Automation and ISO 17025 test validation of a Toxoplasma Gondii antibodies enzyme-linked immunosorbent assay

The authors automated an enzyme-linked immunosorbent assay to detect porcine serum antibodies to Toxoplasma gondii. Two thousand swine sera can be assayed in two eight-hour shifts using a robotic workstation. The automated-ELISA programming is not complex and the test configuration is flexible. This high-throughput screening (HTS) a-ELISA can achieve a 10-fold increase (100→1000 tests) in test capacity over the manual method. The assay has been validated according to the requirements of the ISO/IEC 17025 standard. These include repeatability, reproducibility, and optimal threshold value studies. Other requirements are proficiency panel testing, analyst training, standard operation procedure, and equipment certifications.     

A Critical Analysis of PSP Data Quality: Results from a Case Study

The Personal Software Process (PSP) is used by software engineers to gather and analyze data about their work. Published studies typically use data collected using the PSP to draw quantitative conclusions about its impact upon programmer behavior and product quality. However, our experience using PSP led us to question the quality of data both during collection and its later analysis. We hypothesized that data quality problems can make a significant impact upon the value of PSP measures—significant enough to lead to incorrect conclusions regarding process improvement. To test this hypothesis, we built a tool to automate the PSP and then examined 89 projects completed by ten subjects using the PSP manually in an educational setting. We discovered 1539 primary errors and categorized them by type, subtype, severity, and age. To examine the collection problem we looked at the 90 errors that represented impossible combinations of data and at other less concrete anomalies in Time Recording Logs and Defect Recording Logs. To examine the analysis problem we developed a rule set, corrected the errors as far as possible, and compared the original and corrected data. We found significant differences for measures such as yield and the cost-performance ratio, confirming our hypothesis. Our results raise questions about the accuracy of manually collected and analyzed PSP data, indicate that integrated tool support may be required for high quality PSP data analysis, and suggest that external measures should be used when attempting to evaluate the impact of the PSP upon programmer behavior and product quality.     

基于SVM的大样本集系统辨识与函数拟合仿真

支持向量机是一种优秀的学习方法,也是具有很好泛化性能的回归方法。但由于支持向量机算法实习复杂,效率低,严格限制了其应用,SMO算法的提出大大提高了支持向量机的学习效率。因此,借助SMO算法,便可以实现大样本集的非线性系统辨识和函数拟合。文中对回归问题的SMO算法作了详细介绍,并对其进行改进。然后研究了利用改进SMO算法的非线性系统辨识方法,给出了非线性系统的辨识的仿真结果,和一维二维函数的拟合仿真。并通过仿真,与原始算法进行了比较,显示了改进SMO算法的快速性。     

高通量测序数据分析现状与挑战

基因是遗传的物质基础。生物体的生、长、病、老、死等一切生命现象都与基因有关。基因测序是解读生命的一种途径。随着新一代高通量测序技术的发展,每天会产生TB甚至更多的序列数据。合理诠释这些大规模及复杂高维度的数据成为获取数据后一个更大的难点,是当前生物研究的关键步骤,具有巨大的现实意义。海量高通量测序数据的存储、处理和分析都极大地挑战着当前的计算机系统和计算模式。本文将结合调研情况,尤其是华大基因的实例调研,讨论当前高通量测序数据分析的现状、问题和多方采取的措施。然而,面对高通量测序数据带来的挑战,仍需要多方密切合作和长久深入的研究。     

基于大规模网络语料的藏文音节拼写错误统计与分析

针对从互联网获取的一份包含19万藏文网页,总计427万句、9 328万音节字的藏文文本语料,该文按照预定的规则对其中的藏文音节拼写错误情况进行了统计与分析。数据显示,在语料中出现的共计20 743个藏文音节中,含有拼写错误的音节共有9 700个,占藏文音节总数的46.762 8%,错误音节在语料中共出现27 427次,仅占0.030 8%,说明这份语料的文本质量是相当高的。文中还详细统计了各种不同表现形式的错误音节所占比重,并分析了导致拼写错误的四个主要原因: 一是输入了多余的元音符号;二是音节点或句尾空格缺失;三是同一字丁/字符存在多种表达形式;四是错误地使用了相似字符。     

