检索结果-内蒙古大学图书馆

Fast and customizable image formation model for optical coherence tomography

BIOMEDICAL OPTICS EXPRESS 2024年第12期15卷 6783-6798页

作者： Mazzolani, Andrea Macdonald, Callum Munro, Peter R. T. UCL Dept Med Phys & Biomed Engn Malet PlGower St London WC1E 6BT England

Optical coherence tomography (OCT) is a technique that performs high-resolution, three-dimensional, imaging of semi-transparent scattering biological tissues. Models of OCT image formation are needed for applications such as aiding image interpretation and validating OCT signal processing techniques. Existing image formation models generally trade off between model realism and computation time. In particular, the most realistic models tend to be highly computationally demanding, which becomes a limiting factor when simulating C-scan generation. Here we present an OCT image formation model based on the first-order Born approximation that is significantly faster than existing models, whilst maintaining a high degree of realism. This model is made more powerful because it is amenable to simulation of phase sensitive OCT, thus making it applicable to scenarios where sample displacement is of interest, such as optical coherence elastography (OCE) or Doppler OCT. The low computational cost of the model also makes it suitable for creating large OCT data sets needed for training deep learning OCT signal processing models. We present details of our novel image formation model and demonstrate its accuracy and computational efficiency.

关键词： Biomedical imaging Computer simulation deep learning Optical imaging Signal processing Spectral domain optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sample Utilization in Noise-Robust deep Metric learning With Subgroup-Based Positive-Pair Selection

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 6083-6097页

作者： Yu, Zhipeng Xu, Qianqian Jiang, Yangbangyan Sun, Yingfei Huang, Qingming Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive pairs for noisy samples to enhance the sample utilization. Specifically, SGPS first effectively identifies clean and noisy samples by a probability-based clean sample selectionstrategy. To further utilize the remaining noisy samples, we discover their potential similar samples based on the subgroup information given by a subgroup generation module and then aggregate them into informative positive prototypes for each noisy sample via a positive prototype generation module. Afterward, a new contrastive loss is tailored for the noisy samples with their selected positive pairs. SGPS can be easily integrated into the training process of existing pair-wise DML tasks, like image retrieval and face recognition. Extensive experiments on multiple synthetic and real-world large-scale label noise datasets demonstrate the effectiveness of our proposed method. Without any bells and whistles, our SGPS framework outperforms the state-of-the-art noisy label DML methods.

关键词： Metric learning noisy label deep learning deep learning pair- wise loss pair- wise loss pair- wise loss pair- wise loss positive-pair selection positive-pair selection

来源：评论

学校读者我要写书评

暂无评论

deep Efficient Continuous Manifold learning for time Series Modeling

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第1期46卷 171-184页

作者： Jeong, Seungwoo Ko, Wonjun Mulyadi, Ahmad Wisnu Suk, Heung-Il Korea Univ Dept Artificial Intelligence Seoul 02841 South Korea Korea Univ Dept Brain & Cognit Engn Seoul 02841 South Korea

Modeling non-euclidean data is drawing extensive attention along with the unprecedented successes of deep neural networks in diverse fields. Particularly, a symmetric positive definite matrix is being actively studied in computer vision, signal processing, and medical image analysis, due to its ability to learn beneficial statistical representations. However, owing to its rigid constraints, it remains challenging to optimization problems and inefficient computational costs, especially, when incorporating it with a deep learning framework. In this paper, we propose a framework to exploit a diffeomorphism mapping between Riemannian manifolds and a Cholesky space, by which it becomes feasible not only to efficiently solve optimization problems but also to greatly reduce computation costs. Further, for dynamic modeling of time-series data, we devise a continuous manifold learning method by systematically integrating a manifold ordinary differential equation and a gated recurrent neural network. It is worth noting that due to the nice parameterization of matrices in a Cholesky space, training our proposed network equipped with Riemannian geometric metrics is straightforward. We demonstrate through experiments over regular and irregular time-series datasets that our proposed model can be efficiently and reliably trained and outperforms existing manifold methods and state-of-the-art methods in various time-series tasks.

