检索结果-内蒙古大学图书馆

Improvement of 2D cine image quality using 3D priors and cycle generative adversarial network for low field MRI-guided radiation therapy

引用

MEDICAL PHYSICS 2024年第5期51卷 3495-3509页

作者： Dong, Yuyan Yang, Fei Wen, Jie Cai, Jing Zeng, Feiyan Liu, Mengqiu Li, Shuang Wang, Jiangtao Ford, John Chetley Portelance, Lorraine Yang, Yidong Univ Sci & Technol China Dept Engn & Appl Phys Hefei Anhui Peoples R China Univ Miami Miller Sch Med Miami FL USA Univ Sci & Technol China Affiliated Hosp USTC 1 Dept Radiol Div Life Sci & Med Hefei Anhui Peoples R China Hong Kong Polytech Univ Dept Hlth Technol & Informat Kowloon Hong Kong Peoples R China Sichuan Acad Med Sci Canc Ctr Sichuan Prov Peoples Hosp Chengdu Sichuan Peoples R China Univ Sci & Technol China Affiliated Hosp USTC 1 Dept Radiat Oncol Div Life Sci & Med Hefei Anhui Peoples R China Univ Sci & Technol China Sch Phys Sci Med Phys Program Hefei Anhui Peoples R China

BackgroundCine magnetic resonance (MR) images have been used for real-time MR guided radiation therapy (MRgRT). However, the onboard MR systems with low-field strength face the problem of limited image *** improve the quality of cine MR images in MRgRT using prior image information provided by the patient planning and positioning MR *** study employed MR images from 18 pancreatic cancer patients who received MR-guided stereotactic body radiation therapy. Planning 3D MR images were acquired during the patient simulation, and positioning 3D MR images and 2D sagittal cine MR images were acquired before and during the beam delivery, respectively. A deep learning-based framework consisting of two cycle generative adversarial networks (CycleGAN), Denoising CycleGAN and Enhancement CycleGAN, was developed to establish the mapping between the 3D and 2D MR images. The Denoising CycleGAN was trained to first denoise the cine images using the time domain cine image series, and the Enhancement CycleGAN was trained to enhance the spatial resolution and contrast by taking advantage of the prior image information from the planning and positioning images. The denoising performance was assessed by signal-to-noise ratio (SNR), structural similarity index measure, peak SNR, blind/reference-less image spatial quality evaluator (BRISQUE), natural image quality evaluator, and perception-based image quality evaluator scores. The quality enhancement performance was assessed by the BRISQUE and physician visual scores. In addition, the target contouring was evaluated on the original and processed *** differences were found for all evaluation metrics after Denoising CycleGAN processing. The BRISQUE and visual scores were also significantly improved after sequential Denoising and Enhancement CycleGAN processing. In target contouring evaluation, Dice similarity coefficient, centroid distance, Hausdorff distance, and average surface distance val

关键词： cine MRI CycleGAN image quality positioning MR images prior images

来源：评论

学校读者我要写书评

暂无评论

SEMUS-An Open-Source RF-Level SAR Emulator for Interference modeling in Spaceborne Applications

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC systems 2025年第2期61卷 1394-1408页

作者： Hendy, Nermine Kurnia, Ferdi Ganda Kraus, Thomas Bachmann, Markus Martorella, Marco Evans, Robin J. Zink, Manfred Fayek, Haytham M. Al-Hourani, Akram RMIT Univ STEM Coll Sch Engn Melbourne Vic 3000 Australia German Aerosp Ctr DLR D-82234 Oberpfaffenhofen Germany Univ Melbourne Sch Engn Dept Elect & Elect Engn Parkville Vic 3010 Australia Univ Melbourne Sch Engn Dept Elect & Elect Engn Parkville Vic 3010 Australia RMIT Univ STEM Coll Sch Comp Technol Melbourne Vic 3000 Australia

