检索结果-内蒙古大学图书馆

13th International Conference on image processing Theory Tools and Applications

作者： Karim, Meridja Imene, Sekkiou Aymen, Gammoudi Univ Paris Saclay Campus Evry Evry France Caplogy Velizy Villacoublay France

ISBN: (纸本)9798331541859;9798331541842

Human activity recognition (HAR) using Wi-Fi signals has gained significant attention due to its non-invasive nature, ubiquity, and respect for privacy, in contrast to camera-based systems. This study aims to develop a robust deep learning model for real-time HAR using Channel State Information (CSI) from Wi-Fi signals. We propose a deep Convolutional Neural Network (CNN) architecture incorporating an attention mechanism to process CSI data and classify various human activities. Our model was trained and tested using a comprehensive dataset of Wi-Fi CSI, employing advanced data augmentation techniques to enhance model generalization. The proposed model achieved an impressive accuracy of 99.69%, significantly outperforming existing approaches in terms of precision, recall, and F1 score. These findings demonstrate the potential of using Wi-Fi CSI with deep CNNs and attention mechanisms for accurate and real-time HAR, paving the way for applications in smart homes, healthcare monitoring, and other domains requiring efficient and privacy-preserving activity recognition. Future work will explore adapting this methodology to a variety of datasets and integrating an emotion recognition system to further expand its capabilities.

关键词： human activity recognition (HAR) Wi-Fi sensing deep learning attention mechanism channel state information(CSI) Convolutional neural network (CNN) Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Speed and accuracy in Tandem: deep learning-Powered Millisecond-Level pulmonary embolism detection in CTA

引用

BIOMEDICAL SIGNAL processing AND CONTROL 2025年 106卷

作者： Wu, Houde Chen, Ting Wang, Longshuang Guo, Li Tianjin Med Univ Sch Med Imaging Tianjin 300203 Peoples R China Dalian Med Univ Affiliated Hosp 1 Dalian 116011 Liaoning Peoples R China

Background and Objectives: Pulmonary embolism (PE) is a critical medical condition that requires a rapid and accurate diagnosis. Traditional methods, although highly precise, have focused primarily on accuracy, neglecting the urgency of speed required in emergency settings. This study aims to develop a deep learning model that not only maintains high accuracy but also achieves millisecond-level PE detection speed. Materials and Methods: This study employed an internal dataset comprising 160 patients from Tianjin Medical University General Hospital, and an external RSNA dataset for validation. Our model, built upon the YOLOv5 framework, was enhanced with Partial Convolution, a C2f module, and decoupled head structure. Results: The internal test set achieved a recall of 82.5 %, precision of 84.2 %, and mean average precision (mAP) of 87.2 %, significantly outperforming the other leading models. Notably, our model provided an inference time of just 1.6 ms per image, setting a new benchmark for real-time PE detection, which was faster than YOLOv5 (2.9 ms), YOLOv6 (4.0 ms), and YOLOv8 (3.2 ms). Furthermore, our model demonstrated faster convergence and consistently lower loss values during training, achieving perfect precision at a significantly lower confidence threshold than other YOLO variants, highlighting its superior optimization and generalization capabilities. Conclusion: This study successfully developed a deep learning model capable of millisecond-level PE detection without compromising the accuracy. Its performance underscores its potential to revolutionize PE diagnosis in emergency clinical settings, enabling timely and reliable intervention.

关键词： Artificial Intelligence deep learning Pulmonary Embolism Target Detection YOLO

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor flow state identification and schlieren image generation for supersonic inlet

引用

AEROSPACE SCIENCE AND TECHNOLOGY 2025年 158卷

作者： Wang, Yu-Jie Zhao, Yong-Ping Jin, Yi Hou, Kuan-Xin Nanjing Univ Aeronaut & Astronaut Coll Energy & Power Engn Nanjing 210016 Peoples R China Civil Aviat Flight Univ China Coll Aeronaut Engn Guanghan 618703 Peoples R China

The detection of flow state inside the supersonic inlet, including internal flow patterns and schlieren images, is crucial for advancing supersonic flight technology. However, obtaining precise information from inlets with varying internal contraction ratios (ICR) is challenging due to limitations in the operating environment and equipment, particularly in capturing schlieren images. In this paper, deep learning approaches are applied to flow state identification and schlieren image generation for supersonic inlet. For one thing, a time-frequency deep convolutional neural network model aggregates pressure signals from multiple sensors to predict the current flow pattern. For another, an enhanced pix2pix schlieren generation network (EPSGN) generates flow patterns on a blank inlet schlieren by incorporating recognition results and semantic labels. The experimental results demonstrate that the joint system achieves an accuracy of 99.23% in identifying the flow state of the supersonic inlet. Furthermore, the system is capable of generating schlieren images that depict various flow states under different experimental conditions, including those transient phenomena that are unobservable by high-speed cameras. The entire process requires only approximately 46 ms, underscoring its suitability for realtime applications in detecting the internal flow state of supersonic inlets. The rapid processing time facilitates immediate feedback, which is essential for real-time monitoring and control systems.

