Search

The field of Natural Language Processing (NLP) has experienced significant growth in recent years, largely due to advancements in Deep Learning technology and especially Large Language Models. These improvements have allowed for the development of new models and architectures that have been successfully applied in various real-world applications. Despite this progress, the field of Legal Informatics has been slow to adopt these techniques. In this study, we conducted an extensive literature review of NLP research focused on legislative documents. We present the current state-of-the-art NLP tasks related to Law Consolidation, highlighting the challenges that arise in low-resource languages. Our goal is to outline the difficulties faced by this field and the methods that have been developed to overcome them. Finally, we provide examples of NLP implementations in the legal domain and discuss potential future directions. [ABSTRACT FROM AUTHOR]

Inverse frequent itemset mining can be successfully modelled as an instance of the Probabilistic Satisfiability problem. Given a transaction database we can perform a frequent itemset mining algorithm, like the Apriori algorithm, to obtain useful itemset collections such as frequent or closed itemsets. We then use these itemset collections as frequency constraints in order to reconstruct the original database by solving a linear programming problem. There are cases however, where the reconstructed database is not in direct agreement with the original one. In this study, we analyse the degree of similarity between the original database and the reconstructed one, when different variations of condensed itemset representations are used as the initial frequency constraints. We examine how much the initial database properties and itemset relations have been preserved when we emphasize on the frequent itemset border and assess database quality by measuring database distance metrics. As this solution framework presents increased computational cost, we also consider a heuristic approach that is based on the notion that a transaction can be also considered as an itemset and compare the strengths and weaknesses of each framework when the same conditions apply. We manage to improve the efficiency of existing heuristic based approaches to the problem by utilizing smaller initial itemset collections. Our work contributes in (a) privacy preserving data mining and (b) gain in transaction database storage memory savings. [ABSTRACT FROM AUTHOR]

An open-source management system of Web-based teaching interventions is presented that can be used in general for science curriculum courses and especially for computer science courses. The proposed solution is called System of Teaching Intelligent Interventions (STII) and facilitates the authoring, deployment, and evaluation of Web-based metaphors. This paper discusses the use of metaphors for assisting students to comprehend the substance of cognitive concepts and their basic background. STII has been applied in a particular educational scenario during the learning process of 228 students attending the course 'computer applications.' The presentation of results from a pilot evaluation of two metaphors demonstrates the usefulness of the system. The evaluation focuses on the impact of the two metaphors on student learning, and on detecting potential correlations between metaphors and students' groups. STII evaluation conclusions strongly support that multimedia metaphors can be used as an alternative instructional tool to assist students in confronting their cognitive constraints and developing functional understanding of curriculum courses. Index Terms--Internet technologies, multimedia metaphors, open learning system, teaching intervention.

The broad acceptance of mobile technology has undoubtedly created new opportunities in communication. The proposed environment attempts to enhance the information flow among the members of a department and, furthermore, to provide a test-bed mobile Web application for students undertaking Internet technologies courses. The key ideas are to support the educational process to provide auxiliary access to educational information sources, such as announcements, course schedules, grades, and user directory details. As a second system integration step, additional mobile Web services were introduced, such as application forms of the department's administration office, project assignment, and discussion groups. Technological evaluation and students' feedback indicate that the proposed solution is both efficient in communication perspective and effective for student involvement in the mobile Web initiative. Future steps include multimedia messages (MMS) integration and third-generation (3G)-based information delivery. Index Terms--Internet technologies, mobile communication, mobile education, mobile Web services, Web development.

