检索结果-内蒙古大学图书馆

A Novel Text classification Model Combining Time Correlation Principle and Rough Set Theory

IEEE ACCESS 2023年 11卷 135797-135810页

作者： Zhang, Dejun Leshan Normal Univ Sch Literature & Journalism Leshan 614000 Sichuan Peoples R China

This research aims to design a literary text feature classification and information extraction model based on the principle of temporal association and rough set theory. We put forward a new text classification method through the in-depth study of time series correlation principle algorithm and text classification technology based on rough set theory. First, we propose to use the lexical space feature vector as the input channel of the rough set model to extract literary sentence-level features according to the spatial relationship between words. Secondly, aiming at the problem of low efficiency of KNN text classification algorithm, we propose a KNN literature text classification algorithm based on rough set approximation set, which significantly improves classification efficiency while ensuring classification accuracy. The effectiveness of the algorithm is proved by experiments, and it promotes the progress of rough set theory in practical application research. In addition, we propose an improved attribute reduction algorithm in the process of literary text classification by combining feature selection, information extraction, and the correlation of feature items generated by text description and the evaluation criteria of rough set itself. This algorithm makes the reduced attribute set more important, and then improves the text recognition rate. Through comparative experiments, it is proved that our improved method increases the number of applicable texts by 12.86%, and the improvement effect is good. In summary, our model combines the temporal correlation principle with rough set theory, and provides a new method for feature classification and information extraction of literary texts. Our results demonstrate that the method is able to achieve better classification results when applied to collections of literary texts.

关键词： Text categorization Feature extraction classification algorithms Rough sets Correlation Time series analysis Natural language processing Machine learning Text classification temporal association principle rough set theory machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Compressed Domain Multimedia for Man and Machine: A Taxonomy and Application to Point Cloud classification

引用

IEEE ACCESS 2023年 11卷 128979-128997页

作者： Seleem, Abdelrahman Guarda, Andre F. R. Rodrigues, Nuno M. M. Pereira, Fernando Univ Lisbon Inst Super Tecn P-1049001 Lisbon Portugal Inst Telecomunicacoes P-1049001 Lisbon Portugal South Valley Univ Fac Comp & Informat Qena 83523 Egypt Politecn Leiria ESTG P-2411901 Leiria Portugal

In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, deep learning plays a fundamental role in extracting features from the multimedia representation data, usually producing a compressed representation referred to as latent representation. The increasing development and adoption of deep learning-based solutions in a wide area of multimedia applications have opened an exciting new vision where a common compressed multimedia representation is used for both man and machine. The main benefits of this vision are two-fold: i) improved performance for the computer vision tasks, since the effects of coding artifacts are mitigated;and ii) reduced computational complexity, since prior decoding is not required. This paper proposes the first taxonomy for designing compressed domain computer vision solutions driven by the architecture and weights compatibility with an available spatio-temporal computer vision processor. The potential of the proposed taxonomy is demonstrated for the specific case of point cloud classification by designing novel compressed domain processors using the JPEG Pleno Point Cloud Coding standard under development and adaptations of the PointGrid classifier. Experimental results show that the designed compressed domain point cloud classification solutions can significantly outperform the spatial-temporal domain classification benchmarks when applied to the decompressed data, containing coding artifacts, and even surpass their performance when applied to the original uncompressed data.

关键词： Task analysis Encoding Transform coding Image coding Standards Streaming media Point cloud compression classification algorithms Representation learning Computer vision Deep learning Taxonomy classification coding compressed representation processing computer vision deep learning man and machine consumption point cloud visualization taxonomy

来源：评论

学校读者我要写书评

暂无评论

Comparative study of multiple algorithms classification for land use and land cover change detection and its impact on local climate of Mardan District, Pakistan

引用

Environmental Challenges 2025年 18卷

作者： Farnaz Nuthammachot, Narissara Ali, Muhammad Zeeshan Faculty of Environmental Management Prince of Songkla University Songkhla Hat Yai 90110 Thailand Department of Earth & Space Sciences Southern University of Science & Technology China

