Intelligent data base

Bao, X. H., Lu, W. C. and Chen, N. Y. (2002). Support vector machine applied to intelligent data base of phase diagrams of molten salt systems. Computer and applied chemistry, 19, pp. 723-725. 

The main objective for an intelligent system in electrolyser operations is to gather and process valuable information for a greater control and efficiency. To achieve the aforementioned objective, two key functions have to be performed properly. Firstly, accurate and precise real-time data need to be obtained and secondly, the system should be able to process and interpret these data based on fundamental and acquired industrial electrochemical knowledge. In the case of R2 s EMOS , this second key element refers directly to its capability to use embedded human expertise to find optimal operating solutions and to detect and correctly identify equipment degradation or other anomalies. 

These two actions by the computer are key to the success of this project. This is because it will be impossible for a human to consider all the possibilities of a large data set and to deduce the best (most simple and therefore cost effective) rules to use in order to choose the best protective materials to use. And when the data base is dynamically growing it would be impossible to use a highly structured artificial intelligence system where the user had to rewrite the program modifications himself every time there was a change in the information. 

In the course of these exercise.s you should be stimulated to work through the additional volumes in this series either to learn more about the application of modern NMR experiment.s (Data Acquisition - volume 2), about extracting NMR parameters (Modern Spectra Analysis - volume 3) or about using NMR spectra data bases to unravel unknown molecular structures (Intelligent Data Management - volume 4). 

Amin, Rajan, Max Bramer, and Richard Emslie. Intelligent Data Analysis for Conservation Experiments With Rhino Horn Fingerprint Identification. Knowledge-Based Systems 16 (2003) 329-336. 

Now that the facts are straight, the goal of statistics is to make sense of the matter of direct observation in a way that helps us expose properties of those observations that might otherwise be hidden. For the colorist, direct observation could refer to visual or spectrophotometric data. Once these statistical inferences are laid bare, we then develop intelligent decisions based on our findings—search for facts that support the human observations that lead us to collect the statistical data in the first place. 

As manufacturing processes have become increasingly instrumented in recent years, more variables are being measured and data are being recorded more frequently. This yields data overload, and most of the useful information may be hidden in large data sets. The correlated or redundant information in these process measurements must be refined to retain the essential information about the process. Process knowledge must be extracted from measurement information, and presented in a form that is easy to display and interpret. Various methods based on multivariate statistics, systems theory and artificial intelligence are presented in this chapter for data-based input-output model development. 

Errors in pruning also cause significant problems. Omitted pruned paths generally resulted from our not using reaction rule constraints or nonselective and/or non-intelligent use of the rules. This is one reason why none of SYNLMA s paths represent published syntheses of Ibuprofen (15) in spite of the fact that the requisite rules were in the data base. On the positive side, the synthetic paths to Ibuprofen discovered by SYNLMA are straightforward and would probably work as shown. 

Anon "Intelligent Data/Knowledge Base System" Sol F30602-88-R-0071, February 1988, Rome Air Development Center, USAF... 

The constitution is often desired, however, for all non-repetitive biomolecules or synthetic compounds although, for the latter, the chemist mostly has some preknowledge about the compound in question. HSQC [29], COSY [7], TOCSY [9], and HMBC [31] experiments are the experiments of choice for such molecules. They reflect the connectivities of atoms in the molecule from which the constitution can be derived. With correlation spectra as discussed in Sect. 2.2, connectivity information is obtained. With an intelligent structure builder like Cocon [53], an especially powerful program, that takes the connectivity information and the rules of bonding between atoms into account, all constitutions that are in agreement with the provided correlation data are proposed. These are frequently more than one. Chemical-shift information can be used in addition to single out the most probable constitution. To use chemical shift information, data bases, ab initio calculations, or neuronal networks are available. As an example, the ascididemin constitution has been derived from connectivity information as well as with chemical shifts derived from neuronal networks Fig. 22) [25]. 

The advantage of LP methods for extracting spectroscopic information from spectra is exploited by Haselgrove and Elliott who developed a computer intelligence algorithm which is able to analyze a large quantity of data based on a user-defined pattern of expected components. 

Onboard fault detection is such an important facet of an intelligent sensor that density-based novelty detection may be used in parallel with more traditional approaches such as a residual-based fault detection approach [12]. Here, time series predictions from a data-based model using recent measurements retained in a buffer are compared with the actual current measurement provided by the sensor, to calculate a residual error between the two estimates. Significant discrepancy highlighted by a large residual error is indicative of an error condition. 

---