检索结果-内蒙古大学图书馆

作者： Golmohammadi, Meysam Temple University

学位级别：Ph.D.

Scalp electroencephalograms (EEGs) are used in a broad range of health care institutions to monitor and record electrical activity in the brain. EEGs are essential in diagnosis of clinical conditions such as epilepsy, seizure, coma, encephalopathy, and brain death. Manual scanning and interpretation of EEGs is time-consuming since these recordings may last hours or days. It is also an expensive process as it requires highly trained experts. Therefore, high performance automated analysis of EEGs can reduce time to diagnosis and enhance real-time applications by identifying sections of the signal that need further review. Automatic analysis of clinical EEGs is a very difficult machine learning problem due to the low fidelity of a scalp EEG signal. Commercially available automated seizure detection systems suffer from unacceptably high false alarm rates. Many signal processing methods have been developed over the years including time-frequency processing, wavelet analysis and autoregressive spectral analysis. Though there has been significant progress in machine learning technology in recent years, use of automated technology in clinical settings is limited, mainly due to unacceptably high false alarm rates. Further, state of the art machine learning algorithms that employ high dimensional models have not previously been utilized in EEG analysis because there has been a lack of large databases that accurately characterize clinical operating conditions. deep learning approaches can be viewed as a broad family of neural network algorithms that use many layers of nonlinear processing units to learn a mapping between inputs and outputs. deep learning-based systems have generated significant improvements in performance for sequence recognitions tasks for temporal signals such as speech and for image analysis applications that can exploit spatial correlations, and for which large amounts of training data exists. The primary goal of our proposed research is to develop deep le

关键词：

来源：评论

学校读者我要写书评

暂无评论

TC-YOLOv5: rapid detection of floating debris on raspberry Pi 4B

引用

JOURNAL OF real-time image processing 2023年第2期20卷 17-17页

作者： Li, Shun Liu, Shubo Cai, Zhaohui Liu, Yuan Chen, Geng Tu, Guoqing Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Wuhan Univ Sch Natl Cybersecur Wuhan 430072 Peoples R China

Floating debris is a prominent indicator in measuring water quality. However, traditional object detection algorithms cannot meet the requirement of high accuracy due to the complexity of the environment. It is difficult for some deep learning-based object detection algorithms to achieve fast detection due to the limited performance of embedded devices. To address the above issues, this paper proposes TC-YOLOv5, which improves the detection accuracy by integrating the convolutional block attention module and vision transformer. To ensure the efficiency and low resource consumption of the algorithm, we selectively remove some convolutional layers and reduce some redundant calculations. We evaluated the performance of TC-YOLOv5 on a dataset with multiple species of floating debris, which can process an image in an average of 1.18 s on a Raspberry Pi 4B and achieve the mean average precision (mAP@0.5) of 84.2%. The detection accuracy, speed, and floating-point operations (FLOPs) of TC-YOLOv5 are better than some algorithms of the YOLOv5 series, such as YOLOv5n, YOLOv5s, and YOLOv5m. The above data show that TC-YOLOv5 realizes high-precision, low resource consumption, and rapid detection.

关键词： deep learning Floating debris detection YOLOv5 Raspberry Pi Attention module

来源：评论

学校读者我要写书评

暂无评论

SAR图像目标轮廓增强预处理模块设计

引用

系统工程与电子技术 2024年第12期46卷 4010-4017页

作者：龚峻扬付卫红刘乃安西安电子科技大学通信工程学院陕西西安710071

针对合成孔径雷达(synthetic aperture radar,SAR)图像中的3个通道数据均相同、以至于在使用基于深度学习的目标检测网络对其进行目标检测时会造成通道信息利用效率低下的问题,基于对SAR图像中各种目标物轮廓特点的研究,提出一种基于平... 详细信息

