检索结果-内蒙古大学图书馆

Method and Application of Spraying Developer Defect detection in Three-Dimensional Optical Scanning Measurement Process Based on YOLO v7

引用

IEEE ACCESS 2024年 12卷 77235-77249页

作者： Wang, Zhanhui Zhao, Qisheng Feng, Chaojie Tianjin Sino German Univ Appl Sci Sch Mech Engn Tianjin 300350 Peoples R China Yanshan Univ Sch Mat Sci & Engn Qinhuangdao 066000 Peoples R China

In industrial production, three-dimensional scanning and inspection technology is widely applied, with spraying developer playing a critical role in this process. During the application of spraying developer, the spraying defects generated on the surface of workpieces can greatly affect the accuracy and integrity of the three-dimensional scanning data construction for the products. Currently, the detection of these spraying defects heavily relies on manual visual observation, a process that is both time-consuming and labor-intensive. Moreover, there is no standardized approach, leading to uncertainty in the subsequent construction of three-dimensional scanning data. To address this issue, this study proposes a deep learning algorithm based on YOLO v7 target detection. The research focuses on commonly used inspection parts in the field of three-dimensional optical scanning measurement, constructing a dataset specifically for spraying defects. Real-time target detection is then conducted on the workpieces within an actual production environment. Through model evaluation, it was found that the neural network in this study achieved a remarkable accuracy of 0.996 on the test set, with the highest confidence level of 0.96 during real-time inspection of the workpieces. These results demonstrate the superior accuracy of the proposed method in detecting defect targets, thereby offering valuable insights for evaluating spraying defects and enhancing the quality of three-dimensional optical scanning data construction.

关键词： Spraying Optical variables measurement Surface treatment Optical reflection Powders Three-dimensional displays YOLO Scanning electron microscopy detection algorithms Deep learning Computer vision Three-dimensional scanning spraying developer defects deep learning computer vision image detection

来源：评论

学校读者我要写书评

暂无评论

SCAN: Surveillance Camera Array Network for Enhanced Passenger detection

引用

IEEE ACCESS 2024年 12卷 115237-115255页

作者： Kuchar, Pavol Pirnik, Rastislav Kafkova, Julia Tichy, Tomas Durisova, Jana Skuba, Michal Univ Zilina Dept Control & Informat Syst Fac Elect Engn & Informat Technol Zilina 01026 Slovakia Czech Tech Univ Fac Transportat Sci Prague 11000 Czech Republic Univ Zilina Fac Elect Engn & Informat Technol Dept Phys Zilina 01026 Slovakia

The automated detection of individuals within vehicles, with minimal to no human intervention, hold multifaceted implications in contemporary contexts. These applications span from aiding emergency responders and optimising transportation networks to facilitating automated crash response mechanisms and enforcing regulations concerning High Occupancy Vehicle and High Occupancy Toll lanes. In this paper, we introduce our camera system designed for passenger counting, leveraging five IP cameras equipped with a range of optical filters, employing image registration techniques, and integrating the YOLOv8 object detection model. The Surveillance Camera Array Network (SCAN) operates within the near-infrared domain of the electromagnetic spectrum in conjunction with the visible part. Four VIVOTEK IP cameras are outfitted with near-infrared, neutral density, polarising, and ultraviolet optical filters, while the final camera retains its stock lens. Our primary challenge lies in managing variable lighting conditions throughout the day. However, during nighttime, we achieve nearly perfect image capture of vehicles. To mitigate noise, glare, and other impediments, we initially apply camera calibration, image preprocessing, cropping, image registration, and finally, image fusion. Our findings demonstrate that our cost-effective SCAN system adeptly detects passengers in cars equipped with window tinting. The results obtained during testing conditions resulted in an 66% true positive rate, 8% false positive rate and 26% false negative rate within best dataset. Additionally, we provide created datasets displaying passengers inside Suzuki Vitara, Jaguar XF, and Honda CRV vehicles with various levels of window tinting, to facilitate future community endeavors in addressing this challenging task.

