Iatrellis Omiros | UNIVERSITY OF THESSALY, GREECE (original) (raw)

Papers by Iatrellis Omiros

J. Electrical Systems, 2024

Student dropout remains a pressing concern with significant socio-economic implications. This stu... more Student dropout remains a pressing concern with significant socio-economic implications. This study utilizes supervised
machine learning to forecast potential dropouts by analyzing a diverse array of factors including academic achievements, class attendance,
socio-economic backgrounds, and behavioral patterns. These factors are integrated into a comprehensive predictive model that enhances
our understanding of student retention and informs the design of targeted interventions. Through a comparative analysis of two prominent
algorithms, K-Nearest Neighbors and Naive Bayes, our research assesses the effectiveness of these methods using a detailed dataset. The
findings reveal that the Naive Bayes algorithm outperforms K-Nearest Neighbors in predicting student dropouts, offering valuable data
for educational practitioners focused on data-driven strategies to enhance student retention. The study advances the application of machine
learning in educational settings and contributes practical insights for the development of policies and interventions aimed at reducing
dropout rates, thereby enriching the academic discourse and improving educational outcomes.

Springer Nature, 2022

The Covid-19 pandemic has imposed new challenges in preserving the goal of developing smart and s... more The Covid-19 pandemic has imposed new challenges in preserving the goal of developing smart and sustainable cities worldwide while improving urban resilience. In the smart city domain, disaster or crisis management operations require contributions and collaboration of different type of entities with various functions, rules and protocols, forming complex contexts in decision making or event coordination. The management of the corresponding information usually coming from multiple heterogeneous sources and, sometimes with attributes revealing semantic inconsistencies constitutes an emerging challenge. Furthermore, the demand for interoperability between the various services and IoT devices at local and national level is imperative. Yet, existing literature highlights that the conceptualization of a holistic reference schema that covers all the dimensions of the smart city disaster/crisis management domain and allows the exchange of information through different agents has not been fully addressed so far. We present the RES-Q (RESCUE) semantic model, which includes the needed domain knowledge streams for the smart city post-disaster management domain. This model aims for data consolidation and linkage in order to be further utilized for the implementation of a common knowledge repository and advanced analysis. In this context, semantic web technologies are proposed as a promising solution for providing semantic interoperability in crisis and/or disaster management in the smart city discourse. Finally, data consolidation and harmonization methodology is presented, which is used for the integration of different data sources, according to the RES-Q model.

Proceedings of the 7th International Conference on Algorithms, Computing and Systems, 2023

In the era of data-driven decision-making, Higher Education Institutions (HEIs) can greatly benef... more In the era of data-driven decision-making, Higher Education Institutions (HEIs) can greatly benefit from the potential of eXplainable Artificial Intelligence (XAI) to provide transparent and interpretable insights. This paper presents the KONX (CONNECTS) approach, a comprehensive methodology that leverages semantic web technologies to create a dynamic and comprehensive knowledge graph for advanced predictive models in academic advising. The KONX methodology focuses on harmonizing heterogeneous educational data sources, enabling seamless data querying and manipulation. By incorporating a feedback mechanism, the KONX approach remains adaptable to changes in the academic domain, continuously updating and maintaining its knowledge representation. To practically apply and evaluate the proposed methodology, a prototype was implemented and tested on an experimental case study concerning student outcomes prediction. The implemented prototype includes a graphical SPARQL generator interface to streamline the construction of SPARQL queries in an integrated way. In this way, this paper proposes both a comprehensive XAI methodology and a holistic technological infrastructure for applying the methodology in real-time scenarios. By bridging the gap between AI decision-making and human-comprehensible explanations, the KONX approach enhances transparency and user trust in AI-driven systems in the education sector. CCS CONCEPTS • Computing methodologies • Artificial intelligence • Explainable Artificial Intelligence

Intelligent technologies permeate all aspects of contemporary society and urban life. It is essen... more Intelligent technologies permeate all aspects of contemporary society and urban life. It is essential to educate the workforce of smart cities in order to effectively meet emerging technological demands. In this paper, we present an e-course that focuses on discrete competencies associated with different smart city roles. Initially, we present the conceptual learning framework for the development of the competency-based learning course and we define the objectives of the research. The paper continues with a discussion of the model's application steps and an examination of the course's skills, competencies, and roles. The acquired knowledge was measured using pre-and post-course tests, and questionnaires were used to investigate the relevance and quality of the learning material and the learning acquisition of the participants. Evaluation results showed that the course was relevant to the concept of smart cities, useful for their work duties, while participation in the course resulted in increased overall competency in all three smart city job profiles.

CSUM2022, 2022

Disasters are characterized as a major problem worldwide and a significant threat to sustainable ... more Disasters are characterized as a major problem worldwide and a significant threat to sustainable development, causing the loss of lives, the destruction of infrastructure, economic disruption, etc. The implementation of policies and strategies that will prevent future disaster risk, reduce existing disaster risk, and manage residual risk has become more vital than ever. It requires multi-sector collaboration to achieve enhanced resilience to the multiple hazards so as to prevent and/or reduce the potential losses, assure prompt assistance to victims of disasters, and achieve rapid and effective recovery. Such an approach demands collaboration between scientists and authorities and proper use of the available information so that it can be understood and processed by all the involved stakeholders. The utilization of disaster risk information, along with the use of more sophisticated ICTs, will be able to provide policymakers with a holistic DRM, enabling decision support for a natural and/or man-made crisis. To that end, the key objective of this study was to collect previous research by conducting a Systematic Literature Review, in order to highlight the existing research approaches in ICT for DRM. To analyze and evaluate the findings, the selected studies were classified according to four areas: 1) Stakeholders, 2) Disaster phase, 3) Disaster type, 4) ICT. Additionally, a SWOT analysis was conducted to provide a holistic overview of ICTs and their applications in the DRM sector. Hence, our work attempts to present a comprehensive analysis of the research approaches and determines the arising opportunities and shortcomings that require the attention of the research community.

