Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
2 results
Search Results
Conference Object Citation - WoS: 1Citation - Scopus: 3Endüstriyel Kablosuz Algılayıcı Ağlarda Hata Kontrol Sistemlerinin Ağ Yaşam Süresine Etkileri(IEEE, 2019-04) Tekin, Nazli; Gungor, V. CagriDue to the harsh channel conditions of the industrial environment, the data transmission over wireless channel suffers from erroneous packets. The energy consumption of error control schemes is of vital importance for battery-powered Wireless Sensor Networks (WSNs). In this paper, the performance evaluation of error control schemes namely, Automatic Repeat Request (ARQ), Forward Error Correction (FEC) and Hybrid ARQ (HARQ) in industrial environment in terms of energy efficiency is presented. The impact of the existing error control schemes on the industrial wireless sensor network lifetime is analyzed. A novel Mixed Integer Programming (MIP) framework is developed to maximize network lifetime. Performance results show that utilizing BCH (31,21,5) for Telos at the link layer maximizes the network lifetime while attaining the desired application reliability rate.Conference Object Citation - WoS: 1Citation - Scopus: 5Credit Risk Analysis Based on Hybrid Classification: Case Studies on German and Turkish Credit Datasets(IEEE, 2018-05) Cetiner, Erkan; Kocak, Taskin; Gungor, V. CagriIn 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.