Yazar "Yumusak, Nejat" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Impact of small-world topology on the performance of a feed-forward artificial neural network based on 2 different real-life problems
    (2014) Erkaymaz, Okan; Özer, Mahmut; Yumusak, Nejat
    Since feed-forward artificial neural networks (FFANNs) are the most widely used models to solve real-life problems, many studies have focused on improving their learning performances by changing the network architecture and learning algorithms. On the other hand, recently, small-world network topology has been shown to meet the characteristics of real-life problems. Therefore, in this study, instead of focusing on the performance of the conventional FFANNs, we investigated how real-life problems can be solved by a FFANN with small-world topology. Therefore, we considered 2 real-life problems: estimating the thermal performance of solar air collectors and predicting the modulus of rupture values of oriented strand boards. We used the FFANN with small-world topology to solve both problems and compared the results with those of a conventional FFANN with zero rewiring. In addition, we investigated whether there was statistically significant difference between the regular FFANN and small-world FFANN model. Our results show that there exists an optimal rewiring number within the small-world topology that warrants the best performance for both problems.
  • Küçük Resim Yok
    Öğe
    Impact of small-world topology on the performance of a feed-forward artificial neural network based on 2 different real-life problems
    (Tubitak Scientific & Technological Research Council Turkey, 2014) Erkaymaz, Okan; Ozer, Mahmut; Yumusak, Nejat
    Since feed-forward artificial neural networks (FFANNs) are the most widely used models to solve real-life problems, many studies have focused on improving their learning performances by changing the network architecture and learning algorithms. On the other hand, recently, small-world network topology has been shown to meet the characteristics of real-life problems. Therefore, in this study, instead of focusing on the performance of the conventional FFANNs, we investigated how real-life problems can be solved by a FFANN with small-world topology. Therefore, we considered 2 real-life problems: estimating the thermal performance of solar air collectors and predicting the modulus of rupture values of oriented strand boards. We used the FFANN with small-world topology to solve both problems and compared the results with those of a conventional FFANN with zero rewiring. In addition, we investigated whether there was statistically significant difference between the regular FFANN and small-world FFANN model. Our results show that there exists an optimal rewiring number within the small-world topology that warrants the best performance for both problems.
  • Küçük Resim Yok
    Öğe
    Performance Analysis of A Feed-Forward Artifical Neural Network With Small-World Topology
    (Elsevier Science Bv, 2012) Erkaymaz, Okan; Ozer, Mahmut; Yumusak, Nejat
    Feed Forward Artificial Neural Networks are the most widely used models to explain the information processing mechanism of the brain. Network topology plays a key role in the performance of the feed forward neural networks. Recently, the small-world network topology has been shown to meet the properties of the real life networks. Therefore, in this study, we consider a feed forward artificial neural network with small-world topology and analyze its performance on classifying the epilepsy. In order to obtain the small-world network, we follow the Watts-Strogatz approach. An EEG dataset taken from healthy and epileptic patients is used to test the performance of the network. We also consider different numbers of neurons in each layer of the network. By comparing the performance of small-world and regular feed forward artificial neural networks, it is shown that the Watts-Strogatz small-world network topology improves the learning performance and decreases the training time. To our knowledge, this is the first attempt to use small-world topology in a feed forward artificial neural network to classify the epileptic case.