CSUM2022, 2022

The growing societal demands for Higher Education Institutions (HEIs) actions towards sustainable... more The growing societal demands for Higher Education Institutions (HEIs) actions towards sustainable development triggers new forms of educational programs and research activities. In line with this direction, the Living Lab (LL) approach provides a means to engage various actors in the process of development of a solution fostering inclusive 'quadruple helix' participation and open end-user-oriented innovation. Nowadays, LLs have become a strategy in many universities for co-creating impact for more sustainable and healthier cities and regions. However, LLs can create shared value for society, only if their long-term viability is ensured. The challenge is making LLs effective and self-supportive, but existing models lack a holistic and multi-perspective umbrella view over all dimensions, functions and stakeholder interrelations of a LL. In this paper, we present the conceptualization of the domain of LLs in Higher Education. We present the INVEST LL ontology (INVESTL 2) which models the needed domain knowledge streams for the LLs and consists of 3 main modules: 1) the Living Lab model, 2) the Business model and 3) the Quality Assurance model in education provision environments. Taking into account the multifaceted nature of this challenge, our proposal achieves a holistic conceptualization of the domain of LLs, in order to be further utilized for the implementation of a Semantic Web Rules Repository. This rule base is in control of the required streams of knowledge enclosed in the LL knowledge agendas for developing, recommending and executing tailored workplans to meet the LL goals. Finally, the INVESTL 2 ontology is applied for the definition of a semantic infrastructure for the RES-Q LL case study on disaster risk management.

ICONHIC 2022, 2022

During the last decade, communities at local and national level are implementing actions geared t... more During the last decade, communities at local and national level are implementing actions geared towards improving disaster resilience. In this context, the importance of ICT in disaster risk management is rapidly increasing globally, especially nowadays amidst the climate crisis and the covid-19 pandemic. However, disaster risk management operations require contributions and collaboration of different type of actors and infrastructures with different functions, rules, protocols and datasets, forming complex contexts in decision making and event coordination. Hence, semantic interoperability between the various stakeholders is one of the challenges to be confronted. In this paper, we present the RES-Q (RESCUE) approach that proposes an information technology solution concerning the real-time recommendation and orchestration of post-disaster response plans. The implemented RES-Q prototype comprises an expert system and a workflow execution engine based on an ontological infrastructure for modeling the response actions for each type of disaster. The ontological model is designed using a multi-layer approach encapsulating the required knowledge streams and a semantic rule repository. During the execution of a post-disaster plan, the system reasons over the rules and composes the next steps of the corresponding response processes. The rule repository is able to infer new knowledge as each plan progresses, which can update the RES-Q ontology accordingly.

J. Comput. Educ. 2022 Springer Nature, 2022

Students attending Higher Education Institutions (HEIs) are faced with a variety of complex decis... more Students attending Higher Education Institutions (HEIs) are faced with a variety of complex decisions and procedures. To provide students with more sustained and personalized advising, many HEIs turn to online academic advising systems and tools as a way to minimize costs and streamline their advising services. However, in such systems, uncertainty in the learner’s parameters is a factor, which makes the decision-making process more difficult. Fuzzy logic, a multivalued logic similar to human thinking and interpretation, is highly suitable and applicable for developing knowledge-based academic advising systems that conserve the inherent fuzziness in learner models. In this paper, an innovative hybrid software infrastructure is presented which integrates expert system, fuzzy reasoning, and ontological tools to provide reliable recommendations to students for the next appropriate learning step. The software comprises a fuzzy logic component that determines the student’s interest degree for a specific academic choice accompanied by an ontological model and a conventional rule-based expert system for the composition of personalized learning pathways. In order for the system to recommend the next step of the learning pathway, the output of the fuzzy logic component together with the knowledge that is modeled as part of the multi-facet ontology and the machine perceptible academic advising guidelines expressed as semantic rules interoperate in a dynamic and seamless manner. The paper presents the key modeling artifacts of the proposed approach and the architecture of the implemented prototype system. During the case study, the developed system yielded satisfactory results in terms of overall inter-rater reliability and usefulness.

PCI 2021: 25th Pan-Hellenic Conference on Informatics, 2022

Smart cities are complex ecosystems that use information and communication technologies for helpi... more Smart cities are complex ecosystems that use information and communication technologies for helping their citizens and organizations to face the challenges of urbanization, safety, resilience, and sustainability. The SmartDevOps project proposes a framework aiming to address the shortage of professional skills in municipalities. Following the increased use of AI methods to provide recommendations in training, there is also an increased need for formalization of existing courses to enable recommendations. This work is dedicated to the conceptual formal modeling of the delivered courses for gaining the competences required for smart city professionals by following the SmartDevOps methodology. We present the Smart City Competence Ontology (SCCompO) that provides a formalism for modeling concepts like competence, learning objective and outcome of courses that aims to cooperate with MOOC platform for training of Smart City professionals. It follows the modular, extensible structure of the curriculum, and it is designed to respond to questions regarding prerequisites and outcomes of job profiles, competences, and courses. The impact of using the developed ontology is to augment the MOOC platform by providing reasoning on course selection and their learning outcomes as well on the relations among these concepts in order to make decisions about the learners’ curricula.

Quality Assurance in Education, 2022

Purpose The purpose of this paper is to thoroughly assemble, analyze and synthesize previous re... more Purpose

The purpose of this paper is to thoroughly assemble, analyze and synthesize previous research to investigate and identify teaching staff competencies derived from the roles and tasks attributed to university professors.
Design/methodology/approach

In this literature review, the authors looked at both the conceptual framework exploring the educational concepts and the learning theories focusing on teaching staff roles and competencies in higher education. Thirty-nine scientific papers were studied in detail from a total of 102 results, which were eligible based on the preferred reporting items for systematic reviews and meta-analyses statement.
Findings

A multi-dimensional approach to teacher competencies in higher education was proposed, which consists of six main dimensions with their respective characteristics. Thirty-two discrete teaching staff competencies were identified and distributed in the aforementioned dimensions. The research revealed that specific competencies, such as the digital competence of teachers, which have lately become of high importance worldwide due to the COVID-19 pandemic implications, surprisingly, until recently, they were considered secondary in the educational process.
Research limitations/implications

