检索结果-内蒙古大学图书馆

An Adaptive Safe-Region Diversity Oversampling Algorithm for Imbalanced classification

IEEE ACCESS 2024年 12卷 63713-63724页

作者： Tao, Liangliang Li, Huixian Wang, Faqiang Liu, Maomao Tang, Zhao Wang, Qingya Jiujiang Vocat & Tech Coll Coll Informat Engn Jiujiang 332007 Peoples R China

The challenge of imbalanced data classification stems from the uneven distribution of data across classes, which is a formidable obstacle for traditional classifiers. Although numerous methods have been proposed to address this problem, it is widely recognized that the artificial generation of instances through oversampling methods is a more effective and versatile strategy for balancing the class distribution. We identify that existing oversampling methods are susceptible to generating unnecessary and noisy instances in complex imbalanced scenarios. In light of this, a novel approach called Adaptive Safe-Region Diversity Oversampling (ASRDO) is introduced to tackle difficulties in imbalanced learning. ASRDO starts by calculating the distance from each minority class instance to its nearest majority class instances. Utilizing this distance as a radius, it defines a safe hyperspherical sampling region for each minority instance. The algorithm then assigns weights to minority instances based on the density within their respective sampling regions and the average distance to k nearest majority instances. Finally, It randomly selects two instances from the k nearest minority instances, generates a new direction vector by linear combination, and synthesizes minority instances along this direction vector within the sampling region. Experimental results show a significant performance improvement of the proposed method compared to prevalent oversampling methods on 32 public datasets. A Python implementation of ASRDO is provided for reference.

关键词： classification algorithms Noise measurement Vectors Training Task analysis Sampling methods Sensitivity analysis Biological system modeling Nearest neighbor methods Imbalanced learning SMOTE adaptive safe-region diversity oversampling

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy classification With Deep Learning via Fundus Images: A Short Survey

引用

IEEE ACCESS 2024年 12卷 20540-20558页

作者： Zhu, Shanshan Xiong, Changchun Zhong, Qingshan Yao, Yudong Ningbo Univ Res Inst Med & Biol Engn Ningbo 315211 Peoples R China Ningbo Univ Hlth Sci Ctr Ningbo 315211 Peoples R China Fujian Normal Univ Fujian Prov Key Lab Photon Technol Key Lab Optoelect Sci & Technol Med Minist Educ Fuzhou 350117 Peoples R China Ningbo Univ Fac Elect Engn & Comp Sci Ningbo 315211 Peoples R China Ningbo Univ Sch Mat Sci & Chem Engn Ningbo 315211 Peoples R China

Diabetic retinopathy (DR) is a microvascular disease that is associated with diabetes mellitus. DR can cause irreversible vision loss and low vision. DR classification, that is, early DR diagnosis and accurate DR grading, is critical for vision protection and immediate treatment. Deep learning-based automated systems led to significant expectations for DR classification based on fundus images with several advantages. In the past several years, many outstanding studies in this area have been conducted and several review articles have been published. However, the new trends and the future directions are need to furtherly analyzed. Thus, we carefully included and read 94 related articles published from 2018 to 2023 through Web of Science, PubMed, Scopus, and IEEE Xplore. From this review, we found that transfer learning has been used as an outstanding strategy for overcoming the issue of the limited data resources to support DR analysis. CNN models of ResNet and VGGNet with layers of tens or even hundreds are the most popular frameworks used for DR classification. The APTOS 2019 and EyePACS are the most widely used datasets for DR classification. In addition, some lightweight DL architectures like SqueezeNet and MobileNet have been proposed for DR classification tasks, especially for limited data resources and computational capabilities. Although deep learning has achieved or surpassed human-level accuracy in DR classification, there is still a long way to go in real clinical workflows. Further improvements in model interpretability, trustworthiness from ophthalmologists, cost-effective and reliable DR screening systems are needed.