Earth observation has a crucial role in understanding and monitoring our planet's health and changes. Spaceborne synthetic aperture radar (SAR) has become a valuable technology for Earth monitoring, leading to a massive expansion of satellite launches. However, within the limited radio frequency (RF) band, radio frequency interference (RFI) poses a significant challenge for SAR technology. RFI can have a substantial impact on the overall system performance and particularly on SAR image quality. To analyze and solve the interference problem, a simulator/emulator is required at the RF level to emulate and analyze the effects of different RFI sources on the final focused spaceborne SAR image. This article presents an open-source RF-level SAR emulator for spaceborne applications called SEMUS. SEMUS is an integrated end-to-end framework for realistic spaceborne SAR scenarios that can generate raw RF data (Level-0) for an arbitrary scene and reconstruct the final SAR-focused image (Level-1). Moreover, the emulator is capable of injecting arbitrary RFI waveforms into the raw SAR data. The simulation results prove SEMUS's ability to generate high-quality Level-0 SAR data above Melbourne, Australia. Affirming its capability, SEMUS can reconstruct Level-1 free of RFI or contaminated with interference.

关键词： Synthetic aperture radar Spaceborne radar Radar polarimetry Interference Earth Australia Radio frequency Emulator open-source radar radio frequency interference (RFI) signal processing spaceborne synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Effective Methods of Neural Network Pruning in processing-In-Memory Architecture 24

Effective Methods of Neural Network Pruning in Processing-In...

引用

24th International Conference on Control, Automation and systems

作者： Park, Jonghee Jang, Sung-Joon Shin, Hojong Kwak, Jonghoon Intelligent Image Proc Res Ctr Korea Elect Technol Inst Gyeonggi Do 13488 South Korea

ISBN: (纸本)9798331517939;9788993215380

The PIM (processing in Memory) architecture, performing MAC operations inside memory, garners attention as a next-gen deep learning processor by eliminating memory movement between memory and computation units, unlike NPUs and GPUs. However, applying conventional network pruning for the same purpose faces challenges due to small memory and analog-based MAC operations in PIM. This paper proposes techniques for effective network pruning, demonstrating how weight pruning based on temperature/humidity modeling can mitigate inference noise in PIM. Additionally, it introduces a grouping-based importance metric for channel pruning applicable to any hardware. Both approaches quantitatively enhance performance in simulation, proving their efficacy.

关键词： processing in memory network pruning noise reduction

来源：评论

学校读者我要写书评

暂无评论

eMNv4-YOLO: A High-Efficiency Target Detection Framework for Robotic Driving Vehicle Instrument Reading

引用

IEEE ACCESS 2025年 13卷 47123-47131页

作者： Lei, Yin Shan, Chen Ge, Wancheng Wang, Xinhong Hu, Jianyao Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China Minist Ind & Informat Technol Elect Res Inst 5 Guangzhou 510610 Peoples R China

In the domain of autonomous vehicle testing, a crucial challenge in implementing onboard information perception systems is the development of lightweight detection network models that can be efficiently deployed on edge devices. In this study, we collected and collated 6,168 images encompassing automotive dashboards, industrial instruments, and automotive simulation test instruments, which possess diverse features. Subsequently, we performed manual annotation on these images to construct the instrument detection dataset, namely Complex_Dashboard_Dataset. To satisfy the environmental perception requirements of mobile driving robots, this paper presents an enhanced feature recognition and detection model for automotive dashboards, named *** model combines the YOLO object detection framework with the lightweight deep learning model MobileNetV4. Moreover, a novel lightweight convolutional module, EPDConv, was introduced in this study to further reduce the model parameters, thereby yielding the refined eMNv4 model. In addition, a highly robust and efficient automotive dashboard reading recognition algorithm, SAGR, was developed by integrating machine vision image processing algorithms and template matching algorithms. The experimental results show that the eMNv4-YOLO model achieved an mAP50 detection result of 96.4% on the constructed dataset, whereas the model parameter count was reduced to only 2.0M, substantially reducing the model size and computational complexity. Finally, the verification of a real vehicle validated the effectiveness of the SAGR algorithm. In conclusion, the eMNv4-YOLO model designed in this study has extensive applicability to information perception systems on edge mobile devices, providing an effective object detection solution in the field of autonomous driving.

