检索结果-南通市图书馆

An Enhanced Lung Cancer Detection Approach Using Dual-Model Deep Learning Technique

在线全文

学校读者我要写书评

暂无评论

Computer modeling in Engineering & Sciences 2025年第1期142卷 835-867页

作者： Sumaia Mohamed Elhassan Saad Mohamed Darwish Saleh Mesbah Elkaffas Department of information technology Institute of Graduate Studies and ResearchAlexandria UniversityAlexandria21526Egypt College of Computing and information technology Arab Academy for ScienceTechnology and Maritime TransportAlexandriaP.O.Box 1029Egypt

Lung cancer continues to be a leading cause of cancer-related deaths worldwide,emphasizing the critical need for improved diagnostic *** detection of lung tumors significantly increases the chances of successful treatment and ***,current diagnostic methods often fail to detect tumors at an early stage or to accurately pinpoint their location within the lung ***-model deep learning technologies for lung cancer detection,while beneficial,cannot capture the full range of features present in medical imaging data,leading to incomplete or inaccurate ***,it may not be robust enough to handle the wide variability in medical images due to different imaging conditions,patient anatomy,and tumor *** overcome these disadvantages,dual-model or multi-model approaches can be *** research focuses on enhancing the detection of lung cancer by utilizing a combination of two learning models:a Convolutional Neural Network(CNN)for categorization and the You Only Look Once(YOLOv8)architecture for real-time identification and pinpointing of *** automatically learn to extract hierarchical features from raw image data,capturing patterns such as edges,textures,and complex structures that are crucial for identifying lung ***8 incorporates multiscale feature extraction,enabling the detection of tumors of varying sizes and scales within a single *** is particularly beneficial for identifying small or irregularly shaped tumors that may be challenging to ***,through the utilization of cutting-edge data augmentation methods,such as Deep Convolutional Generative Adversarial Networks(DCGAN),the suggested approach can handle the issue of limited data and boost the models’ability to learn from diverse and comprehensive *** combined method not only improved accuracy and localization but also ensured efficient real-time processing,which is crucial for practical clinical applicati

关键词： Lung cancer detection dual-model deep learning technique data augmentation CNN YOLOv8

Semantic Segmentation of Lumbar Vertebrae Using Meijering U-Net(MU-Net)on Spine Magnetic Resonance Images

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer modeling in Engineering & Sciences 2025年第1期142卷 733-757页

作者： Lakshmi S V V Shiloah Elizabeth Darmanayagam Sunil Retmin Raj Cyril Department of Computer Science and Engineering College of Engineering GuindyAnna UniversityChennai600025India Department of information technology Madras Institute of TechnologyAnna UniversityChrompetChennai600044India

Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people *** to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the *** semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar *** is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation *** work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra ***-colour mask images were generated and used as ground truth for training the *** work has been carried out on 1312 images expanded from T1-weighted mid-sagittal MRI images of 515 patients in the Lumbar Spine MRI Dataset publicly available from Mendeley *** proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DSC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.

关键词： Computer aided diagnosis(CAD) magnetic resonance imaging(MRI) semantic segmentation lumbar vertebrae deep learning U-Net model

Beyond Performance of Learning Control Subject to Uncertainties and Noise: A Frequency-Domain Approach Applied to Wafer Stages

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2025年第1期 198-214页

作者： Fazhi Song Ning Cui Shuaiqi Chen Kai Zhang Yang Liu Xinkai Chen Jiubin Tan IEEE the Center of Ultra-precision Optoelectronic Instrument Engineering Harbin Institute of Technology the Key laboratory of Ultra-Precision Intelligent Instrumentation Ministry of Industry and Information Technology the State Key laboratory of Precision Electronic Manufacturing technology and Equipment Guangdong University of Technology the Center of Ultraprecision Optoelectronic Instrument Engineering Harbin Institute of Technology the Key laboratory of UltraPrecision Intelligent Instrumentation Ministry of Industry and Information Technology the Department of Electronic and information Systems Shibaura Institute of Technology

The increasingly stringent performance requirement in integrated circuit manufacturing, characterized by smaller feature sizes and higher productivity, necessitates the wafer stage executing a extreme motion with the accuracy in terms of nanometers. This demanding requirement witnesses a widespread application of iterative learning control(ILC), given the repetitive nature of wafer scanning. ILC enables substantial performance improvement by using past measurement data in combination with the system model knowledge. However, challenges arise in cases where the data is contaminated by the stochastic noise, or when the system model exhibits significant uncertainties, constraining the achievable performance. In response to this issue, an extended state observer(ESO) based adaptive ILC approach is proposed in the frequency *** being model-based, it utilizes only a rough system model and then compensates for the resulting model uncertainties using an ESO, thereby achieving high robustness against uncertainties with minimal modeling effort. Additionally, an adaptive learning law is developed to mitigate the limited performance in the presence of stochastic noise, yielding high convergence accuracy yet without compromising convergence speed. Simulation and experimental comparisons with existing model-based and data-driven inversion-based ILC validate the effectiveness as well as the superiority of the proposed method.

