This page has only limited features, please log in for full access.
The inherent variability of large-scale renewable energy generation leads to significant difficulties in microgrid energy management. Likewise, the effects of human behaviors in response to the changes in electricity tariffs as well as seasons result in changes in electricity consumption. Thus, proper scheduling and planning of power system operations require accurate load demand and renewable energy generation estimation studies, especially for short-term periods (hour-ahead, day-ahead). The time-sequence variation in aggregated electrical load and bulk photovoltaic power output are considered in this study to promote the supply-demand balance in the short-term optimal operational scheduling framework of a reconfigurable microgrid by integrating the forecasting results. A bi-directional long short-term memory units based deep recurrent neural network model, DRNN Bi-LSTM, is designed to provide accurate aggregated electrical load demand and the bulk photovoltaic power generation forecasting results. The real-world data set is utilized to test the proposed forecasting model, and based on the results, the DRNN Bi-LSTM model performs better in comparison with other methods in the surveyed literature. Meanwhile, the optimal operational scheduling framework is studied by simultaneously making a day-ahead optimal reconfiguration plan and optimal dispatching of controllable distributed generation units which are considered as optimal operation solutions. A combined approach of basic and selective particle swarm optimization methods, PSO&SPSO, is utilized for that combinatorial, non-linear, non-deterministic polynomial-time-hard (NP-hard), complex optimization study by aiming minimization of the aggregated real power losses of the microgrid subject to diverse equality and inequality constraints. A reconfigurable microgrid test system that includes photovoltaic power and diesel distributed generators is used for the optimal operational scheduling framework. As a whole, this study contributes to the optimal operational scheduling of reconfigurable microgrid with electrical energy demand and renewable energy forecasting by way of the developed DRNN Bi-LSTM model. The results indicate that optimal operational scheduling of reconfigurable microgrid with deep learning assisted approach could not only reduce real power losses but also improve system in an economic way.
Fatma Yaprakdal; Mustafa Berkay Yılmaz; Mustafa Baysal; Amjad Anvari-Moghaddam. A Deep Neural Network-Assisted Approach to Enhance Short-Term Optimal Operational Scheduling of a Microgrid. Sustainability 2020, 12, 1653 .
AMA StyleFatma Yaprakdal, Mustafa Berkay Yılmaz, Mustafa Baysal, Amjad Anvari-Moghaddam. A Deep Neural Network-Assisted Approach to Enhance Short-Term Optimal Operational Scheduling of a Microgrid. Sustainability. 2020; 12 (4):1653.
Chicago/Turabian StyleFatma Yaprakdal; Mustafa Berkay Yılmaz; Mustafa Baysal; Amjad Anvari-Moghaddam. 2020. "A Deep Neural Network-Assisted Approach to Enhance Short-Term Optimal Operational Scheduling of a Microgrid." Sustainability 12, no. 4: 1653.
Coordinating two or more dynamic systems such as autonomous vehicles or satellites in a distributed manner poses an important research challenge. Multiple approaches to this problem have been proposed including Nonlinear Model Predictive Control (NMPC) and its model-free counterparts in reinforcement learning (RL) literature such as Deep QNetwork (DQN). This initial study aims to compare and contrast the optimal control technique, NMPC, where the model is known, with the popular model-free RL method, DQN. Simple distributed variants of these for the specific problem of balancing and synchronising two highly unstable cart-pole systems are investigated numerically. We found that both NMPC and trained DQN work optimally under ideal model and small communication delays. While NMPC performs sub-optimally under a model-mismatch scenario, DQN performance naturally does not suffer from this. Distributed DQN needs a lot of realworld experience to be trained but once it is trained, it does not have to spend its time finding the optimal action at every time-step like NMPC. This illustrative comparison lays a foundation for hybrid approaches, which can be applied to complex multi-agent scenarios.
Ifrah Saeed; Tansu Alpcan; Sarah M. Erfani; Mustafa Berkay Yılmaz. Distributed Nonlinear Model Predictive Control and Reinforcement Learning. 2019 Australian & New Zealand Control Conference (ANZCC) 2019, 1 -3.
AMA StyleIfrah Saeed, Tansu Alpcan, Sarah M. Erfani, Mustafa Berkay Yılmaz. Distributed Nonlinear Model Predictive Control and Reinforcement Learning. 2019 Australian & New Zealand Control Conference (ANZCC). 2019; ():1-3.
Chicago/Turabian StyleIfrah Saeed; Tansu Alpcan; Sarah M. Erfani; Mustafa Berkay Yılmaz. 2019. "Distributed Nonlinear Model Predictive Control and Reinforcement Learning." 2019 Australian & New Zealand Control Conference (ANZCC) , no. : 1-3.