关键词： Diabetic retinopathy Retina Lesions Biomedical imaging Deep learning Optical imaging Blood vessels classification algorithms classification diabetic retinopathy deep learning fundus images

来源：评论

学校读者我要写书评

暂无评论

Real-Time classification of Vehicles Using Machine Learning Algorithm on the Extensive Dataset

引用

IEEE ACCESS 2024年 12卷 98338-98351页

作者： Pemila, M. Pongiannan, R. K. Narayanamoorthi, R. Sweelem, Emad A. Hendawi, Essam Abu El-Sebah, Mohamed I. SRM Inst Sci & Technol Dept Elect & Elect Engn Kattankulathur 603203 India SRM Inst Sci & Technol Sch Comp Dept Comp Technol Kattankulathur 603203 India Elect Res Inst Dept PV Cells Cairo 12622 Egypt Taif Univ Coll Engn Dept Elect Engn Taif 21944 Saudi Arabia Elect Res Inst Dept Power Elect & Energy Convers Cairo 12622 Egypt

Vehicle classification (VC) is a prominent research domain within image processing and machine learning (ML) for identifying vehicle volumes and traffic rule violations. In developed countries, nearly 40% of daily accidents are fatal, while in developing countries, the figure rises to 70%. Traditionally, vehicle detection and classification have been performed manually by experts, which is difficult, time-consuming, and prone to errors. Furthermore, incorrect detection and classification can result in hazardous situations. This highlights the need for more reliable techniques to identify and classify vehicles accurately and practically. In existing applications, numerous automated methods have been proposed. However, employing deep and machine learning algorithms on complex datasets of vehicle images has failed to achieve accuracy in various climate conditions and has been time-consuming. This paper presents an accurate, robust, real-time system to classify vehicles from onsite roads. The proposed system utilizes a random wavelet transform for pre-processing, edge and region-based segmentation for feature extraction, an embedded method for feature selection, and the XGBoost algorithm for VC. The proposed work classifies vehicles under complex weather, illumination, color, and occlusion conditions over 10 datasets, including a novel dataset named SRM2KTR, containing 75,436 vehicle images on an FPGA platform. The results show 98.81% accuracy, outperforming the state-of-the-art (98%). The system was demonstrated with four different classifiers, classifying images in 0.16 ns with an average accuracy of 97.79%. The system exhibits high accuracy, rapid identification time, and robustness in practical use.

关键词： Feature extraction Accuracy Task analysis Machine learning algorithms Reluctance motors Image edge detection classification algorithms Gradient methods Boosting Vehicle classification machine learning eXtreme gradient boost algorithm

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation of Time Series classification

引用

IEEE ACCESS 2024年 12卷 38456-38472页

作者： Wang, Xinli Sun, Rencheng Qingdao Univ Coll Comp Sci & Technol Qingdao 266071 Peoples R China

In the era of big data and the rapid development of sensor technology, the time series classification problem has become an important research direction in the field of data mining. The complexity and diversity of time series data itself may lead to the inconsistency of the distribution between the training set and the test set, and this distribution difference may cause significant fluctuations in the model performance in practical applications. In contrast, domain adaptation models aim to adapt to test data with different distributions from the training data to improve the model performance. To address this challenge, we propose the Au-RAINCOAT model based on the RAINCOAT model, which is a closed-set domain adaptation model for complex time series. The model first considers the introduction of an Auto-Correlation mechanism module, which aims to compensate for the shortcomings of the Fourier transform by capturing local information while improving the computational efficiency. Second, to avoid the stability problems associated with the choice of regularization parameters in Sinkhorn divergence, we choose to use the Proxy-A-Distance(PAD).In this paper, we use four common datasets such as WISDM, HAR, HHAR, Sleep-EDF, and experiments are conducted on seven models. The experimental results show that the method has better results on the four datasets.

关键词： Feature extraction Time series analysis Time-frequency analysis Adaptation models Convolutional neural networks Fourier transforms Autocorrelation classification algorithms Big Data Sensors Performance evaluation Auto-correlation mechanism domain adaptation time series classification Proxy-A-Distance

来源：评论

学校读者我要写书评

暂无评论

Fast, Interpretable, and Deterministic Time Series classification With a Bag-of-Receptive-Fields

引用

IEEE ACCESS 2024年 12卷 137893-137912页

作者： Spinnato, Francesco Guidotti, Riccardo Monreale, Anna Nanni, Mirco Univ Pisa Dept Comp Sci I-56127 Pisa Italy ISTI CNR I-56124 Pisa Italy

