检索结果-内蒙古大学图书馆

中国安全科学学报 2023年第S02期33卷 170-175页

作者：魏德志杜志勇滕春阳辛吴天李泽坤国家能源集团宝日希勒能源有限公司露天煤矿内蒙古呼伦贝尔021008

为解决露天矿中破碎站输送机构链条断裂故障检测效率低,传统图像识别方法处理效率低,检测实时性差的问题,提出一种基于深度学习技术的破碎站链条断裂检测技术。首先,从硬件平台搭建和软件架构上提出链条断裂检测系统总体设计方案;其次,... 详细信息

为解决露天矿中破碎站输送机构链条断裂故障检测效率低,传统图像识别方法处理效率低,检测实时性差的问题,提出一种基于深度学习技术的破碎站链条断裂检测技术。首先,从硬件平台搭建和软件架构上提出链条断裂检测系统总体设计方案;其次,使用YOLOv4模型搭建链条检测模型架构,根据破碎站运行工况提出链条断裂检测算法,并结合实际环境特征提出图像预处理方法;然后,采集图像样本用于模型迭代训练,得到链条目标检测识别模型;最后,检测链条断链丢失情况。结果表明:基于深度学习的破碎站链条目标检测可以在输送机构运行过程中精确识别出图像中链条的数量;当链条被遮挡模拟丢失后,能够及时发现并报警。

关键词：露天矿破碎站断裂检测深度学习机器视觉 YOLO

来源：评论

学校读者我要写书评

暂无评论

Computer Aided Diagnosis of Depression Using EEG Signal processing

Computer Aided Diagnosis of Depression Using EEG Signal Proc...

引用

IEEE International Conference on Engineering Education: Innovative Practices and Future Trends (AICERA)

作者： Abin B Anand Alent Michael Aneesha Biju Deryck Joseph Chacko Darsana P Department of E.C.E Amal Jyothi College of Engineering Kottayam India

Major depressive disorder (MDD) emerges as a prominent factor leading to disability on a global scale and contributes significantly to the global burden of illness overall. The traditional method of detecting MDD is by continuous medical examination by a psychologist or psychiatrist. Our objective is to develop a non-invasive device which collects brain signals from the head and gets interfaced with a computer. The purpose of this paper is to develop a computer-aided diagnosis system that can identify depression in real time. The proposed system comprises three main components: the ADS1299 Front-End (FE) Printed Development Kit (PDK) evaluation board, a wearable electrode, and a desktop application. The primary approach involves the utilization of electroencephalogram (EEG) signal processing, along with the ADS1299 FE PDK evaluation board and deep learning techniques. This paper involves the utilisation of a publicly available dataset for training the deep learning model. The convolutional Neural Network (CNN) algorithm is used for the classification process. Absolute and relative powers are computed, and an asymmetry image matrix is generated based on the relative power values. By analysing the image matrix, the system can classify a patient as healthy or suffering from major depression based on higher or lower relative power, respectively. This paper seeks to make a valuable contribution to the academic sphere of the study of mental health diagnosis by leveraging advanced signal processing techniques and deep learning models for more accurate and efficient detection of depression.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach to real-time HIV outbreak detection using genetic data

引用

PLOS COMPUTATIONAL BIOLOGY 2022年第10期18卷 e1010598页

作者： Kupperman, Michael D. Leitner, Thomas Ke, Ruian Los Alamos Natl Lab Theoret Biol & Biophys T6 Los Alamos NM 87545 USA Univ Washington Dept Appl Math Seattle WA 98195 USA

Pathogen genomic sequence data are increasingly made available for epidemiological monitoring. A main interest is to identify and assess the potential of infectious disease outbreaks. While popular methods to analyze sequence data often involve phylogenetic tree inference, they are vulnerable to errors from recombination and impose a high computational cost, making it difficult to obtain real-time results when the number of sequences is in or above the thousands. Here, we propose an alternative strategy to outbreak detection using genomic data based on deep learning methods developed for image classification. The key idea is to use a pairwise genetic distance matrix calculated from viral sequences as an image, and develop convolutional neutral network (CNN) models to classify areas of the images that show signatures of active outbreak, leading to identification of subsets of sequences taken from an active outbreak. We showed that our method is efficient in finding HIV-1 outbreaks with R-0 >= 2.5, and overall a specificity exceeding 98% and sensitivity better than 92%. We validated our approach using data from HIV-1 CRF01 in Europe, containing both endemic sequences and a well-known dual outbreak in intravenous drug users. Our model accurately identified known outbreak sequences in the background of slower spreading HIV. Importantly, we detected both outbreaks early on, before they were over, implying that had this method been applied in real-time as data became available, one would have been able to intervene and possibly prevent the extent of these outbreaks. This approach is scalable to processing hundreds of thousands of sequences, making it useful for current and future real-time epidemiological investigations, including public health monitoring using large databases and especially for rapid outbreak identification. Author summary The analysis of pathogen genomic data to analyze epidemics at scale is constrained by the computational cost associated with phylogen

