Time filter

Source Type

Ahmadizar F.,University of Kurdistan | Soltanian K.,University of Kurdistan | Akhlaghiantab F.,University of Kurdistan | Tsoulos I.,Technological Institute of Epirus
Engineering Applications of Artificial Intelligence | Year: 2015

The most important problems with exploiting artificial neural networks (ANNs) are to design the network topology, which usually requires an excessive amount of expert's effort, and to train it. In this paper, a new evolutionary-based algorithm is developed to simultaneously evolve the topology and the connection weights of ANNs by means of a new combination of grammatical evolution (GE) and genetic algorithm (GA). GE is adopted to design the network topology while GA is incorporated for better weight adaptation. The proposed algorithm needs to invest a minimal expert's effort for customization and is capable of generating any feedforward ANN with one hidden layer. Moreover, due to the fact that the generalization ability of an ANN may decrease because of overfitting problems, the algorithm utilizes a novel adaptive penalty approach to simplify ANNs generated through the evolution process. As a result, it produces much simpler ANNs that have better generalization ability and are easy to implement. The proposed method is tested on some real world classification datasets, and the results are statistically compared against existing methods in the literature. The results indicate that our algorithm outperforms the other methods and provides the best overall performance in terms of the classification accuracy and the number of hidden neurons. The results also present the contribution of the proposed penalty approach in the simplicity and generalization ability of the generated networks. © 2014 Elsevier Ltd. Source

Voidarou C.,Technological Institute of Epirus | Tzora A.,Technological Institute of Epirus | Malamou O.,University of Ioannina | Akrida-Demertzi K.,University of Ioannina | And 9 more authors.
Anaerobe | Year: 2011

The artisan production of a variety of dairy products is a historical tradition since antiquity, which is still practiced nowadays, in the area of Epirus, (northwestern Greece). The common denominator of these products, regardless of the final form of the end product, is the fermentation of raw milk by the use of dried artisan inoculants made of the dehydrated rumen of small ruminants, mainly lambs. The aim of this research project is to study the microbiological parameters as well as certain technological parameters (chymosin activity and lipolytic activity) of these inoculants. The results revealed a wide biodiversity of microorganisms such as Lactobacilli, Lactococci, Leuconostoc, Pediococci, Streptococci, Bifidobacteria, Enterococci, Clostridia and coliforms. Chymosin activity and lipolytic activity were found to be higher in artisan inoculants than in the commercial ones. © 2011 Elsevier Ltd. Source

Skoufos I.,Technological Institute of Epirus | Tzora A.,Technological Institute of Epirus | Giannenas I.,Aristotle University of Thessaloniki | Bonos E.,Aristotle University of Thessaloniki | And 4 more authors.
Asian Journal of Animal and Veterinary Advances | Year: 2016

Due to the variability of feed cost and in order to maintain the competitiveness of pork products, the pig farmers of the European Union try to maximize the use of locally produced feeds, such as rapeseed meal which is a by-product of the oil and biofuel industries. Dietary rapeseed meal of Greek origin was evaluated as alternative for imported soybean meal on the performance, meat quality parameters and gut microbiota of growing-fattening pigs. A total of 120 pigs were allocated to two equal groups for a period of 90 days. The pigs of the control group (C) were fed with commercial soybean meal based growing and fattening rations. The pigs of the second group were fed with isocaloric and isonitrogenous rapeseed meal based rations. Body weight gain did not differ (p>0.05) during the growing and the fattening periods. Feed conversion ratio did not differ (p>0.05) during the growing period but was higher (p≤0.05) for group R during the fattening period. Some differences (p≤0.05) were found in the meat chemical composition (moisture, crude protein, crude fat) between the two groups. In the steak cuts, group R had higher (p≤0.05) total monounsaturated fatty acids and lower (p≤0.05) saturated fatty acids and polyunsaturated fatty acids, compared to group C. No differences (p>0.05) were found on the ham and steak meat lipid oxidative stability after 4 days or 7 days of refrigerated storage 4°C. Group R had higher (p≤0.05) Lactobacillus spp., in the caecum and lower (p≤0.05), Clostridium perfringens in the mid-colon. © 2016 Skoufos et al. Source

Discover hidden collaborations