Land use and land cover (LULC) changes significantly impact global climate change, resource management, and sustainability. This study aims to evaluate the performance of various machine learning classifiers, including Support Vector Machine (SVM), Random Forest Algorithm (RFA), K-Nearest Neighbor (KNN), and Maximum Likelihood (MLH), in detecting Land Use and Land Cover [LULC] changes in Mardan District, Pakistan, from 2015 to 2023. Sentinel-2 satellite imagery was utilized to generate LULC maps, which were subsequently analyzed to quantify changes across five land cover classes: water land, built-up areas, barren land, green land, and farmland. The study also investigates the impact of LULC changes on climate regulation and sustainability within the study area. The findings reveal that SVM and RFA classifiers exhibited the highest overall accuracy and kappa coefficients, outperforming KNN and MLH. Significant transitions were observed, including urban expansion, reforestation efforts, and agricultural stability. Furthermore, an analysis of climate data from 2015 to 2023 revealed a notable increase in minimum, maximum, and mean temperatures within the areas impacted by LULC changes. The study highlights the importance of selecting appropriate classifiers for accurate LULC change detection and underscores the need for informed decision-making in environmental management and urban planning to mitigate the impacts of climate change and promote sustainable development. © 2024

关键词： classification algorithms Climate impact Land use/land cover change Mardan District Sentinel-2 imagery Urban growth

来源：评论

学校读者我要写书评

暂无评论

Aircraft Wake Recognition and Strength classification Based on Deep Learning

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 2237-2249页

作者： Shen, Chun Tang, Weiwei Gao, Hang Wang, Xuesong Chan, Pak-Wai Hon, Kai-Kwong Li, Jianbing Natl Univ Def Technol State Key Lab Complex Electromagnet Environm Effe Changsha 410073 Hunan Peoples R China Hunan Normal Univ Changsha 410073 Hunan Peoples R China Hong Kong Observ 134A Nathan Rd Hong Kong 999077 Peoples R China

Aircraft wake is a pair of counter-rotating vortices generated behind the aircraft, which can greatly impact the safety of fast takeoff and landing of aircraft and limit the improvement of airport capacity. The current wake parameter retrieval methods cannot locate the wake vortex's position and estimate its strength level in real time. To deal with this issue, a novel algorithm based on the YOLOv5s deep learning network is proposed. The new algorithm establishes a single vortex locating concept to adapt the wake vortex's evolution at complicate background wind field conditions, and proposes strength-based classification standard which can represent the real-time hazard of wake vortex to shorten the takeoff and landing intervals. Meanwhile, the EIOU loss function is introduced to improve the precision of YOLOv5s network. Compared with the state-of-the-art object detection approaches, such as Cascade R-CNN, FCOS, and YOLOv5l, the superiority of new method is demonstrated in terms of accuracy and robustness by using the field detection data from Hong Kong International Airport.

关键词： Aircraft Laser radar classification algorithms Deep learning Air traffic control Doppler effect Real-time systems Air traffic management (ATM) deep learning recognition strength classification wake vortex YOLOv5s network

来源：评论

学校读者我要写书评

暂无评论

SSBTCNet: Semi-Supervised Brain Tumor classification Network

引用

IEEE ACCESS 2023年 11卷 141485-141499页

作者： Atha, Zubair Chaki, Jyotismita Vellore Inst Technol Sch Comp Sci & Engn Vellore 632014 India

classification of brain tumors from the Magnetic Resonance Imaging (MRI) is a vital and challenging task for brain tumor diagnosis. Despite favorable results, from current Deep Learning (DL) methods used for the classification of brain tumors, the approaches are also used to cope with inconsistencies where the visual representation of non-brain tumor and brain tumor regions are equivalent. In this article, a novel semi-supervised DL-based approach is proposed for the classification of three types of brain tumors as well as no tumors. The proposed semi-supervised approach, Semi-Supervised Brain Tumor classification Network (SSBTCNet), profits from the combination of an unsupervised AutoEncoder (AE) with supervised classification networks, in which an AE for learning concealed descriptors and a multi-layer perceptron-based classifier are trained concurrently. When compared to training the AE and classifier separately, the proposed semi-supervised learning fundamentally aids in tuning the learning of concealed descriptors for the objective of classification, resulting in improved brain MRI classification performance. To make SSBTCNet efficient, enhanced instances are generated by using a fuzzy-logic-based method to train and test the system. Also, a second approach, for the classification of the brain tumor as well as no tumor, with augmented unlabelled data is trained and tested which applies five types of augmentations to the images of the dataset to make the system robust from the change in different scales, flips and orientation. The output of the proposed method is tested on various datasets (with and without data augmentation as well as with and without labeled data) where the accuracy rate specifies that the proposed approach outperforms the other brain tumor classification approaches used in the literature.

