基于改进BP神经网络的智能控制方法研究

针对典型BP神经网络存在的缺陷提出了一些有效的改进措施。通过采用改进的BP神经网络来对控制规则样本进行学习和训练 ,使网络记忆控制规则 ,以达到智能控制的目的。仿真和实验结果证明 ,该方法具有优良的控制特性 ,能满足伺服电机控制的需要。     

Parametric adaptive time-frequency representation based on time-sheared Gabor atoms

A localized parametric time-sheared Gabor atom is derived by convolving a linear frequency modulated factor, modulating in frequency and translating in time to a dilated Gaussian function, which is the generalization of Gabor atom and is more delicate for matching most of the signals encountered in practice, especially for those having frequency dispersion characteristics. The time-frequency distribution of this atom concentrates in its time center and frequency center along energy curve, with the curve being oblique to a certain extent along the time axis. A novel parametric adaptive time-frequency distribution based on a set of the derived atoms is then proposed using a adaptive signal subspace decomposition method in frequency domain, which is non-negative time-frequency energy distribution and free of cross-term interference for multicomponent signals. The results of numerical simulation manifest the effectiveness of the approach in time-frequency representation and signal de-noising processing.     

Best tracking performance for integrator and dead time plant

The optimal tracking performance for integrator and dead time plant in the case where plant uncertainty and control energy constraints axe to be considered jointly is inrestigated.Firstly,an average cost function of the tracking error and the plant input energy over a class of stochastic model errors are defined.Then,we obtain an internal model controller design method that minimizes the average performance and further studies optimal tracking performance for integrator and dead time plant in the simultaneous presence of plant uncertainty and control energy constraint.The results can be used to evaluate optimal tracking performance and control energy in practical designs.     

一种更优的精度控制故障树解算方法

本文针对安全分析方法中故障树解算问题提出了一种完全依赖于所要求精度的近似算法——精度取舍法。详细给出了近似求解顶事件概率值的两个截断条件。结论表明,它在同时兼顾精度与时间的要求方面优于别的算法。     

科技型中小企业技术创新的资金支持——基于生命周期视角的研究

基于生命周期的视角分析了科技型中小企业发展过程中各个阶段的特点,以及各个阶段中技术创新与资金支持的矛盾.在新的经济环境与政策条件下,构建了解决这种矛盾的资金支持体系,探讨了企业发展和技术创新过程中具体的融资方式,并且提出了相关的政策建议.     

子宫动脉栓塞术在难治性产后出血中的应用

目的:探讨子宫动脉栓塞术在产后出血中的应用。方法:对2008年3月—2011年1月铜川市妇幼保健院及泾阳县医院共10例产后出血应用双侧子宫动脉选择性造影及栓塞术后的观察效果。结果:10例产后出血患者经过双侧子宫动脉选择性造影及栓塞术后,止血时间3～8min,手术时间30～50min,DSA表现为宫腔内弥漫性、局灶性或单侧子宫动脉分支出血。10例均恢复月经周期,子宫得以保留,随访3-6月无严重并发症。结论:对难治性产后出血应用子宫动脉栓塞术微创临床效果好。     

基于新型空间注意力机制和迁移学习的垃圾图像分类算法

随着我国各级政府大力推动垃圾强制分类,分类回收各环节中实现标准化、自动化的垃圾分类识别需要适合云端部署的高准确率、低延时要求的细粒度图像分类模型.本文发挥深度迁移学习的优势建立了一套端到端的迁移学习网络架构GANet (garbage neural network);针对垃圾分类中类别易混淆、背景干扰等挑战,提出一种新型的像素级空间注意力机制PSATT (pixel-level spatial attention).为克服类别多和样本不平衡挑战,提出使用标签平滑正则化损失函数;为改善收敛速度以及模型稳定性与泛化性,提出了阶梯形OneCycle学习率控制方法,并给出了结合Rectified Adam (RAdam)优化方法和权重平滑处理技术的组合使用策略.实验使用了"华为云人工智能大赛.垃圾分类挑战杯"提供的按照深圳市垃圾分类标准标注的训练数据,验证了GANet在垃圾分类问题中的显著效果,获得了全国二等奖(第2名);同时,提出的PSATT机制优于对比方法,且在不同主干网络架构上均得到了提升,具有良好的通用性.本文提出的GANet架构、PSATT机制和训练策略不仅具有重要的工程参考价值,也具有较好的学术价值.     

Exome sequencing of liver fluke-associated cholangiocarcinoma

Opisthorchis viverrini-related cholangiocarcinoma (CCA), a fatal bile duct cancer, is a major public health concern in areas endemic for this parasite. We report here whole-exome sequencing of eight O. viverrini-related tumors and matched normal tissue. We identified and validated 206 somatic mutations in 187 genes using Sanger sequencing and selected 15 genes for mutation prevalence screening in an additional 46 individuals with CCA (cases). In addition to the known cancer-related genes TP53 (mutated in 44.4% of cases), KRAS (16.7%) and SMAD4 (16.7%), we identified somatic mutations in 10 newly implicated genes in 14.8-3.7% of cases. These included inactivating mutations in MLL3 (in 14.8% of cases), ROBO2 (9.3%), RNF43 (9.3%) and PEG3 (5.6%), and activating mutations in the GNAS oncogene (9.3%). These genes have functions that can be broadly grouped into three biological classes: (i) deactivation of histone modifiers, (ii) activation of G protein signaling and (iii) loss of genome stability. This study provides insight into the mutational landscape contributing to O. viverrini-related CCA.     

A genome-wide association study in Han Chinese identifies new susceptibility loci for ankylosing spondylitis

To identify susceptibility loci for ankylosing spondylitis, we performed a two-stage genome-wide association study in Han Chinese. In the discovery stage, we analyzed 1,356,350 autosomal SNPs in 1,837 individuals with ankylosing spondylitis and 4,231 controls; in the validation stage, we analyzed 30 suggestive SNPs in an additional 2,100 affected individuals and 3,496 controls. We identified two new susceptibility loci between EDIL3 and HAPLN1 at 5q14.3 (rs4552569; P = 8.77 × 10(-10)) and within ANO6 at 12q12 (rs17095830; P = 1.63 × 10(-8)). We also confirmed previously reported associations in Europeans within the major histocompatibility complex (MHC) region (top SNP, rs13202464; P < 5 × 10(-324)) and at 2p15 (rs10865331; P = 1.98 × 10(-8)). We show that rs13202464 within the MHC region mainly represents the risk effect of HLA-B*27 variants (including HLA-B*2704, HLA-B*2705 and HLA-B*2715) in Chinese. The two newly discovered loci implicate genes related to bone formation and cartilage development, suggesting their potential involvement in the etiology of ankylosing spondylitis.     

经济落后地区城市规划区范围界定研究——以安徽省涡阳县为例

首先指出目前我国出现的大城市将市域范围全部纳入规划区的现象,阐述经济落后地区不适合采取大城市的做法的原因,接着分析了<城乡规划法>规定的规划区的内涵,指出我国目前规划区划定存在的主要问题,最后以安徽省涡阳县为例,小议对经济落后地区规划区范围界定的研究和认识.