检索结果-内蒙古大学图书馆

Remote Sensing Image Change detection Based on General Deep Forest Module

IEEE ACCESS 2024年 12卷 84815-84829页

作者： Xu, Gang Zhang, Yanqin Mo, Jian Chen, Yiming Wang, Yunge Wang, Peng Zhejiang Coll Secur Technol Wenzhou 325016 Peoples R China Wenzhou Future City Res Inst Wenzhou 325016 Peoples R China Nanjing Univ Aeronaut & Astronaut Key Lab Radar Imaging & Microwave Photon Minist Educ Nanjing 210016 Peoples R China Hunan Inst Geol Disaster Invest & Monitoring Changsha 416099 Peoples R China Natl Dam Safety Engn Res Ctr Wuhan 430079 Peoples R China

Remote sensing image change detection, as one of the important branches of remote sensing technology, has been greatly developed and improved in recent years. The effectiveness of change detection is unstable, as deep learning components exhibit a high degree of sensitivity to hyperparameters, necessitating substantial fine-tuning to achieve optimal outcomes. Additionally, large and intricate deep learning models are not appropriate for smaller-scale datasets. In this paper, a remote sensing image change detection method based on general deep forest module (GDFM) is proposed. In the proposed GDFM, the common remote sensing image change detection method is firstly used for preliminary detection to obtain the detection result to be optimized, and the optimized change detection result is then obtained by using the classification function of the deep forest. This work aims to achieve a general enhancement of the performance of existing change detection methods by utilizing the characteristics of multi-grained scanning in deep forest and the data classification capabilities of cascaded forests. At the same time, this model alleviates the problems of parameter tuning complexity and inapplicability to small datasets in additional deep learning modules. It is worth noting that this general method is not a direct splicing process, but combines the advantages of the two parts and uses the characteristics of the deep forest to achieve the goal. Experiments are conducted on multiple common remote sensing change detection models. The results show that the proposed GDFM has significant improvements in metrics, which include varying degrees of improvement in F1 score by around 1% -14%.

关键词： Remote sensing Feature extraction Random forests Deep learning Regression analysis Monitoring Accuracy detection algorithms Remote sensing image change detection deep forest deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Crop Disease detection With EfficientNet Convolutional Group-Wise Transformer

引用

IEEE ACCESS 2024年 12卷 44147-44162页

作者： Feng, Jing Ong, Wen Eng Teh, Wen Chean Zhang, Rui Univ Sains Malaysia Sch Math Sci George Town 11800 Penang Malaysia Taiyuan Inst Technol Dept Sci Taiyuan 030008 Peoples R China

Crop diseases, as one of the major problems in global agricultural production, lead to crop yield reduction, death, and even total extinction, with serious impacts on farmers and the food supply. Traditionally, crop diseases are identified by visual inspection and based on the experience of farmers and agricultural experts, a method that not only consumes human resources but also has a certain degree of subjectivity and inaccuracy. The development of artificial intelligence technology successfully achieves real-time monitoring, automatic identification, and intelligent decision by combining the Internet of Things (IoT) technology and cloud computing technology. Herein, we proposed an EfficientNet Convolutional Group-Wise Transformer (EGWT) architecture. The local features of crop leaf images are extracted by EfficientNet convolution and then input into a group-wise transformer architecture. In the group-wise transformer process, the input features are divided into multiple groups. An attention mechanism is used within each group to calculate correlations between features. After calculating the intra-group attention, the output features of each group are stitched together to form the final output features. Our proposed model achieves 99.8% accuracy on the PlantVillage dataset, 86.9% accuracy on the cassava dataset, and 99.4% accuracy on the Tomato leaves dataset, with the least number of parameters 23.04M in the state-of-the-art convolutional combinatorial transformer hybrid model. The experimental results indicate that the proposed model has the best accuracy and optimal model complexity so far compared to other neural networks based on CNN, transformer, and the hybrid structure of CNN and transformer.

关键词： Transformers Crops Computer architecture Computational modeling Convolutional neural networks Feature extraction Plant diseases detection algorithms Smart agriculture Convolutional neural network group-wise transformer crop disease detection

来源：评论

学校读者我要写书评

暂无评论

Drift detection for Black-Box Deep Learning Models

引用

IT PROFESSIONAL 2024年第2期26卷 24-31页

作者： Piano, Luca Garcea, Fabio Cavallone, Andrea Vazquez, Ignacio Aparicio Morra, Lia Lamberti, Fabrizio Polytech Univ Turin Dept Control & Comp Engn I-10129 Turin Italy Reale Mutua Assicurazioni Data Sci Ctr Excellence I-10122 Turin Italy Reale Seguros Data Sci Ctr Excellence Madrid 28002 Spain

Dataset drift is a common challenge in machine learning, especially for models trained on unstructured data, such as images. In this article, we propose a new approach for the detection of data drift in black-box models, which is based on Hellinger distance and feature extraction methods. The proposed approach is aimed at detecting data drift without knowing the architecture of the model to monitor, the dataset on which it was trained, or both. The article analyzes three different use cases to evaluate the effectiveness of the proposed approach, encompassing a variety of tasks including document segmentation, classification, and handwriting recognition. The use cases considered for the drift are adversarial assaults, domain shifts, and dataset biases. The experimental results show the efficacy of our drift detection approach in identifying changes in distribution under various training settings.

