Search

With the rapid development of Internet of things and cloud computing,big data and its related science have become the focus of industry and academia.In this paper,we analyzes big data science from the perspective of paradigm theory and expounds the difference and connection between big data and traditional research.Three major challenges brought by big data are proposed in perspective of machine learning,with the corresponding scientific problems following.In addition,this paper introduces several insights of big data science from the perspective of the forth paradigm and its positive significance.In the end,we summarize and look forward to the challenges of big data science in the future. [ABSTRACT FROM AUTHOR]

The spaceborne synthetic aperture radar(SAR) plays an important role in ocean observation owing to its capability of working all-day and being insusceptible to sunlight,cloudiness or rainfall.It has unique advantages in retrieval of ocean surface dynamic parameters and study of multi-scale ocean dynamic processes with high spatial resolution,multi-polarization,and multi-imaging modes.Since the late 1970 s,spaceborne SAR technology has developed rapidly.When combined with big data and machine learning techniques,spaceborne SAR exhibits more powerful vitality in ocean observation.In this paper,the 5‘V’ characteristics of spaceborne SAR big data are elaborated.Then two typical cases,i.e.retrieval of the sea surface wind speed,and scientific recognition of mesoscale dynamic processes of ocean internal waves,are presented to demonstrate the integration of spaceborne SAR,machine learning,and big data in assistance of high-resolution inversion of ocean environmental factors and deep understanding of marine dynamic processes.Finally,the prospective of spaceborne SAR big data for ocean remote sensing is given. [ABSTRACT FROM AUTHOR]

Accurate determination of the severity of secondary equipment defects in power grid can provide an important basis for the operation and maintenance of equipment.Therefore,in this paper,to address problems such as large quantity of defective data features,and the great difficulty of using error-prone human judgment as an evaluation parameter,a defect classification method based on XGBoost (eXtreme Gradient Boosting) is proposed to improve the accuracy of defect classification of secondary equipment.First,a series of pre-processing work,such as removing outliers and coding,is performed on the secondary equipment historical defect data,and the characteristics highly correlated with equipment defects are extracted to establish the feature index set.Subsequently,the XGBoost model is trained and optimized using historical defect data.Finally,the trained classification model is used to realize the accurate classification of secondary equipment defects.Based on the secondary equipment defective data of a power plant,simulation results are presented to illustrate the effectiveness of the proposed algorithm and are compared with those of traditional classifiers (decision tree,logistic regression,etc.).Simulation results show that XGBoost can accurately determine the defect degree of secondary equipment,to assist the maintenance and management of equipment. [ABSTRACT FROM AUTHOR]

The goal of transfer learning is to solve the problem of insufficient training samples in the target domain.It can transfer the acquired knowledge from related source domain to the target domain.It relaxes two basic assumptions in traditional machine learning:the training samples and the new test samples satisfy the conditions of independent and identical distribution; furthermore,there must be enough training samples to learn a good classification model.According to whether the feature space of the source domain and the target domain are the same,it can be divided into homogeneous transfer learning and heterogeneous transfer learning.This paper mainly reviews the related research progress of homogeneous transfer learning,introduces the theory,algorithm and application of homogeneous transfer learning,and points out the hotissues of homogeneous transfer learning. [ABSTRACT FROM AUTHOR]