Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
46 results
Search Results
Publication Metadata only Face frontalization enhanced by deep learning, Derin Öǧrenme Destekli Yüz Önleştirme(Institute of Electrical and Electronics Engineers Inc., 2017) Çelik, Anıl; Arica, Nafiz; Çelik, Anıl, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this study, a new approach based on 3-D models and deep learning to frontalize face images is proposed. Specifically designed for facial expression analysis, the proposed approach aims to reduce possible negative effects that a posed face image can generate, by normalizing the face region. In the first phase, the face image is semi-frontalized, with a pre-established 3-D reference model based approach. Then, missing regions on semi-frontalized images due to geometric transformation are reconstructed with the help of a denoising stacked autoencoder network. In this phase, missing regions created by line of sight are learned, with a deep architecture, using numerous images. When examined, it can be said that, faces acquired with the proposed approach, are objectively better than the faces acquired with a deep learning or 3-D based method alone. Therefore, it is assumed that the proposed approach can be used in face based computer vision methods as a beneficial pre-processing step. © 2017 Elsevier B.V., All rights reserved.Publication Metadata only Facial emotion classification using deep embedding with triplet loss function, Üçlü Yitim Fonksiyonu Tabanli Derin Gömme ile YÜz Duygu Siniflandirmasi(Institute of Electrical and Electronics Engineers Inc., 2017) Bircanoglu, Cenk; Arica, Nafiz; Bircanoglu, Cenk, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this paper, a deep embedding method using triplet loss function is proposed for classification of the emotions in face images. The originality of proposed method lies in the loss function, different from the other deep learning-based facial emotion classification approaches. The input face images are embedded into a lower dimensional feature space using a multi-layer convolutional neural network. In this embedding process the loss function is calculated by taking triple samples in the training dataset. For each sample in batches, two samples are selected in such a way that one of them is from the same class and the other one from the different class. The loss function aims to close the samples belonging to the same class to each other in the Euclidean space and to move away from the samples in the different class. In the performance analysis of proposed method, two popular deep architectures, namely AlexNet and VGG are used on two datasets called CIFE and GaMo. The experiments show that the proposed method outperforms the other popular loss functions and the available studies on this particular datasets. © 2017 Elsevier B.V., All rights reserved.Publication Metadata only Auto-encoder based cognitive analysis of questionnary, Oto-kodlayicilarla anketlerin bilişsel analizi(Institute of Electrical and Electronics Engineers Inc., 2018) Akay, Simge; Korkmaz, Hande; Arica, Nafiz; Akay, Simge, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Korkmaz, Hande, Müh. Ve Doga Bil. Fakültesi, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this study we propose a new method for Likert scale questionnary data analysis using auto-encoders. The proposed method extracts the patterns, which maximally activate the neurons of the hidden layer in the auto-encoder, trained by the questionnary data. These patterns are thought to be cognitive patterns that are influenced by participants filling the questionnary. In the experiments, we employ a questionnary designed to measure the confidence level of a blog author on the web. The cognitive patterns obtained in the auto-encoder are considered as the components that form the general approaches of the participants. In two cognitive patterns drawn from the questionnary, it is observed that the blogger's expertise, integrity, benevolance are evaluated in decreasing or increasing order by the participants. It has also been observed that the proposed method can be used to correct the unintentional mistakes in questionnary answers. © 2018 Elsevier B.V., All rights reserved.Publication Metadata only An ontology based semantic representation for Turkish Cuisine, Türk mutfaǧi için ontoloji tabanli semantik gösterim(Institute of Electrical and Electronics Engineers Inc., 2018) Ergün, Övgü Öztürk; Öztürk, Bengü; Ergün, Övgü Öztürk, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Öztürk, Bengü, İnönü Mah, Yeditepe University, Istanbul, TurkeyFollowing recent advances in digital technologies, many data in various domains have been transformed into digital