The current trend in the literature on Time Series classification is to develop increasingly accurate algorithms by combining multiple models in ensemble hybrids, representing time series in complex and expressive feature spaces, and extracting features from different representations of the same time series. As a consequence of this focus on predictive performance, the best time series classifiers are black-box models, which are not understandable from a human standpoint. Even the approaches that are regarded as interpretable, such as shapelet-based ones, rely on randomization to maintain computational efficiency. This poses challenges for interpretability, as the explanation can change from run to run. Given these limitations, we propose the Bag-Of-Receptive-Field (BORF), a fast, interpretable, and deterministic time series transform. Building upon the classical Bag-Of-Patterns, we bridge the gap between convolutional operators and discretization, enhancing the Symbolic Aggregate Approximation (SAX) with dilation and stride, which can more effectively capture temporal patterns at multiple scales. We propose an algorithmic speedup that reduces the time complexity associated with SAX-based classifiers, allowing the extension of the Bag-Of-Patterns to the more flexible Bag-Of-Receptive-Fields, represented as a sparse multivariate tensor. The empirical results from testing our proposal on more than 150 univariate and multivariate classification datasets demonstrate good accuracy and great computational efficiency compared to traditional SAX-based methods and state-of-the-art time series classifiers, while providing easy-to-understand explanations.

关键词： Time series analysis Transforms Indexes Training Time complexity Standards classification algorithms Time series classification explainable AI symbolic aggregate approximation

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Framework for the classification of Hyperspectral Images in the Wood Domain

引用

IEEE ACCESS 2024年 12卷 38908-38916页

作者： Confalonieri, Roberto Htun, Phyu Phyu Sun, Boyuan Tillo, Tammam Univ Padua Dept Math I-35131 Padua Italy Univ Comp Studies Yangon Yangon 11052 Myanmar Nantong Acad Intelligent Sensing Nantong 226019 Peoples R China Indraprastha Inst Informat Technol New Delhi 110020 Delhi India

Hyperspectral images consist of a multitude of spectral bands for each pixel. Spectral bands provide information about wavelengths that may cover a larger spectrum of what the human eye may see. In the hyperspectral domain, the classification of hyperspectral images is usually addressed by taking into account only the spectral information. However, in the wood domain, spatial information is also relevant. To bridge this gap, this paper proposes a CNN-based end-to-end framework for the classification of hyperspectral images in the wood domain. The proposed framework consists of a spatial and spectral classifier that are integrated to make the final prediction. Each classifier is built by adapting a general image classifier, which is suitable for the classification of three-band images, to handle hyperspectral images. The framework is trained and validated on a real dataset, provided by a company working in the wood domain to detect wood fungi. The results obtained have shown that the proposed framework is a lightweight and effective approach for the recognition of wood fungi categories. The framework outperforms a benchmark classifier by 17% and can generate a classification map of hyperspectral images of wood boards of any size with an accuracy of 96%.

关键词： Hyperspectral imaging Feature extraction Fungi Training Task analysis Convolutional neural networks Spectroscopy classification algorithms Wood industry Application of hyperspectral images detection of wood fungi

来源：评论

学校读者我要写书评

暂无评论

Gastrointestinal Cancer Detection and classification Using African Vulture Optimization Algorithm With Transfer Learning

引用

IEEE ACCESS 2024年 12卷 23122-23131页

作者： Almasoud, Ahmed S. Maray, Mohammed Alkahtani, Hend Khalid Alotaibi, Faiz Abdullah Alnfiai, Mrim M. Sayed, Ahmed Prince Sultan Univ Coll Comp & Informat Sci Dept Informat Syst Riyadh 12435 Saudi Arabia King Khalid Univ Coll Comp Sci Dept Informat Syst Abha 62529 Saudi Arabia Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst POB 84428 Riyadh 11671 Saudi Arabia King Saud Univ Coll Humanities & Social Sci Dept Informat Sci Riyadh 11437 Saudi Arabia Taif Univ Coll Comp & Informat Technol Dept Informat Technol Taif 21944 Saudi Arabia Future Univ Egypt Res Ctr New Cairo 11835 Egypt