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.jss.2005.06.002 Byline: Christos Makris, Yannis Panagis, Evangelos Sakkopoulos, Athanasios Tsakalidis Keywords: Dynamic discovery; Adaptive Web Services; UDDI Abstract: Attempts have been made concerning the search and finding of a Web Service based on keywords and descriptions. However, no work has been done concerning the efficient selection of the appropriate Web Service instance in terms of quality and performance factors at the moment of the Web Service consumption attempt. Such factors may include execution time and response time. The proposed approach adaptively selects the most efficient WS among possible different alternatives with real-time, optimized and countable factors-parameters. Implementation issues and case study experiments are presented along with the corresponding results. Additionally, an optimal selection algorithm for series of Web Services requests is proposed. Finally, conclusions and future steps are discussed. Author Affiliation: Department of Computer Engineering and Informatics, School of Engineering, University of Patras Rio, 26500 Patras, Greece Research Academic Computer Technology Institute, Internet and Multimedia Technologies Research Unit 5, 61 Riga Feraiou Str. 26110 Patras, Greece Article History: Received 16 April 2005; Revised 1 June 2005; Accepted 2 June 2005 Article Note: (footnote) [star] This work is partially supported by the Karatheodory Research Program of the University of Patras, Greece.

Educational Data Mining has turned into an effective technique for revealing relationships hidden in educational data and predicting students' learning outcomes. One can analyze data extracted from the students' activity, educational and social behavior, and academic background. The outcomes which are produced are, the following: A personalized learning procedure, a feasible engagement with students' behavior, a predictable interaction of the students with the learning processes and data. In the current work, we apply several supervised methods aiming at predicting the students' academic performance. We prove that the use of the default parameters of learning algorithms on a voting generalization procedure of the three most accurate classifiers, can produce better results than any single tuned learning algorithm. [ABSTRACT FROM AUTHOR]

This work aims to contribute to the field of COVID-19 pandemic analysis. In this research we applied a twofold analysis that focused initially on the country general social-economic and medical characteristics and on top of that in a second level exploring the correlations to the characteristics that affect COVID-19 patients' mortality level. The approach has been applied to large datasets that include country level medical and the socio-economic data according to World Health Organization, the role of the cigarette consumption per capita using open datasets, and the cumulative data of the "COVID-19 Data Repository by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University" for the total number of Cases, Deaths and Recovered. 101 countries including twenty-two (22) features are studied. We have also drilled in the country of Mexico datasets to show case the effectiveness of our approach. We show that our approach can achieve 96% overall accuracy based on the proposed combination approach of macro and micro features. Our approach outdoes previous study results that utilize machine learning to assist medical decision-making in COVID-19 prognosis. We conclude that country social economic and medical characteristics play important role to COVID-19 patients' prognosis and their outcome. [ABSTRACT FROM AUTHOR]

Face morphing poses a serious threat to Automatic Border Control (ABC) and Face Recognition Systems (FRS) in general. The aim of this paper is to present a qualitative assessment of the morphing attack issue, and the challenges it entails, highlighting both the technological and human aspects of the problem. Here, after the face morphing attack scenario is presented, the paper provides an overview of the relevant bibliography and recent advances towards two central directions. First, the morphing of face images is outlined with a particular focus on the three main steps that are involved in the process, namely, landmark detection, face alignment and blending. Second, the detection of morphing attacks is presented under the prism of the so-called on-line and off-line detection scenarios and whether the proposed techniques employ handcrafted features, using classical methods, or automatically generated features, using deep-learning-based methods. The paper, then, presents the evaluation metrics that are employed in the corresponding bibliography and concludes with a discussion on open challenges that need to be address for further advancing automatic detection of morphing attacks. Despite the progress being made, the general consensus of the research community is that significant effort and resources are needed in the near future for the mitigation of the issue, especially, towards the creation of datasets capturing the full extent of the problem at hand and the availability of reference evaluation procedures for comparing novel automatic attack detection algorithms. [ABSTRACT FROM AUTHOR]

This work is aiming to contribute to the field of Distance Learning through Learning Analytics. We propose a methodological framework based on network analysis metrics to provide multiple indicators for Course Learning Analytics. Social Network Analysis is proposed for this purpose due to its capacity to provide an integrated representation of students' interaction, where individual behavior is expressed within the context of a learning community. We perform experimental evaluation on real-life data from anonymized forum posts of postgraduate students and their tutors in the School of Science and Technology at the Hellenic Open University. Initially, we create and examine two-mode networks (participant-discussion) for two different modules. Subsequently, these networks are transformed into one-mode networks. Key measures are estimated and compared and the differences between their pedagogical interpretations are highlighted. We conclude that the choice between working with a bimodal network or projecting it into a unimodal one is determined by the nature of the research questions because of the distinct features that each one of them exhibits. [ABSTRACT FROM AUTHOR]