关键词： Brain cancer Tumors classification algorithms Magnetic resonance imaging Deep learning Fuzzy logic Semisupervised learning Brain tumor deep learning fuzzy logic MRI semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Swin Transformer-Based classification of Gaze Target Regions

引用

IEEE ACCESS 2023年 11卷 132055-132067页

作者： Wu, Gongpu Wang, Changyuan Gao, Lina Xue, Jinna Xian Technol Univ Sch Optoelect Engn Xian 710021 Peoples R China Xian Technol Univ Sch Comp Sci Xian 710021 Peoples R China

Inferring gaze targeting or gaze following is an effective approach for comprehending human behavior and intentions. This paper employs a non-intrusive appearance-based tracking technique, utilizing a binocular stereo vision camera to capture the face image and head pose to address errors caused by problems such as the disappearance of the eye image and head deflection occlusion in image capture. Each gaze direction is determined based on a single image frame. To improve the classification and detection of the gaze target region by effectively handling head motion and view direction, this paper proposes a hybrid structure for the Swin Transformer gaze target region classification method. The facial image features are extracted using both the ResNet50 model and the Swin Transformer model, followed by fusing head pose features to categorise the gaze target area. The study also compares the classification effects of various structural models. The analysis of the results demonstrates that the hybrid Swin Transformer model outperforms in classifying and detecting the gaze target region, achieving an accuracy rate of 90%. Finally, the research examines the gaze of flight trainees during flight missions by using a heatmap, which lays the groundwork for future analyses of pilot attention and operational intentions during flights.

关键词： Head Transformers Gaze tracking Estimation Target tracking Feature extraction Visualization Computer vision classification algorithms Gaze estimation swin transformer computer vision region classification

来源：评论

学校读者我要写书评

暂无评论

PoxNet22: A Fine-Tuned Model for the classification of Monkeypox Disease Using Transfer Learning

引用

IEEE ACCESS 2023年 11卷 24053-24076页

作者： Yasmin, Farhana Hassan, Md. Mehedi Hasan, Mahade Zaman, Sadika Kaushal, Chetna El-Shafai, Walid Soliman, Naglaa F. Changzhou Univ Dept Comp Applicat Technol Changzhou 213164 Peoples R China Khulna Univ Comp Sci & Engn Discipline Khulna 9208 Bangladesh North Western Univ Dept Comp Sci & Engn Khulna 9000 Bangladesh Chitkara Univ Chitkara Univ Inst Engn & Technol Rajpura 140401 Punjab India Prince Sultan Univ Comp Sci Dept Secur Engn Lab Riyadh 11586 Saudi Arabia Menoufia Univ Fac Elect Engn Dept Elect & Elect Commun Engn Menoufia 32952 Egypt Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Technol Riyadh 11671 Saudi Arabia

Officials in the field of public health are concerned about a new monkeypox outbreak, even though the world is now experiencing an epidemic of COVID-19. Similar to variola, cowpox, and vaccinia, an orthopoxvirus with two double-stranded strands causes monkeypox. The present pandemic has been propagated sexually on a massive scale, particularly among individuals who identify as gay or bisexual. In this instance, the speed with which monkeypox was diagnosed is the most important aspect. It is possible that the technology of machine learning could be of significant assistance in accurately diagnosing the monkeypox sickness before it can spread to more people. This study aims to determine a solution to the problem by developing a model for the diagnosis of monkeypox through machine learning and image processing methods. To accomplish this, data augmentation approaches have been applied to avoid the chances of the model's overfitting. Then, the transfer-learning strategy was utilized to apply the preprocessed dataset to a total of six different Deep Learning (DL) models. The model with the best precision, recall, and accuracy performance matrices was selected after those three metrics were compared to one another. A model called "PoxNet22"has been proposed by performing fine-tuning the model that has performed the best. PoxNet22 outperforms other methods in its classification of monkeypox, which it does with 100% precision, recall, and accuracy. The outcomes of this study will prove to be extremely helpful to clinicians in the process of classifying and diagnosing monkeypox sickness.

