检索结果-内蒙古大学图书馆

Ozone Depletion Identification in Stratosphere Through faster region-based convolutional neural network

Computers, Materials & Continua 2021年第8期68卷 2159-2178页

作者： Bakhtawar Aslam Ziyad Awadh Alrowaili Bushra Khaliq Jaweria Manzoor Saira Raqeeb Fahad Ahmad Department of Computer Sciences Kinnaird College for WomenLahore54000Pakistan Physics Department College of ScienceJouf UniversitySakakaAljouf72341Saudi Arabia Department of Basic Sciences Deanship of Common First YearJouf UniversitySakakaAljouf72341Saudi Arabia

The concept of classification through deep learning is to build a model that skillfully separates closely-related images dataset into different classes because of diminutive but continuous variations that took place in physical systems over time and effect *** study has made ozone depletion identification through classification using faster region-based convolutional neural network(F-RCNN).The main advantage of F-RCNN is to accumulate the bounding boxes on images to differentiate the depleted and non-depleted ***,image classification’s primary goal is to accurately predict each minutely varied case’s targeted classes in the dataset based on ozone *** permanent changes in climate are of serious *** leading causes beyond these destructive variations are ozone layer depletion,greenhouse gas release,deforestation,pollution,water resources contamination,and UV *** research focuses on the prediction by identifying the ozone layer depletion because it causes many health issues,e.g.,skin cancer,damage to marine life,crops damage,and impacts on living being’s immune *** have tried to classify the ozone images dataset into two major classes,depleted and non-depleted regions,to extract the required persuading features through ***,CNN has been used for feature extraction in the existing literature,and those extricated diverse RoIs are passed on to the CNN for grouping *** is difficult to manage and differentiate those RoIs after grouping that negatively affects the gathered *** classification outcomes through F-RCNN approach are proficient and demonstrate that general accuracy lies between 91%to 93%in identifying climate variation through ozone concentration classification,whether the region in the image under consideration is depleted or *** proposed model presented 93%accuracy,and it outperforms the prevailing techniques.

关键词： Deep learning image processing classification climate variation ozone layer depleted region non-depleted region UV radiation faster region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

An Optimal faster region-based convolutional neural network for Oil Adulteration Detection

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2023年第2期48卷 2231-2245页

作者： Surya, V Senthilselvi, A. SRM Inst Sci & Technol Dept Comp Sci Engn Chennai Tamil Nadu India

Natural oils such as avocado oil (AO), corn oil (CO), chamomile oil (CMO), and rapeseed oil (RSO) are used for improving health, skin, and hair care for centuries in different parts of the world. The AO, CO, and RSO oil are known for their antibacterial and moisturizing properties. The growth of the modern health and wellness industries has deceived people to find affordable, additive-free, and effective products. Consumers are always willing to pay a higher price for the unadulterated oils due to the major benefits it offers in terms of complexion and health. However, the AO, CMO, and RSO oils are rarely available in the market and the ones available are subject to adulteration risks which affect the consumer's health and also violate their rights. This paper presents a war strategy optimized faster region-based convolutional neural network (RCNN) architecture named Modified faster RCNN for oil adulteration detection. The pure natural AO, CO, CMO, and RSO oils are adultered with different oils such as vegetable oils with different ratios and these oils themselves. Spectra analysis was conducted to identify the adultered vegetable oil samples and the Modified faster RCNN was employed to classify the pure oil from these unadultered samples. The results show that the proposed model is effective in rapidly identifying the adulterated components presented in high-quality oils.