关键词： YOLO Convolution Feature extraction Automotive engineering Accuracy Computational modeling Robots Autonomous vehicles image edge detection performance evaluation Autonomous driving lightweight model object detection MobileNet meter reading

来源：评论

学校读者我要写书评

暂无评论

ToSiM-IoT: Toward a Sustainable Optimization of Machine Learning Tasks in Internet of Things

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第11期12卷 16829-16840页

作者： Kaushal, Ashish Almurshed, Osama Muftah, Asmail Auluck, Nitin Rana, Omer Indian Inst Technol Ropar Dept Comp Sci Engn Rupnagar 140001 India Cardiff Univ Sch Comp Sci Informat Cardiff CF10 3AT Wales Azzaytuna Univ Dept Comp Sci Tarhunah Libya

With the rise of digital infrastructure and Internet of Things (IoT), a substantial amount of data is continuously generated that needs to be processed efficiently. While modern artificial intelligence (AI) approaches have shown good capabilities in handling large volumes of data, their excessive demands for memory and processing power result in very high utilization of resources. In this work, we propose ToSiM-IoT, an optimization framework that introduces a layer selection approach to identify an ideal mix of active, and inactive layers, using a genetic algorithm for model training. Next, we design a pruning mechanism that identifies performance-critical features using heatmap visualization, during model inference, and eliminates the remaining features. Two machine learning (ML) models: 1) InceptionV3 and 2) VGG16, have been evaluated on an agricultural weed detection scenario, using the DeepWeeds image classification dataset. Experimental results demonstrate that our framework can achieve a significant reduction in model size and training time, while maintaining high accuracy, for both models. Therefore, this approach provides the potential to be efficiently deployed on intelligent IoT systems where computational capabilities are limited.

关键词： Computational modeling Training Internet of Things Accuracy Sustainable development Adaptation models Quantization (signal) performance evaluation Neural networks Memory management Channel pruning genetic algorithm heatmap visualization Internet of Things (IoT) layer selection machine learning (ML) optimization

来源：评论

学校读者我要写书评

暂无评论

Secure biometric systems based on bio-signals and DNA encryption of optical spectrograms

引用

OPTICS EXPRESS 2023年第3期31卷 3927-3944页

作者： Salama, Gerges M. Omar, Basma El-shafai, Walid El-banby, Ghada M. Hamed, Hesham F. A. El-Gazar, Safaa Soliman, Naglaa F. El-Samie, Fathi E. Abd Minia Univ Fac Engn Dept Elect Engn Al Minya 61111 Egypt Prince Sultan Univ Dept Comp Sci Secur Engn Lab Riyadh 11586 Saudi Arabia Menoufia Univ Fac Elect Engn Dept Elect & Elect Commun Engn Menoufia 32952 Egypt Menoufia Univ Fac Elect Engn Dept Ind Elect & Control Engn Menoufia 32952 Egypt Egyptian Russian Univ Fac Engn Dept Elect Engn Cairo Egypt Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Technol POB 84428 Riyadh 11671 Saudi Arabia

Recently, biometrics has become widely used in applications to verify an individual's identity. To address security issues, biometrics presents an intriguing window of opportunity to enhance the usability and security of the Internet of Things (IoT) and other systems. It can be used to secure a variety of newly emerging IoT devices. However, biometric scenarios need more protection against different hacking attempts. Various solutions are introduced to secure biometrics. Cryptosystems, cancelable biometrics, and hybrid systems are efficient solutions for template protection. The new trend in biometric authentication systems is to use bio-signals. In this paper, two proposed authentication systems are introduced based on bio-signals. One of them is unimodal, while the other is multimodal. Protected templates are obtained depending on encryption. The deoxyribonucleic acid (DNA) encryption is implemented on the obtained optical spectrograms of bio-signals. The authentication process relies on the DNA sensitivity to variations in the initial values. In the multimodal system, the singular value decomposition (SVD) algorithm is implemented to merge bio-signals. Different evaluation metrics are used to assess the performance of the proposed systems. simulation results prove the high accuracy and efficiency of the proposed systems as the equal error rate (EER) value is close to 0 and the area under the receiver operator characteristic curve (AROC) is close to 1. The false accept rate (FAR), false reject rate (FRR), and decidability (D) are also estimated with acceptable results of 1.6 x 10-8, 9.05 x 10-6, and 29.34, respectively. simulation results indicate the performance stability of the proposed systems in the presence of different levels of noise. (c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： image encryption image processing Neural networks Power spectral density signal processing Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Environment-Specific Ray-Tracing Channel modeling in Massive MIMO systems 26

Environment-Specific Ray-Tracing Channel Modeling in Massive...