关键词： Cholesky space deep learning manifold learning manifold ordinary differential equation multivariate time series modeling symmetric positive definite matrix

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on weed and crop classification using machine learning and deep learning

引用

Artificial Intelligence in Agriculture 2024年第3期13卷 45-63页

作者： Faisal Dharma Adhinata Wahyono Raden Sumiharto Department of Computer Science and Electronics Faculty of Mathematic and Natural SciencesUniversitas Gadjah MadaYogyakartaIndonesia Faculty of Informatics Institut Teknologi Telkom PurwokertoCentral JavaIndonesia

Machine learning and deep learning are subsets of Artificial Intelligence that have revolutionized object detection and classification in images or *** technology plays a crucial role in facilitating the transition from conventional to precision agriculture,particularly in the context of weed *** agriculture,which previously relied on manual efforts,has now embraced the use of smart devices for more efficient weed ***,several challenges are associated with weed detection,including the visual similarity between weed and crop,occlusion and lighting effects,as well as the need for early-stage weed ***,this study aimed to provide a comprehensive review of the application of both traditional machine learning and deep learning,as well as the combination of the two methods,for weed detection across different crop *** results of this review show the advantages and disadvantages of using machine learning and deep ***,deep learning produced superior accuracy compared to machine learning under various *** learning required the selection of the right combination of features to achieve high accuracy in classifyingweed and crop,particularly under conditions consisting of lighting and early growth ***,a precise segmentation stage would be required in cases of *** learning had the advantage of achieving real-time processing by producing smaller models than deep learning,thereby eliminating the need for additional ***,the development of GPU technology is currently rapid,so researchers are more often using deep learning for more accurate weed identification.

关键词： deep learning Machine learning Precision agriculture Weed control Weed detection

来源：评论

学校读者我要写书评

暂无评论

Advancements in underwater imaging through machine learning: Techniques, challenges, and applications

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Naveen, Palanichamy Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Coimbatore641407 India

Underwater imaging plays a critical role in various fields such as marine biology, environmental monitoring, underwater archaeology, and defense. However, it faces unique challenges including light absorption and scattering, limited visibility, color distortion, and dynamic underwater conditions. Recent advancements in machine learning have provided powerful tools to address these challenges, significantly improving the quality and analysis of underwater images. This review comprehensively explores the intersection of underwater imaging and machine learning, covering supervised learning, unsupervised learning, deep learning, and reinforcement learning techniques. I discuss key applications such as marine species identification, coral reef monitoring, autonomous underwater navigation, archaeological site exploration, and environmental monitoring. Additionally, I examine publicly available datasets, benchmarking methods, and evaluation metrics essential for developing and accessing machine learning models in this domain. Through detailed case studies and practical implementations, I highlight the strengths and weaknesses of various approaches. Emerging trends such as the integration of AI with robotics, advancements in imaging hardware, and the development of specialized algorithms are also discussed. Future directions include enhanced image processing techniques, interdisciplinary collaborations, and real-time processing capabilities. This review aims to provide a comprehensive overview of the current state of underwater imaging and machine learning, highlighting the potential for continued research and innovation in this rapidly evolving field. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

TSDN: Two-Stage Raw Denoising in the Dark

引用

IEEE TRANSACTIONS ON image processing 2023年 32卷 3679-3689页

作者： Chen, Wenshu Huang, Yujie Wang, Mingyu Wu, Xiaolin Zeng, Xiaoyang Fudan Univ Coll Microelect State Key Lab ASIC & Syst Shanghai 200000 Peoples R China Shanghai ExploreX Technol Co Ltd Shanghai 200120 Peoples R China McMaster Univ Dept Elect & Comp Engn Hamilton ON L8G 4K1 Canada Shanghai ExploreX Technol Co Ltd Shanghai 200120 Peoples R China