The study was based on the existing literature without using data drawn from an appropriate questionnaire addressed to students and/or interviews with academics. In addition, in an effort to maintain a homogeneous base of teacher competencies, inclusion of domains of expertise was avoided. Further research should focus on designing and developing a holistic model using analytical learning approaches that will contribute to the assessment of teachers’ competencies and explore the relationship of these competencies to students’ academic achievement, contributing quality to higher education.
Practical implications

A specific framework of teacher competencies in higher education, in practice, can be a useful reference point not only for ensuring quality in the selection of teachers and their career-long professional development but also for national education policy strategies. The definition of teacher competencies framework contributes to facilitating effective dialogue for the evaluation and quality assurance in education between agencies, authorities, researchers, teachers, policymakers, education managers and different communities at large.
Social implications

These competencies are at the heart not only of the teaching and learning process but also in the workplace and in society in general and are increasingly recognized as essential. An adequately prepared community and management equipped with the required employee competencies is able to react immediately and in a positive way to any obstacle, yielding optimal results.
Originality/value

This is the first review, to the authors’ knowledge, to comprehensively explore the literature to identify, classify and rank the teaching staff competencies in higher education, revealing the gap between perceived and actual importance of various competencies.

MDPI / Electronics, 2021

Over recent years, massive open online courses (MOOCs) have gained increasing popularity in the f... more Over recent years, massive open online courses (MOOCs) have gained increasing popularity in the field of online education. Students with different needs and learning specificities are able to attend a wide range of specialized online courses offered by universities and educational institutions. As a result, large amounts of data regarding students’ demographic characteristics, activity patterns, and learning performances are generated and stored in institutional repositories on a daily basis. Unfortunately, a key issue in MOOCs is low completion rates, which directly affect student success. Therefore, it is of utmost importance for educational institutions and faculty members to find more effective practices and reduce non-completer ratios. In this context, the main purpose of the present study is to employ a plethora of state-of-the-art supervised machine learning algorithms for predicting student dropout in a MOOC for smart city professionals at an early stage. The experimental results show that accuracy exceeds 96% based on data collected during the first week of the course, thus enabling effective intervention strategies and support actions.

In this paper we describe an irrigation scheduling system based on wireless sensor network techno... more In this paper we describe an irrigation scheduling system based on wireless sensor network technology as applied in Precision Agriculture and particularly in Precision Irrigation. Precision agriculture, as opposed to traditional agriculture where the whole field is treated as uniform and homogeneous, is a modern method of agricultural practice where temporal and spatial information regarding the field and its parameters is utilized in order to optimize the efficiency of influxes (such as water and fertilizers), while minimizing the environmental effects of their use. Irrigation is a key agricultural process with direct consequences on the crop's yield and quality as well as on the environment, with soil humidity (water content of field) being a very important parameter in composing the appropriate irrigation routine for a field. Until recently, in order to measure soil humidity a farmer had to use practices that are both time and money consuming (e.g. use probes in various field...

4th International Conference on Computers in Management and Business (ICCMB2021), 2021

Services that collaborate alongside other services or systems for performing tasks, need to be aw... more Services that collaborate alongside other services or systems for performing tasks, need to be aware of either predetermined or other abrupt and unexpected behaviors in other to adapt theirs. The service behaviors we consider are performed in smart city domains which are dynamic environments where continuously new services appear, that usually have a large variation in the way they perform the same task. We use roles having teamwork behavior to represent the composition procedure in such domains, and we model the team of services through the individual behavior of each participant as well as their group goal. In this paper, we present a framework, which consists of the approach and IT system in order to serve the choreography between a large number of heterogeneous services so as to achieve a seamless and cooperative environment suitable for a smart city. This enables composite city services to adapt their behavior during execution and themselves intervene from inside the team if a possible unexpected behavior happens during the service activity, in order to run proactively and avoid obstacles or collisions. A scenario from a smart city domain illustrates that, services having different teamwork abilities are composed to a new one which inherits teamwork features and combines them to something novel.

4th SmartBlueCity Euro-Mediterranean Conference, 2020

Covid-19 epidemic has created new challenges for the development of Smart and Sustainable Cities.... more Covid-19 epidemic has created new challenges for the development of Smart and Sustainable Cities. It has proven that it is not anymore sufficient just to focus on providing services for quality of life, or for a better business ecosystems, but we need to prepare cities, so they are able to manage, adapt, maintain and ensure city services and enhance quality of life in the face of hazards, shocks and stresses (ISO 37123). According to this definition resilience does not include only earthquakes, fires, floods, etc. but as well whatever disrupts significantly the operation of a city either occasionally or periodically. Examples include high unemployment; endemic violence; health epidemics and chronic food and water shortages (Cities, 2016)
Even though some standards and projects exist in this area, we have not yet consensus on a common city resilience model that will able to describe what exactly constitutes resilience and a resilient city (Spaans, & Waterhout, 2017). Furthermore, up to now little emphasis has been given to the way municipalities are organized for addressing hazards and even less on training their personnel to the new skills required. Currently, these new required job profiles do not exist, they are overlooked, or they are partially described.
Rockefeller Foundation, founded in 2013 the “100 Resilient Cities (100RC)” project having as objective to help cities face three major threats and challenges: urbanization, globalization, and climate change. In the context of this project, a job profile named “City Chief Resilience Officer” was defined, but without sufficiently describing the required skills. In parallel, other projects e.g. “Smart DevOps competencies for smart cities” (devops.uth.gr) are attempting to define the required skills and job profiles needed for Smart and Sustainable Cities professionals (Kaufmann, 2020).
Obviously, we need to address the skills’ gap between today’s and future’s skills demands of municipal workforce by emphasizing on these emerging needs and by combining the needs for smart and resilient cities development. Exactly on this subject area, this paper presents the results of a survey that attempts to define the required skills for a “Smart and Resilience City Officers”.

