Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
4 results
Search Results
Publication Metadata only Reliable routing in wireless sensor networks for smart grid environments, Akilli şebeke ortaminda kablosuz algilayici aǧ teknolojisi ile güvenilir yönlendirme(2012) Şahin, Dilan; Bülbül, Şafak; Güngör, Vehbi Çağrı; Kocak, Taskin; Şahin, Dilan, Bahçeşehir Üniversitesi, Istanbul, Turkey; Bülbül, Şafak, Bahçeşehir Üniversitesi, Istanbul, Turkey; Güngör, Vehbi Çağrı, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kocak, Taskin, Bahçeşehir Üniversitesi, Istanbul, TurkeyThe environmental conditions, e.g., fading, multi-path, obstructions, in smart grid environment, prevent reliable and successful packet transmissions for Wireless Sensor Network (WSN) technology. To provide reliable communications with WSN, to overcome the harsh environmental conditions of smart grid, and to prolong the network life time, reliable link quality estimation should be made and routing algorithms which consider multiple conditions, e.g., energy consumption, shortest path and link quality, should be used. In this paper, the performances of routing algorithms which can address this need are compared in terms of average delay, network lifetime and packet delivery rate in smart grid substation environment. Moreover, WSN-based smart grid applications and the challenges in estimation of link quality are briefly explained. © 2012 IEEE. © 2012 Elsevier B.V., All rights reserved.Publication Metadata only From asia to europe: Short-term traffic flow prediction between continents(IEEE Computer Society [email protected], 2014) Kaya, Sevgi; Kilic, Necati; Kocak, Taskin; Güngör, Vehbi Çağrı; Kaya, Sevgi, Department of Computer Science, ETH Zürich, Zurich, Switzerland; Kilic, Necati, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kocak, Taskin, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey; Güngör, Vehbi Çağrı, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, TurkeyModelling the traffic flow and predicting the near-future traffic status are two challenging problems of the smart transportation on roads. The difficulty is particularly pronounced in forecasting the complex non-linear dynamics of flow. Most of the state-of-the-art work on traffic flow prediction determine the parameters based on the fundamental relationship between flow, density and speed without considering its influence to the consecutive one. However, these approaches tend to fail in real life scenarios due to the negligence of the spatio-temporal dependence of parameters within road segments. In this paper, we propose a new traffic flow model to predict the arterial travel time using probe data. We then evaluate our model under various traffic conditions to determine its feasibility for near-future traffic flow prediction. The proposed method presents promising results by outperforming the state-of-the-art in predicting near-future traffic flow on roads in case of sparse data and high flow density. © 2014 IEEE. © 2014 Elsevier B.V., All rights reserved.Publication Metadata only Evaluation of hybrid classification approaches: Case studies on credit datasets(Springer Verlag [email protected], 2018) Cetiner, Erkan; Güngör, Vehbi Çağrı; Kocak, Taskin; Perner, P.; Cetiner, Erkan, Bahçeşehir Üniversitesi, Istanbul, Turkey; Güngör, Vehbi Çağrı, Abdullah Gül Üniversitesi, Kayseri, Turkey; Kocak, Taskin, Bahçeşehir Üniversitesi, Istanbul, TurkeyHybrid classification approaches on credit domain are widely used to obtain valuable information about customer behaviours. Single classification algorithms such as neural networks, support vector machines and regression analysis have been used since years on related area. In this paper, we propose hybrid classification approaches, which try to combine several classifiers and ensemble learners to boost accuracy on classification results. We worked with two credit datasets, German dataset which is a public dataset and a Turkish Corporate Bank dataset. The goal of using such diverse datasets is to search for generalization ability of proposed model. Results show that feature selection plays a vital role on classification accuracy, hybrid approaches which shaped with ensemble learners outperform single classification techniques and hybrid approaches which consists SVM has better accuracy performance than other hybrid approaches. © 2018 Elsevier B.V., All rights reserved.Publication Metadata only Credit risk analysis based on hybrid classification: Case studies on German and Turkish credit datasets, Hibrid Siniflandirma Yöntemleriyle Kredi Risk Analizi: Alman ve Türk Kredi Verisetleri Üzerinde Vaka Çalismalari(Institute of Electrical and Electronics Engineers Inc., 2018) Cetiner, Erkan; Kocak, Taskin; Güngör, Vehbi Çağrı; Cetiner, Erkan, Fen Bilimleri Enstitusu, Bahçeşehir Üniversitesi, Istanbul, Turkey; Kocak, Taskin, Fen Bilimleri Enstitusu, Bahçeşehir Üniversitesi, Istanbul, Turkey; Güngör, Vehbi Çağrı, Bilgisayar Mühendisliǧi, Abdullah Gül Üniversitesi, Kayseri, TurkeyIn finance sector, credit risk analysis plays a major role in decision process. Banks and finance institutions gather large amounts of raw data from their customers. Data mining techniques can be employed to obtain useful information from this raw data. Several data mining techniques, such as support-vector machines (SVM), neural networks, naive-bayes, have already been used to classify customers. In this paper, we propose hybrid classification approaches, which try to combine several classifiers and ensemble learners to boost accuracy on classification results. Furthermore, we compare these approaches' performance with respect to their classification accuracy. We work with two diverse datasets, namely, German credit dataset and Turkish bank dataset. The goal of using such diverse dataset is to show generalization capabality of our approaches. Experimental results provide three important consequences. First, feature selection stage has a major role both on result accuracy and calculation complexity. Second, hybrid approaches have better generalability over single classifiers. Third, using SVM-Radial Basis Function (RBF) as the base classifier and a hybrid model member gives the best accuracy and type-1 accuracy results among others. © 2018 Elsevier B.V., All rights reserved.