Byline: Yannis Panagis, Evangelos Sakkopoulos, John Garofalakis, Athanasios Tsakalidis Web searching - one of the most frequent activities in the internet community - is perhaps the most complicated one because of the abundant resulting information available. Users are often puzzled because of long results of ranking lists that are compiled without considering their individual preferences and needs. We present a mechanism in this work that reranks and groups search results on the user's side according to his/her explicit and implicit choices. Furthermore, a caching strategy is introduced to minimise personalisation effect response time. A web environment prototype has been developed to exemplify the potentials of the proposed mechanism. User assessment has been conducted to verify the effectiveness of the mechanism. Results and feedbacks have been efficient and encouraging, respectively.

Byline: Evangelos Sakkopoulos, Dimitris Kanellopoulos, Athanasios Tsakalidis The proposed techniques facilitate semantic discovery and interoperability of web services that manage and deliver web media content. As a test-bed, a web management system is discussed that provides vocational monographs for occupational guidance. The key idea of the proposed web service based architecture is that the WS of participating members share their vocational monographs and related resources, resulting in the overall system capacity increase. Mechanisms and techniques are presented concerning: an 'information desk', which provides an adaptive search user interface; discovery functions based on semantic representation of the WS' monographs; mining into monographs based on their semantic representation; a metric-based evaluation model for the web monographs; dynamic ranking of retrieved content list; consumption mechanisms for the career counsellors' local WS; e-payment; universal usability access. This analysis can be exploited in the practice of a new Occupational Guidance Policy.

This paper addresses the problem of extracting fundamental learning style stereotypes through the exploitation of the biologically-inspired pattern recognition paradigm of Artificial Immune Systems (AIS). We present an unsupervised computational mechanism which exhibits the ability to reveal the inherent group structure of learning patterns that pervade a given set of educational profiles. We rely on the construction of an Artificial Immune Network (AIN) of learning style exemplars by proposing a correlation-based distance metric. This choice is actually imposed by the categoric nature of the underlying data. Our work utilizes an original dataset which was derived during the conduction of an extended empirical study involving students of the Hellenic Open University. The educational profiles of the students were built by collecting their answers on a thoroughly designed questionnaire taking into account a wide range of personal characteristics and skills. The efficiency of the proposed approach was assessed in terms of cluster compactness. Specifically, we measured the average correlation deviation of the students' education profiles from the corresponding artificial memory antibodies that represent the acquired learning style stereotypes. Finally, the unsupervised learning procedure adopted in this paper was tested against a correlation-based version of the k-means algorithm indicating a significant improvement in performance for the AIS-based clustering approach. [ABSTRACT FROM AUTHOR]

Touristic destinations all around the world are struggling to digitally transform the touristic experience and the touristic products they offer and to capitalize a good experience with new tourists and returning ones. There is a lot of research on digital solutions assisting tourism, but it does not provide a follow-up digital product, therefore depending only on physical gifts, postcards and mementos. In this work, we propose a novel platform that can provide a personalized digital memento or digital gift for every route or tourist destination that can become the digital point of reference of visitors' experience giving new dimensions for commercialization to the existing physical mementos at the gift shops. The purpose of this study is to analyze what comprises a memorable touristic experience and to design and, finally, present a total solution that builds and offers a personal e-souvenir of a touristic experience to the tourist for him to hold, sport and share just using his mobile phone. We propose a digital memento-building platform that includes the personalized experience in visits taking place while in vacations. The visitors are usually taking pictures along routes they follow that later need further organization and processing and that in no way substitutes the physical mementos. In our approach, we propose a solution that generates a unique and personalized e-souvenir through a collage of the selfies and photos creating the digital equivalent of the touristic postcards but in our case personalized with the visitor photos with minimum amount of effort and produced real-time. Our approach is also providing a platform to the photographers and designers of touristic destinations to build and graphically generated memento artifacts—templates specific for one or more destinations or routes. In this way, the approach serves the tourism industry vertically, covering all aspects, i.e., the tourist-visitor, the tourism professional players such as photographers, designers of physical mementos and, of course, the touristic destination providing a digital footprint to server marketing of the destination through sharing on social media and word-of-mouth, of course. To support our approach, we have built and run a fully working prototype in the touristic center of Athens, Greece, with real users and designers for several weeks during summer vacations. The results have been greatly encouraging from end-users and professionals. The study shows that it is possible for various lines of business to come together and work along one another for an improve touristic experience using mobile technologies in a personalized, targeted approach. The touristic destination, graphic designers, photographers, tourist agent specialists, software developers and visitors can all now have a digital personalized memorable gift from the visit. [ABSTRACT FROM AUTHOR]

