Nikos Karacapilidis
University of Patras, MEAD - IMIS Lab, Faculty Member
During the last decades, higher educational institutes have managed to accumulate a large volume of data about their students’ characteristics and performance. Machine learning techniques offer a first step and a helping hand in... more
During the last decades, higher educational institutes have managed to accumulate a large volume of data about their students’ characteristics and performance. Machine learning techniques offer a first step and a helping hand in extracting useful information from these data and gaining insights into the prediction of students’ progress and performance. In this work, we present a two-level classification algorithm for predicting students’ graduation time. The proposed algorithm has two major features. Firstly, it identifies with high accuracy the students at risk of not completing their studies; secondly, it classifies the students based on their expected graduation time. Our preliminary numerical experiments indicate that the proposed algorithm exhibits reliable predictions based on the students’ performance in their courses during the first two years of their studies.
Research Interests:
Recommender Systems is a highly applicable subclass of information filtering systems, aiming to provide users with personalized item suggestions. These systems build on collaborative filtering and content-based methods to overcome the... more
Recommender Systems is a highly applicable subclass of information filtering systems, aiming to provide users with personalized item suggestions. These systems build on collaborative filtering and content-based methods to overcome the information overload issue. Hybrid recommender systems combine the abovementioned methods and are generally proved to be more efficient than the classical approaches. In this paper, we propose a novel approach for the development of a hybrid recommender system that is able to make recommendations under the limitation of processing small amounts of data with strong intercorrelation. The proposed hybrid solution integrates Machine Learning and Multi-Criteria Decision Analysis algorithms. The experimental evaluation of the proposed solution indicates that it performs better than widely used Machine Learning algorithms such as the k-Nearest Neighbors and Decision Trees.
Research Interests:
Research Interests:
ABSTRACT to be written 51 50 APPENDIX C. COMMAND SUMMARY Up One level up in the hierarchy of directories. For instance, if you see the List of Workspaces, Up gets you to your personal Home directory. Update ACL Jumps to the ACL editing... more
ABSTRACT to be written 51 50 APPENDIX C. COMMAND SUMMARY Up One level up in the hierarchy of directories. For instance, if you see the List of Workspaces, Up gets you to your personal Home directory. Update ACL Jumps to the ACL editing tool, where you can edit and change ACLs. Upload A document from your computer is loaded to the the Zeno-Server and added to the directory that you have currently selected. A form is shown where you can chose the document and edit a title. User Groups Shows the list of all user groups (as far as you have sufficient access rights to see those users and groups). 49 New User A new user(name) is created. A form to edit the name of the new user is shown. Note: the name must not be identical with the name of existing users and groups. New User Group A new group is created. A form to edit the name of the new group, a description, and to select group memmbers from a lis
Collaborative decision making in today’s knowledge intensive and multi-disciplinary environments is a challenging task. The diversity of these environments and the associated plurality of decision makers’ perceptions of the issue under... more
Collaborative decision making in today’s knowledge intensive and multi-disciplinary environments is a challenging task. The diversity of these environments and the associated plurality of decision makers’ perceptions of the issue under consideration require the exploitation of a variety of meaningful knowledge visualizations and reasoning mechanisms to effectively support the overall stakeholders’ collaboration towards making a decision. This chapter reports on an innovative approach that offers a number of interrelated visualizations of the knowledge exchanged and shared during a collaborative decision making process. These visualizations incorporate suitable reasoning mechanisms that exploit human and machine understandable knowledge to facilitate the underlying what-if analysis and aid stakeholders towards reaching consensus and, ultimately, making a collective decision.
