...

引用

International Conference on Image and signal processing and their Applications (ISPA)

作者： Fadi Abd Eladhim zidi Ouafi Abdelkrim Dept. Electrical Engineering University of Biskra Biskra Algeria

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

Wheat is a significant staple crop worldwide, but its cultivation is challenged by various factors such as pests, diseases, climate change, lack of water, and yield enhancement. To prevent wheat infections, nondestructive and self-sufficient remote detection methods are necessary, which are sensitive and reliable. Hyperspectral imaging with deep learning is a powerful method for identifying diseases early, mapping them accurately, and evaluating their severity in plants in an unbiased way. This method involves data collection, preprocessing, and analysis of Hyperspectral images to identify wheat diseases. The article also presents several Hyperspectral imaging datasets and relevant research on using this technology for detecting wheat illnesses. The integration of spectroscopy and imaging in Hyperspectral imaging represents a novel approach to achieving an in-depth and comprehensive understanding of plant life. Moreover, deep learning, a subset of artificial intelligence, has gained considerable attention due to its ability to process vast and intricate data sets. By synergistically merging these two advanced technologies, researchers and scientists can significantly enhance the analysis of hyperspectral imagery, thereby enabling improved crop monitoring, disease identification, and yield projection in wheat farming This article summarizes the use of deep learning techniques in Hyperspectral imaging for wheat crops. Hyperspectral imaging is a non-destructive way to study crops but generates a lot of data that can be difficult to analyze. Deep learning automates the analysis process and improves accuracy. However, it requires large and diverse datasets, complex model development, and computational resources. This report provides information on the benefits and challenges of using deep learning in Hyperspectral imaging for wheat crops.

关键词： Deep learning Plant diseases Spectroscopy Crops signal processing algorithms signal processing Reliability Climate change Hyperspectral imaging Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture-Driven Speech Aid for Mute Individuals

Hand Gesture-Driven Speech Aid for Mute Individuals

引用

Intelligent Systems and Embedded Design (ISED), International Conference on

作者： Surya Ha K S Venkatram Vishal Seshadri B Sanggit Saaran K C S Malathi M Rahul Satheesh Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9798331522612

ISBN: (纸本)9798331522629

Effective communication is fundamental to human interaction, yet approximately 6.1% of the global population is deprived of this ability due to damaged vocal cords. This impairment hinders their capacity to share thoughts and emotions, isolating them from their community. Traditional methods like hand gestures and sign language offer a solution, but the lack of universal knowledge of these signs creates further obstacles. To bridge this communication gap, a novel system has been introduced that utilizes Arduino Mega and flex sensors as the hardware foundation, and the K-Nearest Neighbors (KNN) machine learning algorithm as the software core, this model facilitates the recognition and interpretation of hand gestures. This innovative approach promises to dismantle the barriers faced by those with speech impairments, fostering and understanding in everyday interactions.

关键词： Hands Support vector machines Flexible printed circuits Accuracy Machine learning algorithms Computational modeling signal processing algorithms Speech recognition Nearest neighbor methods Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Integrated Wavelet Decomposition and Multi-Model Approach with Fractional-Order Sparrow Search Optimization for ECG Classification

Integrated Wavelet Decomposition and Multi-Model Approach wi...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Zhiwei Xiao Jiejie Chen Ping Jiang Bin Wei School of Computer and Information Engineering Hubei Normal University Huangshi China School of Computer Hubei PolyTechnic University Huangshi China

ISBN: (数字)9798331508661

ISBN: (纸本)9798331508678

The classification of electrocardiogram (ECG) signals plays a crucial role in medical diagnostics, as accurate classification can significantly enhance the efficiency of heart disease diagnosis. This research introduces a novel method, Integrated Wavelet Decomposition and Multi-Model Approach with Fractional-Order Sparrow Search Optimization (WMFO). The method employs wavelet decomposition (WD) to decompose ECG signals into six distinct frequency components, with each component being trained using different models. The hyperparameters of these models are fine-tuned through the Fractional-Order Sparrow Search Algorithm (FOSSA), further improving the adaptability and accuracy of the models. The WMFO achieved a balanced accuracy of 93.08%, a geometric mean of 82.87%, and a Youden's index of 80.27% on the MIT-BIH arrhythmia dataset. Additionally, ablation and comparative experiments demonstrated the superior performance of this method in ECG classification tasks.

关键词： Training Adaptation models Accuracy Arrhythmia signal processing algorithms Electrocardiography signal processing Classification algorithms Medical diagnosis Optimization

来源：评论

学校读者我要写书评

暂无评论

User-Centric Cell-Free Massive MIMO With RIS-Integrated Antenna Arrays

User-Centric Cell-Free Massive MIMO With RIS-Integrated Ante...

引用

IEEE Workshop on signal processing Advances in Wireless Communications (SPAWC)

作者： Özlem Tuğfe Demir Emil Björnson Department of Electrical-Electronics Engineering TOBB University of Economics and Technology Ankara Türkiye Department of Computer Science KTH Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9798350393187

ISBN: (纸本)9798350393194

Cell-free massive MIMO (multiple-input multiple-output) is a promising network architecture for beyond 5G systems, which can particularly offer more uniform data rates across the coverage area. Recent works have shown how reconfigurable intelligent surfaces (RISs) can be used as relays in cell-free massive MIMO networks to improve data rates further. In this paper, we analyze an alternative architecture where an RIS is integrated into the antenna array at each access point and acts as an intelligent transmitting surface to expand the aperture area. This approach alleviates the multiplicative fading effect that normally makes RIS-aided systems inefficient and offers a cost-effective alternative to building large antenna arrays. We use a small number of antennas and a larger number of controllable RIS elements to match the performance of an antenna array whose size matches that of the RIS. In this paper, we explore this innovative transceiver architecture in the uplink of a cell-free massive MIMO system for the first time, demonstrating its potential benefits through analytic and numerical contributions. The simulation results validate the effectiveness of our proposed phase-shift configuration and highlight scenarios where the proposed architecture significantly enhances data rates.

关键词： Wireless communication Array signal processing Architecture Transmitting antennas signal processing algorithms Massive MIMO Reconfigurable intelligent surfaces Arrays Uplink Antenna arrays

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：