检索结果-内蒙古大学图书馆

Leveraging Association Rules in Feature Selection for deep learning classification

SN Computer Science 2024年第1期5卷 112页

作者： Kharsa, Ruba Al Aghbari, Zaher Department of Computer Science University of Sharjah Sharjah United Arab Emirates

The number of extracted features from medical data, such as computer-aided diagnosis, has been known to be too large and affects the performance of the used classifiers. Moreover, the large number of input features affects the accuracy of the classifiers, such as the traditional machine learning classifier. Therefore, in this paper, we proposed the use of association rules to select features from medical data, which results in a dimensionality reduction of the input feature space. The selected features become the input to a deep neural network, particularly ResNet, which is known for its high accuracy of classification results. The conducted experiments prove that the use of association rules to select the most representative features and the use of deep neural networks as a classifier outperformed other traditional machine learning models in terms of the accuracy of classification. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Association rules mining classification deep learning classification Feature selection Neural networks Resnet

来源：评论

学校读者我要写书评

暂无评论

Association Rules Based Feature Extraction for deep learning classification 4th

Association Rules Based Feature Extraction for Deep Learning...

引用

4th International Conference on Soft Computing and its Engineering Applications (icSoftComp)

作者： Kharsa, Ruba Al Aghbari, Zaher Univ Sharjah Dept Comp Sci Sharjah U Arab Emirates

ISBN: (纸本)9783031276088;9783031276095

The number of extracted features from medical data, such as computer-aided diagnosis, has been known to be too large and affects the performance of the used classifiers. Moreover, the large number of input features affect the accuracy of the classifiers, such as the traditional machine learning classifier. Therefore, in this paper, we proposed the use of association rules to select features from medical data, which result in dimensionality reduction of the input feature space. The selected features become the input to a deep neural network, particularly ResNet, which is known for its high accuracy of classification results. The conducted experiments prove that the use of association rules to select the most representative features and the use of deep neural networks as a classifier outperformed other traditional machine learning models in terms of accuracy of classification.

关键词： Association rules mining Feature selection deep learning classification Resnet Neural networks classification

来源：评论

学校读者我要写书评

暂无评论

Improving the Generalization of deep learning classification Models in Medical Imaging Using Transfer learning and Generative Adversarial Networks 13th

Improving the Generalization of Deep Learning Classification...

引用

13th International Conference on Agents and Artificial Intelligence (ICAART)

作者： Venu, Sagar Kora Harrisburg Univ Sci & Technol Harrisburg PA 17101 USA

ISBN: (纸本)9783031101618;9783031101601

Data sets for medical images are generally imbalanced and limited in sample size because of high data collection costs, time-consuming annotations, and patient privacy concerns. The training of deep neural network classification models on these data sets to improve the generalization ability does not produce the desired results for classifying the medical condition accurately and often overfit the data on the majority of class samples. To address the issue, we propose a framework for improving the classification performance metrics of deep neural network classification models using transfer learning: pre-trained models, such as Xception, InceptionResNet, DenseNet along with the Generative Adversarial Network (GAN) - based data augmentation. Then, we trained the network by combining traditional data augmentation techniques, such as randomly flipping the image left to right and GAN-based data augmentation, and then fine-tuned the hyper-parameters of the transfer learning models, such as the learning rate, batch size, and the number of epochs. With these configurations, the Xception model outperformed all other pre-trained models achieving a test accuracy of 98.7%, the precision of 99%, recall of 99.3%, f1-score of 99.1%, receiver operating characteristic (ROC) - area under the curve (AUC) of 98.2%.