Denoising is one of the most significant procedures in the image processing pipeline. Nowadays, deep-learning-based algorithms have achieved superior denoising quality than traditional algorithms. However, the noise becomes severe in the dark environment, where even the SOTA algorithms fail to achieve satisfactory performance. Besides, the high computational complexity of deep-learning-based denoising algorithms makes them hardware unfriendly and difficult to process high-resolution images in real-time. To address these issues, a novel low-light RAW denoising algorithm Two-Stage-Denoising (TSDN), is proposed in this paper. In TSDN, denoising consists of two procedures: noise removal and image restoration. Firstly, in the noise-removal stage, most noise is removed from the image, and an intermediate image that is easier for the network to recover the clean image is obtained. Then, in the restoration stage, the clean image is restored from the intermediate image. The TSDN is designed to be light-weight for real-time and hardware friendly. However, the tiny network will be insufficient for satisfactory performance if directly trained from scratch. Therefore, we present an Expand-Shrink-learning (ESL) method to train the TSDN. In the ESL method, firstly, the tiny network is expanded to a larger one with similar architecture but more channels and layers, which enhances the learning ability of the network because of more parameters. Secondly, the larger network is shrunk and restored to the original small network in fine-grained learning procedures, including Channel-Shrink-learning (CSL) and Layer-Shrink-learning (LSL). Experimental results demonstrate that the proposed TSDN achieves better performance (PSNR and SSIM) than other SOTA algorithms in the dark environment. Besides, the model size of TSDN is one-eighth of that of the U-Net for denoising (a classical denoising network).

关键词： image processing denoising light-weight network

来源：评论

学校读者我要写书评

暂无评论

Analysis of Students' Class Status Based on deep learning 20th

Analysis of Students' Class Status Based on Deep Learning

引用

20th Chinese Intelligent Systems Conference

作者： Liu, Qunpo Zhang, Xiaojie Wu, Hongpei Henan Polytech Univ Jiaozuo 454003 Henan Peoples R China Henan Int Joint Lab Direct Drive & Control Intell 2001 Century Ave Jiaozuo 454003 Henan Peoples R China

ISBN: (纸本)9789819786565;9789819786541;9789819786534

Aiming at the problem that it is difficult for teachers to obtain accurate classroom status in daily teaching process, which is not conducive to making targeted adjustments to teaching methods, this paper proposes a deep learning-based student class status analysis system. The system uses camera to capture classroom video, and uses image recognition, target detection, deep learning and other technologies to detect the behavioral state of students in the classroom in real time and concentration information, and through the statistical analysis of the collected data, it helps the teacher to get timely feedback in the classroom, and better judge the learning state and concentration of students. In order to realize the real-time and accuracy of the system design, the system in the paper introduces the OpenPose model into the YOLOv5 network to identify the students' skeletal keypoints, and synthesizes the results of the processing of the YOLOv5 model and the OpenPose model to make an analysis of the students' classroom behaviors and concentration. The experimental results show that the loss curve can achieve good convergence, and the AP and mAP can reach 95.1% and 88.0%, respectively.

关键词： Student status detection deep learning YOLOv5 OpenPose

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Logs Using deep learning

引用

IEEE ACCESS 2024年 12卷 176124-176135页

作者： Aziz, Ayesha Munir, Kashif Natl Univ Comp & Emerging Sci FAST Sch Comp Islamabad 44000 Pakistan Arab Open Univ Fac Comp Studies Riyadh Saudi Arabia

Detection of abnormalities is important for the security and reliability of computer systems as they heavily rely on logs to detect anomalies. The logs provide general information, errors, warnings, and debugging information. Existing approaches for detecting anomalies are sometimes inaccurate due to their limitations related to log-processing leading to loss of semantic significance. Existing approaches, like deeplog and LogAnomaly, have restrictions in detecting irregularities in log frameworks mainly in large dynamic systems. In this paper, we propose a hybrid anomaly detection technique that combines unsupervised approaches such as Self-Organizing Maps, Bert Encoders, and Autoencoders to handle these issues. The approach improves anomaly identification accuracy by employing semantic vectors obtained by the Bert Encoder to recognize patterns with autoencoders. The evaluation results show that the proposed strategy outperforms the existing methods for various types of data including system logs, network traffic, and financial transactions.