关键词： HIV-1 Sequence databases HIV epidemiology deep learning Neural networks Epidemiology Phylogenetic analysis Hierarchical clustering

来源：评论

学校读者我要写书评

暂无评论

Tunable image quality control of 3-D ultrasound using switchable CycleGAN

引用

MEDICAL image ANALYSIS 2023年 83卷 102651页

作者： Huh, Jaeyoung Khan, Shujaat Choi, Sungjin Shin, Dongkuk Lee, Jeong Eun Lee, Eun Sun Chul, Jong Korea Adv Inst Sci & Technol KAIST Dept Bio & Brain Engn Daejeon 34141 South Korea Samsung Medison Co Ltd Syst R&D Grp Seoul South Korea Chungnam Natl Univ Chungnam Natl Univ Hosp Dept Radiol Coll Med 282 Munhwa ro Daejeon 35015 South Korea Chung Ang Univ Hosp Dept Radiol 102 Heukseok-ro Seoul 06973 South Korea Korea Adv Inst Sci & Technol KAIST Kim Jaechul Grad Sch AI Daejeon 34141 South Korea

In contrast to 2-D ultrasound (US) for uniaxial plane imaging, a 3-D US imaging system can visualize a volume along three axial planes. This allows for a full view of the anatomy, which is useful for gynecological (GYN) and obstetrical (OB) applications. Unfortunately, the 3-D US has an inherent limitation in resolution compared to the 2-D US. In the case of 3-D US with a 3-D mechanical probe, for example, the image quality is comparable along the beam direction, but significant deterioration in image quality is often observed in the other two axial image planes. To address this, here we propose a novel unsupervised deep learning approach to improve 3-D US image quality. In particular, using unmatched high-quality 2-D US images as a reference, we trained a recently proposed switchable CycleGAN architecture so that every mapping plane in 3-D US can learn the image quality of 2-D US images. Thanks to the switchable architecture, our network can also provide real-time control of image enhancement level based on user preference, which is ideal for a user-centric scanner setup. Extensive experiments with clinical evaluation confirm that our method offers significantly improved image quality as well user-friendly flexibility.

关键词： 3-D ultrasound imaging deep learning Adaptive Instance Normalization (AdaIN) Obstetrics and gynecology

来源：评论

学校读者我要写书评

暂无评论

复杂退化模型下图像超分辨率算法综述

引用

郑州大学学报（理学版） 2024年第4期56卷 1-10页

作者：陈伟吴凡田子建刘珏廷中国矿业大学计算机科学与技术学院江苏徐州221116 中国矿业大学(北京)机电与信息工程学院北京100083

图像的超分辨率(super-resolution,SR)一直以来是计算机视觉(computer vision,CV)领域的一项热门的研究方向,它旨在从单张或多张低分辨率图像中通过一系列的图像处理和深度学习技术,重建带有丰富边缘纹理等细节特征的高分辨率图像。自... 详细信息

图像的超分辨率(super-resolution,SR)一直以来是计算机视觉(computer vision,CV)领域的一项热门的研究方向,它旨在从单张或多张低分辨率图像中通过一系列的图像处理和深度学习技术,重建带有丰富边缘纹理等细节特征的高分辨率图像。自从深度卷积神经网络应用于图像超分辨率算法后,其性能相较于传统的基于重构和基于样例的SR算法有了非常大的提升。然而,目前的SR算法在实际场景应用、算法性能、模型质量评估标准等方面仍然需要改良和优化。因此,为推进图像超分辨率技术的发展,总结并分析了基于深度学习的SR算法。首先,将目前主流的SR算法分为基于卷积神经网络、基于生成对抗网络、基于Transformer这三类;其次,详细评述了每一类算法的网络结构、算法优缺点、算法特色及适用场景等;然后,对常见的超分辨率数据集及各种评价指标进行阐述,重点比较了不同SR算法在各类数据集上的性能;最后,总结了图像超分辨率目前研究所面临的问题并探讨了图像超分辨率的未来研究方向。

