检索结果-南通市图书馆

Early esophagus cancer segmentation from gastrointestinal endoscopic images based on U-Net++model

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2023年第3期21卷 38-51页

作者： Zenebe markos Lonseko Cheng-Si Luo Wen-Ju Du Tao Gan Lin-Lin Zhu prince Ebenezer Adjei ni-ni Rao School of Life Science and Technology University of Electronic Science and Technology of ChinaChengdu610054China College of Health and medical Sciences Dilla UniversityDilla419Ethiopia West China Hospital of Sichuan University Chengdu610017China

Automatic segmentation of early esophagus cancer(EEC)in gastrointestinal endoscopy(GIE)images is a critical and challenging task in clinical settings,which relies primarily on labor-intensive and time-consuming *** has often been diagnosed at the late stage since early signs of cancer are not obvious,resulting in low survival *** work proposes a deep learning approach based on the U-Net++method to segment EEC in GIE images.A total of 2690 GIE images collected from 617 patients at the Digestive Endoscopy Center,West China Hospital of Sichuan University,China,have been *** experimental result shows that our proposed method achieved promising ***,the comparison has been made between the proposed and other U-Net-related methods using the same *** mean and standard deviation(SD)of the dice similarity coefficient(DSC),intersection over union(IoU),precision(Pre),and recall(Rec)achieved by the proposed framework were DSC(%)=94.62±0.02,IoU(%)=90.99±0.04,Pre(%)=94.61±0.04,and Rec(%)=95.00±0.02,respectively,outperforming the *** proposed method has the potential to be applied in EEC automatic diagnoses.

关键词： Early esophageal cancer(EEC) Gastrointestinal endoscopic(GIE) images Semantic segmentation Supervised learning U-Net++

维普期刊数据库

An Imbalanced Dataset and Class Overlapping Classification model for Big Data

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第2期44卷 1009-1024页

作者： m.ni prince P.m.Joe Prathap Department of Information Technology St.Peter’s College of Engineering and TechnologyChennai600054TamilnaduIndia Department of Information Technology R.M.D Engineering CollegeChennai601206TamilnaduIndia

most modern technologies,such as social media,smart cities,and the internet of things(IoT),rely on big *** big data is used in the real-world applications,two data challenges such as class overlap and class imbalance *** dealing with large datasets,most traditional classiﬁers are stuck in the local optimum *** a result,it’s necessary to look into new methods for dealing with large data *** solutions have been proposed for overcoming this *** rapid growth of the available data threatens to limit the usefulness of many traditional *** such as oversampling and undersampling have shown great promises in addressing the issues of class *** all of these techniques,Synthetic minority Oversampling TechniquE(SmOTE)has produced the best results by generating synthetic samples for the minority class in creating a balanced *** issue is that their practical applicability is restricted to problems involving tens of thousands or lower instances of *** this paper,we have proposed a parallel mode method using SmOTE and mapReduce strategy,this distributes the operation of the algorithm among a group of computational nodes for addressing the aforementioned *** proposed solution has been divided into three ***ﬁrst stage involves the process of splitting the data into different blocks using a mapping function,followed by a pre-processing step for each mapping block that employs a hybrid SmOTE algo-rithm for solving the class imbalanced *** each map block,a decision tree model would be ***,the decision tree blocks would be com-bined for creating a classiﬁcation *** have used numerous datasets with up to 4 million instances in our experiments for testing the proposed scheme’s *** a result,the Hybrid SmOTE appears to have good scalability within the framework proposed,and it also cuts down the processing time.

关键词： Imbalanced dataset class overlapping SmOTE mapReduce parallel programming oversampling

A Novel Approach to Design Distribution Preserving Framework for Big Data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第3期35卷 2789-2803页

