基于孪生支持向量回归机的转炉炼钢终点预测

为了提高转炉炼钢的终点命中率，建立了一种新的转炉终点预测模型，实现了对转炉终点碳质量分数和温度的准确预测。模型采用K最近邻孪生支持向量机(KNNWTSVR)算法，将权重矩阵引入到目标函数中，并利用鲸群优化算法进行求解，提高了传统算法的性能；然后基于某炼钢厂260 t转炉的实际生产数据，建立了转炉炼钢终点预测模型。结果表明，预测模型的终点碳质量分数(误差±0.005%)和温度(误差±15 ℃)的终点单命中率分别为94%和88%，双命中率达到84%。与其他两种现有的建模方法相比，本模型取得了最优的预测效果。该方法满足转炉炼钢实际生产的需求，也可适用于钢铁冶金其他领域的数学建模。     

基于Word2Vec模型特征扩展的Web搜索结果聚类性能的改进

对于用户泛化和模糊的查询，将Web搜索引擎返回的列表内容聚类处理，便于用户有效查找感兴趣的内容。由于返回的列表由称为片段（snippet）的短文本组成，而传统的单词频率-逆文档频率（TF-IDF）特征选择模型不能适用于稀疏的短文本，使得聚类性能下降。一个有效的方法就是通过一个外部的知识库对短文本进行扩展。受到基于神经网络词表示方法的启发，提出了通过词嵌入技术的Word2Vec模型对短文本扩展，即采用Word2Vec模型的TopN个最相似的单词用于对片段（snippet）的扩展，扩展文档使得TF-IDF模型特征选择得到聚类性能的提高。同时考虑到通用性单词造成的噪声引入，对扩展文档的TF-IDF矩阵进行了词频权重修正。实验在两个公开数据集ODP239和SearchSnippets上完成，将所提方法和纯snippet无扩展的方法、基于Wordnet的特征扩展方法和基于Wikipedia的特征扩展方法进行了对比。实验结果表明，所提方法在聚类性能方面优于对比方法。     

DCNN深度特征与交替方向乘子的相关滤波跟踪

针对采用相关滤波的判别式目标跟踪遇到的瓶颈问题：由于目标快速移动引起边界效应，使得相关滤波器在学习与更新过程中可能会引入错误，最终错误的累积将导致跟踪失败。在采集深度学习特征与样本相似性度量的基础上，提出一种引入交替方向乘子方法的改进相关滤波目标跟踪算法，选择DCNN深度特征有效地表征待跟踪目标的初始状态，通过在线分类过程中样本相似性比对与半监督学习，辅助解决相关滤波器在学习过程中存在的自学习问题。所提目标跟踪算法特别适合训练样本为持续获得的、同时存储空间较小的机器学习过程，提高目标在快速运动与部分遮挡等复杂情况下的跟踪成功率，针对VOT2016标准测试视频的实验表明：当目标面临快速运动时，对比CN、SAMF、STC算法，所提DA-CFT跟踪算法将跟踪成功率分别由60.4%～73.4%、67.2%～82.9%、80.9%～88.1%提升至85.6%～91.0%。     

Extraction equilibrium conditions of beryllium and aluminium from a beryl ore for optimal industrial beryllium compound production

This study examines the extraction of beryllium and aluminium from a Nigerian beryl ore using Cyanex®272 in kerosene from an aqueous sulphate pregnant solution. Parameters such as extractant concentration and equilibrium pH that dictates the extraction yield were studied. Under the following conditions: temperature 27?±?2°C, phase ratio 1?1, about 45.50 and 46.76% of beryllium and aluminium were extracted by 0.15?mol?L^?1 Cyanex®272 concentration within 30?min. However, the extraction yield of beryllium and aluminium was increased to 91.68% and 97.89% at equilibrium pH of 3 and 4, respectively, for beryllium and aluminium at 27?±?2°C. A 0.05?mol?L^?1 H₂SO₄ solution was found to be adequate for the stripping of about 99.00% Be and 95.40% Al from the loaded organic phase. The pure solutions containing metal ions were accordingly beneficiated to obtain beryllium and aluminium compounds of industrial values.     

Specific emitter identification for satellite communication using probabilistic neural networks

Electromagnetic signal emitted by satellite communication (satcom) transmitters are used to identify specific individual uplink satcom terminals sharing the common transponder in real environment, which is known as specific emitter identification (SEI) that allows for early indications and warning (I&W) of the targets carrying satcom furnishment and furthermore the real time electromagnetic situation awareness in military operations. In this paper, the authors are the first to propose the identification of specific transmitters of satcom by using probabilistic neural networks (PNN) to reach the goal of target recognition. We have been devoted to the examination by exploring the feasibility of utilizing the Hilbert transform to signal preprocessing, applying the discrete wavelet transform to feature extraction, and employing the PNN to perform the classification of stationary signals. There are a total of 1000 sampling time series with binary phase shift keying (BPSK) modulation originated by five types of satcom transmitters in the test. The established PNNs classifier implements the data testing and finally yields satisfactory accuracy at 8 dB(±1 dB) carrier to noise ratio, which indicates the feasibility of our method, and even the keen insight of its application in military.     