引用

26th International Conference on Digital signal processing and its Applications, DSPA 2024

作者： Strelnikov, Anton Lyashev, Vladimir Sherstobitov, Alexander Volkov, Alexey National Research University of Electronic Technology Moscow Russia Moscow Institute of Physics and Technology Moscow Russia Moscow Radio Transmission Technology Laboratory Moscow Russia

ISBN: (纸本)9798350361728

In this paper we investigate the properties of deterministic ray-tracing channel modeling considering extended options of diffraction and diffuse scattering of electromagnetic waves in modern wireless communications system. The feature of environment-specific simulation describes the geometrical properties, which can be utilized for specific scenarios of frequency-selective channels in Non-Line-of-Site conditions. The theory of channel characterization for diffraction and scattering allows to bring more significant multipath components in application to massive multiple-input multiple-output antenna technology with large signal bandwidth in wireless system. Here a base station utilizes large-scale antenna panels to provide high-performance throughput to the user-equipment by accurate beamforming technique. In this work we analyze spatial consistency of multiplexing problem, power delay profile evaluation and capacity assessments in the ray-tracing channel modeling under the different path propagation conditions. © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Ultrasonic characterization of defects in polycrystalline materials based on TFM image reconstruction using denoising diffusion probabilistic models

引用

MECHANICAL systems AND signal processing 2025年 224卷

作者： Guo, Changrong Ding, Yue Cui, Hua Xu, Jianfeng Bai, Long Huazhong Univ Sci & Technol Sch Mech Sci & Engn State Key Lab Intelligent Mfg Equipment & Technol Wuhan 430074 Peoples R China

This paper presents a refined ultrasonic total focusing method (TFM) for accurately characterizing key defect parameters including size, orientation, and location in complex materials. The proposed approach aims to accurately reconstruct the defect shape in images compromised by grain interference. First, a TFM image database was generated with varying defect parameters and grain noise levels by adopting a custom forward modeling process based on superposition of defect and grain scattering data. Second, a new architecture called TFM-DDPM was then proposed which incorporates TFM and the conditional denoising diffusion probabilistic model (DDPM). Third, pixel-level uncertainty can be quantified through repeated sampling of noise which follows a standard normal distribution. An acceptance criterion for the reconstruction was further established by analyzing the quantified uncertainty. In simulation, the median Dice coefficient between the de-noised TFMs of 30 degrees cracks and their corresponding ground truth images increased from 0.5585 to 0.9137 using the proposed approach, and the median IoU metric rose from 0.3875 to 0.8408. By applying the 6-dB drop approach to the reconstructed images, the root mean squared errors (RMSEs) of size, angle and location were decreased by 93.59%, 86.90% and 86.25%, respectively. It is also demonstrated that our method can reject 69.19% of incorrect characterization results caused by high levels of noise and/or images with steeply inclined (e.g., 45 degrees) cracks, while accepting 97.29% accurate results. Experimental results obtained on nickel-based alloy K403 specimens also exhibited significant improvements. For 2-3 mm cracks, the average sizing error reduced from 0.46 mm to 0.13 mm, and the error in crack angle decreased from 28.63 degrees to 1.50 degrees. Comparable performance enhancements were observed for 4-5 mm cracks using the proposed approach.