46th Euromicro Conference on Software Engineering and Advanced Applications, 2020

In this paper we present a practical method that can be applied to support the prioritization of ... more In this paper we present a practical method that
can be applied to support the prioritization of large sets of
candidate software features in a requirements prioritization
process. We consider as prioritization criteria the
satisfaction/dissatisfaction of users from offering/not offering
software features as part of an upcoming software release.
There is often an asymmetry between users’ satisfaction and
dissatisfaction when these two factors are considered as
prioritization criteria of features: some features may generate
satisfaction to users, if included in the next software release, but
do not create the same value of dissatisfaction, if they are not
included, and vice versa. This asymmetry may introduce
additional hesitation and uncertainty to stakeholders when they
adopt satisfaction/dissatisfaction as prioritization criteria. The
suggested method initially requires from stakeholders to
systematically rank all candidate features based on satisfaction
and dissatisfaction criteria. Then, the method is used to quantify
the hesitation of stakeholders that is inherent in each features
ranking. The final features’ priorities are computed by
calculating objective weights for all stakeholders’ rankings. The
method assumes the larger the hesitation (lack of knowledge and
indeterminacy) associated with each stakeholder ranking, the
smaller will be the weight of that ranking in the calculation of
the final features’ priorities.

Education and Information Technologies, Springer, 2020

Learning analytics have proved promising capabilities and opportunities to many aspects of academ... more Learning analytics have proved promising capabilities and opportunities to many aspects of academic research and higher education studies. Data-driven insights can significantly contribute to provide solutions for curbing costs and improving education quality. This paper adopts a two-phase machine learning approach, which utilizes both unsupervised and supervised learning techniques for predicting outcomes of students following Higher Education programs of studies. The approach has been applied in a case-study which has been performed in the context of an undergraduate Computer Science curriculum offered by the University of Thessaly in Greece. Students involved in the case study were initially grouped based on the similarity of specific educationrelated factors and metrics. Using the K-Means algorithm, our clustering experiments revealed the presence of three coherent clusters of students. Subsequently, the discovered clusters were utilized to train prediction models for addressing each particular cluster of students individually. In this regard, two machine learning models were trained for every cluster of students in order to predict the time to degree completion and student enrollment in the offered educational programs. The developed models are claimed to produce predictions with relatively high accuracy. Finally, the paper discusses the potential usefulness of the clustering-aided approach for learning analytics in Higher Education.

4th Euro- Mediterranean Conference on “VISIONING MED 2020+ / Mediterranean in Transition: Preserving the Past – Preparing for the Future”, 2020

CORP 2020, 2020

1 ABSTRACT A fledgling and still scattered knowledge stream on multidisciplinary Smart city pheno... more 1 ABSTRACT A fledgling and still scattered knowledge stream on multidisciplinary Smart city phenomena is developing. For the development of smart cities intellectual minds and a synthesis of quite diverse competences are required to shape cities to becoming smart with the overall objective to ever more improve the quality of life of its citizens in the most efficient and sustainable way. Both, the master minds and operators behind this development need to embark on an intensive change process, unlearn ingrained behavioral patterns and internalize an innovative competence set. This research is aiming to address the shortage of both, digital and transferrable skills that are needed for the various smart cities' sectors differentiated by more strategic roles of Smart City Planner and Chief Digital Officer as well as the more operational IT Officer. This study addresses the gap of competences by providing preliminary quantitative and qualitative research findings of the still ongoing DevOps project. 2 INTRODUCTION The ever increasing popularity and speed of the Smart City movement is reflected by the results of a Bosch initiated study revealing that the Smart City (SC) market grows at a yearly rate of 19% amounting to an investment volume of 800 bio US$ (Boehne, 2018). A further recent study by Berger (2019) with SC decision makers and experts in 50 mid-sized cities asked, for example, about the key success factors of SC projects. A well-defined strategy and guidance achieved with 58% the highest frequency level. Contradictory to the primacy of strategy and guidance, only 20% of the asked city representatives had a strategy pointing to a still existing research gap. The aim of this research is to differentiate perspectives and competencies between SC planners, chief digital officer and IT officers. In order to successfully cope with this intensive change and digital transformation process and prepare for an effective and efficient future Smart City development, the administrators must thoroughly understand the complexity of smart city areas, new digital technologies facilitating the SC development and map newly required technical and transversal capabilities with newly emerging job profiles. Aiming to support strategic and operational SC administrators, the DevOps project, supported by ERASMUS + Sector Skills Alliances, addresses the gap between today's and future's skills demands of municipal workforce by emphasizing on the exploitation of emerging employment paradigms such as DevOps (http://devops.teilar.gr/). The final aim of the project is the development of VET MOOCs curricula to impart newly required technical and transversal competences and skills provided on a Moodle platform. The project, furthermore, aims to create an international community of best practice. It strives to cover the following identified research gaps: a. lack of explanation of the nexus between Smart City Applications, DevOps (Agile Software Development) differentiated by a Citizen driven or Technology driven perspective. b.

Education and Information Technologies, 2020

The present research work proposes the development of an integrated framework for the personaliza... more The present research work proposes the development of an integrated framework for the personalization and parameterization of learning pathways, aiming at optimizing the quality of the offered services by the Higher Educational Institutions (HEI). In order to achieve this goal, in addition to the educational part, the EDUC8 framework encloses the set of parameters that cover both the technical and the financial dimensions of a learning pathway, thus providing a complete tool for the optimization and calculation of the offered services by the HEIs in combination with the minimization of respective costs. Moreover, the proposed framework incorporates simulation modeling along with machine learning for the purpose of designing learning pathways and evaluating quality assurance indicators and the return on investment of implementation. The study presents a case study in relation to tertiary education in Greece, with a particular focus on Computer Science programs. Data clustering is specifically applied to learn potential insights pertaining to student characteristics, education factors and outcomes. Generally, the framework is conceived to provide a systematic approach for developing tertiary policies that help optimize the quality and cost of education.

TEMU , 2010

It is well known that in a turbo decoder extrinsic information increases with every iteration. In... more It is well known that in a turbo decoder extrinsic information increases with every iteration. In published literature it is shown that there are different techniques which improve the performance of Soft Output Viterbi Algorithm (SOVA) and max-log-Maximum A Posteriori (MAP) turbo decoding algorithms by applying a scaling factor at the extrinsic information. Most of these techniques give good Bit Error Rate (BER) and Frame Error Rate (FER) performance results, but the drawback is increased complexity for the turbo decoder. Following well known techniques and using 3rd Generation Partnership Projext (3GPP) parameters for flat Rayleigh fading channels, this paper shows that for a reconfigurable SOVA/log-MAP turbo decoder, a common constant scaling factor can improve BER and FER performance significantly.

