两阶段领域自适应学习

针对领域自适应问题中源域和目标域的联合分布差异最小化问题,提出两阶段领域自适应学习方法.在第一阶段考虑样本标签和数据结构的判别信息,通过学习一个共享投影变换,使投影后的共享空间中边缘分布的差异最小.第二阶段利用源域标记数据和目标域非标记数据学习一个带结构风险的自适应分类器,不仅能最小化源域和目标域条件分布差异,还能进一步保持源域和目标域边缘分布的流形一致性.在3个基准数据集上的实验表明,文中方法在平均分类准确率和Kappa系数两项评价指标上均表现较优.     

基于平均距离聚类的NSGA-Ⅱ

拥挤度距离是一种用于度量解集多样性的指标. 然而, 在许多情况下, 该指标无法有效区分多样性较优个体. 其原因为拥挤度距离主要利用每个位置的局部信息. 为解决该问题, 基于整个种群全局位置信息, 本文设计了基于平均距离聚类的多样性度量指标, 并进一步提出了基于平均距离聚类的NSGA-Ⅱ. 该算法利用平均距离将种群划分为若干个大致均匀分布的小种群, 然后分别在各小种群内执行选择、交叉和变异等操作. 实验结果表明, 本文所提算法可以有效地保持种群多样性.     

基于深度学习的表面缺陷检测方法综述

近年来, 基于深度学习的表面缺陷检测技术广泛应用在各种工业场景中. 本文对近年来基于深度学习的表面缺陷检测方法进行了梳理, 根据数据标签的不同将其分为全监督学习模型方法、无监督学习模型方法和其他方法三大类, 并对各种典型方法进一步细分归类和对比分析, 总结了每种方法的优缺点和应用场景. 本文探讨了表面缺陷检测中三个关键问题, 介绍了工业表面缺陷常用数据集. 最后, 对表面缺陷检测的未来发展趋势进行了展望.     

基于示波法和高斯拟合的血压测量方法

流行病学调查及大规模前瞻性研究表明,高血压是心血管疾病的独立风险因素,采用电子血压计进行自助式日常血压监护,是预防严重心血管事件的重要途径。提出了一种设计电子血压计的新方法:首先确定振荡波中各个单波的峰值点;然后确定拟合振荡波包络线的最佳拟合曲线;进而查找包络线的最大值,选定积分区间,提出的积分公式和最大值的位置,确定舒张压和收缩压的位置,最后确定舒张压和收缩压。比较该方法与听诊法测得的血压,结果证明使用所介绍的方法测得的血压精度符合AAM I标准、BHS(B)级标准。说明该方法是适用的,使用该方法所设计的电子血压计可以用于血压的日常监护。     

Adaptive modelling of gene regulatory network using Bayesian information criterion‐guided sparse regression approach

Inferring gene regulatory networks (GRNs) from microarray expression data are an important but challenging issue in systems biology. In this study, the authors propose a Bayesian information criterion (BIC)‐guided sparse regression approach for GRN reconstruction. This approach can adaptively model GRNs by optimising the l ₁ ‐norm regularisation of sparse regression based on a modified version of BIC. The use of the regularisation strategy ensures the inferred GRNs to be as sparse as natural, while the modified BIC allows incorporating prior knowledge on expression regulation and thus avoids the overestimation of expression regulators as usual. Especially, the proposed method provides a clear interpretation of combinatorial regulations of gene expression by optimally extracting regulation coordination for a given target gene. Experimental results on both simulation data and real‐world microarray data demonstrate the competent performance of discovering regulatory relationships in GRN reconstruction.Inspec keywords: genetics, Bayes methods, genomics, regression analysis, inference mechanisms, bioinformaticsOther keywords: adaptive modelling, gene regulatory network, Bayesian information criterion‐guided sparse regression approach, GRN, microarray expression data, systems biology, GRN reconstruction, optimisation, l₁ ‐norm regularisation     

Microstructure and mechanical properties of three-dimensional oxide/oxide composite fabricated by a slurry infiltration and sintering process

Oxide/oxide composites reinforced by two-dimensional fiber fabrics are important structural materials at high temperatures but exhibit low delamination resistance. This study developed a simple slurry infiltration and sintering (SIS) process to fabricate three-dimensional oxide/oxide composites. The results showed that a homogeneous microstructure in three directions was obtained. This composite possessed a weak matrix, which had a porous structure and low elastic modulus. Typical mechanical properties of the composite were not lower than those of two-dimensional oxide/oxide composites since the flexural strength and fracture toughness were 332.4 MPa and 11.6 MPa·m^1/2, respectively. Particularly, the composite had a good interlaminar shear strength of 25.4 MPa and a superior transthickness tensile strength of 5.6 MPa. X-ray computed tomography showed that fiber yarns in the through-thickness direction effectively impeded crack propagation and enhanced delamination resistance. Therefore, the reported SIS process is a very promising method for manufacturing three-dimensional oxide/oxide composites.     

An approach to the evaluation of the performance of a discrete classifier

The problem studied is the behavior of a discrete classifier on a finite learning sample. With naive Bayes approach, the value of misclassification probability is represented as a random function, for which the first two moments are analytically derived. For arbitrary distributions, this allows evaluating learning sample size sufficient for the classification with given admissible misclassification probability and confidence level. The comparison with statistical learning theory shows that the suggested approach frequently recommends significantly smaller learning sample size.     

Building efficient CNN architecture for offline handwritten Chinese character recognition

Deep convolutional neural networks-based methods have brought great breakthrough in image classification, which provides an end-to-end solution for handwritten Chinese character recognition (HCCR) problem through learning discriminative features automatically. Nevertheless, state-of-the-art CNNs appear to incur huge computational cost and require the storage of a large number of parameters especially in fully connected layers, which is difficult to deploy such networks into alternative hardware devices with limited computation capacity. To solve the storage problem, we propose a novel technique called weighted average pooling for reducing the parameters in fully connected layer without loss in accuracy. Besides, we implement a cascaded model in single CNN by adding mid output to complete recognition as early as possible, which reduces average inference time significantly. Experiments are performed on the ICDAR-2013 offline HCCR dataset. It is found that our proposed approach only needs 6.9 ms for classifying a character image on average and achieves the state-of-the-art accuracy of 97.1% while requires only 3.3 MB for storage.     

非体力劳动男性静态平衡功能的研究

检测从事非体力劳动男性的静态平衡功能,探讨该人群各年龄段的平衡差异.采用自行研制的便携式人体平衡测试系统对15～65岁的男性人群(N=50)进行平衡功能检测.将该人群划分为5个年龄段,分别分析4种检测姿势(双脚睁眼和闭眼站立、睁眼单脚站立)总轨迹长度(Lng)、左右平均动摇速度(Vx)、前后平均动摇速度(Vy)3个观察...