Analysis of experimental design with multivariate response: A contribution using multiblock techniques

In many application areas, experimental approaches both involve an experimental design that determines changes in the studying factors and an untargeted analytical method (IR, LC-MS, NMR,…) used to characterize the samples by a large number of variables. This leads to a resulting data set which can be structured in blocks with respect to the different levels of the experimental factors. Among the methods that have been developed to address this situation, the ANOVA-Simultaneous Component Analysis (ASCA) is the only one which proposes the use of a multiblock technique to date. Nevertheless, other possibilities are achievable. Therefore in this article, we propose 1) to adopt another way of defining and organizing the blocks from the initial matrix and 2) to apply Multiple Co-inertia Analysis (MCoA) a multiblock method different from Simultaneous Component Analysis to manage this new scenario. The complementarities of our proposal with ASCA are demonstrated on a case study related to cheese processing.     

基于汉明重的LED代数旁路攻击研究

对CHES 2011会议提出的LED轻型分组密码抗代数旁路攻击能力进行了评估。给出了密码算法代数旁路攻击模型及LED密码代数方程表示方法;利用示波器采集微控制器ATMEGA324P上的LED实现功耗泄露,选取功耗特征较为明显的部分泄露点,基于 Pearson 相关系数方法推断加密中间状态汉明重;分别基于可满足性问题、伪布尔优化问题、线性编程问题给出了LED密码和汉明重泄露的3种代数方程表示方法;使用CryptoMinisat和SCIP 2种解析器对建立的代数方程求解恢复密钥,在已知明文、未知明密文、容错等场景下进行了大量的攻击实验。结果表明,LED易遭受代数旁路攻击,一条功耗曲线的1轮汉明重泄露分析即可恢复64 bit完整密钥。     

亚仿电力仿真技术的发展

回顾亚仿科技股份有限公司在仿真技术方面的发展历程，介绍其开发研制的、具有自主知识产权的仿真支撑平台(ASCA和AF2000)和自动开发工具；论述对亚仿公司的发展起重要作用的质量管理体系建立、规范化管理、独特的企业文化等特点。并对今后提高电厂信息化的新的发展方向“在线仿真和数字化电厂”的概念进行简述，指出其实施成功将推动中国仿真技术应用水平的深度和广度，使仿真机的制造更加走向产业化。     

Application of near infrared (NIR) spectroscopy coupled to chemometrics for dried egg-pasta characterization and egg content quantification

Dried egg pasta is an important and traditional food in the Italian cuisine, and the eggs in pasta improve its nutritional value and organoleptic properties. For this reason the percentage of eggs present in the products sold as “egg pasta” has to always be clearly reported in the label. In this respect, the present research addresses the possibility of developing a method which would allow fast, simple and economic determination of egg content in dried egg-pasta, using near-infrared spectroscopy and chemometric analysis. However, as it is very likely that the spectroscopic fingerprint can also be affected by the manufacturing process of this product, in particular by drying temperature and time, the effect of the manufacturing process on the spectral profile of egg-pasta samples was thoroughly investigated, using experimental design coupled to a multivariate exploratory data analytical technique called ANOVA–Simultaneous Component Analysis (ASCA). Moreover, once confirmed the significance of the drying effect on spectral shape, with the aim of building a calibration model to quantify the egg content in pasta samples irrespective of the manufacturing protocol adopted, a non-linear approach based on local regression, namely LWR-PLS, was investigated. This method allowed the determination of the egg content in external validation samples with low error (RMSEP = 1.25), resulting in predictions more accurate and precise than those obtained by a global PLS model.     

A comparison of methods for analyzing multivariate sensory data in designed experiments – A case study of salt reduction in liver paste

This paper presents a comparison of different methods for analyzing designed experiments. The methods used are based on PCA, PLS and ANOVA, used either separately or in combination. Special emphasis will be on how to obtain information about medium and less important factors in the presence of very dominating ones. It will be shown that this could be done by splitting the dataset in two. Our propositions will be illustrated on a data set obtained for studying the effect of salt reduction in liver paste.     

Exploring the analysis of structured metabolomics data

In metabolomics research a large number of metabolites are measured that reflect the cellular state under the experimental conditions studied. In many occasions the experiments are performed according to an experimental design to make sure that sufficient variation is induced in the metabolite concentrations. However, as metabolomics is a holistic approach, also a large number of metabolites are measured in which no variation is induced by the experimental design. The presence of such non-induced metabolites hampers traditional data analysis methods as PCA to estimate the true model of the induced variation. The greediness of PCA leads to a clear overfit of the metabolomics data and can lead to a bad selection of important metabolites. In this paper we explore how, why and how severe PCA overfits data with an underlying experimental design. Recently new data analysis methods have been introduced that can use prior information of the system to reduce the overfit. We show that incorporation of prior knowledge of the system under investigation leads to a better estimation of the true underlying structure and to less overfit. The experimental design information together with ASCA is used to improve the analysis of metabolomics data. To show the improved model estimation property of ASCA a thorough simulation study is used and the results are extended to a microbial metabolomics batch fermentation study. The ASCA model is much less affected by the non-induced variation and measurement error than PCA, leading to a much better model of the induced variation.