关键词： Supersonic inlet deep learning Multi-sensor flow state identification Enhanced pix2pix schlieren generation network

来源：评论

学校读者我要写书评

暂无评论

real-time hand gesture recognition using multiple deep learning architectures

引用

SIGNAL image AND VIDEO processing 2023年第8期17卷 3963-3971页

作者： Aggarwal, Apeksha Bhutani, Nikhil Kapur, Ritvik Dhand, Geetika Sheoran, Kavita Indian Inst Technol Roorkee Dept CSE Roorkee 247667 Uttar Pradesh India Maharaja Surajmal Inst Technol Delhi 110058 Delhi India

Human gesture recognition is one of the most challenging problems in computer vision, striving to analyze human gestures by machine. However, most of the literature on gesture recognition utilizes isolated data with only one gesture in one image or a video for classifying gestures. This work targets the identification of human gestures from the continuous stream of data input taken from a live camera feed, with no pre-defined boundaries. This task becomes even more complex given the diverse lighting conditions, varying backgrounds and different gesture positions in the same input stream of data. This work presents an effective deep learning architecture to classify gestures taken from multiple viewpoints and varying object sizes. To perform the classification, in this work, we have synthesized a real-world dataset consisting of 4500 images collected from different persons of varying age groups ranging from 10 to 50. The dataset is accumulated considering a wide variety of characteristics to address the complexities in the gesture recognition process. A real-time system is developed that captures, analyzes and classifies live gesture videos frame by frame. To prove the validity of our approach, we have compared our results with multiple deep learning architectures and other benchmark datasets. The results depict that our approach outperforms the existing works and is able to detect gestures with deteriorating lighting conditions and murky gesture positions, achieving an accuracy of 99.63%.

关键词： Convolution neural network Artificial neural network Gesture recognition Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A Pavement Crack Registration and Change Identification Method Based on Unsupervised deep Neural Network

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 757-769页

作者： Wang, Zhengfang Zhu, Hongliang Yang, Yujie Jiang, Haonan Li, Wenhao Li, Bingrui Li, Peng Xu, Lei Sui, Qingmei Wang, Jing Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China Shandong Univ Shenzhen Res Inst Shenzhen 518057 Peoples R China Qilu Aerosp Informat Res Inst Jinan 250101 Peoples R China Changjiang Geophys Explorat & Testing Co Ltd Wuhan 430010 Peoples R China

Periodically monitoring the pavement cracks is of great importance to many transportation infrastructures. This paper proposed an unsupervised deep-learning-based method to match the cracks in multi-temporal unmanned aerial vehicle (UAV) images and identify the changes of pavement cracks over time. A regional focus module was specially designed to enforce the network to focus on regions where cracks were located and enhance its capacity for small-crack identification. Moreover, a data augmentation method which combined Poisson blending and random projective transformations was introduced for generating images with crack variations for model training. The superiority of the method was validated using actual image collected from real pavements. The experimental results showed that the proposed method outperformed the feature-based method and existing unsupervised deep learning-based UAV image registration method.

关键词： Feature extraction Autonomous aerial vehicles image registration Inspection Convolutional neural networks Remote sensing image segmentation Biomedical imaging Artificial neural networks Surface cracks deep neural network pavement inspection crack variation identification multi-temporal UAV images

来源：评论

学校读者我要写书评

暂无评论

Spatial interpolation of global DEM using federated deep learning

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-13页

作者： Huo, Ziqiang Wen, Jiabao Li, Zhengjian Chen, Desheng Xi, Meng Li, Yang Yang, Jiachen Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Shihezi Univ Coll Mech & Elect Engn Shihezi 832003 Peoples R China