关键词： Cameras Sensors Lighting Optical filters Automotive components Automobiles Calibration Image registration Machine learning detection algorithms Human factors Camera calibration digital image processing HOV image fusion image registration machine learning near-infrared filter occupancy estimation passenger detection

来源：评论

学校读者我要写书评

暂无评论

Research on Real-Time detection Algorithm for Pedestrian and Vehicle in Foggy Weather Based on Lightweight XM-YOLOViT

引用

IEEE ACCESS 2024年 12卷 7864-7883页

作者： Zhang, Huiying Gong, Yifei Yao, Feifan Zhang, Qinghua Jilin Inst Chem Technol Coll Informat & Control Engn Jilin 132022 Jilin Peoples R China

A novel XM-YOLOViT real-time detection algorithm for pedestrians and vehicles in foggy weather based on YOLOV5 framework is proposed, which effectively solves the problems of dense target interference and obscuration by haze, and the detection effect in complex foggy environments is improved. Firstly, Inverted Residual Block and MobileViTV3 Block are introduced to construct XM-net feature extraction network, secondly, EIOU is used as a location loss function and a high-resolution detection layer is added in the Neck region. In terms of data, a nebulization method is designed to map images from fogless space to foggy space based on the atmospheric scattering model and the dark channel prior. Finally, the validity on four datasets under different foggy environments is verified, respectively. The experimental results show that the accuracy, recall and mAP of the XM-YOLOViT model are 54.95%, 41.93% and 43.15% respectively, and with an F1-Score of 0.474, which is 3.42%,7.08%,7.52% and 13.94% improved, the model parameter reduction of 41.7% to 4.09M, the FLOPs is 25.2G and detection speed is 70.93 FPS compared to the baseline model. The XM-YOLOViT model has better performance than the advanced YOLO detectors, the F1-Score and mAP are improved by 5.57% and 3.65% compared with YOLOv7-tiny, and 2.38%, 2.37% respectively compared with YOLOv8s. Therefore, the XM-YOLOViT algorithm proposed in this article has high detection accuracy and an extremely lightweight structure, which can effectively improve the efficiency and quality of detection tasks for UAV in foggy weather, especially for extremely small targets. Our source code is available at: https://***/AFeiV8/XM-YOLOViT.

关键词： YOLO Meteorology Feature extraction Convolution Autonomous aerial vehicles Real-time systems detection algorithms Fog detection XM-YOLOViT XM-net high-resolution layer nebulization method lightweight structure tiny object

来源：评论

学校读者我要写书评

暂无评论

DMFF-YOLO: YOLOv8 Based on Dynamic Multiscale Feature Fusion for Object detection on UAV Aerial Photography

引用

IEEE ACCESS 2024年 12卷 125160-125169页

作者： Qiu, Xiaoyang Chen, Yajun Sun, Chaoyue Li, Jianying Niu, Meiqi China West Normal Univ Sch Elect Informat Engn Nanchong 637009 Peoples R China

With the rapid proliferation of drones across various domains, aerial target detection has become increasingly crucial. However, the targets in aerial images present challenges such as scale variation, small size, and density, leading to suboptimal performance of current detectors on aerial images. Based on the aforementioned challenges, we design an efficient aerial target detection algorithm called DMFF-YOLO. Specifically, to address the issues of small target size and scale variation, we design the DMFF neck structure, adding a small target detection head to tackle the small target size problem, using the DMC module to fuse different scale features for enriching detailed information, and employing the DSSFF module to construct a scale sequence space to solve the target scale variation problem. In the network backbone, we employ RFCBAMConv modules as downsampling layers, which interact with receptive-field features to mitigate the information disparity caused by positional changes and outperform traditional convolutional layers. Finally, we design the Soft-NMS-CIoU module to address the issue of suppressing adjacent boxes due to dense targets. On the VisDrone dataset, compared to the original algorithm, our method reduces the number of parameters by 31.1% while achieving an 11.7% improvement in mAP50. Extensive experiments on the VisDrone, DOTA, and UAVDT datasets demonstrate that the proposed algorithm performs well in aerial image detection tasks.

