Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
18 results
Search Results
Now showing 1 - 10 of 18
Conference Object Citation - Scopus: 11An Analysis of Large Language Models and Langchain in Mathematics Education(Association for Computing Machinery, 2023) Soygazi,F.; Oğuz, DamlaThe development of large language models (LLMs) has led to the consideration of new approaches, particularly in education. Word problems, especially in subjects like mathematics, and the need to solve these problems by collectively addressing specific stages of reasoning, have raised the question of whether LLMs can be successful in this area as well. In our study, we conducted analyses by asking mathematics questions especially related to word problems using ChatGPT, which is based on the latest language models like Generative Pretrained Transformer (GPT). Additionally, we compared the correct and incorrect answers by posing the same questions to LLMMathChain, a mathematics-specific LLM based on the latest language models like LangChain. It was observed that the answers obtained were more successful with ChatGPT (GPT 3.5), particularly in the field of mathematics. However, both language models were found to be below expectations, particularly in word problems, and suggestions for improvement were provided. © 2023 ACM.Conference Object Citation - Scopus: 1Computing a Parametric Reveals Relation for Bounded Equal-Conflict Petri Nets(Springer, 2024) Adobbati, Federica; Bernardinello, Luca; Kılınç Soylu, Görkem; Pomello, LuciaIn a distributed system, in which an action can be either “hidden” or “observable”, an unwanted information flow might arise when occurrences of observable actions give information about occurrences of hidden actions. A collection of relations, i.e. reveals and its variants, is used to model such information flow among transitions of a Petri net. This paper recalls the reveals relations defined in [3], and proposes an algorithm to compute them on bounded equal-conflict PT systems, using a smaller structure than the one defined in [3]. © 2024, The Author(s), under exclusive license to Springer-Verlag GmbH, DE, part of Springer Nature.Conference Object Citation - Scopus: 1Monocular Vision-Based Prediction of Cut-In Manoeuvres With Lstm Networks(Springer, 2023) Nalçakan, Yağız; Baştanlar, YalınAdvanced driver assistance and automated driving systems should be capable of predicting and avoiding dangerous situations. In this paper, we first discuss the importance of predicting dangerous lane changes and provide its description as a machine learning problem. After summarizing the previous work, we propose a method to predict potentially dangerous lane changes (cut-ins) of the vehicles in front. We follow a computer vision-based approach that only employs a single in-vehicle RGB camera, and we classify the target vehicle’s maneuver based on the recent video frames. Our algorithm consists of a CNN-based vehicle detection and tracking step and an LSTM-based maneuver classification step. It is computationally efficient compared to other vision-based methods since it exploits a small number of features for the classification step rather than feeding CNNs with RGB frames. We evaluated our approach on a publicly available driving dataset and a lane change detection dataset. We obtained 0.9585 accuracy with the side-aware two-class (cut-in vs. lane-pass) classification model. Experiment results also reveal that our approach outperforms state-of-the-art approaches when used for lane change detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.Article Citation - Scopus: 5Unifying Behavioral and Feature Modeling for Testing of Software Product Lines(World Scientific Publishing, 2023) Belli, Fevzi; Tuğlular, Tuğkan; Ufuktepe, EkincanExisting software product line (SPL) engineering testing approaches generally provide positive testing that validates the SPL's functionality. Negative testing is commonly neglected. This research aims to unify behavioral and feature models of an SPL, enable testing before and after variability binding for domain-centric and product-centric testing, and combine positive and negative testing for a holistic testing view. This study suggests behavioral modeling with event sequence graphs (ESGs). This heterogeneous modeling strategy supports bottom-up domain testing and top-down product testing with the feature model. This new feature-oriented ESG test creation method generates shorter test sequences than the original ESG optimum test sequences. Statechart and original ESG test-generating methods are compared. Positive testing findings are similar. The Statechart technique generated 12 test cases with 59 events, whereas the ESG technique created six test cases with 60 events. The ESG technique generated 205 negative test cases with 858 events with the Test Suite Designer tool. However, the Conformiq Designer tool for the Statechart technique does not have a negative test case generation capability. It is shown that the proposed ESG-based holistic approach confirms not only the desirable (positive) properties but also the undesirable (negative) ones. As an additional research, the traditional ESG test-generating approach is compared to the new feature-oriented method on six SPLs of different sizes and features. Our case study results show that the traditional ESG test generation approach demonstrated higher positive test generation scores compare to the proposed feature-oriented test generation approach. However, our proposed feature-oriented test generation approach is capable of generating shorter test sequences, which could be beneficial for reducing the execution time of test cases compared to traditional ESG approach. Finally, our case study has also shown that regardless of the test generation approach, there has been found no significant difference between the Bottom-up and Top-down test strategies with respect to their positive test generation scores. © World Scientific Publishing Company.Article Spectral Test Generation for Boolean Expressions(World Scientific Publishing, 2023) Ayav, TolgaThis paper presents a novel method for testing Boolean expressions. It is based on spectral, aka Fourier analysis of Boolean functions which is exploited to generate test inputs. The approach has three important contributions: (i) It generates a relatively small test suite with a high capability of fault detection, (ii) The test suite is prioritized such that expected fault detection time is shorter, (iii) It is entirely mathematical relying on a simple and straightforward formula. The proposed method is formulated and evaluations are performed on both synthetic and real expressions. It is also compared with two common test generation