BackgroundOver-sampling methods based on Synthetic Minority Over-sampling Technique (SMOTE) have been proposed for classification problems of imbalanced biomedical data. However, the existing over-sampling methods achieve slightly better or sometimes worse result than the simplest SMOTE. In order to improve the effectiveness of SMOTE, this paper presents a novel over-sampling method using codebooks obtained by the learning vector quantization. In general, even when an existing SMOTE applied to a biomedical dataset, its empty feature space is still so huge that most classification algorithms would not perform well on estimating borderlines between classes. To tackle this problem, our over-sampling method generates synthetic samples which occupy more feature space than the other SMOTE algorithms. Briefly saying, our over-sampling method enables to generate useful synthetic samples by referring to actual samples taken from real-world datasets.ResultsExperiments on eight real-world imbalanced datasets demonstrate that our proposed over-sampling method performs better than the simplest SMOTE on four of five standard classification algorithms. Moreover, it is seen that the performance of our method increases if the latest SMOTE called MWMOTE is used in our algorithm. Experiments on datasets for β-turn types prediction show some important patterns that have not been seen in previous analyses.ConclusionsThe proposed over-sampling method generates useful synthetic samples for the classification of imbalanced biomedical data. Besides, the proposed over-sampling method is basically compatible with basic classification algorithms and the existing over-sampling methods.

The method of pancreatogastrointestinal anastomosis should be chosen according to each individual case.

No abstract

This study assessed the effects of acute as well as long-term administration of fluoxetine, a selective serotonin (5-HT) reuptake inhibitor with anti-depressant properties, on hippocampal (HIP) seizures elicited by electrical stimulation in rats. The fluoxetine effect on HIP seizures was also assessed following long-term treatment with gepirone, a 5-HT1A receptor agonist. Acute single administration of fluoxetine (1, 10 mg/kg; IP) was found to produce no significant effect on HIP seizure activity. Following daily IP administration of fluoxetine (10 mg/kg per day) or gepirone (10 mg/kg per day) for 21 days, animals were given a 7-day drug-free period and then challenged with an acute dose of 10 mg/kg fluoxetine. These treatment regimens resulted in a significantly increased afterdischarge threshold of HIP seizures in response to acute fluoxetine administration. The inhibitory effect of fluoxetine, however, was not present 4 weeks after long-term treatment with either fluoxetine or gepirone. The present results indicate that long-term treatment with these compounds enhances the antiepileptic effect of subsequent fluoxetine administration on the generation of HIP seizures. This effect is possibly related to the well-demonstrated evidence that fluoxetine and gepirone, on long-term treatment, facilitate net 5-HT neurotransmission through desensitization of presynaptic 5-HT autoreceptors.

Feeding stimulants for the tiger puffer Takifugu rubripes were identified by omission test using the synthetic clam Tapes japonicus extract, based on a daily feeding rate for casein diet with each test solu tion. The amino acid fraction showed remarkably higher feeding stimulant activity than those of nucleo tide and other chemical fractions in the extract. Among 18 chemicals in the amino acid fraction, Lserine, L-aspartic acid, glycine, and L-alanine showed slightly higher activity than deionized water, but lower than the amino acid fraction. The mixture of the above four amino acids plus betaine showed a markedly higher feeding stimulant activity than that of the synthetic extract, indicating the synergistic effect. The positive supplement level of the four amino acids plus betaine was found to be that corre sponding to 100 g of clam muscle per 100 g of casein diet.