In several fields like financial dealing,industry,business,medicine,et cetera,Big Data(BD)has been utilized extensively,which is nothing but a collection of a huge amount of ***,it is highly complicated along with time-consuming to process a massive amount of ***,to design the Distribution Preserving Framework for BD,a novel methodology has been proposed utilizing manhattan Distance(mD)-centered Partition Around medoid(mD–PAm)along with Conjugate Gradient Artificial Neural Network(CG-ANN),which undergoes various steps to reduce the complications of ***,the data are processed in the pre-processing phase by mitigating the data repetition utilizing the map-reduce function;subsequently,the missing data are handled by substituting or by ignoring the missed *** that,the data are transmuted into a normalized ***,to enhance the classification performance,the data’s dimensionalities are m.nimized by employing Gaussian Kernel(GK)-Fisher Discriminant Analysis(GK-FDA).Afterwards,the processed data is submitted to the partitioning phase after transmuting it into a structured *** the partition phase,by utilizing the mD-PAm,the data are partitioned along with grouped into a ***,by employing CG-ANN,the data are classified in the classification phase so that the needed data can be effortlessly retrieved by the *** analogize the outcomes of the CG-ANN with the prevailing methodologies,the NSL-KDD openly accessible datasets are *** experiential outcomes displayed that an efficient result along with a reduced computation cost was shown by the proposed *** proposed work outperforms well in terms of accuracy,sensitivity and specificity than the existing systems.

关键词： Big data artiﬁcial neural network ﬁsher discriminant analysis distribution preserving framework manhattan distance

A comparative evaluation of Stacked Auto-Encoder neural network and multi-Layer Extreme Learning machine for detection and classification of faults in transmission lines using WAmS data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2023年第4期14卷 598-611页

作者： Ani Harish prince Asok Jayan m.V. APJ Abdul Kalam Technological University Rajiv Gandhi Institute of TechnologyKottayam686501KeralaIndia APJ Abdul Kalam Technological University CET CampusThiruvananthapuram695016KeralaIndia

Smart grid is envisaged as a power grid that is extremely reliable and *** electrical grid has wide-area measuring devices like Phasor measurement units(PmUs)deployed to provide real-time grid information and resolve issues effectively and speedily without compromising system *** development and application of machine learning approaches for power system protection and state estimation have been facilitated by the availability of measurement *** research proposes a transmission line fault detection and classification(FD&C)system based on an auto-encoder neural network.A comparison between a multi-Layer Extreme Learning machine(mL-ELm)network model and a Stacked Auto-Encoder neural network(SAE)is ***,the performance of the models developed is compared to that of state-of-the-art classifier models employing feature datasets acquired by wavelet transform based feature extraction as well as other deep learning *** substantially shorter testing time,the suggested auto-encoder models detect faults with 100% accuracy and classify faults with 99.92% and 99.79%*** computational efficiency of the mL-ELm model is demonstrated with high accuracy of classification with training time and testing time less than 50 *** emulate real system scenarios the models are developed with datasets with noise with signal-to-noise-ratio(SNR)ranging from 10 dB to 40 *** efficacy of the models is demonstrated with data from the IEEE 39 bus test system.

关键词： machine learning Fault detection Fault classification Auto-Encoder Transmission line Smart grid Neural network Extreme Learning machine

Rethinking the architecture design of data center networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2012年第5期6卷 596-603页

作者： Kaishun WU Jiang XIAO Lionel m. ni National Engineering Research Center of Digital Life State-Province Joint Laboratory of Digital Home Interactive Applications School of Physics and Engineering Sun Yat-sen University Guangzhou 510006 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong China

In the rising tide of the Internet of things, more and more things in the world are connected to the Internet. Recently, data have kept growing at a rate more than four times of that expected in moore＇s law. This explosion of data comes from various sources such as mobile phones, video cameras and sensor networks, which often present multidi- mensional characteristics. The huge amount of data brings many challenges on the management, transportation, and pro- cessing IT infrastructures. To address these challenges, the state-of-art large scale data center networks have begun to provide cloud services that are increasingly prevalent. How- ever, how to build a good data center remains an open chal- lenge. Concurrently, the architecture design, which signifi- cantly affects the total performance, is of great research inter- est. This paper surveys advances in data center network de- sign. In this paper we first introduce the upcoming trends in the data center industry. Then we review some popular design principles for today＇s data center network architectures. In the third part, we present some up-to-date data center frame- works and make a comprehensive comparison of them. Dur- ing the comparison, we observe that there is no so-called op- timal data center and the design should be different referring to the data placement, replication, processing, and query pro- cessing. After that, several existing challenges and limitations are discussed. According to these observations, we point out some possible future research directions.