关键词：

Synthesis of pyrazinyl compounds from glycerol and 1,2-propanediamine over Cu-TiO_2 catalysts supported on γ-Al_2O_3

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2013年第8期24卷 751-754页

作者： Xue Li Cheng-Hua Xu Chuan-Qi Liu Yu Chen Jian-Ying Liu Air Environmental modeling and Pollution Controlling Key laboratory of Sichuan Higher Education Institutes Chengdu University of Information Technology Air Environmental modeling and Pollution Controlling Key laboratory of Sichuan Higher Education Institutes.Chengdu University of information technology College of Optoelectronic technology Chengdu University of Information Technology

Cu-TiO_2 catalysts supported onγ-Al_2O_3 are prepared and used in glycerol cyclization with 1,2-propanediamine to produce pyrazinyl compounds including 6-hydroxymethyl-2-methylpyrazine,5-hydroxymethyl -2-methyIpyrazine,2,6-dimethylpyrazine and 2,5-dimethylpyrazine in a fixed-bed *** is found that glycerol cylclization with 1,2-propanediamine gave a high total yield of pyrazinyl compounds（〉80%） over Cu-Ti02/γ-Al_2O_3 catalyst,and cyclization was through the reactions between activated 1,2-propanediamine and the intermediates from glycerol dehydration and *** addition,the regioselectivity of the pyrazinyl compounds was mainly controlled by the steric hindrance of the substrates during the cyclization process.

关键词： Catalytic cyclization Glycerol Alkyl-substituted pyrazines Steric effect

A statistical distribution of quad-pol X-band sea clutter time series acquired at a grazing angle

在线全文

学校读者我要写书评

暂无评论

Acta Oceanologica Sinica 2018年第3期37卷 94-102页

作者： WANG Yunhua LI Qun ZHANG Yanmin College of information Science &Engineering Ocean University of China laboratory for Regional Oceanography and Numerical modeling Qingdao National Laboratory for Marine Science and Technology

Although the complex Wishart distribution has been widely used to analyze the statistic properties of quad-pol SAR spatial data, the applicability of this complex distribution to the time series of sea clutter is rarely *** measured data of the quad-pol X-band marine radar demonstrate that the time series of the sea echoes are also satisfied the circular Gaussian distributions if the low intensity signals, which are mainly dominated by a radar noise, in the shadow regions of the large-scale waves are removed. On the basis of this fact, the probability density functions（PDFs） of the intensity as well as the phase, the real and the imaginary parts of the sea echoes obtained by the marine radar have been derived, and the theoretical models are all expressed in closed forms. In order to validate the theoretical results, the PDFs are compared with the experimental data collected by the Mc Master IPIX radar. And the comparisons show that the PDF models are in good agreement with the experimental data.

关键词： sea clutter quad-pol coherent X-band radar statistical distribution function

Identifying storm-induced wave origins using SAR wave mode data

在线全文

学校读者我要写书评

暂无评论

Science China Earth Sciences 2016年第10期59卷 1971-1980页

作者： WANG Xuan JIANG HaoYu CHEN Ge YU FangJie College of information Science and Engineering Ocean University of China Qingdao Collaborative Innovation Center of Marine Science and Technology laboratory for Regional Oceanography and Numerical modeling Qingdao National Laboratory for Marine Science and Technology

Because of weak dissipation effects, swells generated by fierce storms can propagate across an entire ocean basin;therefore, observing swell generation and decay and retrieving storm characteristics from a swell by satellite remote sensing are possible. In this study, based on the dispersion relation and geometrical optics principle, we used SAR wave mode data from 2003 to 2010 provided by GlobWave to track swells with peak wavelengths of more than 300 m to locate a storm-generated far-traveling swell and present the swell field related to this "static" origin. Through a comparison with ECMWF wind datasets, we conducted validations and explored some conditions that cause misjudgments in swell origins. Finally, we obtained the spatiotemporal distribution characteristics of satellite-observed swell origins(i.e., the fierce wind condition) and their evolution. This work can be used as a reference for wave models, providing early swell warnings, determining air-sea surface interactions, and determining global climate change.