关键词： Chemometric methods Oil adulteration faster region-based convolutional neural network War strategy optimization algorithm Excitation-emission matrix fluorescence

来源：评论

学校读者我要写书评

暂无评论

Computer-aided detection of mass in digital breast tomosynthesis using a faster region-based convolutional neural network

引用

METHODS 2019年 166卷 103-111页

作者： Fan, Ming Li, Yuanzhe Zheng, Shuo Peng, Weijun Tang, Wei Li, Lihua Hangzhou Dianzi Univ Inst Biomed Engn & Instrumentat High Educ Zone Hangzhou 310018 Peoples R China Fudan Univ Shanghai Canc Ctr Dept Radiol Shanghai Peoples R China

Digital breast tomosynthesis (DBT) is a newly developed three-dimensional tomographic imaging modality in the field of breast cancer screening designed to alleviate the limitations of conventional digital mammography-based breast screening methods. A computer-aided detection (CAD) system was designed for masses in DBT using a faster region-based convolutional neural network (faster-RCNN). To this end, a data set was collected, including 89 patients with 105 masses. An efficient detection architecture of convolution neural network with a region proposal network (RPN) was used for each slice to generate region proposals (i.e., bounding boxes) with a mass likelihood score. In each DBT volume, a slice fusion procedure was used to merge the detection results on consecutive 2D slices into one 3D DBT volume. The performance of the CAD system was evaluated using free response receiver operating characteristic (FROC) curves. Our RCNN-based CAD system was compared with a deep convolutional neural network (DCNN)-based CAD system. The RCNN-based CAD generated a performance with an area under the ROC (AUC) of 0.96, whereas the DCNN-based CAD achieved a performance with AUC of 0.92. For lesion-based mass detection, the sensitivity of RCNN-based CAD was 90% at 1.54 false positive (FP) per volume, whereas the sensitivity of DCNN-based CAD was 90% at 2.81 FPs/volume. For breast-based mass detection, RCNN-based CAD generated a sensitivity of 90% at 0.76 FP/breast, which is significantly increased compared with the DCNN-based CAD with a sensitivity of 90% at 2.25 FPs/breast. The results suggest that the faster R-CNN has the potential to augment the prescreening and FP reduction in the CAD system for masses.

关键词： Digital breast tomosynthesis Computer-aided detection Mass faster region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of primary clear cell carcinoma of the liver based on faster region-based convolutional neural network

引用

Chinese Medical Journal 2023年第22期136卷 2706-2711页

作者： Bin Liu Jianfei Li Xue Yang Feng Chen Yanyan Zhang Hongjun Li Department of Radiology Beijing YouAn Hospital Capital Medical UniversityBeijing 100069China Department of Radiology Civil Aviation General HospitalBeijing 100123China Extenics Specialized Committee Chinese Association of Artificial IntelligenceBeijing 100876China

Background:Distinguishing between primary clear cell carcinoma of the liver(PCCCL)and common hepatocellular carcinoma(CHCC)through traditional inspection methods before the operation is *** study aimed to establish a faster region-based convolutional neural network(RCNN)model for the accurate differential diagnosis of PCCCL and ***:In this study,we collected the data of 62 patients with PCCCL and 1079 patients with CHCC in Beijing YouAn Hospital from June 2012 to May 2020.A total of 109 patients with CHCC and 42 patients with PCCCL were randomly divided into the training validation set and the test set in a ratio of 4:*** faster RCNN was used for deep learning of patients’data in the training validation set,and established a convolutional neural network model to distinguish PCCCL and *** accuracy,average precision,and the recall of the model for diagnosing PCCCL and CHCC were used to evaluate the detection performance of the faster RCNN ***:A total of 4392 images of 121 patients(1032 images of 33 patients with PCCCL and 3360 images of 88 patients with CHCC)were uesd in test set for deep learning and establishing the model,and 1072 images of 30 patients(320 images of nine patients with PCCCL and 752 images of 21 patients with CHCC)were used to test the *** accuracy of the model for accurately diagnosing PCCCL and CHCC was 0.962(95%confidence interval[CI]:0.931-0.992).The average precision of the model for diagnosing PCCCL was 0.908(95%CI:0.823-0.993)and that for diagnosing CHCC was 0.907(95%CI:0.823-0.993).The recall of the model for diagnosing PCCCL was 0.951(95%CI:0.916-0.985)and that for diagnosing CHCC was 0.960(95%CI:0.854-0.962).The time to make a diagnosis using the model took an average of 4 s for each ***:The faster RCNN model can accurately distinguish PCCCL and *** model could be important for clinicians to make appropriate treatment plans for patients with PCCCL or CHCC.

