检索结果-内蒙古大学图书馆

IEEE Open Journal of the Communications Society 2025年 6卷 4083-4100页

作者： Lancho, Alejandro Weiss, Amir Lee, Gary C. F. Jayashankar, Tejas Kurien, Binoy G. Polyanskiy, Yury Wornell, Gregory W. Universidad Carlos III de Madrid Signal Theory and Communications Leganés28911 Spain Gregorio Marañón Health Research Institute Madrid28007 Spain Bar-Ilan University Ramat Gan5290002 Israel Institute for Infocomm Research Communications and Networks Fusionopolis 138632 Singapore Massachusetts Institute of Technology Electrical Engineering and Computer Science Department CambridgeMA02139 United States MIT Lincoln Laboratory LexingtonMA02421 United States

We address the critical problem of interference rejection in radio-frequency (RF) signals using a data-driven approach that leverages deep-learning methods. A primary contribution of this paper is the introduction of the RF Challenge, which is a publicly available, diverse RF signal dataset for data-driven analyses of RF signal problems. Specifically, we adopt a simplified signal model for developing and analyzing interference rejection algorithms. For this signal model, we introduce a set of carefully chosen deep learning architectures, incorporating key domain-informed modifications alongside traditional benchmark solutions to establish baseline performance metrics for this intricate, ubiquitous problem. Through extensive simulations involving eight different signal mixture types, we demonstrate the superior performance (in some cases, by two orders of magnitude) of architectures such as UNet and WaveNet over traditional methods like matched filtering and linear minimum mean square error estimation. Our findings suggest that the data-driven approach can yield scalable solutions, in the sense that the same architectures may be similarly trained and deployed for different types of signals. Moreover, these findings further corroborate the promising potential of deep learning algorithms for enhancing communication systems, particularly via interference mitigation. This work also includes results from an open competition based on the RF Challenge, hosted at the 2024 IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP'24). © 2020 IEEE.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

Research on image Enhancement Technology and Signal processing Methods in Teaching Hydraulic systems

Research on Image Enhancement Technology and Signal Processi...

引用

Digital Analysis and processing, Intelligent Computation (DAPIC), International conference on

作者： Shijie Guan Pengpeng Liu Zhengyi Zhang Weiwei Dong Xiangtong Kong High-tech Institute QingZhou Shandong China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

Hydraulic system as an important part of industrial automation, its teaching effect directly affects the quality of related technical personnel training. Hydraulic transmission course is a theoretical and practical combination of the post course offered by our non-commissioned officers' vocational and technical education in mechanical manufacturing technology, because the hydraulic system involves complex images and signal data, students often face difficulties in understanding and analyzing in the learning process. Through the course, students can systematically master the basic theoretical knowledge of the hydraulic transmission system, familiar with the structural composition and working principle of commonly used hydraulic components, and master the working principle and characteristics of common basic circuits. This paper proposes to combine image enhancement technology with signal processing methods to optimize the teaching of hydraulic system. By analyzing the application of image enhancement technology in image denoising, edge detection and brightness adjustment, as well as the practical effect of signal processing methods in frequency domain analysis, time-frequency analysis and intelligent algorithms, we explore how to enhance students' theoretical understanding and practical ability of hydraulic system. The study shows that the integration of image and signal processing technology can not only significantly improve the teaching efficiency, but also provide technical support for the construction of intelligent teaching mode in the future.

关键词： Training Time-frequency analysis image edge detection Education Brightness Hydraulic systems Virtual reality Signal processing image enhancement image denoising

来源：评论

学校读者我要写书评

暂无评论

Exploration of Motion Increase Rate Based on Infrared Feature Capture and CFD Numerical Simulation

Exploration of Motion Increase Rate Based on Infrared Featur...