应用膨胀算法提取目标的直接定位算法

为了解决被动雷达系统中的多发射源定位问题，提出了一种基于多重信号分类(MUSIC)算法和图像膨胀(IE)算法的直接定位方法。该方法结合了谱分析中的MUSIC思想，通过对接收量测协方差矩阵进行特征分析求解目标的位置。首先，在目标个数未知的前提下，利用Akaike信息准则(AIC)来确定模型阶数；然后，推导了基于MUSIC的定位代价函数；之后，利用图像膨胀算法处理得到的代价函数平面；最后，膨胀处理后的输出为目标个数及目标位置的估计值。提出的算法有效地解决了目标检测及提取的问题，能够确定多个目标的位置坐标，为后续的定位性能分析提供可能性，也保证了算法的完整性。进一步地分析了多个临近目标情况下影响目标提取性能的主要因素。     

A hybrid multiple feature construction approach for classification using Genetic Programming

The purpose of feature construction is to create new higher-level features from original ones. Genetic Programming (GP) was usually employed to perform feature construction tasks due to its flexible representation. Filter-based approach and wrapper-based approach are two commonly used feature construction approaches according to their different evaluation functions. In this paper, we propose a hybrid feature construction approach using genetic programming (Hybrid-GPFC) that combines filter’s fitness function and wrapper’s fitness function, and propose a multiple feature construction method that stores top excellent individuals during a single GP run. Experiments on ten datasets show that our proposed multiple feature construction method (Fcm) can achieve better (or equivalent) classification performance than the single feature construction method (Fcs), and our Hybrid-GPFC can obtain better classification performance than filter-based feature construction approaches (Filter-GPFC) and wrapper-based feature construction approaches (Wrapper-GPFC) in most cases. Further investigations on combinations of constructed features and original features show that constructed features augmented with original features do not improve the classification performance comparing with constructed features only. The comparisons with three state-of-art methods show that in majority of cases, our proposed hybrid multiple feature construction approach can achieve better classification performance.     

A Review on the Separation of Niobium and Tantalum by Solvent Extraction

Niobium and tantalum are found together in natural minerals. Leaching with concentrated acid solution or alkaline roasting followed by water/dilute acid leaching results in a solution containing these two metals. In this work, we reviewed the extraction and separation of Nb(V) and Ta(V) from leach liquors in the absence and presence of hydrofluoric acid by acidic, neutral extractants and amines. Several solvent extraction systems were compared in the light of the requirement of hazardous chemicals, extraction/separation efficiency, and stability/solubility of extractants. Since the cationic species of Nb(V) and Ta(V) are unstable in the aqueous solution, the application of acidic extractants for extraction and separation of these metals is limited. Amines can extract Nb(V) as well as Ta(V) irrespective of the presence of fluoride ion but the separation of these metals from the loaded amines should be carried out in stripping process, resulting in process complexity. Another disadvantage encountered for amine is related to high viscosity in extraction process. Neutral extractants are considered as promising extractants which are effective to separate Ta(V) and Nb(V) from either non-fluoride or to moderate fluoride ion concentration in terms of extraction, separation and stripping efficiency. Compared to the traditional methyl iso-butyl ketone (MIBK) based system, methyl isoamyl ketone (MIAK) is found to be a promising extractant to separate Nb(V) and Ta(V).     

Distant Supervised Relation Extraction with Cost-Sensitive Loss

Recently, many researchers have concentrated on distant supervision relation extraction (DSRE). DSRE has solved the problem of the lack of data for supervised learning, however, the data automatically labeled by DSRE has a serious problem, which is class imbalance. The data from the majority class obviously dominates the dataset, in this case, most neural network classifiers will have a strong bias towards the majority class, so they cannot correctly classify the minority class. Studies have shown that the degree of separability between classes greatly determines the performance of imbalanced data. Therefore, in this paper we propose a novel model, which combines class-to-class separability and cost-sensitive learning to adjust the maximum reachable cost of misclassification, thus improving the performance of imbalanced data sets under distant supervision. Experiments have shown that our method is more effective for DSRE than baseline methods.     

基于时空的弱点状运动目标检测技术

如何在复杂背景下持续有效地检测目标位置,一直是研究者们需要面对的主要挑战。本文在研究红外点状移动目标特征的基础上,根据目标无纹理,无形状的特性,提出一种改进的形态学目标增强算法,并利用目标连续时空不变性检测目标。首先,建立多尺度的图像金字塔,在每层上采用改进的形态学算法快速、粗糙定位小目标。然后进一步的根据目标在时空上的位置相关性,提出基于目标运动特征分析的精确检测方法。得到精确稳定的检测结果。最后实验结果表明与经典的形态学检测算法及其他算法相比,该技术能更有效地检测弱小目标,具有更高的鲁棒性。