Signature representations that are extracted by convolutional neural networks (CNN) can achieve low error rates. However, a trade-off exists between such models’ complexities and hand-crafted features’ slightly higher error rates. A novel writer-dependent (WD) recurrent binary pattern (RBP) network, and a novel signer identification CNN is proposed. RBP network is a recurrent neural network (RNN) to learn the sequential relation between binary pattern histograms over image windows. A novel histogram selection method is introduced to remove the stop-word codes. Dimensionality is reduced by more than 25% while improving the results. This work is the first to combine binary patterns and RNNs for static signature verification. Several test sets, derived from large-scale and popular databases (GPDS-960 and GPDS-Synthetic-10000) are used. Without training any global classifier, RBP network provides competitive equal error rates (EER). The proposed architectures are compared and integrated with other recent CNN models. Score-level integration of WD classifiers trained with different representations are investigated. Cross-validation tests demonstrate the EERs reduced compared to the best single classifier. A state-of-the-art EER of 1.11% is reported with a global decision threshold (0.57% EER with user-based thresholds) on GPDS-160 database.
Mustafa Berkay Yılmaz; Kağan Öztürk. Recurrent Binary Patterns and CNNs for Offline Signature Verification. Advances in Intelligent Systems and Computing 2019, 417 -434.
AMA StyleMustafa Berkay Yılmaz, Kağan Öztürk. Recurrent Binary Patterns and CNNs for Offline Signature Verification. Advances in Intelligent Systems and Computing. 2019; ():417-434.
Chicago/Turabian StyleMustafa Berkay Yılmaz; Kağan Öztürk. 2019. "Recurrent Binary Patterns and CNNs for Offline Signature Verification." Advances in Intelligent Systems and Computing , no. : 417-434.
Signature verification task needs relevant signature representations to achieve low error rates. Many signature representations have been proposed so far. In this work we propose a hybrid user-independent/dependent offline signature verification technique with a two-channel convolutional neural network (CNN) both for verification and feature extraction. Signature pairs are input to the CNN as two channels of one image, where the first channel always represents a reference signature and the second channel represents a query signature. We decrease the image size through the network by keeping the convolution stride parameter large enough. Global average pooling is applied to decrease the dimensionality to 200 at the end of locally connected layers. We utilize the CNN as a feature extractor and report 4.13% equal error rate (EER) considering 12 reference signatures with the proposed 200-dimensional representation, compared to 3.66% of a recently proposed technique with 2048-dimensional representation using the same experimental protocol. When the two methods are combined at score level, more than 50% improvement (1.76% EER) is achieved demonstrating the complementarity of them. Sensitivity of the model to gray-level and binary images is investigated in detail. One model is trained using gray-level images and the other is trained using binary images. It is shown that the availability of gray-level information in train and test data decreases the EER e.g. from 11.86% to 4.13%. information about the claimed identity and they can usually be detected with very small error rates. Our focus in this work is offline signature verification where the query is either genuine signature or skilled forgery. Format of the signature image can be binary, gray-level or color. To the best of our knowledge, no public color signature database is available. However the distinction between binary and gray-level image is critical, as a gray-level image carries more information than the binary one such as the pressure of the stroke. Performance of signature verification systems is generally measured by equal error rate (EER) which is the error rate when the false accept (FA) and false reject (FR) rates are equal. If the EER is not reported, distinguishing error rate (DER) can be calculated which is simply the average of FA and FR.
Mustafa Berkay Yılmaz; Kagan Ozturk. Hybrid User-Independent and User-Dependent Offline Signature Verification with a Two-Channel CNN. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2018, 639 -6398.
AMA StyleMustafa Berkay Yılmaz, Kagan Ozturk. Hybrid User-Independent and User-Dependent Offline Signature Verification with a Two-Channel CNN. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2018; ():639-6398.
Chicago/Turabian StyleMustafa Berkay Yılmaz; Kagan Ozturk. 2018. "Hybrid User-Independent and User-Dependent Offline Signature Verification with a Two-Channel CNN." 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) , no. : 639-6398.
Speech analysis can be used for healthcare tasks such as pathology detection. Conventionally, a speech-language pathologist is specialized to detect anomalies from speech. Speech disorders result from a variety of causes such as brain injury, stroke, hearing loss, developmental delay or emotion alteration. Content of the speech is often not of interest for pathology detection, but characteristics are. In the literature of automatic pathology detection by speech analysis, physiological pathologies such as nodule and cancer are taken into account along with neurodegenerative brain disorders such as Parkinson's disease, Alzheimer's disease and mild cognitive impairment. As the problem of pathology detection from speech has become a vast research area, comprehensive reviews are needed by researchers to contribute novel approaches. In this study, a literature survey on pathology detection is provided including data types, features, classification methods and accuracy rates.