J. Electrical Systems, 2024

Student dropout remains a pressing concern with significant socio-economic implications. This stu... more Student dropout remains a pressing concern with significant socio-economic implications. This study utilizes supervised
machine learning to forecast potential dropouts by analyzing a diverse array of factors including academic achievements, class attendance,
socio-economic backgrounds, and behavioral patterns. These factors are integrated into a comprehensive predictive model that enhances
our understanding of student retention and informs the design of targeted interventions. Through a comparative analysis of two prominent
algorithms, K-Nearest Neighbors and Naive Bayes, our research assesses the effectiveness of these methods using a detailed dataset. The
findings reveal that the Naive Bayes algorithm outperforms K-Nearest Neighbors in predicting student dropouts, offering valuable data
for educational practitioners focused on data-driven strategies to enhance student retention. The study advances the application of machine
learning in educational settings and contributes practical insights for the development of policies and interventions aimed at reducing
dropout rates, thereby enriching the academic discourse and improving educational outcomes.

Springer Nature, 2022

The Covid-19 pandemic has imposed new challenges in preserving the goal of developing smart and s... more The Covid-19 pandemic has imposed new challenges in preserving the goal of developing smart and sustainable cities worldwide while improving urban resilience. In the smart city domain, disaster or crisis management operations require contributions and collaboration of different type of entities with various functions, rules and protocols, forming complex contexts in decision making or event coordination. The management of the corresponding information usually coming from multiple heterogeneous sources and, sometimes with attributes revealing semantic inconsistencies constitutes an emerging challenge. Furthermore, the demand for interoperability between the various services and IoT devices at local and national level is imperative. Yet, existing literature highlights that the conceptualization of a holistic reference schema that covers all the dimensions of the smart city disaster/crisis management domain and allows the exchange of information through different agents has not been fully addressed so far. We present the RES-Q (RESCUE) semantic model, which includes the needed domain knowledge streams for the smart city post-disaster management domain. This model aims for data consolidation and linkage in order to be further utilized for the implementation of a common knowledge repository and advanced analysis. In this context, semantic web technologies are proposed as a promising solution for providing semantic interoperability in crisis and/or disaster management in the smart city discourse. Finally, data consolidation and harmonization methodology is presented, which is used for the integration of different data sources, according to the RES-Q model.

Proceedings of the 7th International Conference on Algorithms, Computing and Systems, 2023

In the era of data-driven decision-making, Higher Education Institutions (HEIs) can greatly benef... more In the era of data-driven decision-making, Higher Education Institutions (HEIs) can greatly benefit from the potential of eXplainable Artificial Intelligence (XAI) to provide transparent and interpretable insights. This paper presents the KONX (CONNECTS) approach, a comprehensive methodology that leverages semantic web technologies to create a dynamic and comprehensive knowledge graph for advanced predictive models in academic advising. The KONX methodology focuses on harmonizing heterogeneous educational data sources, enabling seamless data querying and manipulation. By incorporating a feedback mechanism, the KONX approach remains adaptable to changes in the academic domain, continuously updating and maintaining its knowledge representation. To practically apply and evaluate the proposed methodology, a prototype was implemented and tested on an experimental case study concerning student outcomes prediction. The implemented prototype includes a graphical SPARQL generator interface to streamline the construction of SPARQL queries in an integrated way. In this way, this paper proposes both a comprehensive XAI methodology and a holistic technological infrastructure for applying the methodology in real-time scenarios. By bridging the gap between AI decision-making and human-comprehensible explanations, the KONX approach enhances transparency and user trust in AI-driven systems in the education sector. CCS CONCEPTS • Computing methodologies • Artificial intelligence • Explainable Artificial Intelligence

Intelligent technologies permeate all aspects of contemporary society and urban life. It is essen... more Intelligent technologies permeate all aspects of contemporary society and urban life. It is essential to educate the workforce of smart cities in order to effectively meet emerging technological demands. In this paper, we present an e-course that focuses on discrete competencies associated with different smart city roles. Initially, we present the conceptual learning framework for the development of the competency-based learning course and we define the objectives of the research. The paper continues with a discussion of the model's application steps and an examination of the course's skills, competencies, and roles. The acquired knowledge was measured using pre-and post-course tests, and questionnaires were used to investigate the relevance and quality of the learning material and the learning acquisition of the participants. Evaluation results showed that the course was relevant to the concept of smart cities, useful for their work duties, while participation in the course resulted in increased overall competency in all three smart city job profiles.

CSUM2022, 2022

Disasters are characterized as a major problem worldwide and a significant threat to sustainable ... more Disasters are characterized as a major problem worldwide and a significant threat to sustainable development, causing the loss of lives, the destruction of infrastructure, economic disruption, etc. The implementation of policies and strategies that will prevent future disaster risk, reduce existing disaster risk, and manage residual risk has become more vital than ever. It requires multi-sector collaboration to achieve enhanced resilience to the multiple hazards so as to prevent and/or reduce the potential losses, assure prompt assistance to victims of disasters, and achieve rapid and effective recovery. Such an approach demands collaboration between scientists and authorities and proper use of the available information so that it can be understood and processed by all the involved stakeholders. The utilization of disaster risk information, along with the use of more sophisticated ICTs, will be able to provide policymakers with a holistic DRM, enabling decision support for a natural and/or man-made crisis. To that end, the key objective of this study was to collect previous research by conducting a Systematic Literature Review, in order to highlight the existing research approaches in ICT for DRM. To analyze and evaluate the findings, the selected studies were classified according to four areas: 1) Stakeholders, 2) Disaster phase, 3) Disaster type, 4) ICT. Additionally, a SWOT analysis was conducted to provide a holistic overview of ICTs and their applications in the DRM sector. Hence, our work attempts to present a comprehensive analysis of the research approaches and determines the arising opportunities and shortcomings that require the attention of the research community.

