Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
Search Results
Conference Object Citation - WoS: 2Citation - Scopus: 3Impact of Variations in Synthetic Training Data on Fingerprint Classification(IEEE, 2019) İrtem, Pelin; İrtem, Emre; Erdoğmuş, NesliCreating and labeling data can be extremely time consuming and labor intensive. For this reason, lack of sufficiently large datasets for training deep structures is often noted as a major obstacle and instead, synthetic data generation is proposed. With their high acquisition and labeling complexity, this also applies to fingerprints. In the literature, a number of synthetic fingerprint generation systems have been proposed, but mostly for algorithm evaluation purposes. In this paper, we aim to analyze the use of synthetic fingerprint data with different levels of degradation for training deep neural networks. Fingerprint classification problem is selected as a case-study and the experiments are conducted on a public domain database, NIST SD4. A positive correlation between the synthetic data variation and the classification rate is observed while achieving state-of-the-art results.Conference Object Citation - WoS: 3Citation - Scopus: 6Spl-At Gherkin: a Gherkin Extension for Feature Oriented Testing of Software Product Lines(IEEE, 2019) Tuğlular, Tuğkan; Şensülün, SecanAs cloud platforms turn into software product lines (SPLs), testing products composed of customer selected features becomes more and more important. In this paper, we propose a feature-oriented testing approach for platform-based SPLs through a novel extension to Gherkin called SPL-AT Gherkin and a novel automatic test method generation technique, which utilizes TestNG framework. We demonstrate the applicability of the proposed approach by a case study.Conference Object Citation - WoS: 5Citation - Scopus: 5Featured Event Sequence Graphs for Model-Based Incremental Testing of Software Product Lines(IEEE, 2019) Tuğlular, Tuğkan; Beyazıt, Mutlu; Öztürk, DilekThe goal of software product lines (SPLs) is rapid development of high-quality software products in a specific domain with cost minimization. To assure quality of software products from SPLs, products need to be tested systematically. However, testing every product variant in isolation is generally not feasible for large number of product variants. An approach to deal with this issue is to use incremental testing, where test artifacts that are developed for one product are reused for another product which can be obtained by incrementally adding features to the prior product. We propose a novel model-based test generation approach for products developed using SPL that follows incremental testing paradigm. First, we introduce Featured Event Sequence Graphs (FESGs), an extension of ESGs, that provide necessary definitions and operations to support commonalities and variabilities in SPLs with respect to test models. Then we propose a test generation technique for the product variants of an SPL, which starts from any product. The proposed technique with FESGs avoids redundant test generation for each product from SPL. We compare our technique with in-isolation testing approach by a case study.