Search

In this paper, a set of machine learning (ML) tools is applied to estimate the water saturation of shallow unconsolidated sediments at the Bátaapáti site in Hungary. Water saturation is directly calculated from the first factor extracted from a set of direct push logs by factor analysis. The dataset observed by engineering geophysical sounding tools as special variants of direct-push probes contains data from a total of 12 shallow penetration holes. Both one- and two-dimensional applications of the suggested method are presented. To improve the performance of factor analysis, particle swarm optimization (PSO) is applied to give a globally optimized estimate for the factor scores. Furthermore, by a hyperparameter estimation approach, some control parameters of the utilized PSO algorithm are automatically estimated by simulated annealing (SA) to ensure the convergence of the procedure. The result of the suggested ML-based log analysis method is compared and verified by an independent inversion estimate. The study shows that the PSO-based factor analysis aided by hyperparameter estimation provides reliable in situ estimates of water saturation, which may improve the solution of environmental end engineering problems in shallow unconsolidated heterogeneous formations. [ABSTRACT FROM AUTHOR]

This paper will be concerned with undergraduate and graduate students' problem solving as they encounter it in attempting to prove theorems, mainly to satisfy their professors in their courses, but also as they conduct original research for theses and dissertations. We take Schoenfeld's (1985) view of problem, namely, a mathematical task is a problem for an individual if that person does not already know a method of solution for that task. Thus, a given task may be a problem for one individual, who does not already know a solution method for that task, or it may be an exercise for an individual who already knows a procedure or an algorithm for solving that task. [ABSTRACT FROM AUTHOR]

HunCRIS has developed a new semantic application which allows calculation of the numeric value of similarity between any two projects. The paper describes the relevant algorithm by figures and explanations, and compares it to Boolean search solutions. In Boolean search the key expressions describing projects are searched among the items included in the search expression and their sub-terms in the thesaurus. The hits are typically ordered by non-search-relevant properties. The ex- tent of similarity is calculated as the correlation between sets of key expressions and their superterms in the thesaurus that describe the selected projects in the knowledge space. The projects can be ranked according to the metrics of similarity, or according to their relevance to a search expression. The service is available on the public site of HunCRIS. [ABSTRACT FROM AUTHOR]