Introduction. The use of artificial neural networks to study perception in animals

Use of artificial neural networks to identify the predictive factors of extracorporeal shock wave therapy treating patients with chronic plantar fasciitis

The purpose of our study is to identify the predictive factors for a minimum clinically successful therapy after extracorporeal shock wave therapy for chronic plantar fasciitis. The demographic and clinical characteristics were evaluated. The artificial neural networks model was used to choose the significant variables and model the effect of achieving the minimum clinically successful therapy at 6-months’ follow-up. The multilayer perceptron model was selected. Higher VAS (Visual Analogue Score) when taking first steps in the morning, presence of plantar fascia spur, shorter duration of symptom had statistical significance in increasing the odd. The artificial neural networks model shows that the sensitivity of predictive factors was 84.3%, 87.9% and 61.4% for VAS, spurs and duration of symptom, respectively. The specificity 35.7%, 37.4% and 22.3% for VAS, spurs and duration of symptom, respectively. The positive predictive value was 69%, 72% and 57% for VAS, spurs and duration of symptom, respectively. The negative predictive value was 82%, 84% and 59%, for VAS, spurs and duration of symptom respectively. The area under the curve was 0.738, 0.882 and 0.520 for VAS, spurs and duration of symptom, respectively. The predictive model showed a good fitting of with an overall accuracy of 92.5%. Higher VAS symptomatized by short-duration, severer pain or plantar fascia spur are important prognostic factors for the efficacy of extracorporeal shock wave therapy. The artificial neural networks predictive model is reasonable and accurate model can help the decision-making for the application of extracorporeal shock wave therapy.

The key mimetic features of hoverflies through avian eyes

Batesian mimicry occurs when a palatable species (the mimic) gains protection from predators by resembling an unpalatable or otherwise protected species (the model). While some mimetic species resemble their models closely, other species ('imperfect mimics') are thought to bear only a crude likeness. In an earlier study, pigeons (Columba livia) were trained to recognize wasp images in one experiment and non-mimetic (NM) fly images in another by rewarding the pigeons for pecking on the respective image types. These pigeons were subsequently presented with different images, including seemingly wasp-like hoverfly species, and the recorded peck rates on these images were used as a measure of the pigeons' perception of the hoverflies' mimetic similarity. To identify a candidate set of morphological features that the pigeons used when assessing this mimetic similarity, we first extracted a range of biometrical measurements from images originally presented to the pigeons. We then repeatedly optimized an empirical model in an attempt to match the recorded pigeon peck rates while using as few biometrical features as input as possible. Our models were able to fit the pigeon peck rates with considerable accuracy even while excluding many input features. Antennal length, a feature commonly used to discriminate between flies and wasps, was regularly retained as an input variable, but overall a different set of biometrical features was important for predicting the peck rates of pigeons rewarded for identifying wasps compared to those rewarded for identifying NM flies. In highlighting the importance of specific biometrical features in promoting mimicry and the irrelevance of others, our optimized models provide an explanation as to why certain species that appear to be poor mimics to humans are judged to be good mimics by birds.