关键词： Training Degradation Computational Modeling Closed Box Training Data Computer Architecture detection algorithms Data Models Machine Learning Deep Learning Data Integrity Deep Learning Models Drift detection Machine Learning Training Set Data Distribution Training Dataset Changes In Distribution Image Classification Domain Shift Model Architecture Application Programming Interface Inference Time Unstructured Data Artificial Intelligence Systems Dataset Bias Hellinger Distance Auxiliary Model Compact Embedding Artificial Intelligence Solutions Machine Learning Challenges Adversarial Examples Variational Autoencoder Latent Space Fast Gradient Sign Method Adversarial Attacks Source Task Variational Autoencoder Model Time Window Systematic Bias Training Data

来源：评论

学校读者我要写书评

暂无评论

YOLO-FMS: A Lightweight and Efficient Model for Medical Microscopic Smear detection

引用

IEEE ACCESS 2024年 12卷 125253-125265页

作者： Wang, Yan Pan, Lei Shu, Xin Jiangsu Univ Sci & Technol Sch Comp Sci Zhenjiang 212100 Peoples R China

Deep learning-based computer vision technology has been extensively utilized to assist medical microscopic smear diagnoses, such as complete blood count, detecting mycobacterium tuberculosis in sputum samples, and identifying plasmodium in blood smears. Effective medical microscopic smear detection necessitates balancing both detection accuracy and model parameters, facilitating the application of the model on low-resource computing platforms and ensuring real-time detection capabilities. Furthermore, the model should demonstrate superior generalization capabilities on microscopic smears to meet various detection tasks. In this study, we propose YOLO-FMS, a lightweight and efficient model based on YOLOv5 for medical microscopic smear detection with a compact weight of 15.06M, which can resolve the challenge of the balance between detection accuracy and model parameters. Firstly, YOLO-FMS improves the performance of small-scale platelet and mycobacterium tuberculosis detection by adding a small target detection head. Secondly, A lightweight convolutional technique, GSConv, was introduced to make the symbolic ability of the lightweight convolutional as close to the vanilla convolutional as possible and to reduce the computational cost. Thirdly, the feature extraction ability of YOLO-FMS is enhanced by C3-B-CBAM and Tiny-SPPCSPC modules constructed by our proposed method. Comprehensive experiments prove that YOLO-FMS shows high detection accuracy, with 92.5% mAP on the BCCD dataset and 87.6% mAP on the Tuberculosis-Phonecamera dataset. Additionally, numerous verification experiments are conducted on the BCDD and BBBC041 datasets, and the results confirm the effectiveness and generalization capability of YOLO-FMS in the medical microscopic smear detection field. The codes of YOLO-FMS are available at https://***/GefionP/YOLO-FMS.

关键词： Microscopy YOLO Medical diagnostic imaging Accuracy Blood Feature extraction Computational modeling detection algorithms Blood cell detection medical microscopic smear detection lightweight YOLO-FMS

来源：评论

学校读者我要写书评

暂无评论

Real-Time Pavement Damage detection With Damage Shape Adaptation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第11期25卷 18954-18963页

作者： Zhang, Yingchao Liu, Cheng City Univ Hong Kong Dept Syst Engn Hong Kong Peoples R China

Intelligent detection of pavement damage is crucial to road maintenance. Timely identification of cracks and potholes helps prolong the road service life. Current detection models fail to balance accuracy and speed. In this study, we propose a fast damage detection algorithm named FPDDN to achieve real-time and high-accuracy pavement damage detection. FPDDN integrates the deformable transformer, D2f block, and SFB module to predict pavement damage of different sizes in multiple branches. The deformable transformer allows the FPDDN to exhibit adaptability to geometric variations in road defects, thereby improving the detection accuracy of irregular defects such as cracks. D2f block is mainly used to lightweight the network and increase the inference speed. The SFB module can significantly decrease the loss of information during downsampling of small-sized objects. This integration enhances the model's ability to extract global damage features, reduces the loss of information on small-scale defects, and improves the synergy between deep and shallow feature layers. The model's performance was evaluated using the RDD2022 dataset, focusing on inference speed and detection accuracy. When compared to state-of-the-art models such as YOLO v8, FPDDN has a parameter count that is only one-fifth of that of YOLO v8x, yet it surpasses YOLO v8x in detection accuracy. The FPDDN achieved an F1 score of 0.601 and a mAP50 of 0.610 on the RDD2022 dataset, outperforming the compared models. Additionally, the algorithm achieved a balance between accuracy and speed with an inference speed of 1.8ms for pavement damage detection.

