NASA深空网的改造计划及进展

详细介绍了美国的深空网增强计划及进展。     

转化学习理论视域下虚拟学习共同体中深度学习发生机制设计

深度学习指要求学习者能够批判性地进行学习,反思自身原有的认知结构并在此基础上建构新知识的一种学习方式,它有利于培养学习者的高级思维能力。在终身学习的大背景下,学习者要不断提升自己的学习层次,适应新情况,探索新问题,拥有较强的学习能力,因而深度学习的教学价值潜力不言而喻。在转化学习理论的指导下,借助学习共同体环境,对深度学习的发生机制进行了设计,期望引导学习者在解决问题的过程中提升学习能力。     

Key phrase aware transformer for abstractive summarization

Abstractive summarization aims to generate a concise summary covering salient content from single or multiple text documents. Many recent abstractive summarization methods are built on the transformer model to capture long-range dependencies in the input text and achieve parallelization. In the transformer encoder, calculating attention weights is a crucial step for encoding input documents. Input documents usually contain some key phrases conveying salient information, and it is important to encode these phrases completely. However, existing transformer-based summarization works did not consider key phrases in input when determining attention weights. Consequently, some of the tokens within key phrases only receive small attention weights, which is not conducive to encoding the semantic information of input documents. In this paper, we introduce some prior knowledge of key phrases into the transformer-based summarization model and guide the model to encode key phrases. For the contextual representation of each token in the key phrase, we assume the tokens within the same key phrase make larger contributions compared with other tokens in the input sequence. Based on this assumption, we propose the Key Phrase Aware Transformer (KPAT), a model with the highlighting mechanism in the encoder to assign greater attention weights for tokens within key phrases. Specifically, we first extract key phrases from the input document and score the phrases’ importance. Then we build the block diagonal highlighting matrix to indicate these phrases’ importance scores and positions. To combine self-attention weights with key phrases’ importance scores, we design two structures of highlighting attention for each head and the multi-head highlighting attention. Experimental results on two datasets (Multi-News and PubMed) from different summarization tasks and domains show that our KPAT model significantly outperforms advanced summarization baselines. We conduct more experiments to analyze the impact of each part of our model on the summarization performance and verify the effectiveness of our proposed highlighting mechanism.     

Understanding information diffusion with psychological field dynamic

Several approaches focus on how to automatically capture the latent features from original diffusion data and predict the future scale of cascades utilizing a black box framework. However, they ignore the penetrating insight into the underlying mechanism that how each participant is involved in the cascade. In this work, we bridge the gap between prediction and understanding of information diffusion by incorporating deep learning techniques and social psychology. To characterize individual participation driven by both subjective and objective impetus and integrate it into the macro-level cascade, we propose an end-to-end model, named PFDID, which is designed based on the field dynamics theory of psychology, including the intrinsic cognition field and the extrinsic environment field. We represent these two field dynamics respectively with the pairwise semantic relation between the message itself and corresponding comment and the forwarder’s micro-community activity embedding to provide educated explanations for forwarding behaviour. Afterwards, the cross infusion mechanism is designed to calculate the mutual influence of inhomogeneous field dynamics inside users and cross influence of homogeneous field dynamics among individuals, whose output is fed into the diffusion network aggregation layer for the cascade size prediction. Extensive experiments on two typical social networks, Sina Weibo and Twitter, manifest that the proposed PFDID outperforms state-of-the-art approaches. Our model achieves excellent prediction results, with MSLE = 1.856 on Sina Weibo and MSLE = 1.962 on Twitter, providing 6.54% and 10.53% relative performance gains, respectively. Furthermore, the interpretability is also discussed based on detailed visualization. We observe that the psychological impetus behind social behaviour varies mainly following two patterns with the spread of information, including gradual change and joint influence. Additionally, the indirect dependencies have also been verified.     

Ensemble unsupervised autoencoders and Gaussian mixture model for cyberattack detection

Previous studies have adopted unsupervised machine learning with dimension reduction functions for cyberattack detection, which are limited to performing robust anomaly detection with high-dimensional and sparse data. Most of them usually assume homogeneous parameters with a specific Gaussian distribution for each domain, ignoring the robust testing of data skewness. This paper proposes to use unsupervised ensemble autoencoders connected to the Gaussian mixture model (GMM) to adapt to multiple domains regardless of the skewness of each domain. In the hidden space of the ensemble autoencoder, the attention-based latent representation and reconstructed features of the minimum error are utilized. The expectation maximization (EM) algorithm is used to estimate the sample density in the GMM. When the estimated sample density exceeds the learning threshold obtained in the training phase, the sample is identified as an outlier related to an attack anomaly. Finally, the ensemble autoencoder and the GMM are jointly optimized, which transforms the optimization of objective function into a Lagrangian dual problem. Experiments conducted on three public data sets validate that the performance of the proposed model is significantly competitive with the selected anomaly detection baselines.     

