No abstract

No abstract

Among discrete choice problems, travel mode choice modeling has received the most attention in the travel behavior literature. Most traditional mode choice models are based on the principle of random utility maximization derived from econometric theory. Alternatively, mode choice modeling can be regarded as a pattern recognition problem in which multiple human behavioral patterns reflected by explanatory variables determine the choices between alternatives or classes. The capability and performance of two emerging pattern recognition data mining methods, decision trees (DT) and neural networks (NN), for work travel mode choice modeling were investigated. Models based on these two techniques are specified, estimated, and comparatively evaluated with a traditional multinomial logit (MNL) model. For comparison, a unique three-layer formulation of the MNL model is presented. The similarities and differences of the models' mechanisms and structures are identified, and the mechanisms and structures in the models' specifications and estimations are compared. Two performance measures, individual prediction rate and aggregate prediction rate, which represent the prediction accuracies for individual and mode aggregate levels, respectively, were applied to evaluate and compare the performances of the models. Diary data sets from the San Francisco, California, Bay Area Travel Survey 2000 were used for model estimation and evaluation. The prediction results show that the two data mining models offer comparable but slightly better performances than the MNL model in terms of the modeling results, while the DT model demonstrates the highest estimation efficiency and most explicit interpretability, and the NN model gives a superior prediction performance in most cases.

The extract from an edible vine, Pueraria lobata, has long been used in China to lessen alcohol intoxication. We have previously shown that daidzin, one of the major components from this plant extract, is efficacious in lowering blood alcohol levels and shortens sleep time induced by alcohol ingestion. This study was conducted to test the antidipsotropic effect of daidzin and two other major isoflavonoids, daidzein and puerarin, from Pueraria lobata administered by the oral route. An alcohol-preferring rat model, the selectively-bred P line of rats, was used for the study. All three isoflavonoid compounds were effective in suppressing voluntary alcohol consumption by the P rats. When given orally to P rats at a dose of 100 mg/kg/day, daidzein, daidzin, and puerarin decreased ethanol intake by 75%, 50%, and 40%, respectively. The decrease in alcohol consumption was accompanied by an increase in water intake, so that the total fluid volume consumed daily remained unchanged. The effects of these isoflavonoid compounds on alcohol and water intake were reversible. Suppression of alcohol consumption was evident after 1 day of administration and became maximal after 2 days. Similarly, alcohol preference returned to baseline levels 2 days after discontinuation of the isoflavonoids. Rats receiving the herbal extracts ate the same amounts of food as control animals, and they gained weight normally during the experiments. When administered orally, none of these compounds affected the activities of liver alcohol dehydrogenase and aldehyde dehydrogenase. Therefore, the reversal of alcohol preference produced by these compounds may be mediated via the CNS. Data demonstrate that isoflavonoid compounds extracted from Pueraria lobata is effective in suppressing the appetite for alcohol when taken orally, raising the possibility that other constituents of edible plants may exert similar and more potent actions.