关键词： COVID-19 Deep learning Feature extraction Data models Transfer learning Magnetic resonance imaging classification algorithms Monkeypox data augmentation transfer learning classification PoxNet22

来源：评论

学校读者我要写书评

暂无评论

Wireless Capsule Endoscopy Image classification: An Explainable AI Approach

引用

IEEE ACCESS 2023年 11卷 105262-105280页

作者： Varam, Dara Mitra, Rohan Mkadmi, Meriam Riyas, Radi Aman Abuhani, Diaa Addeen Dhou, Salam Alzaatreh, Ayman Amer Univ Sharjah Dept Comp Sci & Engn Sharjah U Arab Emirates Amer Univ Sharjah Dept Math & Stat Sharjah U Arab Emirates

Deep Learning has contributed significantly to the advances made in the fields of Medical Imaging and Computer Aided Diagnosis (CAD). Although a variety of Deep Learning (DL) models exist for the purposes of image classification in the medical domain, more analysis needs to be conducted on their decision-making processes. For this reason, several novel Explainable AI (XAI) techniques have been proposed in recent years to better understand DL models. Currently, medical professionals rely on visual inspections to diagnose potential diseases in endoscopic imaging in the preliminary stages. However, we believe that the use of automated systems can enhance both the efficiency for such diagnoses. The aim of this study is to increase the reliability of model predictions within the field of endoscopic imaging by implementing several transfer learning models on a balanced subset of Kvasir-capsule, a Wireless Capsule Endoscopy imaging dataset. This subset includes the top 9 classes of the dataset for training and testing. The results obtained were an F1-score of 97% +/- 1% for the Vision Transformer model, although other models such as MobileNetv3Large and ResNet152v2 were also able to achieve F1-scores of over 90%. These are currently the highest-reported metrics on this data, improving upon prior studies done on the same dataset. The heatmaps of several XAI techniques, including GradCAM, GradCAM++, LayersCAM, LIME, and SHAP have been presented in image form and evaluated according to their highlighted regions of importance. This is in an effort to better understand the decisions of the top-performing DL models and look beyond their black-box nature.

关键词： Solid modeling Analytical models Endoscopes classification algorithms Feature extraction Wireless communication Gastrointestinal tract Deep learning Artificial intelligence Machine learning explainable AI gastrointestinal diseases machine learning vision transformer wireless capsule endoscopy

来源：评论

学校读者我要写书评

暂无评论

Local and Global Spatial Information for Land Cover Semisupervised classification of Complex Polarimetric SAR Data

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 3892-3904页

作者： Ghanbari, Mohsen Xu, Linlin Clausi, David A. Univ Waterloo Dept Syst Design Engn Vis & Image Proc VIP Res Grp Waterloo ON N2L 3G1 Canada

Each of the three satellites constituting the RADARSAT Constellation Mission (RCM) provides compact polarimetric synthetic aperture radar (CP SAR) data. The complex CP data have similar properties to the complex quad polarimetric (QP) data provided by prior RADARSAT missions. In this article, a land cover classification method using spatial information is designed based on the statistical characteristics of the complex CP and QP SAR data. First, the local spatial dependency among pixels is captured by superpixels. Second, a graph is constructed on the superpixels to model the global spatial dependency among superpixels. The land cover classification image with land cover type labels is then estimated by propagating labels from the few labeled superpixels to the unlabeled superpixels. classification of two RCM complex CP and QP scenes demonstrates that the proposed method, with few labeled pixels, provides much higher classification accuracy than methods that do not exploit global spatial dependency.

关键词： Synthetic aperture radar Convolutional neural networks Backscatter Satellites Covariance matrices classification algorithms Radar polarimetry Compact polarimetry graph-based learning land cover classification multilook complex semisupervised superpixel

来源：评论

学校读者我要写书评

暂无评论

Boosting With Prior for Accurate classification

引用

IEEE ACCESS 2023年 11卷 128125-128134页

作者： Baig, Mubasher Ejaz, Tahir Fahad, Khawaja M. Gilani, Syed Asif Mehmood Awais, Mian M. Saeed, Sana Natl Univ Comp & Emerging Sci NUCES Dept Comp Sci Lahore 54770 Pakistan Lahore Univ Management Sci LUMS Dept Comp Sci Lahore 54792 Pakistan

Adaptive Boosting (AdaBoost) based meta learning algorithms generate an accurate classifier ensemble using a learning algorithm with only moderate accuracy guarantees. These algorithms have been designed to work in typical supervised learning settings and hence use only labeled training data along with a base learning algorithm to form an ensemble. However, significant knowledge about the solution space might be available along with training data. The accuracy and convergence rate of AdaBoost might be improved using such knowledge. An effective way to incorporate such knowledge into boosting based ensemble learning algorithms is presented in this paper. Using several synthetic and real datasets, empirical evidence is reported to show the effectiveness of proposed *** improvements have been obtained by applying the proposed method for detecting roads in aerial images.

关键词： classification algorithms Boosting Training Training data Ensemble learning Mathematical models Convergence AdaBoost ensemble learning prior/domain knowledge

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：