The digital elevation model (DEM) provides important data support for 3D terrain modeling. However, due to the complex and changeable terrain in the real world and the high cost of field measurement, it is extremely difficult to obtain continuous and high-density elevation data directly. Therefore, it is necessary to rely on spatial interpolation technology to restore the DEM overall picture in the original sampling area. The traditional spatial interpolation method usually has the characteristics of low model complexity and high computational cost, which leads to low real-time performance and low precision of the interpolation process. The interpolation operation based on DEM data can be considered as a special image generation process where the input is a DEM image with missing values and the output is a complete DEM image. At present, a large number of studies have proved that deep learning methods are very effective in image generation tasks. However, the training of deep learning models requires the support of a large number of high-quality data sets. DEM data in various countries, especially in key regions, are usually restricted by privacy protection regulations and cannot be disclosed. The emergence of Federated learning (FL) provides a new solution, which supports local training on multiple end nodes, without sending local data to a remote center server for centralized training, effectively protecting data privacy. In this study, we propose a DEM interpolation model based on FL and multiScale U-Net. The experimental results show that compared with the traditional method, this model has faster processing speed and lower interpolation precision. At the same time, this research result provides a new way for efficient and secure use of terrain information, especially in those application scenarios that have strict requirements for DEM data privacy and security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visual Cardiac Signal Classifiers: A deep learning Classification Approach for Heart Signal Estimation From Video

引用

IEEE ACCESS 2024年 12卷 144377-144394页

作者： Moustafa, Mohamed Farooq, Muhammad Ali Elrasad, Amr Lemley, Joseph Corcoran, Peter Univ Galway Dept Elect & Elect Engn Imaging Lab C3I Galway H91 TK33 Ireland FotoNation Sensing Team Galway H91 V0TX Ireland

Heart rate is a crucial metric in health monitoring. Traditional computer vision solutions estimate cardiac signals by detecting physical manifestations of heartbeats, such as facial discoloration caused by blood oxygenation changes, from subject videos using regression methods. As continuous signals are more complex and expensive to de-noise, this study introduces an alternative approach, employing end-to-end classification models to remotely derive a discrete representation of cardiac signals from face videos. These visual cardiac signal classifiers are trained on discretized cardiac signals, a novel pre-processing method with limited precedent in health monitoring literature. Consequently, various methods to convert continuous cardiac signals into binary form are presented, and their impact on training is evaluated. An implementation of this approach, the temporal shift convolutional attention binary classifier, is presented using the regression-based convolutional attention network architecture. The classifier and a baseline regression model are trained and tested using publicly available and locally collected datasets designed for heart signal detection from face video. The model performance is then assessed based on the heart rate error from the extracted cardiac signals. Results show the proposed method outperforms the baseline on the UBFC-rPPG dataset, reducing cross-dataset root mean square error from 2.33 to 1.63 beats per minute. However, both models struggled to generalize to the PURE dataset, with root mean square errors of 12.40 and 16.29 beats per minute, respectively. Additionally, the proposed approach reduces the computational complexity of model output post-processing, enhancing its suitability for real-time applications and deployment on systems with restricted resources.

关键词： Convolutional neural networks Heart rate Computer vision Training Estimation Remote sensing Visualization Standards Monitoring Feature extraction deep learning Biomedical signal processing Photoplethysmography deep learning image classification remote monitoring remote sensing biomedical signal processing heart rate photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Invariant Feature Matching in Spacecraft Rendezvous and Docking Optical Imaging Based on deep learning

引用

REMOTE SENSING 2024年第24期16卷 4690-4690页

作者： Guo, Dongwen Wu, Shuang Weng, Desheng Gao, Chenzhong Li, Wei Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Natl Key Lab Sci & Technol Space Born Intelligent Beijing 100081 Peoples R China

In spacecraft rendezvous and docking, traditional methods that rely on inertial navigation and sensor data face challenges due to sensor inaccuracies, noise, and a lack of multi-approach assurance. Focusing on exploring a new approach as assistance, this study marks the first application of deep learning-based image feature matching in spacecraft docking tasks, introducing the Class-Tuned Invariant Feature Transformer (CtIFT) algorithm. CtIFT incorporates an improved cross-attention mechanism and a custom-designed feature classification module. By using symmetric multi-layer cross-attention, it gradually strengthens inter-feature relationships perception. And, in the feature matcher, it employs feature classification to reduce computational load, thereby achieving high-precision matching. The model is trained on multi-source datasets to enhance its adaptability in complex environments. The method demonstrates outstanding performance across experiments on four spacecraft docking video scenes, with CtIFT being the only feasible solution compared to SIFT and eight state-of-the-art network methods: D2-Net, SuperPoint, SuperGlue, LightGlue, ALIKED, LoFTR, ASpanFormer, and TopicFM+. The number of successfully matched feature points per frame consistently reaches the hundreds, the successful rate remains 100%, and the average processing time is maintained below 0.18 s per frame, an overall performance which far exceeds other methods. The results indicate that this approach achieves strong matching accuracy and robustness in optical docking imaging, supports real-time processing, and provides new technical support for assistance of spacecraft rendezvous and docking tasks.

