改进的PSVM及其在非平衡数据分类中的应用

标准近似支持向量机(PSVM)没有考虑非平衡分布数据的分类问题,为此,在PSVM的基础上,将优化问题中的惩罚因子由数值变更为一个对角阵,提出了一种改进的PSVM算法。该方法利用引入的对角阵对正负样本分别分配不同的惩罚因子,由于其任意性,使得该算法可以解决由多种因素引起的分布不平衡的分类问题,稳健性较好。利用实值免疫克隆算法实现了模型参数的自动选择,进一步提高了算法的泛化性能。实验结果表明新算法对于处理分布不平衡数据的分类问题相当有效。     

选择式机器阅读理解综述

机器阅读理解是自然语言处理领域的研究热点之一,对提升机器阅读能力和智能水平有着重要意义,为跟进相关领域的研究进展对其进行综述。首先,介绍机器阅读理解的发展历程及主要任务;其次,重点梳理当前选择式机器阅读理解基于深度学习方法的相关工作,并从语义匹配、预训练模型、语义推理、外部知识四个方面展开叙述;归纳总结了相关数据集以及评价指标;最后,对选择式机器阅读理解的未来发展趋势进行了展望。     

Prediction of Anticancer Peptides with High Efficacy and Low Toxicity by Hybrid Model Based on 3D Structure of Peptides

Recently, anticancer peptides (ACPs) have emerged as unique and promising therapeutic agents for cancer treatment compared with antibody and small molecule drugs. In addition to experimental methods of ACPs discovery, it is also necessary to develop accurate machine learning models for ACP prediction. In this study, features were extracted from the three-dimensional (3D) structure of peptides to develop the model, compared to most of the previous computational models, which are based on sequence information. In order to develop ACPs with more potency, more selectivity and less toxicity, the model for predicting ACPs, hemolytic peptides and toxic peptides were established by peptides 3D structure separately. Multiple datasets were collected according to whether the peptide sequence was chemically modified. After feature extraction and screening, diverse algorithms were used to build the model. Twelve models with excellent performance (Acc > 90%) in the ACPs mixed datasets were used to form a hybrid model to predict the candidate ACPs, and then the optimal model of hemolytic peptides (Acc = 73.68%) and toxic peptides (Acc = 85.5%) was used for safety prediction. Novel ACPs were found by using those models, and five peptides were randomly selected to determine their anticancer activity and toxic side effects in vitro experiments.     

Parametric Evaluation of Video Motion Tracking Data Sets

Video tracking is a complex problem because the environment, in which video motion needs to be tracked, is widely varied based on the application and poses several constraints on the design and performance of the tracking system. Current datasets that are used to evaluate and compare video motion tracking algorithms use a cumulative performance measure without thoroughly analyzing the effect of these different constraints imposed by the environment. But it needs to analyze these constraints as parameters. The objective of this paper is to identify these parameters and define quantitative measures for these parameters to compare video datasets for motion tracking.     

基于Spark的近地表速度模型快速层析反演

近地表速度模型层析反演多采用基于初至旅行时射线追踪的迭代反演方法。通常采用基于共享存储的MPI并行方式提高计算效率,但当计算节点增至一定规模时会存在网络I/O压力过大的计算瓶颈。为此,提出了一种快速、稳健的基于Spark技术的近地表速度模型层析反演方法,采用分布式内存管理技术将迭代中重复计算的数据持久化至内存中,提高程序运行效率。同时,为了解决共享存储中随着节点规模扩大而产生网络I/O堵塞的瓶颈问题,在分布式存储环境下组织弹性分布式数据集(RDD),设计基本规约单位为深度方向的一维反演数据,基于Spark Shuffle在规约过程中分布并行规约,利用Spark调度器在各个进程中分配任务,实现并行计算。实际数据计算结果表明：在反演结果精度不变的情况下,相对于常规MPI并行技术,该实现方法能够大幅度降低迭代过程中产生的网络I/O;当计算节点较多时,计算效率能够提高4倍以上;并行加速比呈现类线性增长趋势。     

Fast neighborhood operations for images and volume data sets

This paper presents a new approach to carry out erosion, dilation and connected component labeling. We use the extreme vertices model, an orthogonal polyhedra representation, to describe binary images and volume data sets in a very efficient way.

Our proposal does not use a voxel-based approach but deals with the inner sections of the object. It allows to treat images and volumes indistinctly using the same algorithm and data structure with no overhead of memory and can be applied to manifold as well as non-manifold data. The connected component labeling algorithm actually detects non-manifold zones and permits to break or not the objects at these zones by an user-specified parameter.     

Halftoning colour volume datasets based on subdivision

The algorithm for halftoning 2D gray scale images based on subdivision was extended to the processing of colour volume datasets. Two main improvements were made. The first is adding a procedure to deal with cases with large errors so as to reduce the total quantizing error. The second is randomizing the directions in which errors are propagated, assuring the even distribution of the halftoned binary voxels. In addition, a method used to process large volume datasets was also proposed. The new algorithm is simple in principle, but produces good halftoning results, especially in the boundary regions. It is especially applicable in the data preparation for the rapid forming of coloured models and heterogeneous objects.     

泰晤士河潮汐河段水温和水化学特性对无脊椎动物的影响分析

采用长系列数据，分析了影响泰晤士河潮汐河段生态状况的主要因素。1915～2006年的监测数据表明其生态状况经历了污染、恢复和稳定3个阶段，20世纪40-60年代是污染最重的时期，伴随着较高的水温、氨氮和生化需氧量以及较低的溶解氧含量，该时期少有底栖无脊椎动物的记录。自60年代以来，随着水质的恢复，无脊椎动物也逐渐增多，其数量的波动与水化学指标，尤其是溶解氧具有相关性。尽管1960年以前的无脊椎动物和水质资料缺失比较严重，但仍需彻底整理和分析所有数据，以便在以后的研究中建立水质指标与无脊椎动物群落间的定量关系。     

多源雪深数据在中国的空间特征评估

积雪的年际和年内变化强烈地影响着区域及全球的水量平衡,同时,积雪反照率反馈也显著地影响着气候变化。目前长时间序列的格网雪深数据主要来自被动微波遥感及再分析资料,但不同数据之间存在着明显差异。基于多源雪深数据的评估,特别是空间特性的评估还很缺乏。因此,本研究选取了AMSR-E、WESTDC、GlobSnow、RA-Interim及MERRA2这5种雪深数据,以站点观测数据为参考真值,对它们进行了中国地区的空间误差对比及基于误差排序的相对表现分析。评估结果初步显示：①WESTDC在我国西北及东北积雪区表现较好,适合用于我国北方的雪深研究;②MERRA2在西北和东北积雪区也有较好的表现,但由于其分辨率较粗,缺乏细节的空间信息,因此认为比较适用于大区域的统计分析;③AMSR-E在我国中部和东南地区表现最好,因此认为适合我国中部及东南部的雪深研究。