criteria, MC/DC and Minimal MUMCUT. Evaluations show that the test suite generated by the spectral approach is relatively small while expressing the capability of a better and quicker fault detection. The approach presented in this paper provides a useful insight into how spectral/Fourier analysis of Boolean functions can be exploited in software testing.Article Citation - WoS: 2Citation - Scopus: 3Mutation-Based Minimal Test Suite Generation for Boolean Expressions(World Scientific Publishing, 2023) Ayav, Tolga; Belli, FevziBoolean expressions are highly involved in control flows of programs and software specifications. Coverage criteria for Boolean expressions aim at producing minimal test suites to detect software faults. There exist various testing criteria, efficiency of which is usually evaluated through mutation analysis. This paper proposes an integer programming-based minimal test suite generation technique relying on mutation analysis. The proposed technique also takes into account the cost of fault detection. The technique is optimal such that the resulting test suite guarantees to detect all the mutants under given fault assumptions, while maximizing the average percentage of fault detection of a test suite. Therefore, the approach presented can also be considered as a reference method to check the efficiency of any common technique. The method is evaluated using four well-known real benchmark sets of Boolean expressions and is also exemplary compared with MCDC criterion. The results show that the test suites generated by the proposed method provide better fault coverage values and faster fault detection.Article Studying the Co-Evolution of Source Code and Acceptance Tests(World Scientific Publishing, 2023) Yalçın, Ali Görkem; Tuğlular, TuğkanTesting is a vital part of achieving good-quality software. Deploying untested code can cause system crashes and unexpected behavior. To reduce these problems, testing should evolve with coding. In addition, test suites should not remain static throughout the software versions. Since whenever software gets updated, new functionalities are added, or existing functionalities are changed, test suites should be updated along with the software. Software repositories contain valuable information about the software systems. Access to older versions and differentiating adjacent versions' source code and acceptance test changes can provide information about the evolution process of the software. This research proposes a method and implementation to analyze 21 open-source real-world projects hosted on GitHub regarding the co-evolution of both software and its acceptance test suites. Related projects are retrieved from repositories, their versions are analyzed, graphs are created, and analysis related to the co-evolution process is performed. Observations show that the source code is getting updated more frequently than the acceptance tests. They indicate a pattern that source code and acceptance tests do not evolve together. Moreover, the analysis showed that a few acceptance tests test most of the functionalities that take a significant line of code.Data Paper Database Covering the Previously Excluded Daily Life Activities(2023) Mihçin, Şenay; Şahin, Ahmet Mert; Yılmaz, Mehmet; Alpkaya, Alican Tuncay; Tuna, Merve; Can, Nuray Korkmaz; Şahin, Serap; Akdeniz, Sevinç; Tosun, AliyeIn biomedical engineering, implants are designed according to the boundary conditions of gait data and tested against. However, due to diversity in cultural backgrounds, religious rituals might cause different ranges of motion and different loading patterns. Especially in the Eastern part of the world, diverse Activities of Daily Living (ADL) consist of salat, yoga rituals, and different style sitting postures. Although databases cover ADL for the Western population, a database covering these diverse activities of the Eastern world, specific to these populations is non-existent. To include previously excluded ADL is a key step in understanding the kinematics and kinetics of these activities. By means of developments in motion capture technologies, excluded ADL data are captured to obtain the coordinate values to calculate the range of motion and the joint reaction forces. This study focuses on data collection protocol and the creation of an online database of previously excluded ADL activities, targeting 200 healthy subjects via Qualisys and IMU motion capture systems, and force plates, from West and Middle East Asian populations. Anthropometrics are known to affect kinematics and kinetics which are also included in the collected data. The current version of the database covers 50 volunteers for 12 different activities, the database aims for 100- male and 100- female healthy volunteers as the final target including C3D and BVH file types. The tasks are defined and listed in a table to create a database to make a query based on age, gender, BMI, type of activity and motion capture system. The data is collected only from a healthy population to understand healthy motion patterns during these previously excluded ADLs. The collected data is to be used for designing implants to allow these sorts of activities to be performed without compromising the quality of life of patients performing these activities in the future.Conference Object Citation - Scopus: 1A Novel Feature To Predict Buggy Changes in a Software System(Springer, 2022) Yılmaz, Rahime; Nalçakan, Yağız; Haktanır, ElifResearchers have successfully implemented machine learning classifiers to predict bugs in a change file for years. Change classification focuses on determining if a new software change is clean or buggy. In the literature, several bug prediction methods at change level have been proposed to improve software reliability. This paper proposes a model for classification-based bug prediction model. Four supervised machine learning classifiers (Support Vector Machine, Decision Tree, Random Forrest, and Naive Bayes) are applied to predict the bugs in software changes, and performance of these four classifiers are characterized. We considered a public dataset and downloaded the corresponding source code and its metrics. Thereafter, we produced new software metrics by analyzing source code at class level and unified these metrics with the existing set. We obtained new dataset to apply machine learning algorithms and compared the bug prediction accuracy of the newly defined metrics. Results showed that our merged dataset is practical for bug prediction based experiments. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Conference Object Citation - WoS: 1On Defining Security Metrics for Information Systems(Brill Academic Publishers, 2005) Koltuksuz, Ahmet[No abstract available]