关键词： spacecraft rendezvous and docking optical imaging invariant feature feature matching deep learning cross-attention

来源：评论

学校读者我要写书评

暂无评论

AASNet: A Novel image Instance Segmentation Framework for Fine-Grained Fish Recognition via Linear Correlation Attention and Dynamic Adaptive Focal Loss

引用

APPLIED SCIENCES-BASEL 2025年第7期15卷

作者： Kong, Jianlei Tang, Shunong Feng, Jiameng Mo, Lipo Jin, Xuebo Beijing Technol & Business Univ Natl Engn Res Ctr Agriprod Qual Traceabil Beijing 100048 Peoples R China Beijing Wuzi Univ Inst Syst Sci Beijing 101149 Peoples R China

Smart fisheries, integrating advanced technologies such as the Internet of Things (IoT), artificial intelligence (AI), and image processing, are pivotal in enhancing aquaculture efficiency, sustainability, and resource management by enabling real-time environmental monitoring, precision feeding, and disease prevention. However, underwater fish recognition faces challenges in complex aquatic environments, which hinder accurate detection and behavioral analysis. To address these issues, we propose a novel image instance segmentation framework based on a deep learning neural network, defined as the AASNet (Agricultural Aqua Segmentation Network). In order to improve the accuracy and real-time availability of fine-grained fish recognition, we introduce a Linear Correlation Attention (LCA) mechanism, which uses Pearson correlation coefficients to capture linear correlations between features. This helps resolve inconsistencies caused by lighting changes and color variations, significantly improving the extraction of semantic information for similar objects. Additionally, Dynamic Adaptive Focal Loss (DAFL) is designed to improve classification under extreme data imbalance conditions. Abundant experiments on two underwater datasets demonstrated that the proposed AASNet obtains an optimal balance between segmentation performance and efficiency. Concretely, AASNet achieves mAP scores of 31.7 and 47.4, respectively, on the UIIS and USIS dataset, significantly outperforming existing state-of-the-art methods. Moreover, AASNet achieves an inference image recognition speed of up to 28.9 ms/per, which is suitable for practical agricultural applications of smart fish farming.

关键词： digital agriculture intelligent fish farming system deep learning neural network underwater image segmentation fine-grained visual recognition

来源：评论

学校读者我要写书评

暂无评论

real-time Stroke Detection Using deep learning and Federated learning

Real-Time Stroke Detection Using Deep Learning and Federated...

引用

Conference on real-time processing of image, Depth, and Video Information

作者： Elhanashi, Abdussalam Dini, Pierpaolo Saponara, Sergio Zheng, Qinghe Alsharif, Ibrahim Univ Pisa Dip Ingn Informaz Via G Caruso 16 I-56122 Pisa Italy Shandong Management Univ Sch Intelligent Engn Jinan 250357 Shandong Peoples R China Jordan Univ Sci & Technol Ar Ramtha 3030 Jordan

ISBN: (纸本)9781510673199;9781510673182

Stroke is a devastating and life-threatening medical condition that demands immediate intervention. timely diagnosis and treatment are paramount in reducing mortality and mitigating long-term disabilities associated with stroke. This research aims to address these critical needs by proposing a real-time stroke detection system based on deep learning (DL) with the incorporation of Federated learning (FL), which offers improved accuracy and privacy preservation. The purpose of this research is to develop an efficient and accurate model capable of distinguishing between stroke and non-stroke cases in real-time, assisting healthcare professionals in making rapid and informed decisions. Stroke detection has traditionally relied on manual interpretation of medical images, which is time-consuming and prone to human error. DL techniques have shown significant promise in automating this process, but the need for large and diverse datasets, as well as privacy concerns, remains challenging. To achieve this goal, our methodology involves training the DL model on extensive datasets containing both stroke and non-stroke medical images. This training process will enable the model to learn complex patterns and features associated with stroke, thereby improving its diagnostic accuracy. Furthermore, we will employ Federated learning, a decentralized training approach, to enhance privacy while maintaining model performance. This approach allows the model to learn from data distributed across multiple healthcare institutions without sharing sensitive patient information. The proposed approach has been executed on NVIDIA platforms, taking advantage of their advanced GPU capabilities to enable real-time processing and analysis. This optimized model has the potential to revolutionize stroke diagnosis and patient care, ultimately saving lives and improving the quality of healthcare services in the field of neurology.

关键词： Stroke deep learning Federated learning real-time Detection Healthcare Professional

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：