针对合成孔径雷达(synthetic aperture radar,SAR)图像中的3个通道数据均相同、以至于在使用基于深度学习的目标检测网络对其进行目标检测时会造成通道信息利用效率低下的问题,基于对SAR图像中各种目标物轮廓特点的研究,提出一种基于平滑和锐化滤波的通道扩展预处理算法模块,并将其命名为ORLM(Original,Roberts,Laplace,Mean)模块。所提算法可被封装、集成并应用于目标检测算法的数据读取程序,可将每个通道数据均相同的SAR图像进行通道扩展,并且保证扩展后的通道数据充分包含目标的全部轮廓信息。通过将有否搭配本预处理算法的目标检测网络在不同舰船目标检测数据集上进行训练、测试及对比实验,实验结果表明,所提预处理算法可被应用在各种目标检测算法中,起到提升检测准确性的作用,且不会明显降低检测实时性。

关键词：图像处理合成孔径雷达深度学习目标检测

来源：评论

学校读者我要写书评

暂无评论

Empty Cities: A Dynamic-Object-Invariant Space for Visual SLAM

引用

IEEE TRANSACTIONS ON ROBOTICS 2021年第2期37卷 433-451页

作者： Bescos, Berta Cadena, Cesar Neira, Jose Univ Zaragoza Dept Comp Sci & Syst Engn Zaragoza 50018 Spain Swiss Fed Inst Technol Mech & Proc Engn CH-8090 Zurich Switzerland Univ Zaragoza Inst Invest Ingn Aragon Zaragoza 50018 Spain

In this article, we present a data-driven approach to obtain the static image of a scene, eliminating dynamic objects that might have been present at the time of traversing the scene with a camera. The general objective is to improve vision-based localization and mapping tasks in dynamic environments, where the presence (or absence) of different dynamic objects in different moments makes these tasks less robust. We introduce an end-to-end deep learning framework to turn images of an urban environment that include dynamic content, such as vehicles or pedestrians, into realistic static frames suitable for localization and mapping. This objective faces two main challenges: detecting the dynamic objects, and inpainting the static occluded background. The first challenge is addressed by the use of a convolutional network that learns a multiclass semantic segmentation of the image. The second challenge is approached with a generative adversarial model that, taking as input the original dynamic image and the computed dynamic/static binary mask, is capable of generating the final static image. This framework makes use of two new losses, one based on image steganalysis techniques, useful to improve the inpainting quality, and another one based on ORB features, designed to enhance feature matching between real and hallucinated image regions. To validate our approach, we perform an extensive evaluation on different tasks that are affected by dynamic entities, i.e.,visual odometry, place recognition, and multiview stereo, with the hallucinated images. Code has been made available on https://***/bertabescos/EmptyCities_SLAM.

关键词： Vehicle dynamics Simultaneous localization and mapping Task analysis Semantics Dynamics deep learning Gallium nitride Visual SLAM Inpainting Dynamic objects GANs

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network for Beamforming and image Reconstruction in Passive Cavitation Imaging

引用

SENSORS 2023年第21期23卷 8760-8760页

作者： Sharahi, Hossein J. Acconcia, Christopher N. Li, Matthew Martel, Anne Hynynen, Kullervo Sunnybrook Res Inst Phys Sci Platform Toronto ON M4N 3M5 Canada Univ Toronto Dept Med Biophys Toronto ON M5G 1L7 Canada Univ Toronto Inst Biomed Engn Toronto ON M5S 3G9 Canada

Convolutional neural networks (CNNs), initially developed for image processing applications, have recently received significant attention within the field of medical ultrasound imaging. In this study, passive cavitation imaging/mapping (PCI/PAM), which is used to map cavitation sources based on the correlation of signals across an array of receivers, is evaluated. Traditional reconstruction techniques in PCI, such as delay-and-sum, yield high spatial resolution at the cost of a substantial computational time. This results from the resource-intensive process of determining sensor weights for individual pixels in these methodologies. Consequently, the use of conventional algorithms for image reconstruction does not meet the speed requirements that are essential for real-time monitoring. Here, we show that a three-dimensional (3D) convolutional network can learn the image reconstruction algorithm for a 16x16 element matrix probe with a receive frequency ranging from 256 kHz up to 1.0 MHz. The network was trained and evaluated using simulated data representing point sources, resulting in the successful reconstruction of volumetric images with high sensitivity, especially for single isolated sources (100% in the test set). As the number of simultaneous sources increased, the network's ability to detect weaker intensity sources diminished, although it always correctly identified the main lobe. Notably, however, network inference was remarkably fast, completing the task in approximately 178 s for a dataset comprising 650 frames of 413 volume images with signal duration of 20 mu s. This processing speed is roughly thirty times faster than a parallelized implementation of the traditional time exposure acoustics algorithm on the same GPU device. This would open a new door for PCI application in the real-time monitoring of ultrasound ablation.

