Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
6 results
Search Results
Editorial Iwsm-Mensura 2024 Proceedings Preface(CEUR-WS, 2024) Trudel, S.; Demirors, O.; Moulla, D.K.; Hacaloglu, T.[No abstract available]Conference Object Evaluating CUDA-Aware Approximate Computing Techniques(CEUR-WS, 2024) Öz, I.Approximate computing techniques offer performance improvements by performing inexact computations. Moreover, CUDA programs written to be executed on GPU devices employ specific features to utilize the parallel computation units of heterogeneous GPU architectures. While generic software-level approximate computing techniques have been applied to heterogeneous CUDA programs, CUDA-specific approaches may introduce promising performance improvements by not corrupting the target computations. In this work, we propose software approximation techniques for CUDA programs: kernel-aware loop perforation, partition-level synchronization, block-level atomic operations, and warp divergence elimination. We perform source code transformations on target benchmark programs by applying our techniques. We evaluate performance improvements by trading off accuracy in our target computations. Our experimental results reveal that CUDA-aware approximation techniques offer significant performance improvements at the expense of acceptable accuracy loss. © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).Conference Object Software Change Size Measurement: an Exploratory Systematic Mapping Study(CEUR-WS, 2024) Hacaloglu, T.; Demirörs, Onur; Küçükateş Ömüral, N.; Kılınç Soylu, G.; Demirörs, O.Change in software projects can occur through various channels. Customers may request modifications or new features; appraisal activities such as reviews or testing may uncover issues that necessitate adjustments, or products may need to adapt to changes in their operating environment. Therefore, it is essential to assess these changes explicitly and objectively within the scope of software engineering activities. Specifically, quantifying change by measuring its size is crucial for successful management, as without a meaningful metric, it is impossible to accurately assess its impact on the project's effort, schedule, and cost. This study aims to explore the concept of change in software engineering literature, with a particular emphasis on the methods used to measure its size. The study reveals that the current literature on this topic is still in its early stages and the measurement and estimation of changes remain challenging throughout both development and maintenance phases. According to the reviewed articles, size is primarily used for effort estimation. Various software artifacts from different stages of the Software Development Life Cycle (SDLC) serve as input for change measurement, highlighting the need for a versatile size measurement applicable across all SDLC phases. Most of the reviewed articles interpret change in the context of maintenance activities. This research sets a benchmark for the status of software size measures for software change and highlights related problems to suggest further research topics. © 2024 Copyright for this paper by its authors.Conference Object Explaining Graph Neural Network Predictions for Drug Repurposing(CEUR-WS, 2024) Loesch, J.; Yang, Y.; Ekmekci, P.; Dumontier, M.; Celebi, R.Graph Neural Networks (GNNs) are powerful tools for graph-related tasks, excelling in progressing graph-structured data while maintaining permutation invariance. However, their challenge lies in the obscurity of new node representations, hindering interpretability. This paper introduces a framework addressing this limitation by explaining GNN predictions. The proposed method takes any GNN prediction, for which it returns a concise subgraph as explanation. Utilizing Saliency Maps, an attribution gradient-based technique, we enhance interpretability by assigning importance scores to entities withing the knowledge graph via backpropagation. Evaluated on the Drug Repurposing Knowledge Graph, Graph Attention Network achieved a Hits@5 score of 0.451 and a Hits@10 score of 0.672. GraphSAGE demonstrated notable results with the highest recall rate of 0.992. Our framework underscores GNN efficacy and interpretability, which is crucial in complex scenarios like drug repurposing. Illustrated through an Alzheimer’s disease case study, our approach provides meaningful and comprehensible explanations for GNN predictions. This work contributes to advancing the transparency and utility of GNNs in real-world applications. © 2024 Copyright for this paper by its authors.Conference Object Citation - Scopus: 3Predicting Software Size and Effort From Code Using Natural Language Processing(CEUR-WS, 2024) Tenekeci, S.; Demirörs, Onur; Ünlü, H.; Dikenelli, E.; Selçuk, U.; Kılınç Soylu, G.; Demirörs, O.Software Size Measurement (SSM) holds a crucial role in software project management by facilitating the acquisition of software size, which serves as the primary input for development effort and schedule estimation. However, many small and medium-sized companies encounter challenges in conducting objective SSM and Software Effort Estimation (SEE) due to resource constraints and a lack of expert workforce. This often leads to inaccurate estimates and projects exceeding planned time and budget. Hence, organizations need to perform objective SSM and SEE with minimal resources and without relying on an expert workforce. In this research, we introduce two exploratory case studies aimed at predicting the functional size (COSMIC and Event-based size) and effort of software projects from the code using a deep-learning-based NLP model: CodeBERT. For this purpose, we collected and annotated two datasets consisting of 4800 Python and 1100 C# functions. Then, we trained a classification model to predict COSMIC data movements (entry, exit, read, write) and four regression models to predict Event-based size (interaction, communication, process) and effort. Despite utilizing a relatively small dataset for model training, we achieved promising results with an 84.5% accuracy for the COSMIC size, 0.13 normalized mean absolute error (NMAE) for the Event-based size, and 0.18 NMAE for the effort. These findings are particularly insightful as they demonstrate the practical utility of language models in SSM and SEE. © 2024 Copyright for this paper by its authors.Conference Object Yazilim Yapisal Kapsama Analizinde Testlerin Önceliklendirilmesi(CEUR-WS, 2015) Ayav,T.[No abstract available]