关键词： Primary clear cell carcinoma of the liver Common hepatocellular carcinoma Differential diagnosis faster RCNN CT faster region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Establishment and application of an artificial intelligence diagnosis system for pancreatic cancer with a faster region-based convolutional neural network

引用

Chinese Medical Journal 2019年第23期132卷 2795-2803页

作者： Shang-Long Liu Shuo Li Yu-Ting Guo Yun-Peng Zhou Zheng-Dong Zhang Shuai Li Yun Lu Department of General Surgery Affiliated Hospital of Qingdao UniversityQingdaoShandong 266003China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China

Background:Early diagnosis and accurate staging are important to improve the cure rate and prognosis for pancreatic *** study was performed to develop an automatic and accurate imaging processing technique system,allowing this system to read computed tomography(CT)images correctly and make diagnosis of pancreatic cancer ***:The establishment of the artificial intelligence(AI)system for pancreatic cancer diagnosis based on sequential contrastenhanced CT images were composed of two processes:training and *** training process,our study used all 4385 CT images from 238 pancreatic cancer patients in the database as the training data ***,we used VGG16,which was pretrained in ImageNet and contained 13 convolutional layers and three fully connected layers,to initialize the feature extraction *** the verification experiment,we used sequential clinical CT images from 238 pancreatic cancer patients as our experimental data and input these data into the faster region-based convolution network(faster R-CNN)model that had completed ***,1699 images from 100 pancreatic cancer patients were included for clinical ***:A total of 338 patients with pancreatic cancer were included in the *** clinical characteristics(sex,age,tumor location,differentiation grade,and tumor-node-metastasis stage)between the two training and verification groups were *** mean average precision was 0.7664,indicating a good training ejffect of the faster *** contrastenhanced CT images of 100 pancreatic cancer patients were used for clinical *** area under the receiver operating characteristic curve calculated according to the trapezoidal rule was *** took approximately 0.2 s for the faster R-CNN AI to automatically process one CT image,which is much faster than the time required for diagnosis by an imaging ***:faster R-CNN AI is an effective and objective met

关键词： Artificial intelligence Pancreatic cancer Diagnosis faster region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

LWMS-Net: A novel defect detection network based on multi-wavelet multi-scale for steel surface defects

引用

MEASUREMENT 2025年 252卷

作者： Zheng, Xiaoyang Liu, Weishuo Huang, Yan Chongqing Univ Technol Sch Artificial Intelligence Chongqing Peoples R China Chongqing Univ Technol Coll Sci Chongqing 400054 Peoples R China

Steel surface defect detection is crucial to improve industrial product quality and reduce costs. However, attaining high detection accuracy and efficiency based on convolutional neural network (CNN) is challenging due to diversity, random position, irregular shape, low contras, and complex background interference of the defects. The originality of this work is to design a novel defect detection network based on Legendre multi-wavelet multiscale theory (LWMS-Net) to find a subtle balance between high detection accuracy and fast detection speed. In LWMS-Net, a feature difference enhancement (FDE) module is devised to emphasize defect edges and details, improving defect feature representation and reducing irrelevant information. More importantly, a new Backbone framework of LWMS-Net is designed to effectively capture the multi-scale contextual and detailed information of the complex defects in the multi-wavelet domain, resulting in a better interpretable LWMS module and network depth reduction largely. Then, LWMS-Net is designed by incorporating the LWMS module with improved faster region-based CNN to encompass the defect feature interactions between multi-wavelet multi-scale receptive field explicitly. Finally, the effectiveness and generalization of the proposed network are verified on NEU-DET, GC10DET, and PV-Multi-DET datasets, achieving high mean Average Precision (mAP) scores of 81.6%, 73.7%, and 91.2%, respectively, and outperforming state-of-the-art methods.

