New technologies such as big data,artificial intelligence,mobile internet,cloud computing,Internet of Things,and blockchain have brought about significant changes and development in the financial industry.Predicting t...New technologies such as big data,artificial intelligence,mobile internet,cloud computing,Internet of Things,and blockchain have brought about significant changes and development in the financial industry.Predicting the financial situation of enterprises,reducing the probability of uncertainty risks,and reducing the likelihood of financial crises have become important issues in enterprise financial crisis warning.In view of the issues in enterprise financial early warning systems such as lag,low accuracy,and high warning costs in data analysis,a financial early warning system based on big data and deep learning technology has been established,taking into account the different situations of listed and non-listed companies.This carries significance in improving the accuracy of enterprise financial early warning and promoting timely and effective decision-making.展开更多
This study analyzes and summarizes seven main characteristics of the marine data sampled by multiple underwater gliders. These characteristics such as the big data volume and data sparseness make it extremely difficul...This study analyzes and summarizes seven main characteristics of the marine data sampled by multiple underwater gliders. These characteristics such as the big data volume and data sparseness make it extremely difficult to do some meaningful applications like early warning of marine environment. In order to make full use of the sea trial data, this paper gives the definition of two types of marine data cube which can integrate the big marine data sampled by multiple underwater gliders along saw-tooth paths, and proposes a data fitting algorithm based on time extraction and space compression(DFTS) to construct the temperature and conductivity data cubes. This research also presents an early warning algorithm based on data cube(EWDC) to realize the early warning of a new sampled data file.Experiments results show that the proposed methods are reasonable and effective. Our work is the first study to do some realistic applications on the data sampled by multiple underwater vehicles, and it provides a research framework for processing and analyzing the big marine data oriented to the applications of underwater gliders.展开更多
ESCAP/WMO Typhoon Committee Members are directly or indirectly affected by typhoons every year.Members have accumulated rich experiences dealing with typhoons'negative impact and developed the technologies and mea...ESCAP/WMO Typhoon Committee Members are directly or indirectly affected by typhoons every year.Members have accumulated rich experiences dealing with typhoons'negative impact and developed the technologies and measures on typhoon-related disaster risk forecasting and early warning in various ways to reduce the damage caused by typhoon.However,it is still facing many difficulties and challenges to accurately forecast the occurrence of typhoons and warning the potential impacts in an early stage due to the continuously changing weather conditions.With the development of information technology(IT)and computing science,and increasing accumulated hydro-meteorological data in recent decades,scientists,researchers and operationers keep trying to improve forecasting models based on the application of big data and artificial intelligent(AI)technology to promote the capacity of typhoon-related disaster risk forecasting and early warning.This paper reviewed the current status of application of big data and AI technology in the aspect of typhoon-related disaster risk forecasting and early warning,and discussed the challenges and limitations that must be addressed to effectively harness the power of big data and AI technology application in typhoon-related disaster risk reduction in the future.展开更多
针对“校园大数据”累积的海量数据呈现出离散性、稀疏性等问题,如何从基数大、活动广、个性强的校园学生群体中检测出潜在的、有异常行为的学生,已成为学生异常行为分析亟需解决的问题.本文提出了一种大数据环境下基于多模态融合的大...针对“校园大数据”累积的海量数据呈现出离散性、稀疏性等问题,如何从基数大、活动广、个性强的校园学生群体中检测出潜在的、有异常行为的学生,已成为学生异常行为分析亟需解决的问题.本文提出了一种大数据环境下基于多模态融合的大学生异常行为预警方法(early warning method for abnormal behavior of college students based on multi-modal fusion in big data environment,EWMAB).首先,针对学生行为画像的表征不够丰富,行为标签存在时效性、动态性等问题,建立一种基于多模态特征深度学习的跨模态学生行为画像模型;其次,针对学生异常行为预测、预警的时效性和后置性问题,在学生行为画像和学生行为分类预测基础上,提出了一种基于多模态融合的学生异常行为预警方法,通过长短期记忆神经网络(long and short term memory networks,LSTM),结合学生行为多指标数据和文本信息来解决学生异常行为预警问题;最后,本文通过应用实例验证模型以学生学习成绩异常预警为例,与其他预警算法相比,EWMAB方法可以提高预警的准确性,实现学生异常行为预警的时效性和前置性,从而使学生教育工作更具有针对性、个性化和预测性.展开更多
文摘New technologies such as big data,artificial intelligence,mobile internet,cloud computing,Internet of Things,and blockchain have brought about significant changes and development in the financial industry.Predicting the financial situation of enterprises,reducing the probability of uncertainty risks,and reducing the likelihood of financial crises have become important issues in enterprise financial crisis warning.In view of the issues in enterprise financial early warning systems such as lag,low accuracy,and high warning costs in data analysis,a financial early warning system based on big data and deep learning technology has been established,taking into account the different situations of listed and non-listed companies.This carries significance in improving the accuracy of enterprise financial early warning and promoting timely and effective decision-making.