关键词： Accuracy YOLO Transformers Sensors Roads Three-dimensional displays detection algorithms Non-destructive testing transformer damage detection real-time detection

来源：评论

学校读者我要写书评

暂无评论

detection and Analysis of Fake News Users' Communities in Social Media

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第4期11卷 5050-5059页

作者： Amira, Abdelouahab Derhab, Abdelouahid Hadjar, Samir Merazka, Mustapha Alam, Md. Golam Rabiul Hassan, Mohammad Mehedi Res Ctr Sci & Tech Informat CERIST Algiers 16000 Algeria King Saud Univ Ctr Excellence Informat Assurance CoEIA Riyadh 11451 Saudi Arabia BRAC Univ Dept Comp Sci & Engn Dhaka 1212 Bangladesh King Saud Univ Coll Comp & Informat Sci Chair Pervas & Mobile Comp Dept Informat Syst & Res Riyadh 11543 Saudi Arabia

The widespread use of social media platforms has led to an increase in the dissemination of fake news with the intention of manipulating public opinion and causing chaos and panic among the population. To address this issue, we focus on detecting the organized groups that participate together in fake news campaigns without prior knowledge of the news content or the profiles of social accounts. To this end, we propose a spatial-temporal similarity graph, a novel graph structure that connects social accounts that participate in the early stage of similar fake news campaigns. A community detection algorithm is applied on the similarity graph to cluster the users into communities. We propose a community labeling algorithm to label the communities as benign or malicious based on the output of a fake news classifier. Evaluation results show that the community labeling algorithm can correctly label the communities with an accuracy of $99.61\%$ . In addition, we perform a statistical comparison analysis to identify the structural community features that are statistically significant between benign and malicious communities.

关键词： Fake news Social networking (online) Labeling Feature extraction detection algorithms Chatbots Manuals Community detection community labeling fake news similarity graph

来源：评论

学校读者我要写书评

暂无评论

Enhancing Transmission Line Safety: Real-Time detection of Foreign Objects Using MFMAM-YOLO Algorithm

引用

IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE 2024年第3期27卷 13-21页

作者： Ji, Chao Chen, Guoyan Huang, Xinbo Jia, Xinghai Zhang, Fan Song, Zhiwei Zhu, Yongcan Xian Polytech Univ Sch Elect Informat Xian Shaanxi Peoples R China

Image online monitoring technology has been widely used in transmission line inspection, but intelligent and efficient foreign object detection still has a gap with the ideal. The focus of this study is to develop an advanced system using the Multi-Fusion Mixed Attention Module-You Only Look Once (MFMAM-YOLO) algorithm for real-time detection of foreign objects on transmission lines. The main objective is to improve the safety and reliability of power transmission systems by swiftly identifying and removing any foreign objects that may pose hazards. The results demonstrate the effectiveness and efficiency of the proposed approach in accurately detecting foreign objects, thereby providing a valuable tool for maintaining the integrity of transmission lines.

关键词： Power transmission lines Safety Real-time systems Object detection Monitoring YOLO detection algorithms Hazardous areas Power system reliability

来源：评论

学校读者我要写书评

暂无评论

CFAR-DP-FW: A CFAR-Guided Dual-Polarization Fusion Framework for Large-Scene SAR Ship detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 7242-7259页

作者： Zeng, Tianjiao Zhang, Tianwen Shao, Zikang Xu, Xiaowo Zhang, Wensi Shi, Jun Wei, Shunjun Zhang, Xiaoling Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

Effective ship detection in synthetic aperture radar (SAR) imagery is crucial for maritime safety and surveillance. Despite the advancements in deep learning for SAR ship detection, significant challenges remain, particularly in large scenes. These challenges are twofold: the detection of extremely small ships is often hindered by inadequate feature extraction, and the presence of inshore ships is obscured by pronounced land-based interference, both of which lead to reduced detection accuracy. To address these issues, we present a novel deep learning framework that integrates constant false alarm rate (CFAR) processing with dual-polarization data, termed the CFAR-guided dual-polarization fusion framework (CFAR-DP-FW). The integration is designed to enhance the detection sensitivity for small-scale maritime targets by utilizing dual-polarization's rich feature representation, and CFAR's strength in suppressing background noise, highlighting potential targets. The proposed CFAR-DP-FW consists of three core components: the CFAR dual-polarization detector provides initial target indication;the CFAR field generator constructs a probabilistic ship presence map, reducing reliance on CFAR's hard thresholds;and the CFAR guidance dual-polarization network incorporates a novel feature extractor and enhancement module, tailored to amplify relevant features, and suppress noise. This strategic fusion within our framework markedly improves the detection of small and inshore ships. Evaluated on the large-scale SAR ship detection dataset-v1.0, our framework demonstrates superior performance, surpassing 20 state-of-the-art models. It achieves a 3.28% increase in mean average precision for inshore ships over the next best-performing model, validating its efficacy in tackling the intricate challenges of large-scale SAR ship detection.