关键词：深度学习超分辨率卷积神经网络生成对抗网络图像质量评价

来源：评论

学校读者我要写书评

暂无评论

Robust occlusion-aware orbital angular momentum feature extraction via all-optical diffractive processing systems

引用

Optics Express 2025年第11期33卷 23053-23064页

作者： Li, Keyao Jia, Yuetian Gu, Min Fang, Xinyuan School of Artificial Intelligence Science and Technology University of Shanghai for Science and Technology Shanghai200093 China Institute of Photonic Chips University of Shanghai for Science and Technology Shanghai200093 China

As a brain-inspired optical computing architectures, diffractive optical neural networks (DONN) harness light’s wave nature for high-speed, energy efficient and parallel information processing, enabling applications such as image classification and wavefront shaping. However, conventional spatially encoded DONNs struggle with robustness in complex and unpredictable environments, where occlusions and distortions degrade processing accuracy. To address these challenges, we propose a robust all-optical feature extraction framework based on orbital angular momentum (OAM). This approach converts optical information into target OAM modes using a diffractive processing framework trained via deep learning, enabling stable and efficient information representation in the OAM domain. Unlike conventional DONNs, our method maintains high performance across diverse and irregular occlusions without requiring network retraining. This self-adaptive occlusion immune operates with zero additional training samples, effectively enhancing optical computing tasks under dynamic and uncertain conditions. By fully utilizing the helical wavefront and orthogonality of OAM, our approach improves the robustness and scalability of DONNs, demonstrating superior performance in challenging optical environments. Our work paves the way for next-generation optical computing systems that can operate reliably in unpredictable and occlusion-rich environment, unlocking what we believe to be new possibilities for robust, real-time processing in a variety of applications. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Angular momentum

来源：评论

学校读者我要写书评

暂无评论

Including Keyword Position in image-based Models for Act Segmentation of Historical Registers 21

Including Keyword Position in Image-based Models for Act Seg...

引用

6th International Workshop on Historical Document Imaging and processing (HIP)

作者： Boillet, Melodie Maarand, Martin Paquet, Thierry Kermorvant, Christopher TEKLIA Paris France Normandie Univ LITIS Rouen France

ISBN: (纸本)9781450386906

The segmentation of complex images into semantic regions has seen a growing interest these last years with the advent of deep learning. Until recently, most existing methods for Historical Document Analysis focused on the visual appearance of documents, ignoring the rich information that textual content can offer. However, the segmentation of complex documents into semantic regions is sometimes impossible relying only on visual features and recent models embed both visual and textual information. In this paper, we focus on the use of both visual and textual information for segmenting historical registers into structured and meaningful units such as acts. An act is a text recording containing valuable knowledge such as demographic information (baptism, marriage or death) or royal decisions (donation or pardon). We propose a simple pipeline to enrich document images with the position of text lines containing key-phrases and show that running a standard image-based layout analysis system on these images can lead to significant gains. Our experiments show that the detection of acts increases from 38 % of mAP to 74 % when adding textual information, in real use-case conditions where text lines positions and content are extracted with an automatic recognition system.

关键词： Historical Document Act Segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Single-Stage real-time Face Mask Detection 14th

Single-Stage Real-Time Face Mask Detection

引用

14th Asian Conference on Intelligent Information and Database Systems (ACIIDS)

作者： Linh Phung-Khanh Trawinski, Bogdan Vi Le-Thi-Tuong Anh Pham-Hoang-Nam Nga Ly-Tu Int Univ Sch Comp Sci & Engn Ho Chi Minh City Vietnam Wroclaw Univ Sci & Technol Dept Appl Informat Wroclaw Poland