引用

Electronics, Energy systems and Power Engineering (EESPE), IEEE International conference on

作者： Minghan Wang Beijing University of Technology Beijing China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

The purpose of this study is to explore the motion incremental speed technology based on infrared feature capture and CFD numerical simulation, through the sensor, image processing and analysis algorithms, etc. On the basis of exploring the target's motion characteristics, combined with the Chancellor's theory of ballistic trajectory, and real-time capture of the target's thermal feature information is to achieve accurate target tracking and motion trajectory adjustment. Firstly, this paper adopts the image processing and analysis algorithm, and uses the normal distribution model to process the infrared data, so as to construct the target motion model. Secondly, CFD numerical simulation is used to analyse mechanisms such as motion boost guidance in order to provide more accurate target tracking and trajectory correction schemes. Finally, the motion region of the updraft is predicted by spherical averaging of the fluctuation equation. The results show that the infrared feature capture technique is able to maintain efficient motion track correction and motion speed-up capability based on real-time data processing in dynamic environments.

关键词： Target tracking Accuracy image processing Gaussian distribution Numerical simulation Mathematical models Real-time systems Data models Numerical models Trajectory

来源：评论

学校读者我要写书评

暂无评论

A Novel Artistic image Compression Algorithm Based on Multi-Scale Adaptive Discrete Wavelet Transform

A Novel Artistic Image Compression Algorithm Based on Multi-...

引用

Multi-Agent systems for Collaborative Intelligence (ICMSCI), International conference on

作者： Yijun Li China Academy of Art Yuhang District Hangzhou Zhejiang China

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

How to compress information is a challenge in the digital age, and the image compression has a wide range of application scenarios. In order to solve the challenges of low compression efficiency and high loss rate of the traditional algorithms, this study proposes a compression algorithm based on multi-scale adaptive discrete wavelet transform. The core of the proposed algorithm is to make reasonable use of the multiresolution analysis characteristics of discrete wavelet transform. Based on the feature extraction, the image information is decomposed into high-frequency and low-frequency parts. This operation can stably and effectively implement frequency domain threshold processing and reduce redundant data. The proposed algorithm optimizes the encoding efficiency of image features to the greatest extent by introducing block difference features and designing a new iterative function system. In view of the high redundancy and high complexity of the artistic images, the traditional wavelet analysis is improved and optimized, and a multi-scale adaptive model is introduced. In the experiment, the test used multiple sets of artistic image test sets and compared them with mainstream algorithms (JPEG, VAE, etc.). In PSNR analysis, the proposed algorithm achieves better performance.

关键词： image coding Wavelet transforms Transforms Discrete wavelet transforms Feature extraction Wavelet analysis Wavelet domain Compression algorithms Frequency-domain analysis Collaborative intelligence

来源：评论

学校读者我要写书评

暂无评论

processing and Classification algorithms of Medical images

Processing and Classification Algorithms of Medical Images

引用

International image processing, Applications and systems conference (IPAS)

作者： Oltiana Seitaj Department of Industrial Engineering Electronics Mechanics University of Roma Tre Rome Italy

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

This paper evaluates the impact of hybrid deep learning approaches on lung tumor segmentation by combining traditional image processing techniques with advanced AI-driven models. The study integrates Convolutional Neural Networks (CNNs) with preprocessing methods such as noise reduction, adaptive thresholding, and contrast enhancement to address challenges associated with complex anatomical structures and variability in medical image quality. A novel hybrid framework is proposed, leveraging traditional methods to preprocess data and improve input quality for deep learning models, ultimately enhancing segmentation accuracy and *** effectiveness of the proposed approach is assessed using quantitative performance metrics, including Dice Similarity Coefficient (DSC), Hausdorff Distance, Jaccard Index, Precision, and Recall. Preliminary results indicate significant improvements in tumor boundary detection and reduced false-positive rates compared to existing methods. By streamlining segmentation workflows and enabling near-realtime applications in clinical settings, this research offers a pathway to improved diagnostic accuracy, treatment planning, and workflow *** implications include the potential for integration into clinical imaging pipelines, fostering advancements in computer-assisted diagnosis and personalized treatment strategies. This study underscores the value of hybrid methodologies in addressing current limitations and paving the way for more precise and efficient medical image segmentation.