Demand forecasting model using hotel clustering findings for hospitality industry

Tourism has become a growing industry day by day with the developing economic conditions and the increasing communication and social interaction ability of the people. Forecasting tourism demand is not only important for tourism operators to maximize their revenues but also important for the formation of economic plans of the countries on a global scale. Based on the predictions countries are able to regulate the sectors that benefit economically from tourism locally. Therefore, it is crucial to accurately predict the demand in many weeks advance. In this study, we propose a new demand forecasting model for the hospitality industry that forecasts weekly hotel demand four weeks in advance through Attention-Long Short Term Memory (Attention-LSTM). Unlike most of the existing methods, the proposed method utilizes the time series demand data together with additional features obtained from K-Means Clustering findings such as Top 10 Hotel Features or Hotel Embeddings obtained using Neural Networks (NN). While creating our model, the clustering part was influenced by the fact that travelers choose their accommodation according to certain criteria, and the hotels meeting similar criteria may have similar demands. Therefore, before the clustering part, we also applied methods that would enable us to represent the features of the hotels more properly and we observed that 10-D Embedded Hotel Data representation with NN Embeddings came to the fore. In order to observe the performance of the proposed hotel demand forecasting model we used a real-world dataset provided by a tourism agency in Turkey and the results show that the proposed model achieves less mean absolute error and mean absolute percentage error (at worst % 3 and at most % 29 improvements) compared to the currently used machine learning and deep learning models.     

瞬变电磁测深在小秦岭大湖金钼矿床深部找矿中的应用

大湖金矿位于小秦岭金矿田北矿带的东部,是小秦岭地区一个大型石英脉型金、钼矿床,目前主要勘探中深部矿产资源。本文结合矿区地质、地球物理特征,在其所判定的成矿远景区,开展了瞬变电磁测深法找矿工作,圈定电性异常体,指导钻探工程的布设,取得了较好的找矿效果,对小秦岭其它地区深部勘探工作具有一定的参考价值。     

血浆纤维蛋白原水平升高同高血压,冠心病及卒中的联系

选择46岁以上的高血压(HBP)、冠心病(CHD)、卒中及其它内科住院病人共140名进行了血浆纤维蛋白原(FG)、血压、甘油三酯(TG)和吸烟等因素的观察.结果表明高血压、冠心病和车中患者FG值升高,逐步回归分析看出吸烟,HBP和TG水平升高明显影响FG的含量,提示FG水平升高同HBP,CHD和年中存在着紧密的联系。     

Predicting citation counts based on deep neural network learning techniques

With the growing number of published scientific papers world-wide, the need to evaluation and quality assessment methods for research papers is increasing. Scientific fields such as scientometrics, informetrics, and bibliometrics establish quantified analysis methods and measurements for evaluating scientific papers. In this area, an important problem is to predict the future influence of a published paper. Particularly, early discrimination between influential papers and insignificant papers may find important applications. In this regard, one of the most important metrics is the number of citations to the paper, since this metric is widely utilized in the evaluation of scientific publications and moreover, it serves as the basis for many other metrics such as h-index. In this paper, we propose a novel method for predicting long-term citations of a paper based on the number of its citations in the first few years after publication. In order to train a citation count prediction model, we employed artificial neural network which is a powerful machine learning tool with recently growing applications in many domains including image and text processing. The empirical experiments show that our proposed method outperforms state-of-the-art methods with respect to the prediction accuracy in both yearly and total prediction of the number of citations.     

论浅阅读时代图书馆的书评工作

本文通过对时下流行的浅阅读现象产生的社会背景以及负面影响的解读,探讨图书馆在浅阅读时代,如何利用书评的信息功能,影响读者的阅读倾向,激发读者的阅读和求知兴趣,做好指导读者正确阅读书籍内容,深入理解作品的思想内涵,提高阅读鉴别能力和欣赏水平的工作,更好地实现让读者读到有思想力度和精神厚度的图书这一目标.