The contribution of a mobile mental health unit to the promotion of primary mental health in rural areas in Greece: a 2-year follow-up.

During the 2 years of the mobile mental-health unit's operation in Northwestern Greece, the referrals increased rapidly with 29.4% of patients never having received mental-health care before, while hospitalizations and relapses reduced significantly, indicating that community-oriented programs can contribute greatly to successfully addressing the needs of patients in remote rural areas.

Interpretation of artificial neural networks by means of fuzzy rules.

This paper presents an extension of the method presented by Benitez et al (1997) for extracting fuzzy rules from an artificial neural network (ANN) that express exactly its behavior. The extraction process provides an interpretation of the ANN in terms of fuzzy rules. The fuzzy rules presented are in accordance with the domain of the input variables. These rules use a new operator in the antecedent. The properties and intuitive meaning of this operator are studied. Next, the role of the biases in the fuzzy rule-based systems is analyzed. Several examples are presented to comment on the obtained fuzzy rule-based systems. Finally, the interpretation of ANNs with two or more hidden layers is also studied.

Neural networks with a continuous squashing function in the output are universal approximators.

In 1989 Hornik as well as Funahashi established that multilayer feedforward networks without the squashing function in the output layer are universal approximators. This result has been often used improperly because it has been applied to multilayer feedforward networks with the squashing function in the output layer. In this paper, we will prove that also this kind of neural networks are universal approximators, i.e. they are capable of approximating any Borel measurable function from one finite dimensional space into (0,1)" to any desired degree of accuracy, provided sufficiently many hidden units are available.

IL-8 producing cells in patients with Behçet's disease.

OBJECTIVE: IL-8 is thought to be the principal chemokine responsible for neutrophil activation and tissue infiltration in patients with Behçet's disease (BD). In various studies serum levels of IL-8 were reported to be increased. METHODS: IL-8 mRNA was purified from both peripheral whole blood samples and separated lymphocytes, granulocytes and monocytes of patients with BD and compared to that from healthy (HC) and disease controls. IL-8 sequences were revealed by PCR amplification using appropriate sequence-specific primers. mRNA levels were determined semi-quantitatively using an image analyser in comparison with beta-actin. RESULTS: Although the differences did not reach statistical significance, BD patients tended to have higher IL-8 mRNA levels compared to HC in whole blood samples (2.0 +/- 1.4 vs 1.5 +/- 1.2) as well as in their lymphocytes (2.7 +/- 1.6 vs 1.5 +/- 0.9). No differences were observed between BD and HC in monocyte or granulocyte IL-8 mRNA levels. CONCLUSION: Our results suggest that the cellular source of IL-8 is diverse in BD with a possible major contribution by lymphocytes.

SEPARATE: a machine learning method based on semi-global partitions.

This article presents a machine learning method for solving classification and approximation problems. This method uses the divide-and-conquer algorithm design technique (taken from machine learning models based on a tree), with the aim of achieving design ease and good results on the training examples and allows semi-global actions on its computational elements (a feature taken from neural networks), with the aim of attaining good generalization and good behavior in the presence of noise in training examples. Finally, some results obtained after solving several problems with a particular implementation of SEPARATE are presented together with their analysis.