ISBN: (纸本)9783031219665;9783031219672

With the battle against COVID-19 entering a more intense stage against the new Omicron variant, the study of face mask detection technologies has become highly regarded in the research community. While there were many works published on this matter, we still noticed three research gaps that our contributions could possibly suffice. Firstly, despite the introduction of various mask detectors over the last two years, most of them were constructed following the two-stage approach and are inappropriate for usage in real-time applications The second gap is how the currently available datasets could not support the detectors in identifying correct, incorrect and no mask-wearing efficiently without the need for data pre-processing. The third and final gap concerns the costly expenses required as the other detector models were embedded into microcomputers such as Arduino and Raspberry Pi. In this paper, we will first propose a modified YOLO-based model that was explicitly designed to resolve the real-time face mask detection problem;during the process, we have updated the collected datasets and thus will also make them publicly available so that other similar experiments could benefit from;lastly, the proposed model is then implemented onto our custom web application for real-time face mask detection. Our resulted model was shown to exceed its baseline on the revised dataset, and its performance when applied to the application was satisfactory with insignificant inference time. Code available at: https://***/indigoYoshimaru/facemask-web

关键词： Face mask detection Covid-19 Single-stage real-time Face mask dataset deep learning YOLO Web application

来源：评论

学校读者我要写书评

暂无评论

Simplification of deep Neural Network-Based Object Detector for real-time Edge Computing

引用

SENSORS 2023年第7期23卷 3777-3777页

作者： Choi, Kyoungtaek Wi, Seong Min Jung, Ho Gi Suhr, Jae Kyu Daegu Catholic Univ Dept AI Automat Robot 13-13 Hayang Ro Gyongsan 38430 Gyeongsangbugdo South Korea Hyundai Mobis Driving Image Recognit L Cell 17-2 Mabuk Ro 240beon Gil Yongin 16891 Gyeonggi Do South Korea Korea Natl Univ Transportat Dept Elect Engn 50 Daehak Ro Chungju Si 27469 Chungbuk Do South Korea Sejong Univ Dept Intelligent Mechatron Engn 209 Neungdong Ro Seoul 05006 South Korea

This paper presents a method for simplifying and quantizing a deep neural network (DNN)-based object detector to embed it into a real-time edge device. For network simplification, this paper compares five methods for applying channel pruning to a residual block because special care must be taken regarding the number of channels when summing two feature maps. Based on the comparison in terms of detection performance, parameter number, computational complexity, and processing time, this paper discovers the most satisfying method on the edge device. For network quantization, this paper compares post-training quantization (PTQ) and quantization-aware training (QAT) using two datasets with different detection difficulties. This comparison shows that both approaches are recommended in the case of the easy-to-detect dataset, but QAT is preferable in the case of the difficult-to-detect dataset. Through experiments, this paper shows that the proposed method can effectively embed the DNN-based object detector into an edge device equipped with Qualcomm's QCS605 System-on-Chip (SoC), while achieving a real-time operation with more than 10 frames per second.

关键词： object detector network simplification channel pruning edge computing

来源：评论

学校读者我要写书评

暂无评论

A Three-Step Computer Vision-Based Framework for Concrete Crack Detection and Dimensions Identification

引用

BUILDINGS 2024年第8期14卷 2360-2360页

作者： Qi, Yanzhi Ding, Zhi Luo, Yaozhi Ma, Zhi Zhejiang Univ Inst Struct Engn Hangzhou 310058 Peoples R China Hangzhou City Univ Dept Civil Engn Hangzhou 310015 Peoples R China Key Lab Safe Construct & Intelligent Maintenance U Hangzhou 310015 Peoples R China

Crack detection is significant to building repair and maintenance;however, conventional inspection is a labor-intensive and time-consuming process for field engineers. This paper proposes a three-step computer vision-based framework to quickly recognize concrete cracks and automatically identify their length, maximum width, and area in damage images. In step one, a region-based convolutional neural network (YOLOv8) is applied to train the crack localizing model. In step two, Gaussian filtering, Canny, and FindContours are integrated to extract the reference contour (a pre-designed seal) to obtain the conversion scale between pixels and millimeter-wise sizes. In step three, the recognized crack bounding box is cropped, and the ApproxPolyDP function and Hough transform are performed to quantify crack dimensions based on the conversion ratio. The developed framework was validated on a dataset of 4630 crack images, and the model training took 150 epochs. Results show that the average crack detection accuracy reaches 95.7%, and the precision of quantified dimensions is over 90%, while the error increases as the crack size grows smaller (increasing to 8% when the crack width is within 1 mm). The proposed method can help engineers to efficiently achieve crack information at building inspection sites, while the reference frame must be pre-marked near the crack, which may limit the scope of application scenarios. In addition, the robustness and accuracy of the developed image processing techniques-based crack quantification algorithm need to be further improved to meet the requirements in real cases when the crack is located within a complex background.

关键词： computer vision crack detection deep learning image processing techniques dimensional quantification

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：