Yazar "Dalyan, Tuğba" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    Acknowledge of Emotions for Improving Student-Robot Interaction
    (TECH SCIENCE PRESS, 2023-05-25) Han, Hasan; Karadeniz, Oğuzcan; Dalyan, Tuğba; Sönmez, Elena Battini; Sarıoğlu, Baykal
    Robot companions will soon be part of our everyday life and students in the engineering faculty must be trained to design, build, and interact with them. The two affordable robots presented in this paper have been designed and constructed by two undergraduate students; one artifi-cial agent is based on the Nvidia Jetson Nano development board and the other one on a remote computer system. Moreover, the robots have been refined with an empathetic system, to make them more user-friendly. Since automatic facial expression recognition skills is a necessary pre-processing step for acknowledging emotions, this paper tested different variations of Convolutional Neural Networks (CNN) to detect the six facial expressions plus the neutral face. The state-of-the-art performance of 75.1% on the Facial Expression Recognition (FER) 2013 database has been reached by the ensemble voting method. The runner-up model is the Visual Geometry Group (VGG) 16 which has been adopted by the two robots to recognize the expressions of the human partner and behave accordingly. An empirical study run among 55 university students confirmed the hypothesis that contact with empathetic artificial agents contributes to increasing the acceptance rate of robots
  • Küçük Resim
    Öğe
    A Comprehensive Study of Learning Approaches for Author Gender Identification
    (Kauno Technologijos Universitetas, 2022-09-23) Dalyan, Tuğba
    Abstract: In recent years, author gender identification is an important yet challenging task in the fields of information retrieval and computational linguistics. In this paper, different learning approaches are presented to address the problem of author gender identification for Turkish articles. First, several classification algorithms are applied to the list of representations based on different paradigms: fixed-length vector representations such as Stylometric Features (SF), Bag-of-Words (BoW) and distributed word/document embeddings such as Word-2vec, fastText and Doc2vec. Secondly, deep learning architectures, Convolution Neural Network (CNN), Recurrent Neural Network (RNN), special kinds of RNN such as Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU), C-RNN, Bidirectional LSTM (bi-LSTM), Bidirectional GRU (bi-GRU), Hierarchical Attention Networks and Multi-head Attention (MHA) are designated and their comparable performances are evaluated. We conducted a variety of experiments and achieved outstanding empirical results. To conclude, ML algorithms with BoW have promising results. fast-Text is also probably suitable between embedding models. This comprehensive study contributes to literature utilizing different learning approaches based on several ways of representations. It is also first attempt to identify author gender applying SF on Turkish language. © 2022, Kauno Technologijos Universitetas. All rights reserved.
  • Küçük Resim
    Öğe
    Feature selection optimization with filtering and wrapper methods: two disease classification cases
    (Scientific and Technological Research Council Turkey, 2023) Atik, Serhat; Dalyan, Tuğba
    Discarding the less informative and redundant features helps to reduce the time required to train a learning algorithm and the amount of storage required, improving the learning accuracy as well as the quality of results. In this study, we present different feature selection approaches to address the problem of disease classification based on the Parkinson and Cardiac Arrhythmia datasets. For this purpose, first we utilize three filtering algorithms including the Pearson correlation coefficient, Spearman correlation coefficient, and relief. Second, metaheuristic algorithms are compared to find the most informative subset of the features to obtain better classification accuracy. As a final method, a hybrid model involving filtering algorithms is applied to the datasets to eliminate half of the features, and then a metaheuristic algorithm based on a proposed genetic algorithm is applied to the rest of the datasets. With all three methods, we use three classification algorithms: support vector machine, K-nearest neighbor, and random forest. The results show that the best scores are obtained from the metaheuristic algorithm based on the proposed genetic algorithm for both datasets. This comparative study contributes to the literature by increasing the accuracy of classification for both datasets and presenting a hybrid model with filtering and a metaheuristic algorithm.