CSUM2022, 2022

The growing societal demands for Higher Education Institutions (HEIs) actions towards sustainable... more The growing societal demands for Higher Education Institutions (HEIs) actions towards sustainable development triggers new forms of educational programs and research activities. In line with this direction, the Living Lab (LL) approach provides a means to engage various actors in the process of development of a solution fostering inclusive 'quadruple helix' participation and open end-user-oriented innovation. Nowadays, LLs have become a strategy in many universities for co-creating impact for more sustainable and healthier cities and regions. However, LLs can create shared value for society, only if their long-term viability is ensured. The challenge is making LLs effective and self-supportive, but existing models lack a holistic and multi-perspective umbrella view over all dimensions, functions and stakeholder interrelations of a LL. In this paper, we present the conceptualization of the domain of LLs in Higher Education. We present the INVEST LL ontology (INVESTL 2) which models the needed domain knowledge streams for the LLs and consists of 3 main modules: 1) the Living Lab model, 2) the Business model and 3) the Quality Assurance model in education provision environments. Taking into account the multifaceted nature of this challenge, our proposal achieves a holistic conceptualization of the domain of LLs, in order to be further utilized for the implementation of a Semantic Web Rules Repository. This rule base is in control of the required streams of knowledge enclosed in the LL knowledge agendas for developing, recommending and executing tailored workplans to meet the LL goals. Finally, the INVESTL 2 ontology is applied for the definition of a semantic infrastructure for the RES-Q LL case study on disaster risk management.

ICONHIC 2022, 2022

During the last decade, communities at local and national level are implementing actions geared t... more During the last decade, communities at local and national level are implementing actions geared towards improving disaster resilience. In this context, the importance of ICT in disaster risk management is rapidly increasing globally, especially nowadays amidst the climate crisis and the covid-19 pandemic. However, disaster risk management operations require contributions and collaboration of different type of actors and infrastructures with different functions, rules, protocols and datasets, forming complex contexts in decision making and event coordination. Hence, semantic interoperability between the various stakeholders is one of the challenges to be confronted. In this paper, we present the RES-Q (RESCUE) approach that proposes an information technology solution concerning the real-time recommendation and orchestration of post-disaster response plans. The implemented RES-Q prototype comprises an expert system and a workflow execution engine based on an ontological infrastructure for modeling the response actions for each type of disaster. The ontological model is designed using a multi-layer approach encapsulating the required knowledge streams and a semantic rule repository. During the execution of a post-disaster plan, the system reasons over the rules and composes the next steps of the corresponding response processes. The rule repository is able to infer new knowledge as each plan progresses, which can update the RES-Q ontology accordingly.

J. Comput. Educ. 2022 Springer Nature, 2022

Students attending Higher Education Institutions (HEIs) are faced with a variety of complex decis... more Students attending Higher Education Institutions (HEIs) are faced with a variety of complex decisions and procedures. To provide students with more sustained and personalized advising, many HEIs turn to online academic advising systems and tools as a way to minimize costs and streamline their advising services. However, in such systems, uncertainty in the learner’s parameters is a factor, which makes the decision-making process more difficult. Fuzzy logic, a multivalued logic similar to human thinking and interpretation, is highly suitable and applicable for developing knowledge-based academic advising systems that conserve the inherent fuzziness in learner models. In this paper, an innovative hybrid software infrastructure is presented which integrates expert system, fuzzy reasoning, and ontological tools to provide reliable recommendations to students for the next appropriate learning step. The software comprises a fuzzy logic component that determines the student’s interest degree for a specific academic choice accompanied by an ontological model and a conventional rule-based expert system for the composition of personalized learning pathways. In order for the system to recommend the next step of the learning pathway, the output of the fuzzy logic component together with the knowledge that is modeled as part of the multi-facet ontology and the machine perceptible academic advising guidelines expressed as semantic rules interoperate in a dynamic and seamless manner. The paper presents the key modeling artifacts of the proposed approach and the architecture of the implemented prototype system. During the case study, the developed system yielded satisfactory results in terms of overall inter-rater reliability and usefulness.

PCI 2021: 25th Pan-Hellenic Conference on Informatics, 2022

Smart cities are complex ecosystems that use information and communication technologies for helpi... more Smart cities are complex ecosystems that use information and communication technologies for helping their citizens and organizations to face the challenges of urbanization, safety, resilience, and sustainability. The SmartDevOps project proposes a framework aiming to address the shortage of professional skills in municipalities. Following the increased use of AI methods to provide recommendations in training, there is also an increased need for formalization of existing courses to enable recommendations. This work is dedicated to the conceptual formal modeling of the delivered courses for gaining the competences required for smart city professionals by following the SmartDevOps methodology. We present the Smart City Competence Ontology (SCCompO) that provides a formalism for modeling concepts like competence, learning objective and outcome of courses that aims to cooperate with MOOC platform for training of Smart City professionals. It follows the modular, extensible structure of the curriculum, and it is designed to respond to questions regarding prerequisites and outcomes of job profiles, competences, and courses. The impact of using the developed ontology is to augment the MOOC platform by providing reasoning on course selection and their learning outcomes as well on the relations among these concepts in order to make decisions about the learners’ curricula.

Quality Assurance in Education, 2022

Purpose The purpose of this paper is to thoroughly assemble, analyze and synthesize previous re... more Purpose

The purpose of this paper is to thoroughly assemble, analyze and synthesize previous research to investigate and identify teaching staff competencies derived from the roles and tasks attributed to university professors.
Design/methodology/approach

In this literature review, the authors looked at both the conceptual framework exploring the educational concepts and the learning theories focusing on teaching staff roles and competencies in higher education. Thirty-nine scientific papers were studied in detail from a total of 102 results, which were eligible based on the preferred reporting items for systematic reviews and meta-analyses statement.
Findings

A multi-dimensional approach to teacher competencies in higher education was proposed, which consists of six main dimensions with their respective characteristics. Thirty-two discrete teaching staff competencies were identified and distributed in the aforementioned dimensions. The research revealed that specific competencies, such as the digital competence of teachers, which have lately become of high importance worldwide due to the COVID-19 pandemic implications, surprisingly, until recently, they were considered secondary in the educational process.
Research limitations/implications

The study was based on the existing literature without using data drawn from an appropriate questionnaire addressed to students and/or interviews with academics. In addition, in an effort to maintain a homogeneous base of teacher competencies, inclusion of domains of expertise was avoided. Further research should focus on designing and developing a holistic model using analytical learning approaches that will contribute to the assessment of teachers’ competencies and explore the relationship of these competencies to students’ academic achievement, contributing quality to higher education.
Practical implications

