2 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 2 / 2
Öğe Two novel versions of randomized feed forward artificial neural networks: Stochastic and pruned stochastic(Springer Nature, 2017-11-13) Ertuğrul, Ömer FarukAlthough high accuracies were achieved by artificial neural network (ANN), determining the optimal number of neurons in the hidden layer and the activation function is still an open issue. In this paper, the applicability of assigning the number of neurons in the hidden layer and the activation function randomly was investigated. Based on the findings, two novel versions of randomized ANNs, which are stochastic, and pruned stochastic, were proposed to achieve a higher accuracy without any time-consuming optimization stage. The proposed approaches were evaluated and validated by the basic versions of the popular randomized ANNs [1] are the random weight neural network [2], the random vector functional links [3] and the extreme learning machine [4] methods. In the stochastic version of randomized ANNs, not only the weights and biases of the neurons in the hidden layer but also the number of neurons in the hidden layer and each activation function were assigned randomly. In pruned stochastic version of these methods, the winner networks were pruned according to a novel strategy in order to produce a faster response. Proposed approaches were validated via 60 datasets (30 classification and 30 regression datasets). Obtained accuracies and time usages showed that both versions of randomized ANNs can be employed for classification and regression.Öğe Fingerprint recognition system based on law’s texture energy measures with extreme learning machines(INESEC, 2017) Çalışkan, Abidin; Acar, Emrullah; Budak, CaferFingerprint recognition systems are one of the most popular biometric systems used in many areas, including prisons, border controls, educational institutions and forensic medicine. This paper presents a new approach based on the texture features for fingerprint recognition system. The dataset which employed in this study is obtained from the Hong Kong Polytechnic University High-ResolutionFingerprint database. The proposed system was implemented in two basic stages. Firstly, the texture feature vectors were extracted from the images by using Law’s Texture Energy Measures (TEM) and totally 9 parameters were extracted for each image as a feature vector. Then, the obtained feature vectors were classified by using Extreme Learning Machines (ELM) model. Finally, the average performance of the proposed system was computed according to different tuning parameters and the highest accuracy rate was observed as 83.92 % among the all system architectures.
