Browsing by Subject "Training"

Filter results by typing the first few letters
Now showing 1 - 8 of 8
  • Thumbnail Image
    ItemOpen Access
    Effect of high intensity interval training on elite athletes' antioxidant status
    (Elsevier Masson, 2013) Ugras, A. F.
    Objective: The effects of high intensity interval exercises on antioxidant defense system are not clear. Since there is an evident lack of studies focused on oxidative stress experienced following combat sports and high intensity interval training, we investigated oxidative stress markers (malondialdehyde [MDA], catalase [CAT], glutathione peroxidase [GPX], superoxide dismutase [SOD]) by completing high intensity interval training program (HIITP) and following International Muay Thai Championship (IMTC). Methods: The study was carried out on 21 elite players (15 males and six females) who had regular exercising and training habits. The participants were subjected to a daily 3-hour HIITP during brief training camp (10-day) before IMTC. They were instructed to maintain their normal dietary practices throughout the camp and during the study to take no antioxidant containing vitamin tablets. Results: There was a significant increase in MDA levels and significant decrease in CAT activities of players (P<. 0.05). The differences in SOD and GPX activities were not significant. Conclusion: These results suggested that high intensity interval training and competition could affect the oxidative status of Muay Thai (MT) athletes. © 2012 Elsevier Masson SAS.
  • Thumbnail Image
    ItemOpen Access
    FAME: Face association through model evolution
    (IEEE, 2015-06) Gölge, Eren; Duygulu, Pınar
    We attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to other people. Moreover, the photographs are taken in the wild with large variety in poses and expressions. We propose a novel method, Face Association through Model Evolution (FAME), that is able to prune the data in an iterative way, for the models associated to a name to evolve. The idea is based on capturing discriminative and representative properties of each instance and eliminating the outliers. The final models are used to classify faces on novel datasets with different characteristics. On benchmark datasets, our results are comparable to or better than the state-of-the-art studies for the task of face identification. © 2015 IEEE.
  • Thumbnail Image
    ItemOpen Access
    Fractional fourier transform in time series prediction
    (IEEE, 2022-12-09) Koç, Emirhan; Koç, Aykut
    Several signal processing tools are integrated into machine learning models for performance and computational cost improvements. Fourier transform (FT) and its variants, which are powerful tools for spectral analysis, are employed in the prediction of univariate time series by converting them to sequences in the spectral domain to be processed further by recurrent neural networks (RNNs). This approach increases the prediction performance and reduces training time compared to conventional methods. In this letter, we introduce fractional Fourier transform (FrFT) to time series prediction by RNNs. As a parametric transformation, FrFT allows us to seek and select better-performing transformation domains by providing access to a continuum of domains between time and frequency. This flexibility yields significant improvements in the prediction power of the underlying models without sacrificing computational efficiency. We evaluated our FrFT-based time series prediction approach on synthetic and real-world datasets. Our results show that FrFT gives rise to performance improvements over ordinary FT.
  • Thumbnail Image
    ItemOpen Access
    Long short-term memory for improved transients in neural network adaptive control
    (IEEE, 2023-07-03) İnanç, Emirhan; Gürses, Yiğit; Habboush, Abdullah; Yıldız, Yıldıray
    In this study, we propose a novel adaptive control architecture, which provides dramatically better performance compared to conventional methods. What makes this architecture unique is the synergistic employment of a traditional, Adaptive Neural Network (ANN) controller and a Long Short-Term Memory (LSTM) network. LSTM structures, unlike the standard feed-forward neural networks, take advantage of the dependencies in an input sequence, which helps predict the evolution of an uncertainty. Through a training method we introduced, the LSTM network learns to compensate for the deficiencies of the ANN controller. This substantially improves the transient response by allowing the controller to quickly react to unexpected events. Through careful simulation studies, we demonstrate that this architecture can improve the estimation accuracy on a diverse set of unseen uncertainties. We also provide an analysis of the contributions of the ANN controller and LSTM network, identifying their individual roles in compensating low and high frequency error dynamics. This analysis provides insight into why and how the LSTM augmentation improves the system’s transient response.
  • Thumbnail Image
    ItemOpen Access
    Multivariate time series imputation with transformers
    (IEEE, 2022-11-25) Yıldız, A. Yarkın; Koç, Emirhan; Koç, Aykut
    Processing time series with missing segments is a fundamental challenge that puts obstacles to advanced analysis in various disciplines such as engineering, medicine, and economics. One of the remedies is imputation to fill the missing values based on observed values properly without undermining performance. We propose the Multivariate Time-Series Imputation with Transformers (MTSIT), a novel method that uses transformer architecture in an unsupervised manner for missing value imputation. Unlike the existing transformer architectures, this model only uses the encoder part of the transformer due to computational benefits. Crucially, MTSIT trains the autoencoder by jointly reconstructing and imputing stochastically-masked inputs via an objective designed for multivariate time-series data. The trained autoencoder is then evaluated for imputing both simulated and real missing values. Experiments show that MTSIT outperforms state-of-the-art imputation methods over benchmark datasets.