A specific framework of teacher competencies in higher education, in practice, can be a useful reference point not only for ensuring quality in the selection of teachers and their career-long professional development but also for national education policy strategies. The definition of teacher competencies framework contributes to facilitating effective dialogue for the evaluation and quality assurance in education between agencies, authorities, researchers, teachers, policymakers, education managers and different communities at large.
Social implications

These competencies are at the heart not only of the teaching and learning process but also in the workplace and in society in general and are increasingly recognized as essential. An adequately prepared community and management equipped with the required employee competencies is able to react immediately and in a positive way to any obstacle, yielding optimal results.
Originality/value

This is the first review, to the authors’ knowledge, to comprehensively explore the literature to identify, classify and rank the teaching staff competencies in higher education, revealing the gap between perceived and actual importance of various competencies.

MDPI / Electronics, 2021

Over recent years, massive open online courses (MOOCs) have gained increasing popularity in the f... more Over recent years, massive open online courses (MOOCs) have gained increasing popularity in the field of online education. Students with different needs and learning specificities are able to attend a wide range of specialized online courses offered by universities and educational institutions. As a result, large amounts of data regarding students’ demographic characteristics, activity patterns, and learning performances are generated and stored in institutional repositories on a daily basis. Unfortunately, a key issue in MOOCs is low completion rates, which directly affect student success. Therefore, it is of utmost importance for educational institutions and faculty members to find more effective practices and reduce non-completer ratios. In this context, the main purpose of the present study is to employ a plethora of state-of-the-art supervised machine learning algorithms for predicting student dropout in a MOOC for smart city professionals at an early stage. The experimental results show that accuracy exceeds 96% based on data collected during the first week of the course, thus enabling effective intervention strategies and support actions.

In this paper we describe an irrigation scheduling system based on wireless sensor network techno... more In this paper we describe an irrigation scheduling system based on wireless sensor network technology as applied in Precision Agriculture and particularly in Precision Irrigation. Precision agriculture, as opposed to traditional agriculture where the whole field is treated as uniform and homogeneous, is a modern method of agricultural practice where temporal and spatial information regarding the field and its parameters is utilized in order to optimize the efficiency of influxes (such as water and fertilizers), while minimizing the environmental effects of their use. Irrigation is a key agricultural process with direct consequences on the crop's yield and quality as well as on the environment, with soil humidity (water content of field) being a very important parameter in composing the appropriate irrigation routine for a field. Until recently, in order to measure soil humidity a farmer had to use practices that are both time and money consuming (e.g. use probes in various field...

4th International Conference on Computers in Management and Business (ICCMB2021), 2021

Services that collaborate alongside other services or systems for performing tasks, need to be aw... more Services that collaborate alongside other services or systems for performing tasks, need to be aware of either predetermined or other abrupt and unexpected behaviors in other to adapt theirs. The service behaviors we consider are performed in smart city domains which are dynamic environments where continuously new services appear, that usually have a large variation in the way they perform the same task. We use roles having teamwork behavior to represent the composition procedure in such domains, and we model the team of services through the individual behavior of each participant as well as their group goal. In this paper, we present a framework, which consists of the approach and IT system in order to serve the choreography between a large number of heterogeneous services so as to achieve a seamless and cooperative environment suitable for a smart city. This enables composite city services to adapt their behavior during execution and themselves intervene from inside the team if a possible unexpected behavior happens during the service activity, in order to run proactively and avoid obstacles or collisions. A scenario from a smart city domain illustrates that, services having different teamwork abilities are composed to a new one which inherits teamwork features and combines them to something novel.

4th SmartBlueCity Euro-Mediterranean Conference, 2020

Covid-19 epidemic has created new challenges for the development of Smart and Sustainable Cities.... more Covid-19 epidemic has created new challenges for the development of Smart and Sustainable Cities. It has proven that it is not anymore sufficient just to focus on providing services for quality of life, or for a better business ecosystems, but we need to prepare cities, so they are able to manage, adapt, maintain and ensure city services and enhance quality of life in the face of hazards, shocks and stresses (ISO 37123). According to this definition resilience does not include only earthquakes, fires, floods, etc. but as well whatever disrupts significantly the operation of a city either occasionally or periodically. Examples include high unemployment; endemic violence; health epidemics and chronic food and water shortages (Cities, 2016)
Even though some standards and projects exist in this area, we have not yet consensus on a common city resilience model that will able to describe what exactly constitutes resilience and a resilient city (Spaans, & Waterhout, 2017). Furthermore, up to now little emphasis has been given to the way municipalities are organized for addressing hazards and even less on training their personnel to the new skills required. Currently, these new required job profiles do not exist, they are overlooked, or they are partially described.
Rockefeller Foundation, founded in 2013 the “100 Resilient Cities (100RC)” project having as objective to help cities face three major threats and challenges: urbanization, globalization, and climate change. In the context of this project, a job profile named “City Chief Resilience Officer” was defined, but without sufficiently describing the required skills. In parallel, other projects e.g. “Smart DevOps competencies for smart cities” (devops.uth.gr) are attempting to define the required skills and job profiles needed for Smart and Sustainable Cities professionals (Kaufmann, 2020).
Obviously, we need to address the skills’ gap between today’s and future’s skills demands of municipal workforce by emphasizing on these emerging needs and by combining the needs for smart and resilient cities development. Exactly on this subject area, this paper presents the results of a survey that attempts to define the required skills for a “Smart and Resilience City Officers”.

