The Chang＇e-3 （CE-3） mission is China＇s first exploration mission on the surface of the Moon that uses a lander and a rover. Eight instruments that form the scientific payloads have the following objectives： （1...The Chang＇e-3 （CE-3） mission is China＇s first exploration mission on the surface of the Moon that uses a lander and a rover. Eight instruments that form the scientific payloads have the following objectives： （1） investigate the morphological features and geological structures at the landing site; （2） integrated in-situ analysis of minerals and chemical compositions; （3） integrated exploration of the structure of the lunar interior; （4） exploration of the lunar-terrestrial space environment, lunar sur- face environment and acquire Moon-based ultraviolet astronomical observations. The Ground Research and Application System （GRAS） is in charge of data acquisition and pre-processing, management of the payload in orbit, and managing the data products and their applications. The Data Pre-processing Subsystem （DPS） is a part of GRAS. The task of DPS is the pre-processing of raw data from the eight instruments that are part of CE-3, including channel processing, unpacking, package sorting, calibration and correction, identification of geographical location, calculation of probe azimuth angle, probe zenith angle, solar azimuth angle, and solar zenith angle and so on, and conducting quality checks. These processes produce Level 0, Level 1 and Level 2 data. The computing platform of this subsystem is comprised of a high-performance computing cluster, including a real-time subsystem used for processing Level 0 data and a post-time subsystem for generating Level 1 and Level 2 data. This paper de- scribes the CE-3 data pre-processing method, the data pre-processing subsystem, data classification, data validity and data products that are used for scientific studies.展开更多
A novel technique for automatic seismic data processing using both integral and local feature of seismograms was presented in this paper. Here, the term integral feature of seismograms refers to feature which may depi...A novel technique for automatic seismic data processing using both integral and local feature of seismograms was presented in this paper. Here, the term integral feature of seismograms refers to feature which may depict the shape of the whole seismograms. However, unlike some previous efforts which completely abandon the DIAL approach, i.e., signal detection, phase identifi- cation, association, and event localization, and seek to use envelope cross-correlation to detect seismic events directly, our technique keeps following the DIAL approach, but in addition to detect signals corresponding to individual seismic phases, it also detects continuous wave-trains and explores their feature for phase-type identification and signal association. More concrete ideas about how to define wave-trains and combine them with various detections, as well as how to measure and utilize their feature in the seismic data processing were expatiated in the paper. This approach has been applied to the routine data processing by us for years, and test results for a 16 days＇ period using data from the Xinjiang seismic station network were presented. The automatic processing results have fairly low false and missed event rate simultaneously, showing that the new technique has good application prospects for improvement of the automatic seismic data processing.展开更多
针对句子分类任务常面临着训练数据不足,而且文本语言具有离散性,在语义保留的条件下进行数据增强具有一定困难,语义一致性和多样性难以平衡的问题,本文提出一种惩罚生成式预训练语言模型的数据增强方法(punishing generative pre-train...针对句子分类任务常面临着训练数据不足,而且文本语言具有离散性,在语义保留的条件下进行数据增强具有一定困难,语义一致性和多样性难以平衡的问题,本文提出一种惩罚生成式预训练语言模型的数据增强方法(punishing generative pre-trained transformer for data augmentation,PunishGPT-DA)。设计了惩罚项和超参数α,与负对数似然损失函数共同作用微调GPT-2(generative pre-training 2.0),鼓励模型关注那些预测概率较小但仍然合理的输出;使用基于双向编码器表征模型(bidirectional encoder representation from transformers,BERT)的过滤器过滤语义偏差较大的生成样本。本文方法实现了对训练集16倍扩充,与GPT-2相比,在意图识别、问题分类以及情感分析3个任务上的准确率分别提升了1.1%、4.9%和8.7%。实验结果表明,本文提出的方法能够同时有效地控制一致性和多样性需求,提升下游任务模型的训练性能。展开更多
Emotion represents the feeling of an individual in a given situation. There are various ways to express the emotions of an individual. It can be categorized into verbal expressions, written expressions, facial express...Emotion represents the feeling of an individual in a given situation. There are various ways to express the emotions of an individual. It can be categorized into verbal expressions, written expressions, facial expressions and gestures. Among these various ways of expressing the emotion, the written method is a challenging task to extract the emotions, as the data is in the form of textual dat. Finding the different kinds of emotions is also a tedious task as it requires a lot of pre preparations of the textual data taken for the research. This research work is carried out to analyse and extract the emotions hidden in text data. The text data taken for the analysis is from the social media dataset. Using the raw text data directly from the social media will not serve the purpose. Therefore, the text data has to be pre-processed and then utilised for further processing. Pre-processing makes the text data more efficient and would infer valuable insights of the emotions hidden in it. The preprocessing steps also help to manage the text data for identifying the emotions conveyed in the text. This work proposes to deduct the emotions taken from the social media text data by applying the machine learning algorithm. Finally, the usefulness of the emotions is suggested for various stake holders, to find the attitude of individuals at that moment, the data is produced. .展开更多