关键词： Deep learning image segmentation Adaptation models Accuracy Thresholding (Imaging) Streaming media Reliability MATLAB Biomedical imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

A Study on multi-scale landscape character extraction combining GIS and graphic processing algorithms 3

A Study on multi-scale landscape character extraction combin...

引用

3rd International conference on Environmental Remote Sensing and Geographic Information Technology, ERSGIT 2024

作者： Wang, Shuwei Liu, Yang Li, Guangqi Su, Xueying Wang, Sen Bai, Xuyong Center for Geophysical Survey China Geological Survey Langfang China Technology Innovation Center for Earth Near Surface Detection China Geological Survey China

ISBN: (纸本)9781510690219

This research presents an innovative approach to accurately extract multi-scale landscape characters by combining geographic information systems (GIS) and graphic processing algorithms. It is essential to recognize and analyze landscape characters at different scales. This study uses GIS advantages in spatial analysis and the K-Means clustering algorithm in image enhancement, feature extraction, image segmentation, and color quantification. Through image interpretation and deep learning, the distribution characteristics of buildings in Langfang City are obtained to provide guidance and suggestions for the future construction and development of the city. The proposed method covers data preparation, algorithm design, and system implementation. In addition, the future research direction of improving the method is also discussed, and the possibility of its application in other fields is explored. © 2025 SPIE.

关键词： deep learning K-Means multi-scale landscape analysis spatial analysis. GIS

来源：评论

学校读者我要写书评

暂无评论

OCTA-Based Biomarker Characterization in nAMD

OCTA-Based Biomarker Characterization in nAMD

引用

International image processing, Applications and systems conference (IPAS)

作者： Maria Simona Tivadar Ioana Damian Adrian Petru Groza Simona Delia Nicoara Department of Computer Science Technical University of Cluj-Napoca Romania European University of Technology European Union Department of Ophthalmology "Iuliu Hatieganu" University of Medicine and Pharmacy Emergency County Hospital Cluj-Napoca Romania

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

We aim to enhance ophthalmologists’ decision-making when diagnosing the Neovascular Age-Related Macular Degeneration (nAMD). We developed three tools to analyze Optical Coherence Tomography Angiography images: (1) extracting biomarkers such as mCNV area and vessel density using image processing; (2) generating a 3D visualization of the neovascularization for a better view of the affected regions; and (3) applying an ensemble of three white box machine learning algorithms (decision tree, support vector machines and DL-Learner) for nAMD diagnosis. The learned expressions reached 100% accuracy for the training data and 68% accuracy in testing. The main advantage is that all the learned models white-box, which ensures explainability and transparency, allowing clinicians to better understand the decision-making process.

关键词： Three-dimensional displays Accuracy Optical coherence tomography image processing Angiography Decision making Medical services Machine learning Biomarkers Glass box

来源：评论

学校读者我要写书评

暂无评论

Sclera Segmentation on the Half-UNet Neural Network

Sclera Segmentation on the Half-UNet Neural Network

引用

Digital Signal processing and its Applications (DSPA), International conference on

作者： Sergei Chernyadyev Natalya Kharina Department of the Radio Electronic Means Vyatka State University Kirov Russia

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

Nowadays, technology for biometric authentication technologies is actively implemented, users can usually authenticate themselves by their face, voice, fingerprint, vascular bed of the finger, palm, iris. Using images of sclera vessels for authentication is mathematically and technically more complex, so it is used less often. In addition, existing sclera segmentation algorithms often do not allow ensuring the required quality of authentication systems. The paper proposes an algorithm for sclera segmentation based on the lightweight convolutional neural network Half-UNet, and compares the obtained results with known algorithms for sclera segmentation. Analysis of the obtained results shows that the developed algorithm effectively highlights the eye sclera region, surpassing known modern algorithms, and can be used in implementation of biometric authentication system as a stage of processing scanner images before the sclera vessels segmentation stage.