Mustafa Berkay Yılmaz; Mounim A. El Yacoubi. Methods of pathology detection by speech analysis: Survey. 2017 International Conference on Computer Science and Engineering (UBMK) 2017, 28 -33.
AMA StyleMustafa Berkay Yılmaz, Mounim A. El Yacoubi. Methods of pathology detection by speech analysis: Survey. 2017 International Conference on Computer Science and Engineering (UBMK). 2017; ():28-33.
Chicago/Turabian StyleMustafa Berkay Yılmaz; Mounim A. El Yacoubi. 2017. "Methods of pathology detection by speech analysis: Survey." 2017 International Conference on Computer Science and Engineering (UBMK) , no. : 28-33.
Face recognition is a mature domain with lots of different techniques proposed in the literature. Convolutional neural networks have been the most successful approach to face recognition problem recently. In this work, performance of three different face recognition models are compared. Features are extracted using a pre-trained convolutional neural network. The first model is trained using the available face images of a subject as positive samples and all other available face images as negative samples. In this case, recognition is done by looking at the scores of binary verification models. The second model is trained using the available face images of a subject as positive samples and all other registered subjects' available face images as negative samples (one versus all). The third model is trained using the training samples of a subject and other subjects one by one (one-versus-one). These models are compared in terms of recognition accuracy, efficiency, suitability to incremental learning, complexity, rejection accuracy, score normalization necessity. We show that even when other enrolled subjects are not taken into account as negative samples, verification model is easy to manage and outperforms other models.
Kagan Ozturk; Mustafa Berkay Yılmaz. A comparison of classification approaches for deep face recognition. 2017 International Conference on Computer Science and Engineering (UBMK) 2017, 227 -232.
AMA StyleKagan Ozturk, Mustafa Berkay Yılmaz. A comparison of classification approaches for deep face recognition. 2017 International Conference on Computer Science and Engineering (UBMK). 2017; ():227-232.
Chicago/Turabian StyleKagan Ozturk; Mustafa Berkay Yılmaz. 2017. "A comparison of classification approaches for deep face recognition." 2017 International Conference on Computer Science and Engineering (UBMK) , no. : 227-232.
Offline signature verification is a task that benefits from matching both the global shape and local details; as such, it is particularly suitable to a fusion approach. We present a system that uses a score-level fusion of complementary classifiers that use different local features (histogram of oriented gradients, local binary patterns and scale invariant feature transform descriptors), where each classifier uses a feature-level fusion to represent local features at coarse-to-fine levels. For classifiers, two different approaches are investigated, namely global and user-dependent classifiers. User-dependent classifiers are trained separately for each user, to learn to differentiate that user’s genuine signatures from other signatures; while a single global classifier is trained with difference vectors of query and reference signatures of all users in the training set, to learn the importance of different types of dissimilarities. The fusion of all classifiers achieves a state-of-the-art performance with 6.97% equal error rate in skilled forgery tests using the public GPDS-160 signature database. The proposed system does not require skilled forgeries of the enrolling user, which is essential for real life applications.
Mustafa Berkay Yılmaz; Berrin Yanıkoğlu. Score level fusion of classifiers in off-line signature verification. Information Fusion 2016, 32, 109 -119.
AMA StyleMustafa Berkay Yılmaz, Berrin Yanıkoğlu. Score level fusion of classifiers in off-line signature verification. Information Fusion. 2016; 32 ():109-119.
Chicago/Turabian StyleMustafa Berkay Yılmaz; Berrin Yanıkoğlu. 2016. "Score level fusion of classifiers in off-line signature verification." Information Fusion 32, no. : 109-119.
A labeled text corpus made up of Turkish papers' titles, abstracts and keywords is collected. The corpus includes 35 number of different disciplines, and 200 documents per subject. This study presents the text corpus' collection and content. The classification performance of Term Frequcney - Inverse Document Frequency (TF-IDF) and topic probabilities of Latent Dirichlet Allocation (LDA) features are compared for the text corpus. The text corpus is shared as open source so that it could be used for natural language processing applications with academic purposes.
Secil Öztürk; Bulent Sankur; Tunga Güngör; Mustafa Berkay Yilmaz; Bilge Koroglu; Onur Agin; Mustafa Isbilen; Çağdas. Ulaş; Mehmet Ahat. Turkish labeled text corpus. 2014 22nd Signal Processing and Communications Applications Conference (SIU) 2014, 1395 -1398.
