Browsing by Subject "Hybrid approach"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    A novel hybrid approach to improve neural machine translation decoding using phrase-based statistical machine translation
    (Institute of Electrical and Electronics Engineers Inc., 2021) Satir E.; Bulut H.
    Phrase-based models are among the best performing statistical machine translation (SMT) systems. These systems make translations phrase-by-phrase at a time. The decoding process is done locally in these systems. In addition, neural machine translation (NMT) systems have become very popular for the past four or five years with essential features such as more fluent translations. However, sometimes NMT systems give up accuracy for fluent translations due to the nature of the decoding technique they use. In this study, we aim to develop a hybrid system by guiding NMT decoding using the output sentences of the phrase-based SMT systems. According to the two-way translation experiments, German-to-English and English-to-German, and the results obtained in terms of two popular machine translation evaluation metrics: BLEU and METEOR, our method improves the quality of NMT system translations. © 2021 IEEE.
  • No Thumbnail Available
    Item
    A hybrid approach based on deep learning for gender recognition using human ear images; [Insan kulaǧi görüntüleri kullanarak cinsiyet tanima için derin öǧrenme tabanli melez bir yaklaşim]
    (Gazi Universitesi, 2022) Karasulu B.; Yücalar F.; Borandaǧ E.
    Nowadays, the use of the human ear images gains importance for the sustainability of biometric authorization and surveillance systems. Contemporary studies show that such processes can be done semi-automatically or fully automatically, instead of being done manually. Due to the fact that deep learning uses abstract features (i.e., representation learning), it reaches quite high performance values compared to classical methods. In our study, a synergistic gender recognition approach based on hybrid deep learning was created based on the use of human ear images in classifying people fully automatically according to their gender. By means of hybridization, hybrid deep neural network architectural models are used, which include both convolutional neural network component and recurrent neural network type components together. In these models, long-short term memory and gated recurrent unit are taken as recurrent neural network type components. Thanks to these components, the hybrid model extracts the relational dependencies between the pixel regions in the image very well. On account of this synergistic approach, the gender classification accuracy of hybrid models is higher than the standalone convolutional neural network model in our study. Two different image datasets with gender marking were used in our experiments. The reliability of the experimental results has been proven by objective metrics. In the conducted experiments, the highest values in gender recognition with hybrid models were obtained with the test accuracy of 85.16% for the EarVN dataset and 87.61% for the WPUT dataset, respectively. Discussion and conclusions are included in the last section of our study. © 2022 Gazi Universitesi Muhendislik-Mimarlik. All rights reserved.
  • No Thumbnail Available
    Item
    A new hybrid approach in selection of optimum establishment location of the biogas energy production plant
    (Springer Science and Business Media Deutschland GmbH, 2023) Ceylan A.B.; Aydın L.; Nil M.; Mamur H.; Polatoğlu İ.; Sözen H.
    In this study, a new hybrid modeling optimization approach is presented for choosing the best installation location of a biogas power plant. This approach was evaluated in a case study for Manisa province in Turkey. First, the animal waste potential in Manisa was determined. By examining the biogas potential in Manisa, the mathematical model of the process is identified with the neuro-regression approach. Comparisons were made with the traditional and hybrid models, and it was seen that the values of the hybrid model based on the introduced approach were at more acceptable levels. Depending on this model, the most appropriate district where the power plant can be installed was calculated by considering the potentials in the environment. The single-objective and multi-objective approaches were considered to acquire the optimum design for the system. The modified versions of the optimization methods differential evolution (MDE), Nelder-Mead (MNM), simulated annealing (MSA), and random search (MRS) algorithms were used to solve problems. Thanks to the calculations and optimizations, it was concluded that it would be more appropriate to establish a biogas plant around Gölmarmara, Salihli, and Ahmetli triangle in Manisa. It was determined that when this installation takes place, 68 GWh of electrical energy can be produced annually. This study is a pioneering study for the installation locations of bioenergy power plants in terms of the methods and approaches. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
  • No Thumbnail Available
    Item
    A deep learning feature extraction-based hybrid approach for detecting pediatric pneumonia in chest X-ray images
    (Springer Science and Business Media Deutschland GmbH, 2024) Bal U.; Bal A.; Moral Ö.T.; Düzgün F.; Gürbüz N.
    Pneumonia is a disease caused by bacteria, viruses, and fungi that settle in the alveolar sacs of the lungs and can lead to serious health complications in humans. Early detection of pneumonia is necessary for early treatment to manage and cure the disease. Recently, machine learning-based pneumonia detection methods have focused on pneumonia in adults. Machine learning relies on manual feature engineering, whereas deep learning can automatically detect and extract features from data. This study proposes a deep learning feature extraction-based hybrid approach that combines deep learning and machine learning to detect pediatric pneumonia, which is difficult to standardize. The proposed hybrid approach enhances the accuracy of detecting pediatric pneumonia and simplifies the approach by eliminating the requirement for advanced feature extraction. The experiments indicate that the hybrid approach using a Medium Neural Network based on AlexNet feature extraction achieved a 97.9% accuracy rate and 98.0% sensitivity rate. The results show that the proposed approach achieved higher accuracy rates than state-of-the-art approaches. © Australasian College of Physical Scientists and Engineers in Medicine 2023.