关键词： Feature extraction Drones Monte Carlo methods Object detection YOLO Autonomous aerial vehicles Target tracking detection algorithms Multi-scale feature fusion small object detection UAV

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Change detection Based on Multi-Level Diversity Feature Fusion

引用

IEEE ACCESS 2024年 12卷 81495-81505页

作者： Xie, Honggang Ma, Wanjie Hubei Univ Technol Sch Elect & Elect Engn Wuhan 430068 Peoples R China

Urban topographic changes have a crucial impact on the environment, which serves as the foundation for human survival. However, due to the different spectral response characteristics of various remote sensing satellite sensors and the presence of aging issues, the captured remote sensing images exhibit color imbalance under different seasons and lighting conditions. Existing change detection methods fail to establish the correlation between changed and unchanged information in color-imbalanced urban topographic remote sensing images, thereby reducing the utilization of feature extraction information. Additionally, using fixed thresholds for region determination may inaccurately and incompletely generate change areas. Therefore, this paper proposes a remote sensing image change detection method based on multi-level and multi-diversity feature fusion. Firstly, a ResNet-18 network is employed to extract dual-temporal features. Secondly, to enhance the discrimination between change and unchanged regions during feature extraction and improve the utilization of feature extraction information, a Diversity Feature Fusion Module (DFFM) is designed to reduce false alarms and omissions in the detection results. Furthermore, to effectively address the problem of boundary misjudgment in change areas caused by fixed thresholds, an Adaptive Threshold Module is devised to adaptively learn the texture features of change and unchanged regions, enabling the generation of more accurate thresholds for boundary determination, thereby improving the robustness of the algorithm model and alleviating false alarms. Finally, experimental tests demonstrate that our method achieves excellent performance in two public change detection datasets.

关键词： Feature extraction Remote sensing Adaptive systems Data mining Transformers Spatial resolution Robustness detection algorithms Threshold current Change detection remote sensing diversity feature adaptive threshold

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyberattack detection Using Dimensionality Reduction With Hybrid Deep Learning on Internet of Things Environment

引用

IEEE ACCESS 2024年 12卷 84752-84762页

作者： Duraibi, Salahaldeen Mujawib Alashjaee, Abdullah Jazan Univ Coll Engn & Comp Sci Dept Elect & Elect Engn Jazan 45142 Saudi Arabia Northern Border Univ Coll Sci Dept Comp Sci Ar Ar 73213 Saudi Arabia

Cybersecurity in the Internet of Things (IoT) ecosystem is vital to protect sensitive data, stop unauthorized access, and mitigate the risk of disruptive cyberattacks. Cyberattack recognition utilizing an intrusion detection system (IDS) is a major imperative given the increase in the number of connected devices. Advanced cybersecurity methods deploy machine learning (ML) approaches, anomaly detection, and behavioral analysis to analyze IoT network traffic for irregular patterns indicative of potential cyberattacks. The combination of feature selection (FS) and deep learning (DL) approaches in cyberattack recognition suggests a proactive and sophisticated manner to bolster cybersecurity. Leveraging DL structures like neural networks (NNs) assists the automatic extraction and analysis of intricate patterns in the difficult IoT data landscape. This paper develops an Improved Mayfly Optimization Algorithm with a Hybrid Deep Learning based Intrusion detection (IMFOHDL-ID) approach in IoT environments. The designed IMFOHDL-ID approach's main goal is to classify intrusions and accomplish security in the IoT environment. The IMFOHDL-ID technique initially follows data normalization as a preprocessing stage. In addition, the IMFOHDL-ID technique makes use of the IMFO-based feature selection (FS) method to elect feature subsets. For IDs, the IMFOHDL-ID technique applies the Long Short Term Memory based Deep Stacked Sequence-to-Sequence Autoencoder (LSTM-DSSAE) model. Finally, the dipper-throated optimization algorithm (DTOA) was utilized for optimal hyperparameter selection of the LSTM-DSSAE method. To highlight better results of the IMFOHDL-ID model, a series of simulation analyses were performed. Extensive comparative results stated the improved outcome of the IMFOHDL-ID technique over existing approaches.