AMA StyleSecil Öztürk, Bulent Sankur, Tunga Güngör, Mustafa Berkay Yilmaz, Bilge Koroglu, Onur Agin, Mustafa Isbilen, Çağdas. Ulaş, Mehmet Ahat. Turkish labeled text corpus. 2014 22nd Signal Processing and Communications Applications Conference (SIU). 2014; ():1395-1398.
Chicago/Turabian StyleSecil Öztürk; Bulent Sankur; Tunga Güngör; Mustafa Berkay Yilmaz; Bilge Koroglu; Onur Agin; Mustafa Isbilen; Çağdas. Ulaş; Mehmet Ahat. 2014. "Turkish labeled text corpus." 2014 22nd Signal Processing and Communications Applications Conference (SIU) , no. : 1395-1398.
Mustafa Berkay Yilmaz; Hakan Erdoğan; Mustafa Unel. Facial feature extraction using a probabilistic approach. Signal Processing: Image Communication 2012, 27, 678 -693.
AMA StyleMustafa Berkay Yilmaz, Hakan Erdoğan, Mustafa Unel. Facial feature extraction using a probabilistic approach. Signal Processing: Image Communication. 2012; 27 (6):678-693.
Chicago/Turabian StyleMustafa Berkay Yilmaz; Hakan Erdoğan; Mustafa Unel. 2012. "Facial feature extraction using a probabilistic approach." Signal Processing: Image Communication 27, no. 6: 678-693.
We present an offline signature verification system based on a signature's local histogram features. Test signature is divided into zones using both the Cartesian and log polar coordinate systems and histogram of oriented gradients (HOG) is calculated for each zone. Verification is considered as a two-class classification problem and for this purpose, a user independent Support Vector Machine (SVM) model is trained using both genuine and skilled forgery signatures of a completely different set of people than those in the test set. For each feature type, a single SVM model which learns the differences of query and reference signatures' feature vectors, is trained. The fusion of all classifiers, using skilled forgeries as negative test examples, achieves a 24.30% equal error rate in the GPDS-160 signature database, with 5 references.
Mustafa Berkay Yılmaz; Berrin Yanikoglu. Effect of alignment and multiple-scale features in offline signature verification. 2012 20th Signal Processing and Communications Applications Conference (SIU) 2012, 1 -4.
AMA StyleMustafa Berkay Yılmaz, Berrin Yanikoglu. Effect of alignment and multiple-scale features in offline signature verification. 2012 20th Signal Processing and Communications Applications Conference (SIU). 2012; ():1-4.
Chicago/Turabian StyleMustafa Berkay Yılmaz; Berrin Yanikoglu. 2012. "Effect of alignment and multiple-scale features in offline signature verification." 2012 20th Signal Processing and Communications Applications Conference (SIU) , no. : 1-4.
We present an offline signature verification system based on a signature's local histogram features. The signature is divided into zones using both the Cartesian and polar coordinate systems and two different histogram features are calculated for each zone: histogram of oriented gradients (HOG) and histogram of local binary patterns (LBP). The classification is performed using Support Vector Machines (SVMs), where two different approaches for training are investigated, namely global and user-dependent SVMs. User-dependent SVMs, trained separately for each user, learn to differentiate a user's signature from others, whereas a single global SVM trained with difference vectors of query and reference signatures' features of all users, learns how to weight dissimilarities. The global SVM classifier is trained using genuine and forgery signatures of subjects that are excluded from the test set, while user dependent SVMs are separately trained for each subject using genuine and random forgeries. The fusion of all classifiers (global and user-dependent classifiers trained with each feature type), achieves a 15.41 % equal error rate in skilled forgery test, in the GPDS 160 signature database without using any skilled forgeries in training.
Mustafa Berkay Yılmaz; Berrin Yanikoglu; Caglar Tirkaz; Alisher Kholmatov. Offline signature verification using classifier combination of HOG and LBP features. 2011 International Joint Conference on Biometrics (IJCB) 2011, 1 -7.
AMA StyleMustafa Berkay Yılmaz, Berrin Yanikoglu, Caglar Tirkaz, Alisher Kholmatov. Offline signature verification using classifier combination of HOG and LBP features. 2011 International Joint Conference on Biometrics (IJCB). 2011; ():1-7.
Chicago/Turabian StyleMustafa Berkay Yılmaz; Berrin Yanikoglu; Caglar Tirkaz; Alisher Kholmatov. 2011. "Offline signature verification using classifier combination of HOG and LBP features." 2011 International Joint Conference on Biometrics (IJCB) , no. : 1-7.