关键词： Performance evaluation image segmentation Neural networks Memory management Signal processing algorithms Authentication Biometric authentication Mobile handsets System implementation Iris recognition

来源：评论

学校读者我要写书评

暂无评论

Productivity Estimation Based on Optical Remote Sensing image Spatiotemporal Fusion Algorithm 6th

Productivity Estimation Based on Optical Remote Sensing Imag...

引用

6th International conference on Cyber Security Intelligence and Analytics, CSIA 2024

作者： Chu, Jingyi UC Santa Barbara Santa BarbaraCA93117 United States

ISBN: (纸本)9783031882869

With the rapid development of remote sensing technology, the application of optical remote sensing images in productivity estimation is becoming increasingly widespread. However, due to the limited temporal and spatial resolution of remote sensing images, accurately estimating productivity still faces challenges. This study improves the spatiotemporal resolution of optical remote sensing images through spatiotemporal fusion algorithms to achieve more accurate productivity estimation. We use advanced spatiotemporal fusion technology to combine high temporal resolution but low spatial resolution images with high spatial resolution but low temporal resolution images to generate composite images with high spatiotemporal resolution. These composite images can more accurately capture the dynamic changes in surface productivity. Even at the longest time scale of 3 months, the spectral fidelity remains at a high level of 0.87, indicating that the model still has good spectral fidelity performance when processing remote sensing images with long time intervals. This study not only improves the accuracy of productivity estimation, but also provides new data support for resource management and decision-making in industries such as agriculture and forestry, which has important theoretical and practical significance. In addition, our method can also provide reference for other fields and promote the widespread application and development of remote sensing technology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign and Obstacle Detection for Autonomous Vehicle Navigation using Edge Computing

Traffic Sign and Obstacle Detection for Autonomous Vehicle N...

引用

International conference on Wireless Communications, Signal processing and Networking (WiSPNET)

作者： M. Vijayalakshmi M. Bharathwaj D. Anjelin Deva Dharshini Department of IST CEG Anna University Chennai India

ISBN: (数字)9798331524227

ISBN: (纸本)9798331524234

The advancement of autonomous vehicle technology necessitates robust systems for real-time traffic sign recognition and obstacle detection to ensure safe navigation. This paper proposes a comprehensive autonomous vehicle (AV) simulation framework utilizing the Carla simulator, advanced image processing, and state-of-the-art machine learning models to enhance autonomous navigation capabilities. The system initiates by loading a specified virtual map within the Carla simulator and deploying an ego vehicle equipped with a camera sensor to capture environmental images. These images undergo preprocessing techniques, to ensure suitability for analysis. Traffic sign recognition system uses a pre-trained YOLOv7 model, enabling the AV to identify and respond to various traffic signals amidst occlusion, adverse weather, and variations in placement and size. Concurrently, a pre-trained Faster R-CNN model detects obstacles such as vehicles and pedestrians along the vehicle’s path. A dedicated distance estimation module further analyzes these preprocessed images to calculate the relative distances of detected obstacles using depth estimation techniques, providing crucial spatial information. The decision-making algorithm resolves conflicts between recommended actions from traffic sign recognition and obstacle detection modules, prioritizing safety-critical commands to ensure operational safety and efficiency. The models are stored on the network edge, facilitating efficient deployment and real-time processing. This framework demonstrates an effective integration of simulation, image analysis, and decision-making, advancing the reliability and performance of autonomous navigation systems.

关键词： Navigation Heuristic algorithms Decision making Signal processing algorithms Cameras Real-time systems Road safety Classification algorithms Autonomous vehicles Edge computing

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：