关键词： Internet of Things Feature extraction Optimization Cyberattack Long short term memory Safety Intrusion detection Computer security detection algorithms Cybersecurity intrusion detection system feature selection hybrid deep learning

来源：评论

学校读者我要写书评

暂无评论

Low-Complexity MIMO detection Based on DRSD With ISMMSE-PIC

引用

IEEE ACCESS 2024年 12卷 70235-70244页

作者： Shin, Sang-Sik Jae Kim, Ho Kim, Hyoung-Nam Pusan Natl Univ Dept Elect Engn Busan 46241 South Korea

This paper introduces a low-complexity multiple-input multiple-output (MIMO) detection method based on dimension-reduction-soft-demodulation (DRSD) with iterative soft minimum-mean-squared-error parallel interference cancellation (ISMMSE-PIC). The conventional ISMMSE-PIC detection method exhibits several drawbacks, such as inordinate dependence on decoder performance and modulation-order sensitivity. Therefore, a DRSD-based strategy is presented to search over a part of the set of transmitted symbols for calculating log-likelihood ratio (LLR) values, such as maximum likelihood detection, to improve detection performance. The scheme for the rest of the symbols directly utilizes ISMMSE-PIC detection for computing the corresponding LLR values. The computational complexity of the proposed scheme is similar to that of ISMMSE-PIC, whereas its bit error rate performance is comparatively higher. The complexity analysis and simulation results validate the proposed algorithm.

关键词： Symbols MIMO communication Vectors Detectors Transmitting antennas Receiving antennas Computational complexity detection algorithms Multiple-input multiple-output iterative soft minimum-mean-squared-error parallel interference cancellation dimension reduction soft demodulation geometric symmetry

来源：评论

学校读者我要写书评

暂无评论

MoVAE: Multi-Omics Variational Auto-Encoder for Cancer Subtype detection

引用

IEEE ACCESS 2024年 12卷 133617-133631页

作者： Rahmanian, Mohsen Mansoori, Eghbal G. Shiraz Univ Sch Elect & Comp Engn Shiraz *** Iran

With the advent of advanced genomic data extraction methods, numerous studies have been utilized these data to identify cancer subtypes. Given the complexity of cancer subtyping and the limitations of single-omics data, multi-omics approaches have emerged as a promising solution. Despite the challenges of multi-omics data integration, these methods have shown acceptable results. Various strategies, including matrix decomposition, kernel-based fusion, and deep learning, have been proposed for data fusion and subtyping. As a deep model, we present the Multi-omics Variational Auto Encoder (MoVAE), an innovative strategy for integrating multi-omics data. MoVAE facilitates adaptive fusion by extracting unique and synergistic features from high-dimensional multi-omics data using an AggreEncoder network. Unlike previous methods, MoVAE effectively handles the integration of heterogeneous data, accommodates missing omics, and manages high-dimensionality. As a variational autoencoder, MoVAE encodes each multi-omics input into a low-dimensional latent space while extracting the omics-dependency and complementary information of multi-omics data according to a prior joint distribution. Using the mined knowledge in the cancer subtype detection model, its prediction efficiency would be improved. By decoding the latent vectors, MoVAE reconstructs the input multi-omics data as accurately as possible. To demonstrate MoVAE's effectiveness in identifying biologically meaningful and clinically relevant cancer subtypes, we conducted several experiments and compared the results with state-of-the-art VAE-based methods.

关键词： Cancer Data models Feature extraction Data mining Genomics Computational modeling Bioinformatics detection algorithms Autoencoders Cancer subtype detection encoder aggregator multi-omics data variation auto-encoder

来源：评论

学校读者我要写书评

暂无评论

TransMixer-AF: Advanced Real-Time detection of Atrial Fibrillation Utilizing Single-Lead Electrocardiogram Signals

引用

IEEE ACCESS 2024年 12卷 143149-143162页

作者： Mahim, S. M. Emamul Hossen, Md Al Hasan, Shakib Islam, Md Khairul Iqbal, Zafar Alibakhshikenari, Mohammad Collotta, Mario Miah, Md Sipon Islamic Univ Dept Biomed Engn Kushtia 7003 Bangladesh King Saud Univ Coll Med Dept Gen Surg Riyadh 11472 Saudi Arabia Univ Roma Tor Vergata Dept Elect Engn I-00133 Rome Italy Kore Univ Enna Dept Engn & Architecture I-94100 Enna Italy Carlos III Univ Madrid UC3M Dept Signal Theory & Commun Leganes 28911 Madrid Spain Islamic Univ Dept Informat & Commun Technol Kushtia 7003 Bangladesh