Research Interests:
to be written 51 50 APPENDIX C. COMMAND SUMMARY Up One level up in the hierarchy of directories. For instance, if you see the List of Workspaces, Up gets you to your personal Home directory. Update ACL Jumps to the ACL editing tool, where... more
to be written 51 50 APPENDIX C. COMMAND SUMMARY Up One level up in the hierarchy of directories. For instance, if you see the List of Workspaces, Up gets you to your personal Home directory. Update ACL Jumps to the ACL editing tool, where you can edit and change ACLs. Upload A document from your computer is loaded to the the Zeno-Server and added to the directory that you have currently selected. A form is shown where you can chose the document and edit a title. User Groups Shows the list of all user groups (as far as you have sufficient access rights to see those users and groups). 49 New User A new user(name) is created. A form to edit the name of the new user is shown. Note: the name must not be identical with the name of existing users and groups. New User Group A new group is created. A form to edit the name of the new group, a description, and to select group memmbers from a lis
Research Interests:
Summary This document reports on the awareness services offered through the two tools that are being developed in the context of WP4: Collaboration Services, namely eLogbook and CoPe_it!. We first present the awareness types that need to... more
Summary This document reports on the awareness services offered through the two tools that are being developed in the context of WP4: Collaboration Services, namely eLogbook and CoPe_it!. We first present the awareness types that need to be supported and we proceed by describing in detail how these are conceived and implemented in the abovementioned tools. Moreover, we briefly report on the integration of these tools, focusing on the additional awareness services resulting from this integration. hal-00257170, ...
Research Interests:
The main purpose of this article is to provide an up-to-date understanding of the utilization and deployment of emerging technologies in the public sector, as this is reflected through nineteen recently funded Horizon 2020 research... more
The main purpose of this article is to provide an up-to-date understanding of the utilization and deployment of emerging technologies in the public sector, as this is reflected through nineteen recently funded Horizon 2020 research projects. For the needs of this study, we have adopted a well-known literature review method that enables a concept-centric analysis of the accumulated knowledge in the field under consideration, and accordingly proposed a conceptual framework that facilitates such an analysis. Through a detailed consideration of these projects and their pilot case implementations, a series of insights about recent research development and applications in the public sector are extracted and discussed. To the best of our knowledge, this is the first attempt to gain such insights from a research projects perspective, which may reveal useful information about the utilization and deployment of these technologies in real-life pilots. The findings of this study are also justifi...
This paper employs techniques and algorithms from the fields of natural lan-guage processing, graph representation learning and word embeddings to assistproject managers in the task of personnel selection. To do so, our approachinitially... more
This paper employs techniques and algorithms from the fields of natural lan-guage processing, graph representation learning and word embeddings to assistproject managers in the task of personnel selection. To do so, our approachinitially represents multiple textual documents as a single graph. Then, it com-putes word embeddings through representation learning on graphs and performsfeature selection. Finally, it builds a classification model that is able to estimatehow qualified a candidate employee is to work on a given task, taking as inputonly the descriptions of the tasks and a list of word embeddings. Our approachdiffers from the existing ones in that it does not require the calculation of keyperformance indicators or any other form of structured data in order to operateproperly. For our experiments, we retrieved data from the Jira issue trackingsystem of the Apache Software Foundation. The evaluation results show, inmost cases, an increase of 0.43% in the accuracy of the proposed classificationmodels when compared against a widely-adopted baseline method, while theirvalidation loss is significantly decreased by 65.54%
Research Interests:
We consider the discovery of future research collaborations as a link prediction problem applied on scientific knowledge graphs Our approach integrates into a single knowledge graph both structured and unstructured textual data through a... more
We consider the discovery of future research collaborations as a link prediction problem applied on scientific knowledge graphs Our approach integrates into a single knowledge graph both structured and unstructured textual data through a novel representation of multiple scientific documents The Neo4j graph database is used for the representation of the proposed scientific knowledge graph For the implementation of our approach, we use the Python programming language and the scikit-learn ML library We benchmark our approach against classical link prediction algorithms using accuracy, recall, and precision as our performance metrics Our initial experimentations demonstrate a significant improvement of the accuracy of the future collaboration prediction task The experimentations reported in this paper use the new COVID-19 Open Research Dataset © 2020, Springer Nature Switzerland AG
Research Interests:
Research Interests:
Research Interests:
CoPe_it! is an innovative web-based tool that complies with collaborative practices to provide members of communities with the appropriate means to manage individual and collective knowledge during a sense-making and/or decision-making... more
CoPe_it! is an innovative web-based tool that complies with collaborative practices to provide members of communities with the appropriate means to manage individual and collective knowledge during a sense-making and/or decision-making session. In this article, we demonstrate its applicability in tackling cognitively-complex collaboration settings, which are characterized by big volumes of interrelated data obtained from diverse sources, and knowledge expressed by diverse participants. We focus on issues related to the representation of such settings and the proposed approach towards making it easier for participants to follow the evolution of a collaboration, comprehend it in its entirety, and meaningfully aggregate data in order to resolve the issue under consideration.