关键词： deep learning beamforming passive cavitation imaging convolutional neural network focused ultrasound

来源：评论

学校读者我要写书评

暂无评论

Continuous Learned Primal Dual

Continuous Learned Primal Dual

引用

IEEE Workshop on Machine learning for Signal processing

作者： Christina Runkel Ander Biguri Carola-Bibiane Schönlieb Department of Applied Mathematics and Theoretical Physics University of Cambridge

ISBN: (数字)9798350372250

ISBN: (纸本)9798350372267

Neural ordinary differential equations (Neural ODEs) propose the idea that a sequence of layers in a neural network is just a discretisation of an ODE, and thus can instead be directly modelled by a parameterised ODE. This idea has had resounding success in the deep learning literature, with direct or indirect influence in many state of t he art ideas, such as diffusion models or time dependant models. Recently, a continuous version of the U-net architecture has been proposed, showing increased performance over its discrete counterpart in many imaging applications and wrapped with theoretical guarantees around its performance and robustness. In this work, we explore the use of Neural ODEs for learned inverse problems, in particular with the well-known Learned Primal Dual algorithm, and apply it to computed tomography (CT) reconstruction.

关键词： Machine learning algorithms Inverse problems Computed tomography Neural networks Signal processing algorithms Signal processing Ordinary differential equations Robustness Mathematical models image reconstruction

来源：评论

学校读者我要写书评

暂无评论

MFNet-LE: Multilevel fusion network with, Laplacian embedding for face presentation attacks detection

引用

IET image processing 2021年第14期15卷 3608-3622页

作者： Niu, Sijie Qu, Xiaofeng Chen, Junting Gao, Xizhan Wang, Tingwei Dong, Jiwen Jinan Univ Sch Informat Sci & Engn Shandong Prov Key Lab Network Based Intelligent C Jinan Peoples R China Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China

Face detection is playing a pivotal role for crowd counting and abnormal events detection. However, it is vulnerable to face presentation attacks by printed photos, videos, and 3D masks of real human faces. Although numerous detection techniques based on deep learning have been employed to address the problem of face presentation attacks, there are still several weaknesses in these approaches, such as high algorithm complexity and a lack of detection ability. To overcome these weaknesses, a method based on a multilevel fusion network with Laplacian embedding (MFNet-LE) for the detection of face presentation attacks is proposed. First, a shallow network that contains just three layers was developed, which makes the model faster. Then, an optimised multilevel fusion strategy was developed to combine the input with the output of all previous layers to improve the detection ability of the method. Finally, a Laplacian embedding algorithm is introduced to maintain the inter-class discrimination and penalise the intra-class distance. Under the joint supervision of Laplacian loss and softmax loss, the proposed approach can obtain more discriminative features, which enhance the accuracy of attack detection. Experiments were conducted with three public databases for face presentation attacks: CASIA FASD, Idiap Replay Attack database and MSU USSA. The results demonstrate that the MFNet-LE model can outperform the state-of-the-art methods.

关键词： Algebra Integral transforms Optical, image and video signal processing image recognition image sensors Integral transforms Computer vision and image processing techniques Video signal processing Data handling techniques Spatial and pictorial databases

来源：评论

学校读者我要写书评

暂无评论

Applying Reservoir Computing and Machine learning Techniques for image Enhancement in Biomedical Imaging

Applying Reservoir Computing and Machine Learning Techniques...