基于改进灰狼算法和多核极限学习机的铁水硅含量预测建模

针对高炉铁水硅含量难以在线检测的问题,本文提出一种基于改进灰狼算法(IGWO)优化的多核极限学习机(MKELM)高炉铁水硅含量预测建模方法.首先,针对灰狼算法(GWO)寻优能力的不足,将最优–最差正交反向学习(OWOOBL)策略应用于灰狼算法的位置更新,得到一种改进灰狼优化算法.通过10种标准函数对所提算法进行仿真测试,结果表明此算法具有更好的寻优能力.其次,针对单核极限学习机(KELM)回归能力不足,将不同种类的核函数加权组合,并采用改进灰狼算法对多核极限学习机中的加权系数等参数进行优化.最后,基于某钢厂的实测数据对高炉铁水硅含量进行预测建模,仿真结果表明,本文所提方法的预测效果优于反向传播神经网络(BP–NN)、极限学习机(ELM)、KELM和GWO–MKELM,对高炉炼铁具有较好的指导意义.     

基于视觉数据融合和机器学习算法的在役桥梁病害智能检测方法

为了准确检测在役桥梁病害问题，研究了基于视觉数据融合和机器学习算法的在役桥梁病害智能检测方法。采用雷达与视觉数据融合的无人机航拍技术，采集和定位在役桥梁高清图像；构建基于Ｍask R-CNN卷积神经网络的在役桥梁病害检测模型，通过迁移学习法动态优化训练检测模型，得出最优的在役桥梁病害检测模型；对定位到的在役桥梁高清图像进行去噪增强处理，输入该检测模型进行分类识别，输出病害检测结果。实验结果表明：该方法可以快速准确检测出多种在役桥梁病害，减少误检和漏检，实现一图多病害的精细化检测。     

以LDA为例的大规模分布式机器学习系统分析

针对构建大规模机器学习系统在可扩展性、算法收敛性能、运行效率等方面面临的问题,分析了大规模样本、模型和网络通信给机器学习系统带来的挑战和现有系统的应对方案。以隐含狄利克雷分布（LDA）模型为例,通过对比三款开源分布式LDA系统——Spark LDA、PLDA+和LightLDA,在系统资源消耗、算法收敛性能和可扩展性等方面的表现,分析各系统在设计、实现和性能上的差异。实验结果表明：面对小规模的样本集和模型,LightLDA与PLDA+的内存使用量约为Spark LDA的一半,系统收敛速度为Spark LDA的4至5倍;面对较大规模的样本集和模型,LightLDA的网络通信总量与系统收敛时间远小于PLDA+与SparkLDA,展现出良好的可扩展性。“数据并行+模型并行”的体系结构能有效应对大规模样本和模型的挑战;参数弱同步策略（SSP）、模型本地缓存机制和参数稀疏存储能有效降低网络开销,提升系统运行效率。     

Design and development of a technology enhanced hybrid instruction based on MOLTA model: Its effectiveness in comparison to traditional instruction

Using the model for learning and teaching activities (MOLTA), a new technology enhanced hybrid instruction was designed, developed and implemented. The effectiveness of the hybrid instruction in regard to students’ achievement, knowledge retention, attitudes towards the subject, and course satisfaction was evaluated in comparison to traditional classroom instruction. Experimental study with pre-test, post-test control group design was carried out. The sample of the study consisted of 50 university students enrolled in “Computer Networks and Communication” course. The control and experimental groups composed of 24 and 26 students respectively, and the experiment lasted 14 weeks. The findings of the study indicated no significant difference between the hybrid course and the traditional course in students’ achievement, knowledge retention, satisfaction, and attitude.