“Tandem approach” is a method used in speech recognition to increase performance by using classifier posterior probabilities as observations in a hidden Markov model. In this work we study the effect of using multiple visual tandem features to improve audio-visual recognition accuracy. In addition, we investigate methods to combine outputs of several audio and visual tandem classifiers with a classifier fusion system to generate outputs using learned weights. Experiments show that both approaches help to improve audio-visual speech recognition with respect to regular audio-visual speech recognition especially in noisy environments.
Ibrahim Saygin Topkaya; Mehmet Umut Şen; Mustafa Berkay Yilmaz; Hakan Erdogan. Improving speech recognition with audio-visual tandem classifiers and their fusions. 2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU) 2011, 407 -410.
AMA StyleIbrahim Saygin Topkaya, Mehmet Umut Şen, Mustafa Berkay Yilmaz, Hakan Erdogan. Improving speech recognition with audio-visual tandem classifiers and their fusions. 2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU). 2011; ():407-410.
Chicago/Turabian StyleIbrahim Saygin Topkaya; Mehmet Umut Şen; Mustafa Berkay Yilmaz; Hakan Erdogan. 2011. "Improving speech recognition with audio-visual tandem classifiers and their fusions." 2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU) , no. : 407-410.
Lip segmentation is an important problem which is necessary to be solved in many applications, especially in audio-visual speech recognition. In this paper, a level-set based method that utilizes adaptive color distributions and shape priors for lip segmentation is introduced. More precisely, an implicit curve representation which learns the color information of lip and non-lip points and shape information of lip regions from a training set is employed. The model can adapt itself to the image of interest using a coarse elliptical region. Extracted lip contour provides detailed information about the lip shape. We show that using shape priors improve the segmentation performance, especially the recall rate.
Mustafa Berkay Yılmaz; Hakan Erdogan; Mustafa Unel. Using shape priors for improved lip segmentation. 2010 IEEE 18th Signal Processing and Communications Applications Conference 2010, 288 -291.
AMA StyleMustafa Berkay Yılmaz, Hakan Erdogan, Mustafa Unel. Using shape priors for improved lip segmentation. 2010 IEEE 18th Signal Processing and Communications Applications Conference. 2010; ():288-291.
Chicago/Turabian StyleMustafa Berkay Yılmaz; Hakan Erdogan; Mustafa Unel. 2010. "Using shape priors for improved lip segmentation." 2010 IEEE 18th Signal Processing and Communications Applications Conference , no. : 288-291.
A facial feature extraction method is proposed in this work, which uses location and texture information given a face image. Location and texture information can automatically be learnt by the system, from a training data. Best facial feature locations are found by maximizing the joint distribution of location and texture information of facial features. Performance of the method was found promising after it is tested using 100 test images. Also it is observed that this new method performs better than active appearance models for the same test data.
Mustafa Berkay Yilmaz; Hakan Erdogan; Mustafa Unel. Statistical facial feature extraction using joint distribution of location and texture information. 2009 IEEE 17th Signal Processing and Communications Applications Conference 2009, 616 -619.
AMA StyleMustafa Berkay Yilmaz, Hakan Erdogan, Mustafa Unel. Statistical facial feature extraction using joint distribution of location and texture information. 2009 IEEE 17th Signal Processing and Communications Applications Conference. 2009; ():616-619.
Chicago/Turabian StyleMustafa Berkay Yilmaz; Hakan Erdogan; Mustafa Unel. 2009. "Statistical facial feature extraction using joint distribution of location and texture information." 2009 IEEE 17th Signal Processing and Communications Applications Conference , no. : 616-619.
In this work, we propose a method which can extract critical points on a face using both location and texture information. This new approach can automatically learn feature information from training data. It finds the best facial feature locations by maximizing the joint distribution of location and texture parameters. We first introduce an independence assumption. Then, we improve upon this model by assuming dependence of location parameters but independence of texture parameters. We model combined location parameters with a multivariate Gaussian for computational reasons. The texture parameters are modeled with a Gaussian mixture model. It is shown that the new method outperforms active appearance models for the same experimental setup.
Mustafa Berkay Yilmaz; Hakan Erdogan; Mustafa Unel. Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information. Transactions on Petri Nets and Other Models of Concurrency XV 2009, 1171 -1180.
AMA StyleMustafa Berkay Yilmaz, Hakan Erdogan, Mustafa Unel. Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information. Transactions on Petri Nets and Other Models of Concurrency XV. 2009; ():1171-1180.
Chicago/Turabian StyleMustafa Berkay Yilmaz; Hakan Erdogan; Mustafa Unel. 2009. "Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 1171-1180.