文摘The Chang＇e-3 （CE-3） mission is China＇s first exploration mission on the surface of the Moon that uses a lander and a rover. Eight instruments that form the scientific payloads have the following objectives： （1） investigate the morphological features and geological structures at the landing site; （2） integrated in-situ analysis of minerals and chemical compositions; （3） integrated exploration of the structure of the lunar interior; （4） exploration of the lunar-terrestrial space environment, lunar sur- face environment and acquire Moon-based ultraviolet astronomical observations. The Ground Research and Application System （GRAS） is in charge of data acquisition and pre-processing, management of the payload in orbit, and managing the data products and their applications. The Data Pre-processing Subsystem （DPS） is a part of GRAS. The task of DPS is the pre-processing of raw data from the eight instruments that are part of CE-3, including channel processing, unpacking, package sorting, calibration and correction, identification of geographical location, calculation of probe azimuth angle, probe zenith angle, solar azimuth angle, and solar zenith angle and so on, and conducting quality checks. These processes produce Level 0, Level 1 and Level 2 data. The computing platform of this subsystem is comprised of a high-performance computing cluster, including a real-time subsystem used for processing Level 0 data and a post-time subsystem for generating Level 1 and Level 2 data. This paper de- scribes the CE-3 data pre-processing method, the data pre-processing subsystem, data classification, data validity and data products that are used for scientific studies.
文摘A novel technique for automatic seismic data processing using both integral and local feature of seismograms was presented in this paper. Here, the term integral feature of seismograms refers to feature which may depict the shape of the whole seismograms. However, unlike some previous efforts which completely abandon the DIAL approach, i.e., signal detection, phase identifi- cation, association, and event localization, and seek to use envelope cross-correlation to detect seismic events directly, our technique keeps following the DIAL approach, but in addition to detect signals corresponding to individual seismic phases, it also detects continuous wave-trains and explores their feature for phase-type identification and signal association. More concrete ideas about how to define wave-trains and combine them with various detections, as well as how to measure and utilize their feature in the seismic data processing were expatiated in the paper. This approach has been applied to the routine data processing by us for years, and test results for a 16 days＇ period using data from the Xinjiang seismic station network were presented. The automatic processing results have fairly low false and missed event rate simultaneously, showing that the new technique has good application prospects for improvement of the automatic seismic data processing.
文摘针对句子分类任务常面临着训练数据不足,而且文本语言具有离散性,在语义保留的条件下进行数据增强具有一定困难,语义一致性和多样性难以平衡的问题,本文提出一种惩罚生成式预训练语言模型的数据增强方法(punishing generative pre-trained transformer for data augmentation,PunishGPT-DA)。设计了惩罚项和超参数α,与负对数似然损失函数共同作用微调GPT-2(generative pre-training 2.0),鼓励模型关注那些预测概率较小但仍然合理的输出;使用基于双向编码器表征模型(bidirectional encoder representation from transformers,BERT)的过滤器过滤语义偏差较大的生成样本。本文方法实现了对训练集16倍扩充,与GPT-2相比,在意图识别、问题分类以及情感分析3个任务上的准确率分别提升了1.1%、4.9%和8.7%。实验结果表明,本文提出的方法能够同时有效地控制一致性和多样性需求,提升下游任务模型的训练性能。
文摘Emotion represents the feeling of an individual in a given situation. There are various ways to express the emotions of an individual. It can be categorized into verbal expressions, written expressions, facial expressions and gestures. Among these various ways of expressing the emotion, the written method is a challenging task to extract the emotions, as the data is in the form of textual dat. Finding the different kinds of emotions is also a tedious task as it requires a lot of pre preparations of the textual data taken for the research. This research work is carried out to analyse and extract the emotions hidden in text data. The text data taken for the analysis is from the social media dataset. Using the raw text data directly from the social media will not serve the purpose. Therefore, the text data has to be pre-processed and then utilised for further processing. Pre-processing makes the text data more efficient and would infer valuable insights of the emotions hidden in it. The preprocessing steps also help to manage the text data for identifying the emotions conveyed in the text. This work proposes to deduct the emotions taken from the social media text data by applying the machine learning algorithm. Finally, the usefulness of the emotions is suggested for various stake holders, to find the attitude of individuals at that moment, the data is produced. .