Research Interests:
Research Interests:
In this paper we present Co-LEAN, an integrated suite of software tools suitable for the design and management of lean supply chains. In addition to providing full operational support in the planning and execution of the lean supply... more
In this paper we present Co-LEAN, an integrated suite of software tools suitable for the design and management of lean supply chains. In addition to providing full operational support in the planning and execution of the lean supply chain, Co-LEAN supports internet-based collaboration in the innovation and product design, manufacturing strategy, and supply-chain improvement tasks. The paper discusses the information system support requirements of a lean supply chain, describes the main components and the integration mechanisms of Co-LEAN and concludes with a brief description of its pilot use in a major
Research Interests:
Research Interests:
Aiming to support a cross-sector and cross-border eGovernance paradigm for sharing common public services, this paper introduces an AI-enhanced solution that enables beneficiaries to participate in a decentralized network for effective... more
Aiming to support a cross-sector and cross-border eGovernance paradigm for sharing common public services, this paper introduces an AI-enhanced solution that enables beneficiaries to participate in a decentralized network for effective big data exchange and service delivery that promotes the once-only priority and is by design digital, efficient, cost-effective, interoperable and secure. The solution comprises (i) a reliable and efficient decentralized mechanism for data sharing, capable of addressing the complexity of the processes and their high demand of resources; (ii) an ecosystem for delivering mobile services tailored to the needs of stakeholders; (iii) a single sign-on Wallet mechanism to manage transactions with multiple services; and (iv) an intercommunication layer, responsible for the secure exchange of information among existing eGovernment systems with newly developed ones. An indicative application scenario showcases the potential of our approach.
Research Interests:
This paper aims to meaningfully analyse the Horizon 2020 data existing in the CORDIS repository of EU, and accordingly offer evidence and insights to aid organizations in the formulation of consortia that will prepare and submit winning... more
This paper aims to meaningfully analyse the Horizon 2020 data existing in the CORDIS repository of EU, and accordingly offer evidence and insights to aid organizations in the formulation of consortia that will prepare and submit winning research proposals to forthcoming calls. The analysis is performed on aggregated data concerning 32,090 funded projects, 34,295 organizations participated in them, and 87,067 public deliverables produced. The modelling of data is performed through a knowledge graph-based approach, aiming to semantically capture existing relationships and reveal hidden information. The main contribution of this work lies in the proper utilization and orchestration of keyphrase extraction and named entity recognition models, together with meaningful graph analytics on top of an efficient graph database. The proposed approach enables users to ask complex questions about the interconnection of various entities related to previously funded research projects. A set of repr...
Research Interests:
By adopting a capabilities perspective, we develop a flexible framework of ICTs for supporting an organization’s strategy towards Open Innovation (OI). OI is associated with strategic capabilities, as well as with operational ones. ICT... more
By adopting a capabilities perspective, we develop a flexible framework of ICTs for supporting an organization’s strategy towards Open Innovation (OI). OI is associated with strategic capabilities, as well as with operational ones. ICT support in the strategic capabilities development is related to the cognitive processes of managerial staff to develop the appropriate level of absorptive capacity, whereas ICT as part of operational capabilities aims at enhancing the performance of day-to-day OI activities. Taking this into account, we develop a framework that associates specific ICTs with functionalities needed in the entire OI process. Paying much attention to the issues of collaboration and data analysis, we also comment on the integration of these technologies and their embedment in organizational processes.
