WavNet — Visual saliency detection using Discrete Wavelet Convolutional Neural Network

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.     

Exploration of GH94 Sequence Space for Enzyme Discovery Reveals a Novel Glucosylgalactose Phosphorylase Specificity

The substantial increase in DNA sequencing efforts has led to a rapid expansion of available sequences in glycoside hydrolase families. The ever-increasing sequence space presents considerable opportunities for the search for enzymes with novel functionalities. In this work, the sequence-function space of glycoside hydrolase family 94 (GH94) was explored in detail, using a combined approach of phylogenetic analysis and sequence similarity networks. The identification and experimental screening of unknown clusters led to the discovery of an enzyme from the soil bacterium Paenibacillus polymyxa that acts as a 4-O-β-d -glucosyl-d -galactose phosphorylase (GGalP), a specificity that has not been reported to date. Detailed characterization of GGalP revealed that its kinetic parameters were consistent with those of other known phosphorylases. Furthermore, the enzyme could be used for production of the rare disaccharides 4-O-β-d -glucosyl-d -galactose and 4-O-β-d -glucosyl-l -arabinose. Our current work highlights the power of rational sequence space exploration in the search for novel enzyme specificities, as well as the potential of phosphorylases for rare disaccharide synthesis.     

IRS辅助的SWIPT系统中基于能效优先的波束成形设计与优化

以智能反射面(intelligent reflecting surface,IRS)辅助的无线携能通信(simultaneous wireless information and power transfer,SWIPT)系统为背景,研究了该系统中基于能效优先的多天线发送端有源波束成形与IRS无源波束成形联合设计与优化方法。以最大化接收端的最小能效为优化目标,构造在发送端功率、接收端能量阈值、IRS相移等多约束下的非线性优化问题,用交替方向乘子法(alternating direction method of multipliers,ADMM)求解。采用Dinkelbach算法转化目标函数,通过奇异值分解(singular value decomposition,SVD)和半定松弛(semi-definite relaxation,SDR)得到发送端有源波束成形向量。采用SDR得到IRS相移矩阵与反射波束成形向量。结果表明,该系统显著降低了系统能量收集(energy harvesting,EH)接收端的能量阈值。当系统总电路功耗为?15 dBm时,所提方案的用户能效为300 KB/J。当IRS反射阵源数与发送天线数均为最大值时,系统可达最大能效。     

Practical Application of the Probabilistic‐Statistical Model of the Suspension Separation in Hydrocyclones

An effective practical approach that allows not only a significant reduction in the scope of practical experiments in the course of studying suspension separation processes in hydrocyclones, but also makes it possible to assess the intensity of random components of the processes and define the interrelation between such components and hydrodynamics of flows in a hydrocyclone is presented. Within the frames of the developed probabilistic‐statistical model of suspension separation in hydrocyclones on the basis of statistical self‐similarity properties, a relationship was found between determined and random components of the processes. This allowed transitioning from three‐parameter probability density functions for suspension particles in hydrocyclones to two‐parameter functions; thus significantly improving the efficiency of practical application of the developed model.     

波形驱动下多参数约束高分辨率反演方法——以四川盆地渝西地区龙马溪组页岩气为例

基于叠后地震波形指示反演在薄储层预测方面的优势，以及叠前弹性参数较叠后弹性参数信息更丰富、对储层的敏感性更高的特点，根据岩石物理资料，应用地震驱动+储层构型约束的高精度叠前随机反演方法，探寻定量表征优质薄页岩的技术，以期为深层页岩气地质甜点预测提供技术支撑。首先，基于道集波形相似性、AVO特征和空间距离的三变量优选方法提取结构相似的井数据作为空间估值样本，然后建立待判别道集初始模型；其次，以统计的弹性阻抗作为先验信息，应用“基于叠前道集特征指示的马尔科夫链-蒙特卡洛随机模拟算法”进行叠前地震波形指示反演，最终得到高精度的叠前弹性参数反演成果。实际应用表明，应用所提方法有效预测了龙一段一亚段1-2小层优质页岩厚度，基于特征参数的井震高频模拟精确模拟了龙一段一亚段1-2小层地质甜点参数，为页岩气勘探提供了技术支撑。     

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%。     

The generalized Dice similarity measures for Pythagorean fuzzy multiple attribute group decision making

The Pythagorean fuzzy set (PFS) is characterized by two functions expressing the degree of membership and the degree of nonmembership, which square sum of them is equal or less than 1. It was proposed as a generalization of a fuzzy set to deal with indeterminate and inconsistent information. In this study, we shall present some novel Dice similarity measures of PFSs and the generalized Dice similarity measures of PFSs and indicates that the Dice similarity measures and asymmetric measures (projection measures) are the special cases of the generalized Dice similarity measures in some parameter values. Then, we propose the generalized Dice similarity measures-based multiple attribute group decision-making models with Pythagorean fuzzy information. Then, we apply the generalized Dice similarity measures between PFSs to multiple attribute group decision making. Finally, an illustrative example is given to demonstrate the efficiency of the similarity measures for selecting the desirable ERP system.     

Distance and similarity measures of Pythagorean fuzzy sets based on the Hausdorff metric with application to fuzzy TOPSIS

Pythagorean fuzzy sets (PFSs) were proposed by Yager in 2013 to treat imprecise and vague information in daily life more rigorously and efficiently with higher precision than intuitionistic fuzzy sets. In this paper, we construct new distance and similarity measures of PFSs based on the Hausdorff metric. We first develop a method to calculate a distance between PFSs based on the Hasudorff metric, along with proving several properties and theorems. We then consider a generalization of other distance measures, such as the Hamming distance, the Euclidean distance, and their normalized versions. On the basis of the proposed distances for PFSs, we give new similarity measures to compute the similarity degree of PFSs. Some examples related to pattern recognition and linguistic variables are used to validate the proposed distance and similarity measures. Finally, we apply the proposed methods to multicriteria decision-making by constructing a Pythagorean fuzzy Technique for Order Preference by Similarity to an Ideal Solution and then present a practical example to address an important issue related to social sector. Numerical results indicate that the proposed methods are reasonable and applicable and also that they are well suited in pattern recognition, linguistic variables, and multicriteria decision-making with PFSs.     

面向智能客服的句子相似度计算方法

针对金融领域中智能客服的句子相似度计算方法进行了研究。利用基于词性的分词纠正模型减少中文歧义词、金融相关词汇的分词错误；通过词向量方法和循环神经网络分别提取词语级和句子级的语义特征，并且得到句子向量；用融合层计算出句子向量间的差异特征；对差异特征进行降维和归一化得到句子相似度计算结果。实验结果表明，该方法具有较高的准确率和[F1]值。     

区分站点状态的两级轮询控制系统

针对提高轮询控制模型工作效率和区分网络优先级的问题，提出了区分站点忙闲状态的完全-门限两级轮询控制模型（ETTPSS）。模型以两级优先级为基础，依据站点的忙闲状态采用并行处理方式只对忙站点进行信息分组发送服务。模型既能区分传输服务优先级又能避开对无信息分组的空闲站点的查询，从而提高了模型资源利用率和工作效率。运用概率母函数与马尔可夫链相结合的方法对该模型进行理论分析研究，精确解析了模型各个重要性能参数。仿真实验结果表明，仿真值与理论值近似相等，说明理论分析正确合理。与普通轮询模型相比，该模型性能大幅度提高。