New Trends in Computer Sciences

Review and experimental comparison of generative adversarial networks for synthetic image generation

2024-05-30T14:51:36+03:00

The application of machine learning algorithms has become widespread particularly in fields such as medicine, business, and commerce. However, achieving accurate classification results with these algorithms often relies on large-scale training datasets, making data collection a lengthy and complex process. This paper reviews the current utilization of generative adversarial network (GAN) architectures and discusses recent scientific research on their practical applications. The study emphasizes the significance of addressing data scarcity in the process of training the machine learning algorithms and highlights the potential of advanced GAN architectures, in particular StyleGAN2-ADA, to mitigate this challenge. The findings contribute to ongoing efforts aimed at enhancing the efficiency and applicability of artificial intelligence across diverse domains by presenting a viable solution to the constraint of limited training data for image classification tasks.

Educational data mining and learning analytics: text generators usage effect on students’ grades

2024-06-04T10:37:26+03:00

Today, various types of data are constantly growing, so they can be used for different purposes. In this investigation, educational data has been analyzed to determine the influence of assessment on student knowledge. The newly collected dataset has been prepared and statistically analyzed. The dataset consists of open-question answers collected on one study subject during the midterm exam at Vilnius Gediminas Technical University. The results of the statistical analysis have shown that by using the text generators, students obtained higher grades by paraphrasing the answers to the questions in good quality. Furthermore, research has shown which types of questions are more difficult for students to answer without additional material and using text generation tools. It can be useful for lecturers planning course assessment tasks.

Leveraging generative adversarial networks to improve training image dataset

2024-06-05T15:22:13+03:00

Convolutional neural networks (CNNs) are powerful models of deep learning that are widely used in computer vision classification tasks. The purpose of this study is to investigate the impact of datasets on CNN performance, employing original datasets and expanded datasets with synthetically generated images. The Generative Adversarial Network (GAN) is an unsupervised deep learning method used for synthetic data generation and can address the limitations of image augmentations. In this study, a new GAN architecture is used to synthesize high-resolution images when dealing with limited training data. The StyleGAN2-ADA model is specifically designed to generate high-quality images using limited datasets. Adaptive Discriminator Augmentation (ADA) dynamically adjusts data augmentation, enhancing discriminator efficiency and stability. The findings indicate a reduction in the likelihood of overfitting, enhancement in network generalization, mitigation of class imbalance concerns, and a concurrent increase in the accuracy and stability of network classification.

The efficiency of machine learning algorithms in classifying non-functional requirements

2024-06-19T12:50:22+03:00

Machine learning (ML) algorithms are more and more widely applied in various types of systems, so the research related to them is also increasing. One of the areas of research under consideration is the classification of non-functional requirements (NFRs) using ML algorithms. This area of research is important because the automatic classification of NFRs using high-performance ML algorithms and corresponding features helps requirements engineers classify non-functional requirements more accurately. This paper examines ML algorithms suitable for solving classification problems and their effectiveness in classifying non-functional requirements. Based on the described stages of the research methodology ML algorithms models were compared using the accuracy, precision, recall, and F-score metrics. A majority voting classifier model was created using Support Vector Machine, Naïve Bayes and K Nearest Neighbor Algorithm algorithms. After K-Fold cross validation were obtained these results: accuracy – 0.710 (scale from 0 to 1), precision – 0.845, recall – 0.814 and F-score – 0.815.

Identification of software quality attributes from code defect prediction: a systematic literature review

2024-06-27T13:03:38+03:00

Identifying and understanding reasons for deriving software development defects is crucial for ensuring software product quality attributes such as maintainability. This paper presents a systematic literature review and the objective is to analyze the suggestions of other authors regarding software code defect prediction using machine learning, deep learning, or other artificial intelligence methods for the identification of software quality. The systemic literature review reveals that many analyzed papers considered multiple software code defects, but they were analyzed individually. However, more is needed to identify software quality attributes. The more profound analysis of code smells indicates the significance when considering multiple detected code smells and their interconnectedness; it helps to identify the software quality sub-attributes of maintainability.