关键词： SAR Fierce storm Swell tracking

Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental & Earth Sciences 2023年第2期5卷 118-134页

作者： Hafsa Ouchra Abdessamad Belangour Allae Erraissi laboratory of information technology and modeling ltim Hassan II UniversityFaculty of Sciences Ben M’sikCasablanca20670Morocco Chouaib Doukkali University Polydisciplinary Faculty of Sidi BennourEl Jadida24000Morocco

Satellite image classification is crucial in various applications such as urban planning,environmental monitoring,and land use *** this study,the authors present a comparative analysis of different supervised and unsupervised learning methods for satellite image classification,focusing on a case study in Casablanca using Landsat 8 *** research aims to identify the most effective machine-learning approach for accurately classifying land cover in an urban *** methodology used consists of the pre-processing of Landsat imagery data from Casablanca city,the authors extract relevant features and partition them into training and test sets,and then use random forest(RF),SVM(support vector machine),classification,and regression tree(CART),gradient tree boost(GTB),decision tree(DT),and minimum distance(MD)*** a series of experiments,the authors evaluate the performance of each machine learning method in terms of accuracy,and Kappa *** work shows that random forest is the best-performing algorithm,with an accuracy of 95.42%and 0.94 Kappa *** authors discuss the factors of their performance,including data characteristics,accurate selection,and model influencing.

关键词： Supervised learning Unsupervised learning Satellite image classification Machine learning Google Earth Engine

From solar terms to medical terms(Part Ⅰ): A first step with big data

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Earth Sciences 2017年第9期60卷 1707-1718页

作者： CHEN Ge SHI Jie College of information Science and Engineering Ocean University of China laboratory for Regional Oceanography and Numerical modeling Qingdao National Laboratory for Marine Science and Technology Department of Pharmacy Municipal Hospital of Qingdao

The story of the Twenty-four Solar Terms(24-ST_s) is one of the most popular elements in Chinese culture, which has a profound influence on agriculture production, health care, and even daily life in both ancient and modern China. This traditional calendric system was invented by the Chinese ancestors through combining fundamental astronomical knowledge with climatic and phenological conditions in the Yellow River Basin some 2000 years ago. Although the basic philosophy of the 24-ST_s remains valid for the country as a whole to date, their regional robustness has been increasingly challenged by accumulating observational data in terms of temporal shift and spatial inhomogeneity. To tackle these issues, we propose to recalibrate the medically related critical timings of Great Heat and Great Cold in the classic ST system by using big meteorological data, and adjust them by introducing geographically correlated analytical models. As a result, a novel calendric system, called the Twenty-four Medical Terms(24-MT_s), has been developed as an upgraded version of the traditional 24-ST_s. The proposed 24-MT_s are characterized by two striking features with respect to the 24-ST_s: A varying duration of each MT instead of a fixed one for the ST, and a geographically dependent timing for each MT instead of a unified one for the entire nation. As such, the updated 24-MT_s are expected to provide a more realistic estimate of these critical timings around the year, and hence, a more precise guidance to agronomic planning and health care activity in China.

关键词： Solar Terms Medical Terms Big Data

A Real-Time Photo-Realistic Rendering Algorithm of Ocean Color Based on Bio-Optical Model

在线全文

学校读者我要写书评

暂无评论

Journal of Ocean University of China 2016年第6期15卷 996-1006页

作者： MA Chunyong XU Shu WANG Hongsong TIAN Fenglin CHEN Ge College of information Science and Engineering Ocean University of China laboratory for Regional Oceanography and Numerical modeling Qingdao National Laboratory for Marine Science and Technology

Abstract A real-time photo-realistic rendering algorithm of ocean color is introduced in the paper, which considers the impact of ocean bio-optical model. The ocean bio-optical model mainly involves the phytoplankton, colored dissolved organic material （CDOM）, inorganic suspended particle, etc., which have different contributionsto absorption and scattering of light. We decompose the emergent light of the ocean surface into the reflected light from the sun and the sky, and the subsurface scattering light. We estab- lish an ocean surface transmission model based on ocean bidirectional reflectance distribution function （BRDF） and the Fresnel law, and this model＇s outputs would be the incident light parameters of subsurface scattering. Using ocean subsurface scattering algorithm combined with bio-optical model, we compute the scattering light emergent radiation in different directions. Then, we blend the re- flection of sunlight and sky light to implement the real-time ocean color rendering in graphics processing unit （GPU）. Finally, we use two kinds of radiance reflectance calculated by Hydrolight radiative transfer model and our algorithm to validate the physical reality of our method, and the results show that our algorithm can achieve real-time highly realistic ocean color scenes.

关键词： ocean color BRDF subsurface scattering bio-optical model