This paper describes a neural network approach for time series data forecasting. This study looks at the application of neural computing to an agricultural problem. In the selected application, the first step was to construct the multilayer feedforward neural network and the backpropagation training was employed. Elements of preprocessing, preparatory work, and network design are discussed. In order to improve efficiency and achieve stability, experiments were done while varying the learning rate and the number of hidden units. As a result, successful generalization has been observed on the test sets. Also a statistical approach (regression analysis) was applied to the same application. A comparative study between the applied methods was described. The comparative study can also be beneficial for implementing other forecasting applications. Our study suggests that the neural network is very useful for forecasting problems and in terms of comparative accuracy, the network was able to achieve more accurate results than the multipe regression model.

This work was designed with the purpose of determining whether the presence of allelic imbalances (AI) such as microsatellite instability (MSI) and loss of heterozygosity (LOH) in chromosomes 2, 11, 13, and 17 in primary breast cancer could be used as prognostic indicators of patient survival. The DNA from breast cancers removed from 29 patients who were followed-up for up to five years was analyzed for MSI and LOH using a panel of 24 markers located at chromosome 2 (TPO, D2S131, D2S144, D2S171, D2S177, D2S119, D2S123, D2S147 and D2S136), chromosome 11 (C-RAS, Int-2, D11S940, D11S912), chromosome 13 (D13S289, D13S260, D13S267, D13S218, D13S263, D13S155, and D13S162), and chromosome 17 (D17S513, TP53, D17S855, and D17S785). The frequency of AI in the markers studied ranged from 30-55%, being highest for D11S912, D2S171, TP53 and D17S855. Univariate analysis showed association between overall survival rate and AI in 9 out of the 24 markers tested. Five of them were located at the area of the mismatch repair gene (MMR)-2 gene, two at 11p, one at 13q and one at 17p. Using multivariate analysis, it was observed that only pathological and clinical stage (defined as stage II or not) and AI at D2S171, D11S912, or D17STP53 generated significant predictive models for survival.