Institutional Repository of Academic Research University of Macedonia
Not a member yet
2215 research outputs found
Sort by
Enhancing Deep Learning Model Explainability in Brain Tumor Datasets Using Post-Heuristic Approaches
No full textThe application of deep learning models in medical diagnosis has showcased considerable efficacy in recent years. Nevertheless, a notable limitation involves the inherent lack of explainability during decision-making processes. This study addresses such a constraint by enhancing the interpretability robustness. The primary focus is directed towards refining the explanations generated by the LIME Library and LIME image explainer. This is achieved through post-processing mechanisms based on scenario-specific rules. Multiple experiments have been conducted using publicly accessible datasets related to brain tumor detection. Our proposed post-heuristic approach demonstrates significant advancements, yielding more robust and concrete results in the context of medical diagnosis.10923
Rapid prototyping of process-driven applications using low-code development platforms: A case study from the Greek public sector
No full textThis paper investigates the feasibility of rapid prototyping for process-driven applications using Low-Code Development Platforms (LCDPs). The authors analyze various LCDPs and their key features such as drag-and-drop UI development, process modeling with BPMN, and data manipulation capabilities. The paper proposes a development methodology that leverages BPMN for process modeling and integrates it with a LCDP for rapid application development. The process models are used to guide the development process including the database creation, UI development, and code writing (PL/SQL). To demonstrate the effectiveness of the approach, the authors implement a real-world public service application. The selected process involves a citizen submitting a request and supporting documents, followed by validation and potential compensation by a government agency. The proposed approach details the conversion of the public service process to an executable BPMN model and its subsequent implementation, including database design, webpage development, and code writing. The results suggest that LCDPs with BPMN support can enable rapid development of process-driven applications compared to traditional coding methods. Additionally, using BPMN for process modeling streamlines the design phase and facilitates parallel development and testing. While acknowledging limitations like the need for further development process refinement, the authors conclude that the proposed methodology offers a promising approach for rapid prototyping of process-driven applications using LCDPs.6506562024 International Conference Automatics and Informatics (ICAI
Evaluating support systems and interface efficiency in Hour of Code’s Minecraft Adventurer
No full textHour of Code is a widely recognized global event that aims to introduce programming to novice users and integrate computer science into education. This paper presents an analysis of the effectiveness of the support system and user interface of Minecraft Adventurer, a serious game designed for the Hour of Code global event. Although previous studies have primarily focused on the educational benefits of Hour of Code games, there has been limited research on their support methods. Therefore, this paper aims to address this gap with an empirical study of the experience of 104 students who played the game for one hour. Student progress was tracked by an administering teacher and after the game session, a questionnaire was administered to collect data on the participant’s perceptions of the support system, interface efficiency, and overall experience with Hour of Code. The results of the study reveal significant problems with the aforementioned systems, which apply not only to Minecraft Adventurer but also to several other similar serious games. Additionally, the findings showed a correlation between the utilization of the support system and student performance, indicating that student’s comprehension of the support system significantly influences their learning outcomes. This paper concludes by providing potential solutions to address the identified insufficiencies, offering valuable insights for future researchers and game developers on the design and evaluation of serious games for educational purposes.2910118691188
A practical approach for technical debt prioritization based on class-level forecasting
No full textMonitoring technical debt (TD) is considered highly important for software companies, as it provides valuable information on the effort required to repay TD and in turn maintain the system. When it comes to TD repayment, however, developers are often overwhelmed with a large volume of TD liabilities that they need to fix, rendering the procedure effort demanding. Hence, prioritizing TD liabilities is of utmost importance for effective TD repayment. Existing approaches rely on the current TD state of the system; however, prioritization would be more efficient by also considering its future evolution. To this end, the present work proposes a practical approach for prioritization of TD liabilities by incorporating information retrieved from TD forecasting techniques, emphasizing on the class-level granularity to provide highly actionable results. Specifically, the proposed approach considers the change proneness and forecasted TD evolution of software artifacts and combines it with proper visualization techniques, to enable the early identification of classes that are more likely to become unmaintainable. To demonstrate and evaluate the approach, an empirical study is conducted on six real-world applications. The proposed approach is expected to facilitate developers better plan refactoring activities, in order to manage TD promptly and avoid unforeseen situations long term.364e256