Gastrointestinal (GI) cancer comprises esophageal, gastric, colon and rectal tumors. The diagnosis of GI cancer often relies on medical imaging modalities namely magnetic resonance imaging (MRI), histopathological slides, endoscopy, and computed tomography (CT) scans. This provides particular details about the size, location, and characteristics of tumors. The high death rate for GI cancer patients shows that it is possible to increase analysis for a more personalized therapy strategy which leads to improved prognosis and few side effects although many extrapolative and predictive biomarkers exist. Gastrointestinal cancer classification is a challenging but vital area of research and application within medical imaging and machine learning. Artificial intelligence (AI) based diagnostic support system, especially convolution neural network (CNN) based image examination tool, has enormous potential in medical computer vision. The study presents a GI Cancer Detection and classification utilizing the African Vulture Optimization Algorithm with Transfer Learning (GICDC-AVOADL) methodology. The major aim of the GICDC-AVOADL model is to examine GI images for the identification of cancer. To achieve this, the GICDC-AVOADL method makes use of an improved EfficientNet-B5 method to learn features from input images. Furthermore, AVOA is exploited for optimum hyperparameter selection of the improved EfficientNet-B5 method. The GICDC-AVOADL technique applies dilated convolutional autoencoder (DCAE) For GI cancer detection and classification. A complete set of simulations was conducted to examine the enhanced GI cancer detection performance of the GICDC-AVOADL technique. The extensive results inferred superior performance of the GICDC-AVOADL algorithm over current models.

关键词： Cancer classification algorithms Feature extraction Cancer detection Tumors Task analysis Tuning Computer aided diagnosis Artificial intelligence Parameter estimation Computer-aided diagnosis cancers GI cancer artificial intelligence parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Deep Fuzzy Envelope Sample Generation Mechanism for Imbalanced Ensemble classification

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2024年第3期32卷 1248-1262页

作者： Li, Fan Li, Yongming Shen, Yinghua Pedrycz, Witold Zhang, Xiaoheng Wang, Pin Li, Pufei Zhou, Chuanyan Cheng, Huan Chongqing Univ Sch Microelectorn & Commun Engn Chongqing 400044 Peoples R China Chongqing Univ Sch Econ & Business Adm Chongqing 400044 Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton T6G 2R3 AB Canada Polish Acad Sci Syst Res Inst PL-00901 Warsaw Poland Istinye Univ Fac Engn & Nat Sci Dept Comp Engn TR-34010 Sariyer Turkiye

Ensemble methods are widely used to tackle class imbalance problem. However, for existing imbalanced ensemble (IE) methods, the samples in each subset are resampled from the same dataset, and are directly input to the classifier for training, so the quality (diversity and separability) of the subsets is unsatisfactory usually. To solve the problem, a deep fuzzy envelope sample generation mechanism is proposed. First, the fuzzy C-means clustering based deep sample envelope prenetwork (DSEN) is designed to mine correlation information among samples, thereby increasing the quality of the subsets. Second, the local manifold structure metric and global structure distribution metric are designed to construct local-global structure consistency mechanism (LGSCM) to enhance distribution consistency of interlayer samples of DSEN. Third, the DSEN and LGSCM are combined to form the final deep sample envelope network-DSENLG to refresh the existing subsets. Finally, base classifiers are applied on the new subsets generated by the DSENLG and then fused, thereby realizing a new IE algorithm. The experimental results show that the proposed algorithm is significantly better than existing representative IE algorithms and it achieves the highest improvement of 10.64%, 19.5%, 18.67% and 22.33% on four criteria over the state-of-the-art methods. The originality of the article is threefold: proposing the concept of "deep fuzzy samples" or "envelope samples", which comprehensively considers the correlation information among original samples;proposing the LGSCM to resolve the distribution inconsistency of interlayer samples;and forming an fuzzy envelope sample based IE algorithm.