关键词： Anomaly detection deep learning Semantics Encoding Bidirectional control real-time systems Data models Pipelines Machine learning algorithms Clustering algorithms classification unsupervised learning deep learning

来源：评论

学校读者我要写书评

暂无评论

The Application of 6G and Augmented reality Technology in Education and Training

引用

WIRELESS PERSONAL COMMUNICATIONS 2024年 1-19页

作者： Zhang, Yangloucai Bin Azizui, Muhammad Farid Azizul Yan, Cong Univ Teknol Malaysia Fac Built Environm & Surveying Skudai 81200 Malaysia Chengdu Neusoft Univ Sch Digital Art & Design Chengdu 61000 Peoples R China Univ Teknol Malaysia Coll Educ & Surveying Skudai 81200 Malaysia

The short evolution of 6G and augmented reality (AR) technology heralds a transformative era in education and training, promising to redefine traditional learning paradigms using immersive, interactive reports. This paper explores the integration of advanced capsule networks (CapsNet) architectures with semantic segmentation techniques to cope with the inherent annoying conditions of applying 6G and AR in academic contexts. CapsNets, well known for its efficiency in discerning spatial hierarchies and relationships, are paired with semantic segmentation to enhance object recognition and interplay within AR environments. It offers a deep, contextual understanding essential for growing dynamic, personalised learning studies. The synergy among this technology allows for the unique delineation and classification of each image pixel into corresponding object training, facilitating seamless interaction among virtual content and the real world. Need of the highly dependable, low-latency communication exchange skills of 6G, this combination guarantees powerful processing of complex scenes in real-time, crucial for preserving student engagement and facilitating adaptive learning pathways. The paper discusses optimisation techniques for real-time performance, including version pruning and effective routing mechanisms, to cope with the computational needs of CapsNets and semantic segmentation. Moreover, it highlights the role of 6G in assisting the bandwidth and latency necessities critical for deploying these state-of-the-art AI models in AR-based instructional programs. Through this integration, we aim to release new potentials for personalised, context-aware learning experiences, which can considerably enhance knowledge retention, engagement, and accessibility in education and training across various fields.

关键词： 6G Augmented reality Capsule networks Semantic segmentation Training Personalised learning

来源：评论

学校读者我要写书评

暂无评论

Automated Recognition of Hand Gestures From Multichannel EMG Sensor Data Using time-Frequency Domain deep learning for IoT Applications

IEEE SENSORS LETTERS

引用

IEEE SENSORS LETTERS 2024年第6期8卷 1页

作者： Mohapatra, Amlan deep Aggarwal, Amol Tripathy, Rajesh Kumar BITS Pilani Dept Elect & Elect Engn Hyderabad Campus Hyderabad 500078 India BITS Pilani Dept Pharm Pilani Campus Pilani 333031 India

The automated recognition of hand gestures from multicha- nnel electromyogram (MEMG) sensor data is essential for human-computer interaction, prosthetic control, rehabilitation, and biometric-related applications. This letter proposes a time-frequency domain deep neural network (TFDDNN)-based approach to recognize hand gestures using MEMG recordings. The MEMG recordings are segmented into frames, and the average of all channel information (mean EMG signal) for each frame is evaluated. The continuous wavelet transform is applied to the mean EMG signal to obtain the joint time-frequency representation (TFR). The TFR-based image of the mean EMG signal is used as the input to a deep representation learning network (DRLN) model to recognize hand gestures. Two publicly available databases are utilized to evaluate the performance of the proposed TFDDNN approach. The results show that the proposed TFDDNN has obtained overall accuracy values of 92.73% and 80.33% using MEMG signals from database 1 and database 2 for multiclass-based recognition of hand gestures. The suggested DRLN model has demonstrated higher accuracy for automated hand gesture recognition than existing deep-learning-based methods. We have deployed the proposed TFDDNN approach in a web application for Internet of Things (IoT)-enabled real-time recognition of hand gestures using MEMG sensor data.

关键词： Databases Electromyography Solid modeling Sensors Recording Continuous wavelet transforms Gesture recognition Sensor signal processing accuracy continuous wavelet transform (CWT) deep representation learning electromyogram (EMG) hand gestures Internet of Things (IoT)

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：