关键词： Surface defect detection Deep learning Legendre multi-wavelet transform faster region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Advanced image segmentation and severity prediction for COVID-19 using nnU-Net and optimized FRCNN-GJS algorithm

引用

International Journal of Machine Learning and Cybernetics 2025年 1-21页

作者： Vinothini, R. Niranjana, G. Computing Technologies SRM Institute of Science and Technology Tamilnadu Kattankulathur India

The global spread of Coronavirus Disease 2019 (COVID-19) has led to infections in millions of individuals with infected patients facing the risk of death as symptoms progress. Early identification of severely sick patients is crucial for timely intervention. This study presents a technique for image segmentation and disease prediction based on severity levels. The process starts with preprocessing steps, including denoising, grayscale binarization, Gaussian blur, and image flipping to enhance image quality. The No new U-Net (nnU-Net) model is employed for accurate semantic image segmentation, to identify lung regions. Subsequently, a novel faster region-based convolutional neural network-Golden Jackal Search (FRCNN-GJS) algorithm is introduced for predicting disease severity based on the lung infection percentage. This approach classifies severity levels into five grades: healthy, mild, moderate, severe, and critical, thus increasing diagnostic capabilities for medical professionals. The integration of the GJS algorithm optimizes hyperparameters, which improves model performance and accuracy. The experimental results indicate the accuracy of 98.84%, Dice Similarity Index (DSI) of 0.916, and Mean Absolute Error (MAE) of 0.324 which outperforms existing methods. The model shows the lowest prediction time and efficient resource utilization, aiding COVID-19 patients and minimizing the strain on healthcare systems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： COVID-19 CT scan images faster region-based convolutional neural network Golden Jackal Optimization Image segmentation No new U-Net

来源：评论

学校读者我要写书评

暂无评论

Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network

引用

STRUCTURAL CONTROL & HEALTH MONITORING 2019年第3期26卷 e2313-e2313页

作者： Xu, Yang Wei, Shiyin Bao, Yuequan Li, Hui Minist Ind & Informat Technol Key Lab Intelligent Disaster Mitigat Harbin Heilongjiang Peoples R China Minist Educ Key Lab Struct Dynam Behav & Control Harbin Heilongjiang Peoples R China Harbin Inst Technol Sch Civil Engn Harbin 150090 Heilongjiang Peoples R China

This paper proposed a modified faster region-based convolutional neural network (faster R-CNN) for the multitype seismic damage identification and localization (i.e., concrete cracking, concrete spalling, rebar exposure, and rebar buckling) of damaged reinforced concrete columns from images. Four hundred raw images containing different damages and complicated background information are taken by a consumer-grade camera in various locations and arbitrary perspectives to simulate the diverse situations where real-world postearthquake damaged structural images are taken by nonprofessionals. Rectangular bounding boxes are obtained to localize multitype structural damages along with the corresponding category labels and classification probabilities. Data augmentation is implemented by rotation at every 90 degrees, vertical and horizontal flipping operations. An interactive labeling process for the ground-truth regions of the aforementioned damages is performed by a semiautomatic MATLAB program. A four-step alternating training procedure is adopted on the basis of the mini-batch stochastic gradient decent algorithm with momentum by backpropagation. Test results show that the trained faster R-CNN can automatically identify and localize the aforementioned multitype seismic damages and the overall average precision reaches 80%. The relative errors of coordinates of the left-top point obey minimum extreme value distributions, and those of width and height obey three-parameter lognormal distributions. The intersection ratio between the identification and ground truth has a mean value of 0.88, and the width-height ratio obeys a two-parameter lognormal distribution. Updated convolutional kernels in the first layer have shown trending, focusing, and line detectors for the feature extraction of multitype damages. Trending and focusing detectors contribute to the recognition of local damage regions, for example, concrete spalling and rebar exposure, whereas line detectors are more s

关键词： consumer-grade camera images damage localization faster region-based convolutional neural network multitype seismic damage identification reinforced concrete columns

来源：评论

学校读者我要写书评

暂无评论

Integration of gradient guidance and edge enhancement into super-resolution for small object detection in aerial images