  • Thumbnail Image
    ItemOpen Access
    The performance comparison of different training strategies for reinforcement learning on DeepRTS
    (IEEE, 2022-08-29) Şahin, Safa Onur; Yücesoy, Veysel
    In this paper, we train reinforcement learning agents on the game of DeepRTS under different training strategies, which are i) training against rule based agents, ii) self-training and iii) training by adversarial attack to another agent. We perform certain modifications on the DeepRTS game and the reinforcement learning framework to make it closer to real life decision making problems. For this purpose, we allow agents take macro actions based on human heuristics, where these actions may last multiple time steps and the durations for these actions may differ from each other. In addition, the agents simultaneously take actions for each available unit at a time step. We train the reinforcement learning based agents under three different training strategies and we provide a detailed performance analysis of these agents against several reference agents.
  • Thumbnail Image
    ItemRestricted
    Polatlı Belediyespor Kadın Hentbol Takımı'nın tarihi
    (Bilkent University, 2020) İşsever, Defne; Eviz, Efe Musa; Baysal, Ceren; Gürsoy, Kaan; Temimhan, Yasemin
    Araştırma konumuz Polatlı Belediyespor Kadın Hentbol Takımı tarihi olup öncelikle hentbolun genel tarihi araştırılmış ve Polatlı Belediyesi'nin spor üzerine yaptığı çalışmalar ortaya konulmuştur. Polatlı Belediyesi'nin spor ile ilgili yürüttüğü projeler arasında hentbolun yanında futbol, tekvando, yüzme, voleybol ve atletizm alanındaki çalışmaları da araştırma konusunun bir kısmında bulunmaktadır. Polatlı Belediyesi'nin belirtilen spor dallarındaki aktifliği incelenerek ve özellikle kadın hentbol takımının tarihi araştırılarak, geçmişten günümüze başarı aşamaları kaydedilmiştir. Hentbolun tarihinden itibaren, hentbol sporunun Türkiye'ye gelişi, Polatlı Belediyespor'un tarihi ve hentbolun bu kulübe kazandırılmasına kadar geçen süre ele alınarak tarihi müsabakalardaki başarılar ve mağlubiyetler incelenmiştir. "Hentbol nasıl bulundu?", "Nasıl bir yol izledi?", "Türkiye'ye geldikten sonra hentbol ülkeye neler kazandırdı?" ve "Polatlı Belediyespor hentbolla nasıl tanıştı?" gibi sorular araştırmanın içerisinde verilmeye çalışılmıştır. Özellikle Polatlı Belediyespor Kadın Hentbol takımının yakın tarihimizde elde ettiği başarılar ve takımın izlediği doğrultu, otuz senelik bir zaman dilimini içerisinde incelenmiş, araştırmacıya ölçme ve kıyaslama becerileri kazandırmıştır. Okuyucuya az bilinen, yerel takımların tarihi hakkında izlenim kazandırılmaya çalışılmıştır.
  • Thumbnail Image
    ItemOpen Access
    StyleRes: transforming the residuals for real ımage editing with StyleGAN
    (IEEE, 2023-07-22) Pehlivan, Hamza; Dalva, Yusuf; Dündar, Aysegül
    We present a novel image inversion framework and a training pipeline to achieve high-fidelity image inversion with high-quality attribute editing. Inverting real images into StyleGAN’s latent space is an extensively studied problem, yet the trade-off between the image reconstruction fidelity and image editing quality remains an open challenge. The low-rate latent spaces are limited in their expressiveness power for high-fidelity reconstruction. On the other hand, high-rate latent spaces result in degradation in editing quality. In this work, to achieve high-fidelity inversion, we learn residual features in higher latent codes that lower latent codes were not able to encode. This enables preserving image details in reconstruction. To achieve high-quality editing, we learn how to transform the residual features for adapting to manipulations in latent codes. We train the framework to extract residual features and transform them via a novel architecture pipeline and cycle consistency losses. We run extensive experiments and compare our method with state-of-the-art inversion methods. Qualitative metrics and visual comparisons show significant improvements. Code: https://github.com/hamzapehlivan/StyleRes