Chinese-based research on subject-covered information retrieval supervised by textual semantic domain

By means of analysis of artificial intervention in ready-retrieved text, training set used to compare with new texts from large-scale real texts corpus is provided. It is based on the data-originated presentation of training set that a special formula to calculate semantic cohesion between new texts and training set is devised. The semantic cohesion of new text is the average value of semantic evaluation of all elements involved, and semantic evaluation of an element depends on its semantic relevance with the training set and on the semantic ratio of its domain to synonymous domain. In terms of empirical verification a conclusion is drawn that semantic cohesion is the key measurement standard of textual retrieval. Despite the advantages of textual retrieval, limitations of formula-raised condition and analyst＇s accomplishments make the analysis involved in this paper imperfect.     

基于动态贝叶斯网络的社交圈归属匹配模型

为了帮助社交网中新成员寻找与之最为合适的社交圈,尝试采用动态贝叶斯网（DBN）理论解决社交网分析应用中成员（节点）与社交圈（集合）的匹配问题。将圈内成员个人的多项兴趣爱好程度作为描述社交圈基本属性的特征向量,对每一类圈子建立了带有辅助信息形式的DBN模型,求解最大输出概率即为最佳匹配对象。结果表明,在客观测试和主观评价两方面,该模型都收到了较为满意的结果。     

军用嵌入式系统发展思考

当前各军种嵌入式系统往往都是根据自身的需要,研制适合自身需求的计算机,结果造成各军种间计算机的硬件、软件“烟囱”式发展,品种型号繁多,兼容性差,难以取得统一标准。由当前陆军一体化的建设思路,对军用嵌入式系统的发展提出一些思考。     

基于多流网络一致性的视频显著性检测

现有的视频显著性检测算法通常采用双流结构提取视频的时空线索,其中运动信息作为双流结构的一个分支,在显著物体发生剧烈或慢速移动时存在运动估计准确率低的问题,并且不合理的训练数据或方案使得权重偏向单个分支结构。提出一种基于多流网络一致性的视频显著性检测算法MSNC。设计并使用一种新的三重网络结构提取预选目标区域的颜色信息、时序信息和先验特征,通过先验特征补偿运动流的缺陷,并提高运动线索的利用率。采用多流一致性融合模型优化三流分支,得到不同特征的最佳融合方案。同时通过循环训练策略平衡三重网络的权重,以避免网络过度拟合单流分支,从而有效地提高运动估计和定位的准确率。在Davis数据集上的实验结果表明,相比PCSA、SSAV、MGA等算法,该算法的鲁棒性更优,其maxF和S-Measure值分别达到0.893和0.912,MAE仅为0.021。     

Compact,ultra-low vibration,closed-cycle helium recycler for uninterrupted operation of MEG with SQUID magnetometers

A closed-cycle helium recycler was developed for continuous uninterrupted operation for magnetometer-based whole-head magnetoencephalography (MEG) systems. The recycler consists of a two stage 4 K pulse-tube cryocooler and is mounted on the roof of a magnetically shielded room (MSR). A flexible liquid helium (LHe) return line on the recycler is inserted into the fill port of the MEG system in the MSR through a slotted opening in the ceiling. The helium vapor is captured through a line that returns the gas to the top of the recycler assembly. A high-purity helium gas cylinder connected to the recycler assembly supplies the gas, which, after it is liquefied, increases the level of LHe in the MEG system during the start-up phase. No storage tank for evaporated helium gas nor a helium gas purifier is used. The recycler is capable of liquefying helium with a rate of ∼17 L/d after precooling the MEG system. It has provided a fully maintenance-free operation under computer control for 7 months without refill of helium. Although the recycler is used for single-orientation operation at this initial testing site, it is designed to operate at ±20° orientations, allowing the MEG system to be tilted for supine and reclining positions. Vibration of the recycler is dampened to an ultra-low level by using several vibration isolation methods, which enables uninterrupted operation during MEG measurements. Recyclers similar to this system may be quite useful even for MEG systems with 100% magnetometers.     

Neural Machine Translation by Fusing Key Information of Text

When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are translated incorrect, the final translation results’ quality can still be guaranteed. In order to solve the problem of mistranslation and missed translation effectively, and improve the accuracy and completeness of long sentence translation in machine translation, this paper proposes a key information fused neural machine translation model based on Transformer. The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder. After the same encoding as the source language text, it is fused with the output of the source language text encoded by the encoder, then the key information is processed and input into the decoder. With incorporating keyword information from the source language sentence, the model’s performance in the task of translating long sentences is very reliable. In order to verify the effectiveness of the method of fusion of key information proposed in this paper, a series of experiments were carried out on the verification set. The experimental results show that the Bilingual Evaluation Understudy (BLEU) score of the model proposed in this paper on the Workshop on Machine Translation (WMT) 2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset. The experimental results show the advantages of the model proposed in this paper.     

社交网站监管法律问题研究

本文着重分析了社交网站常见的法律问题,并通过比较研究各国的做法,试图总结出我国加强社交网站管理的监管措施。     

创新实践教学模式,培养复合型人才

针对目前高校现行实践教学体制存在的弊端,在分析产生原因的基础上,提出一种科学的实践教学模式,该模式与信息与计算科学专业培养的目标以及社会发展的内在需求相结合,在信息处理和软件开发能力培养方面取得一定效果,增强了学生就业竞争力。     

A level set method based on the Bayesian risk for medical image segmentation

This paper proposes an alternative criterion derived from the Bayesian risk classification error for image segmentation. The proposed model introduces a region-based force determined through the difference of the posterior image densities for the different classes, a term based on the prior probability derived from Kullback-Leibler information number, and a regularity term adopted to avoid the generation of excessively irregular and small segmented regions. Compared with other level set methods, the proposed approach relies on the optimum decision of pixel classification and the estimates of prior probabilities; thus the approach has more reliability in theory and practice. Experiments show that the proposed approach is able to extract the complicated shapes of targets and robust for various types of medical images. Moreover, the algorithm can be easily extendable for multiphase segmentation.     

网络信息安全问题的法律探析

网络技术的发展以及应用深刻地影响着人类社会,在给人类带来巨大便利的同时也带来了诸如网络信息安全问题等隐患,这不仅在技术层面给我们提出新的问题,在法律层面也提出了更高的要求。本文介绍了对网络信息安全问题进行法理探讨的背景,并且在分析了国内外研究现状的基础上提出在法律层面解决网络信息安全问题的初步构想。