Research Interests:
Research Interests:
Today, there are excellent resources for the semantic annotation of biomedical text. These resources span from ontologies, tools for NLP, annotators, and web services. Most of these are available either in the form of open source... more
Today, there are excellent resources for the semantic annotation of biomedical text. These resources span from ontologies, tools for NLP, annotators, and web services. Most of these are available either in the form of open source components (i.e., MetaMap) or as web services that offer free access (i.e., Whatizit). In order to use these resources in automatic text annotation pipelines, researchers face significant technical challenges. For open-source tools, the challenges include the setting up of the computational environment, the resolution of dependencies, as well as the compilation and installation of the software. For web services, the challenge is implementing clients to undertake communication with the respective web APIs. Even resources that are available as Docker containers (i.e., NCBO annotator) require significant technical skills for installation and setup. This work deals with the task of creating ready-to-install and run Research Objects (ROs) for a large collection ...
Research Interests:
We consider the prediction of future research collaborations as a link prediction problem applied on a scientific knowledge graph. To the best of our knowledge, this is the first work on the prediction of future research collaborations... more
We consider the prediction of future research collaborations as a link prediction problem applied on a scientific knowledge graph. To the best of our knowledge, this is the first work on the prediction of future research collaborations that combines structural and textual information of a scientific knowledge graph through a purposeful integration of graph algorithms and natural language processing techniques. Our work: (i) investigates whether the integration of unstructured textual data into a single knowledge graph affects the performance of a link prediction model, (ii) studies the effect of previously proposed graph kernels based approaches on the performance of an ML model, as far as the link prediction problem is concerned, and (iii) proposes a three-phase pipeline that enables the exploitation of structural and textual information, as well as of pre-trained word embeddings. We benchmark the proposed approach against classical link prediction algorithms using accuracy, recall...
Research Interests:
Interaction among actors involved in a Web-based learning environment is widely thought of as a valuable process, in that it stimulates collaborative work and augments the effectiveness of learning itself. This may be extensively achieved... more
Interaction among actors involved in a Web-based learning environment is widely thought of as a valuable process, in that it stimulates collaborative work and augments the effectiveness of learning itself. This may be extensively achieved by the integration of groupware tools and techniques, originally coming from the Computer-Supported Cooperative Work discipline. This paper reports on MEDIT, a Web-based environment that addresses various pedagogical issues and has been developed in line with the above. Offering complementary support, and not substituting traditional practices, our approach distinguishes three virtual workspaces and provides appropriate services for each of them. The paper focuses on the presentation of the innovative tools MEDIT is composed of. These concern the multiple view representation of a course, the creation and maintenance of student customised courses, several exercise methods, argumentative discourse between teachers and students, and group decision mak...
Research Interests:
Research Interests:
Research Interests:
Although the pedagogical advantages of online interactive learning are well known, much needs to be done in instructional design of applicable collaborative learning tasks that motivate sustained student participation and interaction. In... more
Although the pedagogical advantages of online interactive learning are well known, much needs to be done in instructional design of applicable collaborative learning tasks that motivate sustained student participation and interaction. In a previous study based on a Web-based course offered in 2004, Wang (2007) investigated the factors that promote sustained online collaboration for knowledge building. By providing new data from the same Web-based course offered in 2006 and 2007, this study investigates students’ attitudes toward process- and product-oriented online collaborative learning. The analysis of 93 post course survey questionnaire data show that the overwhelming majority of students have positive experience with online collaborative learning. Data also suggest that students are more enthusiastic about process-oriented tasks and their attitudes toward product-oriented collaborative learning tasks are mixed.