引用

IET IMAGE PROCESSING 2021年第13期15卷 3037-3052页

作者： Mu, Jinzhen Li, Shuang Liu, Zongming Zhou, Yan Nanjing Univ Aeronaut & Astronaut Coll Astronaut Nanjing 211106 Peoples R China Shanghai Aerosp Control Technol Inst Shanghai Peoples R China Shanghai Key Lab Aerosp Intelligent Control Techn Shanghai Peoples R China Xiangtan Univ Sch Automat & Elect Informat Xiangtan Peoples R China

Detecting small objects are difficult because of their poor-quality appearance and small size, and such issues are especially pronounced for aerial images of great importance. To address the small object detection (SOD) problem, a united architecture that tries to upsample small objects into super-resolved versions, achieving characteristics similar to those large objects and thus resulting in more discriminative detection is used. For this purpose, a new end-to-end multi-task generative adversarial network (GAN) is proposed. In the architecture, the generator is a super-resolution (SR) network, and the discriminator is a multi-task network. In the generator, a gradient guide and an edge-enhancement strategy are introduced to alleviate structural distortions. In the discriminator, a faster region-based convolutional neural network (FRCNN) is incorporated for the task of object detection. Specifically, the discriminator outputs a distribution scalar to measure the realness. Then, each super-resolved image passes through the discriminator with a realness distribution, classification scores, and bounding box regression offsets. Furthermore, the losses of the detection task are backpropagated into the generator during training rather than being optimized independently. Extensive experiments on the challenging cars overhead with context dataset (COWC), detectIon in optical remote sensing images (DIOR), vision meets drones (VisDrone), and dataset for object detection in aerial images (DOTA) demonstrate the effectiveness of the proposed method in reconstructing structures while generating natural super-resolved images and show the superiority of the proposed method in detecting small objects over state-of-the-art detectors.

关键词： image resolution image representation multitask network regression analysis neural nets optical remote sensing images edge enhancement Computer vision and image processing techniques Other topics in statistics object detection problem geophysical image processing remote sensing gradient guidance Optical, image and video signal processing super-resolution network image classification object detection discriminative detection super-resolved image passes edge-enhancement strategy faster region-based convolutional neural network end-to-end multitask generative adversarial network image sensors Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research Image sensors super-resolved versions aerial images backpropagation natural super-resolved images

来源：评论

学校读者我要写书评

暂无评论

Two-stage ship detection in synthetic aperture radar images based on attention mechanism and extended pooling

引用

JOURNAL OF APPLIED REMOTE SENSING 2020年第4期14卷

作者： Wang, Chenchen Su, Weimin Gu, Hong Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing Peoples R China

Object detection in synthetic aperture radar (SAR) images remains a challenging problem due to the particular imaging mechanism of SAR systems. The sizes of targets are relatively small and the scenes are large, indicating that the intersection over union value between the targets and anchors is probably small. In addition, SAR images are severely polluted by speckles under normal conditions. The edges of objects in SAR images are blurred. In this study, we proposed an improved object-detection framework based on a two-stage faster region-based convolutional neural network. A feature-enhancement module based on self-attention mechanism is designed to learn a target-oriented feature map, where the spatial attention and channel attention work simultaneously, such that targets can be highlighted and the speckles can be suppressed to a certain extent. Two separate feature maps serve as the input of the region proposal network to isolate the classification and regression tasks. Because only one category exists in the ship-detection task, correctly distinguishing targets from the background results in the correct detection of ships. In the final classification stage, an extended region-of-interest pooling operation is performed on the potential proposals and contexture information. The usage of extra information can improve target fine-tuning in the final network. To avoid ignoring small targets, we carefully set the anchors' parameters based on the analysis of ground truth and select the appropriate shapes of feature maps. With the help of these modifications, the proposed method can detect small, weak, and dense targets in SAR images. Ablation experiments over networks with different configurations prove that the proposed modules are working. Experiments on real SAR Gaofen-3 and Sentinel-1 images demonstrate the efficiency of the proposed object-detection framework. (C) 2020 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： synthetic aperture radar object detection self-attention anchor-based faster region-based convolutional neural network

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：