Epoka University

Context: The growing complexity of modern web and mobile applications, shaped by rapid UI/UX advancements and agile software development practices, demands efficient and automated recognition of graphical user interface (GUI) elements, as manual testing remains costly and time-consuming. Objective: This study aims to evaluate the performance of the YOLOv8 deep learning architecture for accurate recognition of diverse GUI components, such as buttons, fields, headings, links, and images, from real-world application screenshots. Method: A small YOLOv8 model was trained on the Roboflow GUI element detection dataset containing over 1,000 annotated website screenshots, using 35 training epochs, a batch size of 8, and an image resolution of 640×640. Results: The model achieved measurable improvements, with precision rising from 0.368 to 0.454, recall increasing from 0.296 to 0.425, and mAP50–95 improving from 0.101 to 0.232. Strongest detection was observed for buttons and input fields, while weaker performance was noted for iframes and labels due to their inherent ambiguity. Conclusions: The results demonstrate that YOLOv8 has significant potential in automating GUI recognition, reducing reliance on manual testing in agile workflows, and improving interface validation. Further optimization with larger datasets and advanced augmentation methods is recommended to enhance robustness and generalization

Abstract The successful implementation of sustainability in construction projects increases in urgency when considered against the specific economic, social and environmental pressure of particular regions. Kurdistan Region in Iraq faces major barriers in pursuing sustainable development because of its expanding infrastructure needs. The fuzzy analytic hierarchy process (FAHP) serves as the research method to find out and rank sustainability issues across regional construction projects. The implementation of expert opinions along with linguistic variables within fuzzy AHP improves uncertain decision-making processes to deliver enhanced evaluation of essential challenges. The main purpose of the study is to identify and assess a crucial sustainability’s challenges by ranking them based on their significant. The challenges have been categorized into six main categories: organization and managerial, cultural and human attitudes, technical, financial, governmental and regulatory and technological barriers. Among the others, governmental and regulatory occupied the first place with 0.319 normalized weight. While organization and managerial and cultural and human attitudes weighted 0.256 and 0.167 respectively as second and third significant barriers among main challenges groups. Ineffective government policies on green construction ranked the first barrier among the sub-main challenges that construction project faced in Kurdistan Region. On the other hand, Communication of clean technology advantages to home buyers is ranked the less significant barrier among the others. The result provides valuable insights for policymakers, project manager and stakeholders offering a structured approach to address sustainability concerns and improving construction practices.

The Responsibility to Protect (R2P) and the International Criminal Court (ICC) share a common moral foundation rooted in the post-WWII human rights agenda. They constitute the response of the international community to mass atrocities around the world. R2P, as a political and normative framework, seeks to ensure that states uphold their duty to protect populations from genocide, crimes against humanity, war crimes and ethnic cleaning, and the ICC as an independent judicial mechanism, aims to prosecute and try those individuals alleged to have committed mass atrocity crimes. This paper traces the historical foundations of both frameworks, shared objectives and conceptual complementarities that underpin their roles in atrocity prevention and response. It also explores the tensions that have emerged in their interaction, particularly in the face of political realities, issues of sovereignty and challenges of contested implementation. It further analyzes how the functions and relevance of R2P and ICC have evolved over time, how they have affected the response to more recent conflicts and how these developments have influenced their overall effectiveness. By situating R2P and the ICC within the broader architecture of atrocity prevention and accountability, the paper aims to offer a nuanced understanding of their interplay and propose pathways for enhancing their coherence and impact in the face of ongoing and future mass atrocities.

Purpose Over the last decades, Tirana has undergone continuous urban development, leading to denser urban fabric and a reduction in existing urban green spaces (UGS). This study examines the present distribution of UGS in Tirana and establishes a method for identifying suitable areas for future urban greenery. Design/methodology/approach The research begins by documenting the existing UGS using a combination of OpenStreetMap data and NDVI analysis. A service area network analysis is employed to assess UGS accessibility based on travel distance and time, and to identify areas that are unreachable. A multicriteria overlay suitability analysis is conducted to identify potential locations for new urban green spaces, and an accessibility analysis is performed to assess changes in the served area and verify the suitability of the proposed green spaces. Findings The NDVI analysis indicates that vegetation covers 29% of Tirana, while the thematic map illustrates that classified urban green spaces occupy only 11% of the city’s surface. The accessibility analysis shows that currently, half of the city is not served by UGS. This study implements a method to identify new locations for urban parks and pocket gardens. Evaluation results reveal that with the new UGS, approximately 2% of Tirana remains unserved, a significant improvement from the initial 52% unserved areas. Research limitations/implications The study focuses on green spaces located within Tirana’s administrative borders. For more precise results, peri-urban areas can be incorporated into the analysis. Originality/value This study presents a GIS-based framework for UGS allocation, classification, and distribution analysis. It emphasizes the need to address the uneven distribution of green spaces within the city and provides a decision-making tool for future urban planning initiatives.

Developments in the medical field have opened the opportunity to conduct analyses on a personalized patient level. One of the important analyses that can be conducted is the cellular response to engineered materials, and the most appropriate non-invasive methods are imaging. These images of the cells are unstained brightfield images, as they are acquired from multiparametric microfluidic chambers in the presence of biomaterials and fluids that can change the optical path length over time as the cells’ health state is monitored. These experimental conditions lead to an image dataset with unique illumination, texture, and noise spectrum. This study explores the optimization of supervised cell classification by combining feature extraction architectures and machine learning classifiers, with a focus on applications in biomaterial risk assessment. Brightfield microscopy images of three cell types (A549, BALB 3T3, and THP1) were analyzed to evaluate the impact of Inception V3, Squeeze Net, and VGG16 architectures paired with classifiers including KNN, Decision Tree, Random Forest, AdaBoost, Neural Networks, and Naïve Bayes. Dimensionality reduction using Information Gain was applied to improve computational efficiency and accuracy. Butterworth filters with varying parameters were used to balance the enhancement of image features and noise removal, improving classification performance in certain cases. Experimental results demonstrate that the VGG16 architecture, when paired with Neural Networks, achieves higher classification accuracy as measured by different metrics. The improved accuracy when using Butterworth filters compared to the unfiltered dataset and the differences between various Butterworth filters indicate the importance of optimizing filter parameters for these types of images.

Abstract This study investigates how cultural diversity affects entrepreneurship in the Western Balkans. We obtain insights into the complex dynamics by looking at variables like ethnic composition, language variety, and religious diversity, in conjunction with economic, institutional, and sociocultural issues. Additionally, we assess entrepreneurial activity including the number of new businesses started. Sociocultural factors, including social norms toward entrepreneurship, risk attitudes, and gender equality, are considered to uncover their influence on entrepreneurial behavior. Lastly, we focus on economic indicators of Western Balkans including GDP per capita, unemployment rate, and income inequality to provide context for their economic activity. This study underlines the significance of local environment and regional differences in fostering social integration and economic prosperity in Western Balkans. The results are useful for research, entrepreneurship, and policymaking. This study provides a comprehensive analysis of the relationship between cultural diversity and entrepreneurship in the Western Balkans, considering contextual factors and variations across countries. It sheds light on the importance of cultural diversity for entrepreneurial activity and offers actionable insights for various stakeholders.