引用

International Conference on Smart Communications and Networking (SmartNets)

作者： Andre Slonopas Adam Beatty Yenni Djajalaksana Department of Cybersecurity American Public University Sysytem (APUS) School of Security and Global Studies (SSGS) Charles Town WV International Council of E-Commerce Consultants (EC-Council) Academia Division Tampa FL

ISBN: (数字)9798350385328

ISBN: (纸本)9798350385335

The paper presents a comprehensive study on the application of Machine learning (ML) in enhancing the contrast of biomedical images. This research is pivotal in addressing the challenges of low visibility and detail in medical imaging, which are crucial for accurate diagnosis and treatment. The paper introduces innovative ML-based Histogram Equalization (ML - HE), leveraging deep learning algorithms and advanced image processing methods, to significantly improve the quality of biomedical images. These techniques enhance image clarity, detail, and overall contrast without compromising the integrity of the original data. This paper seeks to explore the integration of ML, specifically Reservoir Computing, with traditional image enhancement methods, creating a synergistic approach that leverages the strengths of both ML and conventional techniques and expedites image enhancements in near real-time. This hybrid approach is shown to be more effective in handling diverse and complex imaging scenarios encountered in biomedical applications. The study also discusses the implications of these advancements for medical professionals, highlighting how ML-enhanced images can lead to more accurate diagnoses, better patient outcomes, and advancements in medical research. Overall, this paper sheds light on the transformative potential of ML in revolutionizing biomedical imaging, setting a new standard for image quality and diagnostic precision in healthcare.

关键词： Histograms Visualization Accuracy Machine learning algorithms Soft sensors Thermocouples Speech recognition

来源：评论

学校读者我要写书评

暂无评论

deep learning Approach for Object Features Detection 4th

Deep Learning Approach for Object Features Detection

引用

4th International Conference on Communication, Device and Networking, ICCDN 2020

作者： Mitra, Ambik Mohanty, Debasis Ijaz, Muhammad Fazal Rana, Abu ul Hassan S. Deemed To Be University Bhubaneswar Odisha India iNurture Education Solutions Private Limited Bengaluru Karnataka India Department of Intelligent Mechatronics Engineering Sejong University Seoul05006 Korea Republic of

ISBN: (纸本)9789811629105

Object detection and identification system basically find real-world objects in a digital image or any video. In order to detect an object in any video or digital image, few components are necessary, which are a model database, a feature detector, a hypothesizer and a hypothesizer verifier. This paper shows several techniques that are used for object detection, such as localization of an object, categorization of an object, extraction of features, showing information and so on, in images and videos. The document also stresses the idea of a possible solution for multi-class object detection. This paper basically relates to the researchers who are working on this particular domain. Object detection is a field distributing into a lot of enterprises, along with its uses extended from personal security to a healthy working environment. This field has its applications in various categories of image processing, such as image retrieval, security, observation, computerized vehicle systems and machine investigation. The outcomes of this particular system are inestimable on the basis of future use cases for this particular field. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Smart agriculture: real-time classification of green coffee beans by using a convolutional neural network

IET SMART CITIES

引用

IET SMART CITIES 2020年第4期2卷 167-172页

作者： Huang, Nen-Fu Chou, Dong-Lin Lee, Chia-An Wu, Feng-Ping Chuang, An-Chi Chen, Yi-Hsien Tsai, Yin-Chun Natl Tsing Hua Univ Dept Comp Sci Hsinchu Taiwan

Coffee is an important economic crop and one of the most popular beverages worldwide. The rise of speciality coffees has changed people's standards regarding coffee quality. However, green coffee beans are often mixed with impurities and unpleasant beans. Therefore, this study aimed to solve the problem of time-consuming and labour-intensive manual selection of coffee beans for speciality coffee products. The second objective of the authors' study was to develop an automatic coffee bean picking system. They first used image processing and data augmentation technologies to deal with the data. They then used deep learning of the convolutional neural network to analyse the image information. Finally, they applied the training model to connect an IP camera for recognition. They successfully divided good and bad beans. The false-positive rate was 0.1007, and the overall coffee bean recognition rate was 93%.

关键词： quality control image classification learning (artificial intelligence) beverages crops feature extraction agriculture convolutional neural nets real-time classification green coffee beans convolutional neural network economic crop coffee quality unpleasant beans labour-intensive manual selection speciality coffee products automatic coffee bean picking system coffee bean recognition rate smart agriculture image processing data augmentation technologies deep learning

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：