Atrial Fibrillation (AF) is a prevalent cardiac arrhythmia that carries an increased risk of stroke and heart failure. The manual interpretation of Electrocardiograms (ECGs) for diagnosing AF is time-consuming and subject to observer variability. Deep Learning (DL) techniques offer a promising solution for robust AF detection. This paper introduces a novel DL model that leverages ConvMixer and Transformer architecture, combining convolutional neural networks and attention mechanism to extract both local and global features from ECG data. It excels in accurately classifying ECG rhythms into two categories: normal and atrial fibrillation. Additionally, the model utilizes GradCAM++ visualization to provide interpretability. The model was evaluated using the PhysioNet/CinC 2017 Database, achieving accuracies of 91.66% on original data and 96.59% on preprocessed data. When applied to the the MIT-BIH Arrhythmia Database, it achieved accuracies of 95.86% on original data and 98.78% on preprocessed data, employing a ten-fold cross-validation strategy. This innovative approach has the potential to assist clinicians in the real-time detection of common atrial fibrillation during routine ECG screening, significantly enhancing the efficiency and accuracy of diagnosis. With a strong focus on improving patient outcomes and reducing the burden on healthcare professionals, this research represents a crucial step forward in cardiac arrhythmia detection.

关键词： Atrial fibrillation deep learning TransMixer-AF detection algorithms signal detection Atrial fibrillation deep learning TransMixer-AF detection algorithms signal detection

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on COVID-19 detection Based on Cough Sounds, Symptoms, CXR, and CT Images

引用

IEEE ACCESS 2024年 12卷 75412-75425页

作者： Mahanty, Chandrakanta Patro, S. Gopal Krishna Rathor, Sandeep Rachapudi, Venubabu Mohanty, Jnanaranjan Muzammil, Khursheed Islam, Saiful Khan, Wahaj Ahmad GITAM Deemed Univ GITAM Sch Technol Dept Comp Sci & Engn Visakhapatnam 530045 India Woxsen Univ Sch Technol Hyderabad 502345 Telangana India GLA Univ Dept CEA Mathura 281406 India Dept Comp Sci & Engn Dept Comp Sci & Engn Guntur 522302 Andhra Pradesh India Parala Maharaja Engn Coll Govt Dept Comp Sci & Engn Berhampur 761003 Odisha India King Khalid Univ Coll Appl Med Sci Dept Publ Hlth Khamis Mushait Campus Abha 61421 Saudi Arabia King Khalid Univ Coll Engn Civil Engn Dept Abha 61421 Saudi Arabia Dire Dawa Univ Inst Technol Sch Civil Engn & Architecture Dire Dawa 1362 Ethiopia

The worldwide spread of the coronavirus illness has led to the requirement of creating machine-based technologies to identify the diseases. The worldwide pandemic caused by new coronaviruses has resulted in a significant loss of life and necessitates the development of several affordable diagnostic methods to detect the presence of COVID-19 infection. Thankfully, the current era of advanced technology, including transfer learning (TL) approaches, has improved several areas of human health and enabled the identification of chronic and communicable diseases. There is a need for thorough investigation in order to combat the transmission of this alarming virus via the use of evidence-based intelligence models and implementation of preventive measures. The present systematic review focuses on the examination of TL and fuzzy ensemble techniques that have been described in the literature pertaining to strategies for detecting COVID-19. Multiple studies have used cough sounds, CT scans, X-ray images, and symptoms information to identify cases of COVID-19. The application of DL/ML, TL, fuzzy ensemble, and fuzzy inference approaches for COVID-19 identification is discussed in this paper.

关键词： COVID-19 Computed tomography Convolutional neural networks Residual neural networks Noise measurement X-ray imaging Mel frequency cepstral coefficient Acoustics Ensemble learning Predictive models detection algorithms Prediction cough sounds CXR images CT images symptoms ensemble

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：