关键词： data center networks switch-based networks,direct networks hybrid networks

Ordered proposition fusion based on consistency and uncertainty measurements

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(Information Sciences) 2017年第8期60卷 117-135页

作者： Dayou LIU Yungang ZHU ni ni Jie LIU College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of m.nistry of Education Jilin University Beijing Entry-Exit Inspection and Quarantine Bureau

The fusion of ordered propositions is an important and widespread problem in artificial intelligence,but existing fusion methods have difficulty handling the fusion of ordered propositions. In this paper, we propose a solution based on consistency and uncertainty measurements. The main contributions of this paper are as follows. First, we propose the concept of convexity degree, mean, and center of basic support function to comprehensively describe the basic support function of ordered propositions. Second, we introduce entropy as a measure of uncertainty in the basic support function of ordered propositions. Third, we generalize the indeterminacy of the basic support function and propose a novel method to measure the consistency between two basic support functions. Finally, based on the above researches, we propose a novel algorithm for fusing ordered propositions. Theoretical analysis and experimental results demonstrate that the proposed method outperforms state-of-the-art methods.

关键词： uncertainty processing ordered proposition evidence theory dempster rule of combination information fusion

Rethinking big data in a networked world

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2016年第6期10卷 965-967页

作者： Lionel m. ni Haoyu TAN Jiang XIAO Department of Computer and Information Science University of Macao Macao China Fok Ying Tung Graduate School Hong Kong University of Science and Technology Hong Kong China

Since the early 21st century, big data has drawn much attention from both academia and industry. In the last decade of collecting massive data, seeking innovative applications, and developing powerful technologies, the major focus of the research and engineering in big data has shifted substantially in many aspects. It is time to rethink about this fuzzy term to make clear the upcoming opportunities and the most urgent challenges.

关键词：

维普期刊数据库

Hepatitis C:a successful story of cure

在线全文

学校读者我要写书评

暂无评论

Science Bulletin 2016年第24期61卷 1884-1887页

作者： Yi ni Department of Infectious Diseases Molecular VirologyUniversity Hospital Heidelberg 69120 Heidelberg Germany

On September 23, the 2016 Lasker-DeBakey clinical medical research award ceremony was celebrated in New York City. This annual prize has been awarded by the Lasker Foundation for over 71 years, and it is the most prestigious biomedical award in the United States, popu- larly known as ＂America＇s Nobel Prize＂. Indeed, 87 Lasker laureates have received the Nobel Prize, including 41 within the last 30 years （one example is the Chinese pharmaceutical chemist Youyou Tu, who won the 2011 Lasker-DeBakey award and four years later received the Nobel Prize）. This year, the honor went to Ralf F. W. Bartenschlager （Heidelberg University, Germany）, Charles m. Rice （Rockefeller University, NY, USA）, and michael J. Sofia （Arbutus Biopharma, PA, USA） for the development of cell culture system to study the replication of Hepatitis C virus （HCV） and for the use of this system to develop drugs capable of eliminating Hepatitis C.

关键词：丙型肝炎病毒 michael 故事治愈诺贝尔奖生物制药开发能力培养系统

维普期刊数据库

Infrared chemical imaging through non-degenerate two-photon absorption in silicon-based cameras

在线全文

学校读者我要写书评

暂无评论

Light(Science & Applications) 2020年第1期9卷 813-822页

作者： David Knez Adam m.Hanninen Richard C.prince Eric O.Potma Dmitry A.Fishman Department of Chemistry University of CaliforniaIrvineCA 92697USA Department of Biomedical Engineering University of CaliforniaIrvineCA 92697USA

Chemical imaging based on mid-infrared(mIR)spectroscopic contrast is an important technique with a myriad of applications,including biomedical imaging and environmental *** mIR cameras,however,lack performance and are much less affordable than mature Si-based devices,which operate in the visible and nearinfrared ***,we demonstrate fast mIR chemical imaging through non-degenerate two-photon absorption(NTA)in a standard Si-based charge-coupled device(CCD).We show that wide-field mIR images can be obtained at 100 ms exposure times using picosecond pulse energies of only a few femtojoules per pixel through NTA directly on the CCD *** this on-chip approach does not rely on phase matching,it is alignment-free and does not necessitate complex postprocessing of the *** emphasize the utility of this technique through chemically selective mIR imaging of polymers and biological samples,including mIR videos of moving targets,physical processes and live nematodes.

关键词： absorption Infrared chemical