world and shared with millions of users via social media and web technologies. As a result, big amount of data has presented many challenging problems in different fields, e.g internet of things, artificial intelligence. One of application areas is in food domain. Recognition of food category from images, automatic recipe retrieval from internet and analysis and matching of food images with recipes, ingredients, nutrition values bring cooperation of multi disciplines and technologies. In this work, for the first time, semantical analysis of Turkish Cuisine is held and various information related to food in Turkish Cuisine is structured in a hierarchical ontology model. A new database containing 50 different food categories and related images is constructed and linked with data such as food properties, recipes, etc. As a result, multimodal information retrieval can be achieved faster in a more semantic way. At the same time, food image classification with deep learning methods is performed and faster connection of recognized food category to related semantic data is provided. © 2018 Elsevier B.V., All rights reserved.Publication Metadata only A comparison of activation functions in artificial neural networks, Yapay sinir aǧlarinda aktivasyon fonksiyonlarinin karşilaştirilmasi(Institute of Electrical and Electronics Engineers Inc., 2018) Bircanoglu, Cenk; Arica, Nafiz; Bircanoglu, Cenk, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this study, the effects of Activation Functions (AF) in Artificial Neural Network (ANN) on regression and classification performance are compared. In comparisons, success rates in test data and duration of training are evaluated for both problems. A total of 11 AF functions, 10 AF commonly used in the literature and Square function proposed in this study, are compared using 7 different datasets, 2 for regression and 5 for classification. 3 different ANN architectures, which are considered to be the most appropriate for each dataset are employed in the experiments. As a result of totally 231 different training procedures, the effects of Afs are examined for different datasets and architectures. Similarly, the effects of AF on training time are shown for different datasets. In the experiments it is shown that ReLU is the most succesfull AF in general purposes. In addition to ReLU, Square function gives the better results in image datasets. © 2018 Elsevier B.V., All rights reserved.Publication Metadata only Automatically inserting ads into images, Imgelere Otomatik Reklam Yerlȩstirme(Institute of Electrical and Electronics Engineers Inc., 2018) Citak, Erol; Eseoglu, Mustafa Furkan; Celik, Ibrahim Omer; Disanli, Onur; Kutluk, Sezer; Arica, Nafiz; Citak, Erol, Ar-Ge Merkezi, Istanbul, Turkey; Eseoglu, Mustafa Furkan, Ar-Ge Merkezi, Istanbul, Turkey; Celik, Ibrahim Omer, Ar-Ge Merkezi, Istanbul, Turkey; Disanli, Onur, Ar-Ge Merkezi, Istanbul, Turkey; Kutluk, Sezer, Ar-Ge Merkezi, Istanbul, Turkey; Arica, Nafiz, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyIn this study a new method is proposed for inserting advertisement visuals into images automatically and without disturbing the image content. In this method important areas are determined using deep learning based object, face and text detection, edge and saliency maps are obtained, and these information are used for the identification of the best location for inserting the advertisement visual. In order to select the best available advertisement visual from an advertisement pool shape and color features are utilized. © 2018 Elsevier B.V., All rights reserved.Publication Metadata only Flood detection by using FCN-AlexNet(SPIE [email protected], 2019) Son, Keumyoung; Yıldırım, Mustafa Eren; Park, Jangsik; Song, Jongkwan; Zhou, J.; Verikas, A.; Nikolaev, D.P.; Radeva, P.; Son, Keumyoung, Department of Electronics Engineering, Kyungsung University, Busan, South Korea; Yıldırım, Mustafa Eren, Department of Electrical and Electronic Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Park, Jangsik, Department of Electronics Engineering, Kyungsung University, Busan, South Korea; Song, Jongkwan, Department of Electronics Engineering, Kyungsung University, Busan, South KoreaFloods are the natural disasters which can give serious damage to properties, roads, vehicles and even people. These damages bring huge payload both to individuals and governments. Thus, a system which can detect floods at early stage and warn the related offices immediately will be very useful for public. Detecting flooding early can save human lives, time, money for the government, as well as an important step to move towards smarter cities. In this paper, we propose the use of a deep learning architecture to detect