关键词： Generative adversarial networks Transfer learning Medical imaging deep learning classification Chest X-ray's

来源：评论

学校读者我要写书评

暂无评论

CT evaluation of extranodal extension of cervical lymph node metastases in patients with oral squamous cell carcinoma using deep learning classification

引用

ORAL RADIOLOGY 2020年第2期36卷 148-155页

作者： Ariji, Yoshiko Sugita, Yoshihiko Nagao, Toru Nakayama, Atsushi Fukuda, Motoki Kise, Yoshitaka Nozawa, Michihito Nishiyama, Masako Katumata, Akitoshi Ariji, Eiichiro Aichi Gakuin Univ Sch Dent Dept Oral & Maxillofacial Radiol Chikusa Ku 2-11 Suemori Dori Nagoya Aichi 4648651 Japan Aichi Gakuin Univ Dept Oral Pathol Sch Dent Nagoya Aichi Japan Aichi Gakuin Univ Dept Maxillofacial Surg Sch Dent Nagoya Aichi Japan Aichi Gakuin Univ Dept Oral & Maxillofacial Surg Sch Dent Nagoya Aichi Japan Asahi Univ Dept Oral Radiol Sch Dent Mizuho Japan

Objective To clarify CT diagnostic performance in extranodal extension of cervical lymph node metastases using deep learning classification. Methods Seven-hundred and three CT images (178 with and 525 without extranodal extension) in 51 patients with cervical lymph node metastases from oral squamous cell carcinoma were enrolled in this study. CT images were cropped to an arbitrary size to include lymph nodes and surrounding tissues. All images were automatically divided into two datasets, assigning 80% as the training dataset and 20% as the testing dataset. The automated selection was repeated five times. Each training dataset was imported to a deep learning training system "DIGITS". Five learning models were created after 300 epochs of the learning process using a neural network "AlexNet". Each testing dataset was applied to each created learning model and resulting five performances were averaged as estimated diagnostic performances. A radiologist measured the minor axis and three radiologists evaluated central necrosis and irregular borders of each lymph node, and the diagnostic performances were obtained. Results The deep learning accuracy of extranodal extension was 84.0%. The radiologists' accuracies based on minor axis >= 11 mm, central necrosis, and irregular borders were 55.7%, 51.1% and 62.6%, respectively. Conclusions The deep learning diagnostic performance in extranodal extension was significantly higher than that of radiologists. This method is expected to improve diagnostic accuracy by further study with increasing the number of patients.

关键词： deep learning classification Extranodal extension Cervical lymph node metastasis Oral squamous cell carcinoma Computed tomography

来源：评论

学校读者我要写书评

暂无评论

deep learning neural classification for structure-property modelling with engineering alloys

Deep learning neural classification for structure-property m...

引用

International Academic Conference on Advances in Materials, Mechanics, Mechatronics and Manufacturing (IC4M)

作者： Raja, P. M. Siva Sumithra, R. P. Vidhya, S. Ramanan, K. Amrita Coll Engn & Technol Dept Comp Sci & Engn Nagercoil 629901 Tamil Nadu India NPR Coll Engn & Technol Dept Comp Sci & Engn Dindigul 624401 Tamil Nadu India

Integrated Computational Materials Engineering (ICME) is the method used for performing material discovery and design. Computational techniques presented a new deep learning classification method to screen the candidate material designs. The materials are adapted. In ICME process-structure-property workflows, ambiguity was ubiquitous. A Piecewise Regressive Tversky Similarity based deep learning Neural classification (PRTS-DLNC) Method is introduced for minimizing as well as transmit uncertainties for robust uncertainties. PRTS-DLNC Method has number of compound data are considered as input. An input compound information were given to hidden layer 1. In that layer, piecewise regression is employed for performing the compound data analysis with structure-property linkages. After that, the regression coefficient value is sent to the hidden layer 2. In that layer, tversky similarity function is used to identify the similarity between the regression coefficient value of training compound data and threshold value. Ttversky similarity value varies from 0 to 1 and the results are transmitted to the output layer. By this way, PRTS-DLNC Method improves the performance of structure-property linkages. The computational cost of proposed PRTS-DLNC Method is higher than conventional uncertainty quantification. Copyright (C) 2022 Elsevier Ltd. All rights reserved.