关键词： Marine vehicles Feature extraction Radar polarimetry Synthetic aperture radar detection algorithms Manuals Visualization Constant false alarm rate (CFAR) dual polarization inshore ship detection small ship synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

A Data-Centric Contrastive Embedding Framework for Contextomized Quote detection

引用

IEEE ACCESS 2024年 12卷 40168-40181页

作者： Song, Seonyeong Han, Jiyoung Park, Kunwoo Soongsil Univ Dept Intelligent Semicond Seoul 06978 South Korea Korea Adv Inst Sci & Technol Moon Soul Grad Sch Future Strategy Daejeon 34141 South Korea Soongsil Univ Sch AI Convergence Seoul 06978 South Korea

Quotations are essential in lending credibility to news articles. A direct quote, typically enclosed in quotation marks, not only stands out visually but also indicates a reliable source. However, there is a practice known as 'contextomizing,' where words are extracted from their original context, changing the speaker's intended meaning. This results in a headline quote that semantically diverges from any other quote in the main article. This misrepresentation can lead to misunderstandings, especially in online environments where information is often consumed solely through headlines. To address this issue, this paper introduces QuoteCSE++, a data-centric contrastive embedding framework designed for the representation of quote semantics. Utilizing knowledge about the data and the news domain, QuoteCSE++ enhances a BERT-like transformer encoder to represent the complex semantics of news quotes and enables the detection of articles with contextomized headline quotes accurately. Our evaluation experiments demonstrate the superiority of the proposed method over both general-purpose embedding and domain-adapted methods in terms of detection accuracy. Remarkably, the proposed method exhibits a few-shot detection capability, achieving the performance level of SimCSE with just 200 training samples. We also test the ability of this framework for more general tasks of retrieving relevant quotes, implying its potential contribution to relevant fields. We release a dataset of 3,000 examples with high-quality manual annotations to support future research endeavors. Code and dataset are available at https://***/ssu-humane/contextomized-quotes-access.

关键词： Semantics Training Task analysis Self-supervised learning Context modeling Artificial intelligence Fake news Data models Contrast resolution detection algorithms Professional communication Data-centric AI contrastive learning contextomy

来源：评论

学校读者我要写书评

暂无评论

Cervical Spine Fracture detection and Classification Using Two-Stage Deep Learning Methodology

引用

IEEE ACCESS 2024年 12卷 72131-72142页

作者： Yaseen, Muhammad Ali, Maisam Ali, Sikandar Hussain, Ali Joo, Moon-Il Kim, Hee-Cheol Inje Univ Inst Digital Antiaging Healthcare Gimhae 50834 South Korea Inje Univ u AHRC Inst Digital Antiaging Healthcare Coll AI Convergence Gimhae 50834 South Korea

Cervical spine fractures are a medical emergency that can cause permanent paralysis and even death. Traditional fracture detection techniques, such as manual radiography image interpretation, are time-consuming and prone to human error. Deep learning algorithms have shown promising results in various medical imaging applications i.e., disease diagnosis, including fracture detection of bones. In this study, we propose a two-stage approach for detecting cervical spine fractures. The first stage employs a convolutional neural network (CNN) model to determine the presence or absence of a fracture in the cervical spine, using a dataset of cervical spine Computed Tomography (CT) scan images as well as Grad-CAM for enhanced visualization and interpretation. In the second stage, our focus shifts to specific vertebrae within the cervical spine. To accomplish this task, we trained and evaluated the performance of the YOLOv5 and YOLOv8 models with 9170 images consisting of seven vertebrae. The detection results of both YOLO versions are compared and evaluated. The precision, recall, mAP50, and mAP50-90 were 0.900, 0.890, 0.935, 0.872, respectively. The results of this research demonstrate the potential of deep learning-based approaches for cervical spine fracture detection. By automating the detection process, these algorithms can assist radiologists and healthcare professionals in making accurate and timely diagnoses, leading to improved patient outcomes.

关键词： Deep learning Feature extraction Computed tomography Convolutional neural networks Biomedical imaging YOLO Bones Spine Computer vision detection algorithms Medical diagnosis Cervical spine computed tomography (CT) computer vision deep learning medical image

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

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

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：