floods in certain susceptible areas. We used FCN AlexNet deep learning architecture to train and test our dataset. Images of our dataset are collected from two PTZ cameras with different view angles. According to the experimental results, used system gets above 95% classification accuracy on both cameras. © 2019 Elsevier B.V., All rights reserved.Publication Metadata only Detection of e-commerce anomalies using LSTM-recurrent neural networks(SciTePress, 2019) Bozbura, Merih; Tunc, Hunkar C.; Kusak, Miray Endican; Sakar, C. Okan; Hammoudi, S.; Quix, C.; Bernardino, J.; Bozbura, Merih, Inveon Digital Commerce Solutions Limited, Istanbul, Turkey; Tunc, Hunkar C., Department of Computer and Information Science, Universität Konstanz, Konstanz, Germany; Kusak, Miray Endican, Inveon Digital Commerce Solutions Limited, Istanbul, Turkey; Sakar, C. Okan, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyAs the e-commerce sales grow in global retail sector year by year, detecting anomalies that occur in the most important key performance indicators (KPI) in real-time has become a critical requirement for e-commerce companies. Such anomalies that may arise from software updates, server failures, or incorrect price entries cause substantial revenue loss in the meantime until they are detected with their root-causes. In this paper, we present a comparative analysis of various anomaly detection methods in detecting e-commerce anomalies. For this purpose, we first present the univariate analysis of six commonly used anomaly detection methods on two important KPIs of an e-commerce website. The highest F1 Scores and recall values on the test sets of both KPIs are obtained using Long-Short Term Memory (LSTM) network, showing that LSTM fits better to the dynamics of e-commerce KPIs than time-series based prediction methods. Then, in addition to the univariate analysis of the methods, we feed the campaign information into LSTM network considering that campaigns have significant effects on the values of KPIs in e-commerce domain and this information can be helpful to prevent false positives that may occur in the campaign periods. The results also show that constructing a multivariate LSTM by feeding the campaign information as an additional input improves the adaptability of the model to sudden changes occurring in campaign periods. © 2020 Elsevier B.V., All rights reserved.Publication Metadata only Analysis of price models in istanbul stock exchange, Borsa istanbul hisse senedi fiyat modelleri analizi(Institute of Electrical and Electronics Engineers Inc., 2019) Tekin, Sefa; Çanakoǧlu, Ethem; Tekin, Sefa, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Çanakoǧlu, Ethem, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, TurkeyEquity investments are one of the most important asset classes. Equity investments have high return yield however also high risk due to the variability of share prices. Therefore, precise share price modeling is essential. In this study, we examined the data of 30 leading companies of Borsa Ë™Istanbul. We applied ARIMA, Machine learning algorithms and Deep learning techniques (LSTM) to BIST30 stock prices. As a result of the computational analysis, we observed that ARIMA performs better than LSTM and linear regression performs better than other machine learning techniques. © 2020 Elsevier B.V., All rights reserved.Publication Metadata only Turkish Movie Genre Classification from Poster Images using Convolutional Neural Networks(Institute of Electrical and Electronics Engineers Inc., 2019) Gözüacik, Necip; Sakar, C. Okan; Gözüacik, Necip, NETAS, Istanbul, Turkey; Sakar, C. Okan, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyAccessing to the best matching multimedia data is a trending topic due to the enormous amount of demand from people for movies, online TV series, videos etc. Advertising/Introducing form/image of such multimedia applications is important to give the key information to the audience. Sometimes a movie poster may play an important role to present the movie genre correctly. In recent years, Convolutional Neural Networks (CNN) as a deep learning architecture achieved state of-the- art performance in many image processing and recognition applications. In this paper, we implement transfer learning and fine-tuning methods on top of Google Inception-v3 algorithm, which is one of the most popular CNN architectures in this domain, and present comparative results of these methods in classifying the movie genre on a dataset consisting of Turkish movie posters. The obtained results show that fine tuning method performs better than pure CNN and transfer learning models on movie genre classification task. © 2020 Elsevier B.V., All rights reserved.