关键词： Integrated Computational Materials Engineering Tversky similarity function deep learning classification Structure-property linkages[maximum of 6]

来源：评论

学校读者我要写书评

暂无评论

Coupling speckle noise suppression with image classification for deep-learning-aided ultrasound diagnosis

引用

PHYSICS IN MEDICINE AND BIOLOGY 2024年第6期69卷 065001-065001页

作者： Wang, Ruixin Liu, Xiaohui Tan, Guoping Hohai Univ Coll Comp Sci & Software Engn Nanjing 210098 Peoples R China Jiangsu Univ Peoples Hosp Kunshan 1 Affiliated Kunshan Hosp Kunshan 215300 Peoples R China

Objective. During deep-learning-aided (DL-aided) ultrasound (US) diagnosis, US image classification is a foundational task. Due to the existence of serious speckle noise in US images, the performance of DL models may be degraded. Pre-denoising US images before their use in DL models is usually a logical choice. However, our investigation suggests that pre-speckle-denoising is not consistently advantageous. Furthermore, due to the decoupling of speckle denoising from the subsequent DL classification, investing intensive time in parameter tuning is inevitable to attain the optimal denoising parameters for various datasets and DL models. Pre-denoising will also add extra complexity to the classification task and make it no longer end-to-end. Approach. In this work, we propose a multi-scale high-frequency-based feature augmentation (MSHFFA) module that couples feature augmentation and speckle noise suppression with specific DL models, preserving an end-to-end fashion. In MSHFFA, the input US image is first decomposed to multi-scale low-frequency and high-frequency components (LFC and HFC) with discrete wavelet transform. Then, multi-scale augmentation maps are obtained by computing the correlation between LFC and HFC. Last, the original DL model features are augmented with multi-scale augmentation maps. Main results. On two public US datasets, all six renowned DL models exhibited enhanced F1-scores compared with their original versions (by 1.31%-8.17% on the POCUS dataset and 0.46%-3.89% on the BLU dataset) after using the MSHFFA module, with only approximately 1% increase in model parameter count. Significance. The proposed MSHFFA has broad applicability and commendable efficiency and thus can be used to enhance the performance of DL-aided US diagnosis. The codes are available at https://***/ResonWang/MSHFFA.

关键词： feature augmentation discrete wavelet transform speckle noise suppression deep learning classification computer-aided diagnosis ultrasound imaging

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study for Chest Radiograph Image Retrieval using Binary, Texture and deep learning classification

A Comparative Study for Chest Radiograph Image Retrieval usi...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Yaron Anavi Ilya Kogan Elad Gelbart Ofer Geva Hayit Greenspan the Medical Image Processing Lab Department of Biomedical Engineering Faculty of Engineering Tel Aviv University Israel.

ISBN: (纸本)9781424492695

In this work various approaches are investigated for X-ray image retrieval and specifically chest pathology retrieval. Given a query image taken from a data set of 443 images, the objective is to rank images according to similarity. Different features, including binary features, texture features, and deep learning (CNN) features are examined. In addition, two approaches are investigated for the retrieval task. One approach is based on the distance of image descriptors using the above features (hereon termed the "descriptor"-based approach);the second approach ("classification"-based approach) is based on a probability descriptor, generated by a pair-wise classification of each two classes (pathologies) and their decision values using an SVM classifier. Best results are achieved using deep learning features in a classification scheme.

关键词： Comparative Study Texture deep learning classification

来源：评论

学校读者我要写书评

暂无评论

deep learning BASED PATCH-WISE LAND COVER LAND USE classification: A NEW SMALL BENCHMARK SENTINEL-2 IMAGE DATASET

DEEP LEARNING BASED PATCH-WISE LAND COVER LAND USE CLASSIFIC...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Alp, Gulsah Sertel, Elif Istanbul Tech Univ Inst Informat Satellite Commun & Remote Sensing Program Istanbul Turkey Istanbul Tech Univ Dept Geomat Engn Istanbul Turkey

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

In this paper, patch-wise land cover and land use (LCLU) classification was performed using the state-of-art ResNet 50 and Inception-ResNet-V2 architecture trained with Stochastic Gradient Descent(SGD) and Nadam optimizers. A new dataset was generated for the classification task using Sentinel-2 images having different patch sizes. The image patches were labeled using CORINE Land Cover (CLC) 2018 map. The dataset has 1961 image patches and it was divided into 1397 training and 564 testing patches during the experiment. Our dataset contains samples labeled with 7 CLC Level-2 classes. While the best training accuracy of 98.0% was obtained by Inception-ResNet-V2 trained with Nadam. The best testing accuracy of 93.0% was achieved with Inception-ResNet-V2 by using SGD optimizer.

