ESCA, Expert Systems Applied to Chemical Analysis, started its research in March 1987, with the aim of building prototype expert systems for HPLC method development. Results of this research have been published as the work has progressed. The project is now completed and this paper summarises some of the overall project conclusions. Seven different expert systems have been built which tackle problems throughout the process of method development, four stand-alone systems and three integrated systems. The object of ESCA was to evaluate the applicability of expert system technology to analytical chemistry and not all the systems were built for commercial uses. Many of the systems tackle problems specific to one or more of the partners and thus may not be useful outside this environment. However, the results of the work are still pertinent to analysts wishing to build their own systems. These results are described, however, the emphasis of the paper is on those systems developed for method validation.Method validation for HPLC is a complex task which requires many characteristics of the method to be tested, e.g. accuracy, precision, etc. The expert systems built within ESCA concern the validation of precision. Two systems were developed for repeatability testing and ruggedness testing. The method validation process can be divided into several discrete stages, these include: (1) The selection of the method feature to test, for instance which factors can influence the ruggedness of a method. (2) The definition of a test procedure, for instance an efficient statistical design. (3) The execution of experiments and the interpretation of results. (4) A diagnosis of any observed problem. This paper describes these two systems in some detail and summarises some of the results obtained from their evaluation. It concludes that expert systems can be useful in solving analytical problems and the integration of several expert systems can provide extremely powerful tools for the analyst. 相似文献
A new and simple LC-MS method for analysis of flavonoids from Sambucus ebulus berry extracts was developed and validated. Successfully were quantitated seven polyphenols: epicatechin, epigallocatechin gallate, rutin, resveratrol, myricetin, quercetin, and kaempferol.
Two detectors, working in parallel, were used: photodiode-array and single quadrupole mass-detector. The mass detection was used for identification and quantification of the analytes, while the diode-array detector was as confirmation tool. The following m/z were tracked: 457.15 (epigallocatechin gallate); 289.06 (epicatechin); 609.13 (rutin); 227.05 (resveratrol); 317.0 (myricetin); 301.02 (quercetin); 285.02 (kaempferol). For optimization the chromatographic separation three wavelengths 205?nm, 305?nm, 272?nm were monitored. The method was capable to detect in one run compounds with no UV or fluorescence chromophore and with very similar structures, such as plant polyphenols. The linearity was from 0.05?mg/L to 50?mg/L (R2 0.9962–0.9987). The recoveries for all tested analytes were between 81.6% and 104.7%.
The method was applied for analysis of crude extract of Sambucus ebulus ripe fruits. Three major polyphenols – epicatechin (0.84?mg/100gFW), quercetin (0.15?mg/100gFW) and kaempferol (0.05?mg/100gFW) were identified and quantified.
The proposed method could be successfully used for routine analysis of epigallocatechin gallate, epicatechin, rutin, resveratrol, myricetin, quercetin, and kaempferol in Sambucus ebulus extracts. 相似文献
Bitcoin (BTC)—the first cryptocurrency—is a decentralized network used to make private, anonymous, peer-to-peer transactions worldwide, yet there are numerous issues in its pricing due to its arbitrary nature, thus limiting its use due to skepticism among businesses and households. However, there is a vast scope of machine learning approaches to predict future prices precisely. One of the major problems with previous research on BTC price predictions is that they are primarily empirical research lacking sufficient analytical support to back up the claims. Therefore, this study aims to solve the BTC price prediction problem in the context of both macroeconomic and microeconomic theories by applying new machine learning methods. Previous work, however, shows mixed evidence of the superiority of machine learning over statistical analysis and vice versa, so more research is needed. This paper applies comparative approaches, including ordinary least squares (OLS), Ensemble learning, support vector regression (SVR), and multilayer perceptron (MLP), to investigate whether the macroeconomic, microeconomic, technical, and blockchain indicators based on economic theories predict the BTC price or not. The findings point out that some technical indicators are significant short-run BTC price predictors, thus confirming the validity of technical analysis. Moreover, macroeconomic and blockchain indicators are found to be significant long-term predictors, implying that supply, demand, and cost-based pricing theories are the underlying theories of BTC price prediction. Likewise, SVR is found to be superior to other machine learning and traditional models. This research’s innovation is looking at BTC price prediction through theoretical aspects. The overall findings show that SVR is superior to other machine learning models and traditional models. This paper has several contributions. It can contribute to international finance to be used as a reference for setting asset pricing and improved investment decision-making. It also contributes to the economics of BTC price prediction by introducing its theoretical background. Moreover, as the authors still doubt whether machine learning can beat the traditional methods in BTC price prediction, this research contributes to machine learning configuration and helping developers use it as a benchmark. 相似文献
This paper compares model development strategies based on different performance metrics. The study was conducted in the area of credit risk modeling with the usage of diverse metrics, including general-purpose Area Under the ROC curve (AUC), problem-dedicated Expected Maximum Profit (EMP) and the novel case-tailored Calculated Profit (CP). The metrics were used to optimize competitive credit risk scoring models based on two predictive algorithms that are widely used in the financial industry: Logistic Regression and extreme gradient boosting machine (XGBoost). A dataset provided by the American Fannie Mae agency was utilized to conduct the study. In addition to the baseline study, the paper also includes a stability analysis. In each case examined the proposed CP metric that allowed us to achieve the most profitable loan portfolio. 相似文献
Novel pyridine-thiazole hybrid molecules were synthesized and subjected to physico-chemical characterization and screening of their cytotoxic action towards a panel of cell lines derived from different types of tumors (carcinomas of colon, breast, and lung, glioblastoma and leukemia), and normal human keratinocytes, for comparison. High antiproliferative activity of the 3-(2-fluorophenyl)-1-[4-methyl-2-(pyridin-2-ylamino)-thiazol-5-yl]-propenone 3 and 4-(2-{1-(2-fluorophenyl)-3-[4-methyl-2-(pyridin-2-ylamino)-thiazol-5-yl]-3-oxopropylsulfanyl}-acetylamino)-benzoic acid ethyl ester 4 was revealed. The IC50 of the compound 3 in HL-60 cells of the acute human promyelocytic leukemia was 0.57 µM, while in the pseudo-normal human cell lines, the IC50 of this compound was >50 µM, which suggests that the compounds 3 and 4 might be perspective anticancer agents. The detected selectivity of the derivatives 3 and 4 for cancer cell lines inspired us to study the mechanisms of their cytotoxic action. It was shown that preincubation of tumor cells with Fluzaparib (inhibitor of PARP1) reduced the cytotoxic activity of the derivatives 3 and 4 by more than twice. The ability of these compounds to affect DNA nativity and cause changes in nucleus morphology allows for the suggestion that the mechanism of action of the novel pyridine-thiazole derivatives might be related to inducing the genetic instability in tumor cells. 相似文献