Information Systems in the context of the health domain play a critical role. The evolution of the semantic web and knowledge management technologies in the last years set a new context for the exploitation of patient-centric strategies based on well-defined semantics and knowledge. In this paper we have two critical objectives. On the one hand to exploit the state of the art on Semantic Web and Knowledge Management (KM) approaches in the context of the health domain and on the other hand to underline the key challenges within the FP7 framework of the European Union for customised and personalised health services. [ABSTRACT FROM AUTHOR]

Privacy enhancing technologies (PETs) allow to achieve user's transactions unlinkability across different online Service Providers. However, current PETs fail to guarantee unlinkability against the Identity Provider (IdP), which becomes a single point of failure in terms of privacy and security, and therefore, might impersonate its users. To address this issue, OLYMPUS EU project establishes an interoperable framework of technologies for a distributed privacy-preserving identity management based on cryptographic techniques that can be applied both to online and offline scenarios. Namely, distributed cryptographic techniques based on threshold cryptography are used to split up the role of the Identity Provider (IdP) into several authorities so that a single entity is not able to impersonate or track its users. The architecture leverages PET technologies, such as distributed threshold-based signatures and privacy attribute-based credentials (p-ABC), so that the signed tokens and the ABC credentials are managed in a distributed way by several IdPs. This paper describes the Olympus architecture, including its associated requirements, the main building blocks and processes, as well as the associated use cases. In addition, the paper shows how the Olympus oblivious architecture can be used to achieve privacy-preserving M2M offline transactions between IoT devices. [ABSTRACT FROM AUTHOR]

Web services serve as a leading technology platform for web-based data-centric environments providing flexibility of loose coupling, message-based communication. Interest in more efficient web services selection strategies is rather requisite especially from the business process workflow perspective. We present several strategies to efficiently select a set of web services performing a workflow, fulfilling quality specifications at all workflow steps. The focus is on finding the best performing web service given a history of the execution times and current measured variation in operating system and network resource consumption. To assess their efficiency, we experimentally evaluate them and present comparative results, which strongly indicate that they can effectively reduce the overall workflow execution time in a web service-based workflow with QoS constraints. Approaches are presented for a number of workflows depending on their particular characteristics. [ABSTRACT FROM AUTHOR]

Privacy enhancing technologies (PETs) allow to achieve user's transactions unlinkability across different online Service Providers. However, current PETs fail to guarantee unlinkability against the Identity Provider (IdP), which becomes a single point of failure in terms of privacy and security, and therefore, might impersonate its users. To address this issue, OLYMPUS EU project establishes an interoperable framework of technologies for a distributed privacy-preserving identity management based on cryptographic techniques that can be applied both to online and offline scenarios. Namely, distributed cryptographic techniques based on threshold cryptography are used to split up the role of the Identity Provider (IdP) into several authorities so that a single entity is not able to impersonate or track its users. The architecture leverages PET technologies, such as distributed threshold-based signatures and privacy attribute-based credentials (p-ABC), so that the signed tokens and the ABC credentials are managed in a distributed way by several IdPs. This paper describes the Olympus architecture, including its associated requirements, the main building blocks and processes, as well as the associated use cases. In addition, the paper shows how the Olympus oblivious architecture can be used to achieve privacy-preserving M2M offline transactions between IoT devices.