关键词： Polycrystalline materials Denoising diffusion probabilistic model Total focusing method Uncertainty quantification Ultrasonic arrays

来源：评论

学校读者我要写书评

暂无评论

RNS-Based FPGA Accelerators for High-Quality 3D Medical image Wavelet processing Using Scaled Filter Coefficients

引用

IEEE ACCESS 2022年 10卷 19215-19231页

作者： Nagornov, Nikolay N. Lyakhov, Pavel A. Valueva, Maria V. Bergerman, Maxim, V North Caucasus Fed Univ Dept Math Modeling Stavropol 355017 Russia North Caucasus Fed Univ North Caucasus Ctr Math Res Stavropol 355017 Russia

Medical imaging using different modalities has many problems. The main ones are low informativeness, various distortion noises, and a large amount of information. Fusion, denoising, and visual data compression are used to solve them in practice. Discrete wavelet transform is one way to implement various fusion, denoising, and compression methods for 2D and 3D medical image processing. Medical imaging systems produce increasingly accurate images with scanning technology and digital devices development. These images have improved quality using both higher spatial resolutions and color bit-depth. processing a large volume of medical imaging data requires considerable resources and processing time. Modern wavelet-based devices for medical image processing do not meet the current performance demand. Hardware accelerators are being designed to solve this problem. This paper proposes new (field-programmable gate array) FPGA accelerators using wavelet processing (WP) with scaled filter coefficients (SFC) and parallel computing in residue number system (RNS) to improve the performance of high-quality 3D medical image WP systems. The computational complexity is reduced using the developed WP method with SFC and the proposed wavelet filter coefficients scaling algorithm. Parallel computing is organized in RNS using moduli sets of a particular type. Hardware implementation of 3D medical image WP using the proposed FPGA accelerators increases device performance by 2.89-3.59 times, increasing the hardware resources by 1.18-3.29 times compared to state-of-the-art solutions. The device performance improvement is achieved while maintaining high-quality 3D medical image processing in peak signal-to-noise ratio terms.

关键词： Biomedical imaging Three-dimensional displays Discrete wavelet transforms performance evaluation Field programmable gate arrays image coding Wavelet transforms Medical image processing discrete wavelet transform scaled filter coefficients residue number system high-performance computing hardware accelerator field-programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

A robust dual-layer medical image watermarking scheme based on matrix factorization in the LWT domain for E-healthcare applications

引用

Multimedia Tools and Applications 2024年 1-31页

作者： Latreche, Boubakeur Merrad, Ahmed Benziane, Ali Naimi, Hilal Saadi, Slami Laboratory of Telecommunications and Smart Systems Faculty of Sciences and Technology University of Djelfa PO Box 3117 Djelfa17000 Algeria Laboratory of Telecommunications and Smart Systems Faculty of Exact Sciences and Informatics University of Djelfa PO Box 3117 Djelfa17000 Algeria Laboratory of Modeling Simulation and Optimization of Systems Complexes Faculty of Sciences and Technology University of Djelfa PO Box 3117 Djelfa17000 Algeria Faculty of Exact Sciences and Informatics University of Djelfa PO Box 3117 Djelfa17000 Algeria

This research introduces an innovative method for watermarking medical images to address security concerns during the transmission of medical images and patient data over insecure networks between hospitals and healthcare professionals. The proposed method aims to safeguard the integrity and confidentiality of medical information, ensuring its vital role in patient health remains protected. The proposed method is based on the lifting wavelet transform (LWT), Hessenberg decomposition (HD), singular value decomposition (SVD), and Chaotic encryption using the Logistic map. First, in the embedding process, the medical cover image undergoes decomposition using multi-level LWT, resulting in several sub-bands. The acquired coefficients are subsequently employed as input for HD. The watermark is subjected to a scrambling process using a chaotic system generated by the Logistic map. To incorporate an extra layer of security. The watermark is ultimately inserted into the medical cover image within the SVD domain using the optimum scaling factor, which is calculated adaptively. Moreover, the watermarking procedure is highly adaptable and can be implemented on images of any size. Experimental results indicate that the method achieves an imperceptibility rate of over 98% with a Peak signal-to-Noise Ratio (PSNR) above 45 dB. Additionally, robustness tests demonstrate that the method maintains watermark integrity with less than 3% degradation after common image processing attacks, such as compression and noise addition. The approach is adaptable to various image sizes, showcasing significant improvements in both security and performance. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Singular value decomposition

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：