Research Interests:
Much research has been performed on how computer-based technologies might facilitate awareness among cooperating actors. However, existing approaches in providing awareness services prove to be inadequate in data-intensive instances of... more
Much research has been performed on how computer-based technologies might facilitate awareness among cooperating actors. However, existing approaches in providing awareness services prove to be inadequate in data-intensive instances of argumentative collaboration. Moreover, they fail to address the needs of dynamic, web-based communities. In this context, this chapter presents a list of awareness mechanisms that have been integrated in an innovative web-based collaboration support tool, namely CoPe_it!, the ultimate aim being to satisfy the requirements associated to the above remarks. The proposed mechanisms are described and elaborated with respect to various awareness types reported in the literature.
Research Interests:
Research Interests: Computer Science and IEEE
Communities of practice need the appropriate means to collaborate in order to reach decisions by exploiting all possible knowledge resources. To address this issue, we have developed a web-based platform that enables members of such... more
Communities of practice need the appropriate means to collaborate in order to reach decisions by exploiting all possible knowledge resources. To address this issue, we have developed a web-based platform that enables members of such communities collaborate through carrying out well-structured argumentative discourses. Our approach comprises a variety of concepts, methods, models and techniques, deriving among others from the decision
Research Interests: Computer Science, Artificial Intelligence, Knowledge Management, Decision Making, Data Mining, and 15 moreComputer Animation, Data Analysis, Argumentation, Information Extraction, Distributed System, Decision support system, Community of Practice, Computer Network, Knowledge Engineering, IT Security, Knowledge Elicitation, Exploratory Data Analysis, Domain Specificity, Association Rule, and Internet
Research Interests:
Research Interests:
Abstract: Expert knowledge and decision-making capabilities are widely considered as organisational resources of high value. In order to exploit the organisational knowledge capital in collaborative decisionmaking settings, we propose a... more
Abstract: Expert knowledge and decision-making capabilities are widely considered as organisational resources of high value. In order to exploit the organisational knowledge capital in collaborative decisionmaking settings, we propose a generic ontology model that has been defined with the use of XML technologies, as it attempts to achieve maximum interoperability and reuse. In this paper we present the structure and the main features of the proposed ontology model, and we describe its application through a case concerning ...
Research Interests:
... List of Evaluators ▪ Adil El Ghali, INRIA ▪ Yannick Naudet, CRP-HT Summary This document presents the technical specifications of the services that will be published by the two tools being developed in the context of WP4, namely... more
... List of Evaluators ▪ Adil El Ghali, INRIA ▪ Yannick Naudet, CRP-HT Summary This document presents the technical specifications of the services that will be published by the two tools being developed in the context of WP4, namely CoPe_it! and e-Logbook. ...
Research Interests:
Although a plethora of Web 2.0 applications exist today, there is little literature reporting on experiences, concrete recommendations or best practices when developing such applications. The scarcity of such records makes it difficult... more
Although a plethora of Web 2.0 applications exist today, there is little literature reporting on experiences, concrete recommendations or best practices when developing such applications. The scarcity of such records makes it difficult for developers to determine how best to support the practices of communities with the use of Web 2.0 technologies. In this paper, we report on eight practical lessons learned while developing Web 2.0 collaboration services for Communities of Practice in the framework of a three years long ...
Research Interests:
Research Interests: Cognitive Science, Social Psychology, Knowledge Management, Logistics, Concurrent Engineering, and 15 moreModeling, Engineering Design, Confidence, Supply Chain, Simulation, Accommodation, Transparency, Modelling and simulation, Business and Management, Knowledge Engineering, World Wide Web, Asynchronous, Availability, Process Modelling and Simulation, and Internet
Research Interests:
Aiming to augment the quality of decision making in vessel dismantling, this paper presents an innovative decision support system that takes into account the diversity of the associated constraints to aid stakeholders handle issues such... more
Aiming to augment the quality of decision making in vessel dismantling, this paper presents an innovative decision support system that takes into account the diversity of the associated constraints to aid stakeholders handle issues such as the appropriateness of a disposal methodology or the level of safety in a dismantling yard. Being seamlessly integrated with an advanced simulation environment, the system also facilitates the collaborative design of dismantling processes.