关键词： Ensemble learning Correlation classification algorithms Training Manifolds Measurement Clustering algorithms Class imbalance problem domain adaption ensemble approach envelope learning fuzzy C-means (FCMs) clustering

来源：评论

学校读者我要写书评

暂无评论

Relative Entropy and PageRank-Based Classifier Chains for Multi-Label classification

引用

IEEE ACCESS 2024年 12卷 87665-87674页

作者： Li, Xinyu Ding, Jiaman Hu, Shuang Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Peoples R China Kunming Univ Sci & Technol Kunming 650500 Peoples R China

The Classifier Chains (CC) method is an effective method for multi-label classification, with its performance significantly contingent on the label order. However, most existing algorithms focus on determining the label order by considering label correlations as symmetric, ignoring that label correlations prevail asymmetric in real-world applications. To overcome the problem, we propose a novel Relative Entropy and PageRank-based Classifier Chains for multi-label classification (REPCC). Firstly, to completely capture label correlation, REPCC exploits relative entropy to estimate the asymmetric correlation between pairs of labels, filter out those pairs of labels with lower correlation, and construct a label correlation matrix. Secondly, by treating each label as a node, a directed graph is generated based on the filtered label correlation matrix. Finally, drawing an analogy between labels and web pages, the idea of PageRank, commonly used to measure the importance of web pages, is employed to rank labels in the directed graph and establish a classifier chain. Experimental results on ten public datasets from various domains show that REPCC outperforms state-of-the-art methods in CC.

关键词： Correlation Entropy classification algorithms Task analysis Optimization Directed graphs Welding Asymmetric label correlation classifier chains multi-label classification PageRank relative entropy

来源：评论

学校读者我要写书评

暂无评论

classification of Bone Marrow Cells Based on Dual-Channel Convolutional Block Attention Network

引用

IEEE ACCESS 2024年 12卷 96205-96219页

作者： Wang, Zhaorong Zheng, Rui Zhu, Xiayin Luo, Wenda He, Sailing Zhejiang Univ Coll Opt Sci & Engn Ctr Opt & Electromagnet Res Hangzhou 310058 Peoples R China Zhejiang Univ Taizhou Hosp Taizhou Inst Med Hlth & New Drug Clin Res Linhai 317000 Peoples R China Wenzhou Med Univ Taizhou Hosp Zhejiang Prov Dept Clin Lab Linhai 317000 Peoples R China Wenzhou Med Univ Taizhou Hosp Zhejiang Prov Dept Hematol Linhai 317000 Peoples R China Zhejiang Univ Taizhou Hosp Dept Hematol Linhai 317000 Peoples R China Zhejiang Univ Natl Engn Res Ctr Opt Instruments Hangzhou 310058 Peoples R China KTH Royal Inst Technol Sch Elect Engn Dept Electromagnet Engn S-10044 Stockholm Sweden

Morphological differentiation between myeloblasts and monoblasts is pivotal for the majority of acute myeloid leukemia (AML) diagnosis in clinical settings. Manual morphology-based classification of blasts encounters challenges due to the limited differentiation of these bone marrow cells (BMC) of early stages. Hence, the utilization of artificial intelligence is essential to assist in the classification of these cells. 4001 single-cell images of monoblasts and myeloblasts were collected from Taizhou Hospital to form the BMC-1 dataset. The main novelties and features of the proposed method are as follows: 1) A maximum connected domain extraction method grounded in the watershed algorithm is introduced to efficiently eliminate stained impurity cells from single cell images. 2) A dynamic focal loss is introduced to gradually focus on difficult-to-classify samples as the training progresses. 3) A dual-channel convolutional block attention network (DCCBANet) is introduced to enhance feature extraction. It employs attention mechanisms to focus on key features, utilizing ordinary convolution for local feature extraction, dilated convolution for global feature extraction, and a decreasing dilation rate sequence to preserve detailed information. A macro F1-score (macro_F) of 96.8% is achieved on the BMC-1 validation dataset. Additionally, the presence of multiple differentiation types of granulocytes pose difficulties in granulocytes distinction. To further validate the efficacy of our proposed method on multi-classification tasks, we collected 6626 granulocyte single-cell images from Taizhou Hospital. Augmenting the dataset with 2441 granulocyte single-cell images from the public dataset BM_cytomorphology addressed sample shortages, forming the BMC-2 dataset. We applied our model to the BMC-2 dataset for experiments and ultimately achieved a macro_F of 87.49%. Our proposed method effectively distinguishes monoblasts and myeloblasts and excels in the classification of granu

关键词： Cells (biology) Bones Task analysis classification algorithms Watersheds Image segmentation Feature extraction Cancer Blood vessels Convolutional neural networks Acute myeloid leukemia bone marrow cell classification convolutional neural network loss function attention mechanism

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：