This article describes the use of connectionist and symbolic learning algorithms in the problem of Bankruptcy Prediction. Data about Brazilian banks represented by 26 or I O indicators of their current financial situation were used. The difference among the number of existent examples in the classes of bankrupt and non-bankrupt banks was livened up through the reduction of learning examples of the class of nonbankrupts and the addition of noise samples in the class of bankrupts.

No abstract

This paper shows the results obtained from several pump tests of two wells drilled 13.2 meters apart, in the Agrarian Sciences Department of the University of Taubaté farm, located in the Una river hydrographic basin, Taubaté municipality, State of São Paulo, Brazil. During well drilling some difficulties were encountered due to the presence of sandy grains without inter-granular cementation of the Tremembé Formation sandstones, Taubaté Group. The detailed description of the geologic profile obtained by sampling the perforated sedimentary layers shows the presence of persistent sandstone and conglomerate sequences, intercalated by layers of shale and claystone with limestone nodules. In order to determine the hydrodynamic parameters of the Tremembé aquifer, several pump tests were conducted during well perforation and the unconfined, leaky, water-table, and confined aquifer layers were sampled. Once the boreholes were completed, tests were conducted to determine maximum discharge rate, interference between wells and artificial recharge potential. In addition to establishing appropriated methodologies for the determination of aquifer hydrodynamics, this paper describes techniques for interpreting the effects of artificial recharge and interference between wells, and demonstrated the application of image well theory complemented with a new theory, the image well water-mirror.