关键词： Land Cover Land Use CORINE (CLC) deep learning classification Satellite Image Dataset Sentinel-2 Remote Sensing

来源：评论

学校读者我要写书评

暂无评论

Collaborative multi-modal deep learning and radiomic features for classification of strokes within 6 h

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期228卷

作者： Yoon, Chiho Misra, Sampa Kim, Kwang-Ju Kim, Chulhong Kim, Bum Joon Pohang Univ Sci & Technol Dept Elect Engn Pohang 37673 South Korea Elect & Telecommun Res Inst Daegu South Korea Pohang Univ Sci & Technol Convergence IT Engn Mechanical Engn Dept Elect EngnMed Device Innovat Ctr Pohang 37673 South Korea Pohang Univ Sci & Technol Grad Sch Artificial Intelligence Pohang 37673 South Korea Asan Med Ctr Dept Neurol Seoul South Korea

Clinicians use imaging-based acute stroke onset time (SOT) to make crucial decisions regarding stroke treatments, such as thrombolysis or thrombectomy. Patients may receive intravenous thrombolysis and undergo endovascular thrombectomy (EVT) within 3 or 4.5 h and 6 h from SOT, respectively. Most of the classification algorithms developed so far classify SOT within 4.5 h for thrombolysis. In this study, we demonstrated a deep learning (DL) method to classify SOT within 6 h to identify patients requiring EVT. We developed a DL-based segmentation model using a multi-modal UNet (MM-UNet) to predict the region of interest (ROI) from magnetic resonance (MR) images. Radiomic features were extracted from the MR images and ROI. Additionally, we proposed a DL model to extract hidden representations (deep features) using the MM-UNet and ResNet-18 models. We found that the classification performance improved by combining radiomic and deep features. The cross-validation results indicate that our proposed method sufficiently classified SOT within 6 h, achieving an F0.5 score of 80.6%. The DL model using multi-modal MR images can potentially become a practical decision-support tool for stroke treatments.

关键词： deep learning classification Endovascular thrombectomy Magnetic resonance imaging Stroke Stroke onset time

来源：评论

学校读者我要写书评

暂无评论

An efficient automated multi-modal cyberbullying detection using decision fusion classifier on social media platforms

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第7期83卷 20507-20535页

作者： Singh, Neha Minder Sharma, Sanjay Kumar Oriental Univ Comp Sci & Engn Indore 453555 Maharashtra India

Cyberbullying poses a dangerous threat to teens, children, young people, and adults in today's digital world. Bullies use virtual social media platforms like Twitter, Facebook, YouTube, and Instagram to harm their victims. Therefore, this online bullying (cyberbullying) is now rising as an important societal issue that affects the person emotionally and psychologically. Among the number of studies conducted to deal with cyberbullying detection, most of them are limited to only text-based content. Since the network is continuously growing, the presence of visual and audio based provoking is also needed to be considered. Therefore, the proposed study aims to develop an automatic multi-modal cyberbullying detection on social media platforms through Multi-modal Decision Fusion Classifier. The proposed multi-modal cyberbullying detection steps are data collection, multi-modality generation, score-based fusion and classification. Multiple major modalities, such as audio, visual and textual, are initially gathered from appropriate datasets. The data collected is provided as input to a multi-modal generation, where the modality is generated separately for each input. The text modality is initially generated using the hybrid Bi-directional Long Short-Term Memory assisted Attention Hierarchical Capsule Network (BiLSTM-AHCNet) model. Next, the imaging modality is generated with the Tuned Aquila EfficientB0 (Tuned AEB0) model. Finally, the audio features are extracted through the Librosa library, and the extracted features are fed to the Attention Convolutional Neural Network (ACNN) model for acoustic modality generation. In the proposed work, the Multi-Modality Decision Fusion Classifier (MMDFC) is employed to fuse all modalities, and the classification is performed by adopting the softmax layer. In addition, a weighting scheme based on horse herd optimization is applied in the fusion phase to allow accurate characterization of the features. For the simulation analysis, the pr

关键词： Multi-modal generation Multi-modal decision fusion classifier Score based fusion Term frequency-average inverse document frequency deep learning classification

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：