基金financially supported by the National Natural Science Foundation of China(Grant Nos.U1709202 and No.61502069)the Foundation of State Key Laboratory of Robotics(Grant No.2015-o03)the Fundamental Research Funds for the Central Universities(Grant Nos.DUT18JC39 and DUT17JC45)
文摘This study analyzes and summarizes seven main characteristics of the marine data sampled by multiple underwater gliders. These characteristics such as the big data volume and data sparseness make it extremely difficult to do some meaningful applications like early warning of marine environment. In order to make full use of the sea trial data, this paper gives the definition of two types of marine data cube which can integrate the big marine data sampled by multiple underwater gliders along saw-tooth paths, and proposes a data fitting algorithm based on time extraction and space compression(DFTS) to construct the temperature and conductivity data cubes. This research also presents an early warning algorithm based on data cube(EWDC) to realize the early warning of a new sampled data file.Experiments results show that the proposed methods are reasonable and effective. Our work is the first study to do some realistic applications on the data sampled by multiple underwater vehicles, and it provides a research framework for processing and analyzing the big marine data oriented to the applications of underwater gliders.
文摘ESCAP/WMO Typhoon Committee Members are directly or indirectly affected by typhoons every year.Members have accumulated rich experiences dealing with typhoons'negative impact and developed the technologies and measures on typhoon-related disaster risk forecasting and early warning in various ways to reduce the damage caused by typhoon.However,it is still facing many difficulties and challenges to accurately forecast the occurrence of typhoons and warning the potential impacts in an early stage due to the continuously changing weather conditions.With the development of information technology(IT)and computing science,and increasing accumulated hydro-meteorological data in recent decades,scientists,researchers and operationers keep trying to improve forecasting models based on the application of big data and artificial intelligent(AI)technology to promote the capacity of typhoon-related disaster risk forecasting and early warning.This paper reviewed the current status of application of big data and AI technology in the aspect of typhoon-related disaster risk forecasting and early warning,and discussed the challenges and limitations that must be addressed to effectively harness the power of big data and AI technology application in typhoon-related disaster risk reduction in the future.
文摘针对“校园大数据”累积的海量数据呈现出离散性、稀疏性等问题,如何从基数大、活动广、个性强的校园学生群体中检测出潜在的、有异常行为的学生,已成为学生异常行为分析亟需解决的问题.本文提出了一种大数据环境下基于多模态融合的大学生异常行为预警方法(early warning method for abnormal behavior of college students based on multi-modal fusion in big data environment,EWMAB).首先,针对学生行为画像的表征不够丰富,行为标签存在时效性、动态性等问题,建立一种基于多模态特征深度学习的跨模态学生行为画像模型;其次,针对学生异常行为预测、预警的时效性和后置性问题,在学生行为画像和学生行为分类预测基础上,提出了一种基于多模态融合的学生异常行为预警方法,通过长短期记忆神经网络(long and short term memory networks,LSTM),结合学生行为多指标数据和文本信息来解决学生异常行为预警问题;最后,本文通过应用实例验证模型以学生学习成绩异常预警为例,与其他预警算法相比,EWMAB方法可以提高预警的准确性,实现学生异常行为预警的时效性和前置性,从而使学生教育工作更具有针对性、个性化和预测性.