46th Euromicro Conference on Software Engineering and Advanced Applications, 2020

In this paper we present a practical method that can be applied to support the prioritization of ... more In this paper we present a practical method that
can be applied to support the prioritization of large sets of
candidate software features in a requirements prioritization
process. We consider as prioritization criteria the
satisfaction/dissatisfaction of users from offering/not offering
software features as part of an upcoming software release.
There is often an asymmetry between users’ satisfaction and
dissatisfaction when these two factors are considered as
prioritization criteria of features: some features may generate
satisfaction to users, if included in the next software release, but
do not create the same value of dissatisfaction, if they are not
included, and vice versa. This asymmetry may introduce
additional hesitation and uncertainty to stakeholders when they
adopt satisfaction/dissatisfaction as prioritization criteria. The
suggested method initially requires from stakeholders to
systematically rank all candidate features based on satisfaction
and dissatisfaction criteria. Then, the method is used to quantify
the hesitation of stakeholders that is inherent in each features
ranking. The final features’ priorities are computed by
calculating objective weights for all stakeholders’ rankings. The
method assumes the larger the hesitation (lack of knowledge and
indeterminacy) associated with each stakeholder ranking, the
smaller will be the weight of that ranking in the calculation of
the final features’ priorities.

Education and Information Technologies, Springer, 2020

Learning analytics have proved promising capabilities and opportunities to many aspects of academ... more Learning analytics have proved promising capabilities and opportunities to many aspects of academic research and higher education studies. Data-driven insights can significantly contribute to provide solutions for curbing costs and improving education quality. This paper adopts a two-phase machine learning approach, which utilizes both unsupervised and supervised learning techniques for predicting outcomes of students following Higher Education programs of studies. The approach has been applied in a case-study which has been performed in the context of an undergraduate Computer Science curriculum offered by the University of Thessaly in Greece. Students involved in the case study were initially grouped based on the similarity of specific educationrelated factors and metrics. Using the K-Means algorithm, our clustering experiments revealed the presence of three coherent clusters of students. Subsequently, the discovered clusters were utilized to train prediction models for addressing each particular cluster of students individually. In this regard, two machine learning models were trained for every cluster of students in order to predict the time to degree completion and student enrollment in the offered educational programs. The developed models are claimed to produce predictions with relatively high accuracy. Finally, the paper discusses the potential usefulness of the clustering-aided approach for learning analytics in Higher Education.

4th Euro- Mediterranean Conference on “VISIONING MED 2020+ / Mediterranean in Transition: Preserving the Past – Preparing for the Future”, 2020

CORP 2020, 2020

1 ABSTRACT A fledgling and still scattered knowledge stream on multidisciplinary Smart city pheno... more 1 ABSTRACT A fledgling and still scattered knowledge stream on multidisciplinary Smart city phenomena is developing. For the development of smart cities intellectual minds and a synthesis of quite diverse competences are required to shape cities to becoming smart with the overall objective to ever more improve the quality of life of its citizens in the most efficient and sustainable way. Both, the master minds and operators behind this development need to embark on an intensive change process, unlearn ingrained behavioral patterns and internalize an innovative competence set. This research is aiming to address the shortage of both, digital and transferrable skills that are needed for the various smart cities' sectors differentiated by more strategic roles of Smart City Planner and Chief Digital Officer as well as the more operational IT Officer. This study addresses the gap of competences by providing preliminary quantitative and qualitative research findings of the still ongoing DevOps project. 2 INTRODUCTION The ever increasing popularity and speed of the Smart City movement is reflected by the results of a Bosch initiated study revealing that the Smart City (SC) market grows at a yearly rate of 19% amounting to an investment volume of 800 bio US$ (Boehne, 2018). A further recent study by Berger (2019) with SC decision makers and experts in 50 mid-sized cities asked, for example, about the key success factors of SC projects. A well-defined strategy and guidance achieved with 58% the highest frequency level. Contradictory to the primacy of strategy and guidance, only 20% of the asked city representatives had a strategy pointing to a still existing research gap. The aim of this research is to differentiate perspectives and competencies between SC planners, chief digital officer and IT officers. In order to successfully cope with this intensive change and digital transformation process and prepare for an effective and efficient future Smart City development, the administrators must thoroughly understand the complexity of smart city areas, new digital technologies facilitating the SC development and map newly required technical and transversal capabilities with newly emerging job profiles. Aiming to support strategic and operational SC administrators, the DevOps project, supported by ERASMUS + Sector Skills Alliances, addresses the gap between today's and future's skills demands of municipal workforce by emphasizing on the exploitation of emerging employment paradigms such as DevOps (http://devops.teilar.gr/). The final aim of the project is the development of VET MOOCs curricula to impart newly required technical and transversal competences and skills provided on a Moodle platform. The project, furthermore, aims to create an international community of best practice. It strives to cover the following identified research gaps: a. lack of explanation of the nexus between Smart City Applications, DevOps (Agile Software Development) differentiated by a Citizen driven or Technology driven perspective. b.

Education and Information Technologies, 2020

The present research work proposes the development of an integrated framework for the personaliza... more The present research work proposes the development of an integrated framework for the personalization and parameterization of learning pathways, aiming at optimizing the quality of the offered services by the Higher Educational Institutions (HEI). In order to achieve this goal, in addition to the educational part, the EDUC8 framework encloses the set of parameters that cover both the technical and the financial dimensions of a learning pathway, thus providing a complete tool for the optimization and calculation of the offered services by the HEIs in combination with the minimization of respective costs. Moreover, the proposed framework incorporates simulation modeling along with machine learning for the purpose of designing learning pathways and evaluating quality assurance indicators and the return on investment of implementation. The study presents a case study in relation to tertiary education in Greece, with a particular focus on Computer Science programs. Data clustering is specifically applied to learn potential insights pertaining to student characteristics, education factors and outcomes. Generally, the framework is conceived to provide a systematic approach for developing tertiary policies that help optimize the quality and cost of education.

TEMU , 2010

It is well known that in a turbo decoder extrinsic information increases with every iteration. In... more It is well known that in a turbo decoder extrinsic information increases with every iteration. In published literature it is shown that there are different techniques which improve the performance of Soft Output Viterbi Algorithm (SOVA) and max-log-Maximum A Posteriori (MAP) turbo decoding algorithms by applying a scaling factor at the extrinsic information. Most of these techniques give good Bit Error Rate (BER) and Frame Error Rate (FER) performance results, but the drawback is increased complexity for the turbo decoder. Following well known techniques and using 3rd Generation Partnership Projext (3GPP) parameters for flat Rayleigh fading channels, this paper shows that for a reconfigurable SOVA/log-MAP turbo decoder, a common constant scaling factor can improve BER and FER performance significantly.