What Is Being Patented in Software Engineering?: Empirical Evidence From the U.S. Patent and Trademark Office
No full textIn this study, we collect software engineering patents data and conduct an exploratory analysis to describe the U.S. Patent and Trademark Office patent landscape in terms of what is being patented (software engineering aspects), by whom (organizations), and where (countries).41112313
Forecasting exchange rate volatility: An amalgamation approach
No full textThe importance of exchange rate volatility forecasting has both practical and academic merit. Our aim is to provide a comprehensive analysis of the forecasting ability of financial and macroeconomics variables for future exchange rate volatility. We employ seven widely traded currencies against the US dollar and examine linear models and a variety of machine learning, dimensionality reduction and forecast combination approaches, along with creating a grand forecast (amalgamation approach) from these approaches. Our findings highlight the predictive power of the amalgamation approach, as well as the positive contribution of macroeconomic and financial variables in the forecasting experiment. Furthermore, we generate forecasts on the separate frequencies of volatility using wavelet analysis, in order to extract frequency-related information and examine timing effects in the performance of the methods.9710206
Cross-media advertising strategies and brand attitude: the role of cognitive load
No full textIn recent years, cross-media advertising has received widespread attention from researchers and practitioners seeking effective ways to communicate with their audience. Building on Kahneman’s dual-system theory, the present article proposes a model of the impact of cross-media advertising on brand attitude (Abr). An eye-tracking experiment with 60 participants indicates that simultaneous (vs. sequential) exposure to ads for the same brand on TV and the Internet increases cognitive load and, through subjective comprehension, decreases brand attitude. Two online experiments with 395 and 198 participants in a low- and high-involvement product category, respectively, validate the proposed model. Experiment 2 reveals that in sequential exposure to TV and the internet, the fit between campaign ads further decreases the cognitive load leading to improved brand attitude. Experiment 3 strongly suggests that in simultaneous exposure, synchronous (vs. asynchronous) ads reduce cognitive demands and, through subjective comprehension and TV ad engagement, improve brand attitude.43460363
The Role of Artificial Intelligence of Things in Achieving Sustainable Development Goals: State of the Art
No full textWith the environmental and societal changes, the achievement of sustainable development goals (SDGs) and the realization of sustainability in general is now more important than ever. Through a bibliometric analysis and scientific mapping analysis, this study aims to explore and provide a review regarding the role of artificial intelligence (AI), the Internet of Things (IoT), and artificial intelligence of things (AIoT) in realizing sustainable development and achieving SDGs. AIoT can be defined as the combination of AI with IoT to create more efficient and data-driven interconnected, intelligent, and autonomous IoT systems and infrastructure that use AI methods and algorithms. The analysis involved 9182 documents from Scopus and Web of Science (WoS) from 1989 to 2022. Descriptive statistics of the related documents and the annual scientific production were explored. The most relevant and impactful authors, articles, outlets, affiliations, countries, and keywords were identified. The most popular topics and research directions throughout the years and the advancement of the field and the research focus were also examined. The study examines the results, discusses the main findings, presents open issues, and suggests new research directions. Based on the results of this study, AIoT emerged as an important contributor in ensuring sustainability and in achieving SDGs.244109
COVID-19, tourism and road traffic accidents: Evidence from Greece
No full textThe COVID-19 pandemic has resulted in the implementation of traffic and movement restrictions as governments were trying to limit the spread of the virus. Tourism has been affected by these travel restrictions. We examine the impact of curfews and the re-opening of borders on road traffic accidents. We investigate the effects of lockdown on motor vehicle collisions by analyzing recorded car accidents in 58 districts in Greece. We employ a difference-in-differences approach to compare motor vehicle collisions in 2020 with the previous five years. We reveal a decline in road traffic collisions during the curfew period (with 1617 fewer collisions). This is followed by an increase after the re-opening of borders (168 more vehicle collisions in tourist-popular areas despite the decline in tourist arrivals), compared to what would have been expected in the absence of the pandemic restrictions.16889391
A Platform for Time-Sensitive Networking in Converged IoT-Cloud Environments
No full textIoT-enabled applications benefit from various forms of digital twinning, such as the so-called Virtual Objects (VOs). A crucial requirement in the communication among IoT devices and their associated VOs is low latency. In this respect, we showcase a software platform for Time-Sensitive Networking (TSN), which enables the rapid computation of TSN schedules, based on flow demands, and the configuration of Gate Control Lists (GCLs) on the TSN bridges that reside between IoT Gateways and VOs.94962024 27th Conference on Innovation in Clouds, Internet and Networks (ICIN