196 research outputs found
TCEC-FCM: Efficient Algorithm for Total Causal Effect Calculation in Fuzzy Cognitive Maps
No full text<p>This repository contains the source code developed and used in the paper: <em>"Advancing Explainable AI with Causal Analysis in Large-Scale Fuzzy Cognitive Maps",</em> written by <strong>Marios Tyrovolas</strong>, <strong>Nikolaos D. Kallimanis</strong>, and <strong>Chrysostomos Stylios</strong>.</p>
<p>While this paper is under review, please cite this work as follows:</p>
<blockquote>
<p>Tyrovolas, M., Kallimanis, N. D., & Stylios, C. (2024). Advancing Explainable AI with Causal Analysis in Large-Scale Fuzzy Cognitive Maps.</p>
</blockquote>
<h3>Acknowledgements</h3>
<p>This research has been financed by the European Union: Next Generation EU through the Program Greece 2.0 - National Recovery and Resilience Plan, under the call "Flagship actions in interdisciplinary scientific fields with a special focus on the productive fabric”, project name "Greece4.0 - Network of Excellence for developing, disseminating and implementing digital transformation technologies in Greek Industry" (project code: TAEDR-0535864).</p>
<h3>Contact</h3>
<p>For any question, please raise an issue or contact</p>
<div>
<pre><code>Marios Tyrovolas: [email protected]</code></pre>
</div>
Guidelines for Elaboration Management Action Plan for Ecologically Sustainable Development and Management of SEE Seaports of Trans-European Transport Networks
No full textSea transport is considered globally as one of the most environmentally harmless forms of transport. For this reason the ports’ activities are a subject to special precautions to ensure that they support the sustainable and environment friendly development of sea conditions. The work presents, first, the main features of the common model (CM) for improved seaports’ ecology, and second, it elucidates the guidelines about the preparation of Managing Action Plans (MAP) for South-East Europe (SEE) harbors. Also, the work describes the general structure of MAP and gives a list of tangible instructions and recommendations streaming the elaboration of MAP for an improved management of SEE seaports of TEN-T
Harmony search augmented with optimal computing budget allocation capabilities for noisy optimization
No full textIn this work we introduce the combinatory use of Harmony Search (HS) with Optimal Computing Budget Allocation (OCBA) as a means to tackle noisy optimization situations as those that occur during the execution of Discrete Event Systems (DES) for modeling complex systems. The OCBA procedure is employed for the exclusion of the worst harmony during the memory updating process in order to minimize the computational cost and at the same time retain a pool of promising solutions. The proposed hybrid approach is tested on real valued test functions as a proof of concept and the results are promising in case of small computational budgets
Tiphys: An Open Networked Platform for Higher Education on Industry 4.0
No full textObjective of Tiphys project is building an Open Networked Platform for the learning of Industry 4.0 themes. The project will create a Virtual Reality (VR) platform, where users will be able to design and create a VR based environment for training and simulating industrial processes but they will be able to study and select among a set of models in order to standardize the learning and physical processes as a virtual representation of the real industrial world and the required interactions so that to acquire learning and training capabilities. The models will be structured in a modular approach to promote the integration in the existing mechanisms as well as for future necessary adaptations. The students will be able to co-create their learning track and the learning contents by collaborative working in a dynamic environment. The paper presents the development and validation of the learning model, built on CONALI learning ontology. The concepts of the ontology will be detailed and the platform functions will be demonstrated on selected use cases
A Virtual Reality Laboratory for Blended Learning Education: Design, Implementation and Evaluation
No full textLaunched during the pandemic, the EU-funded JANUS project aimed to ensure the continuity of student workshops at universities using a virtual reality (VR) robotics laboratory. With the return to normality, the project has been redesigned to capitalise on the positive outcomes of the experience. The VR lab provides safe and unrestricted access to the labs and experiments with the machines, reducing the consequences of student mistakes and improving the user experience by allowing the experiment to be repeated from different angles, some of which are impossible to access in the real lab. In addition, integration with an interactive learning platform called “ViLLE” allows for continuous assessment of the learning experience. Self-evaluation of the material taught and learned can be integrated with the execution of the exercises that pave the way for Kaizen. Two VR workshops for the blended learning of robotics were developed during the JANUS project. Their evaluation reported favourable responses from the students whose learning performance was indirectly measured
Exploring the detectability of short-circuit faults in inverter-fed induction motors
No full textThis paper explores the possibility of creating an automatic method for assessing the condition of induction motor circuits fed by inverters. The stator current and magnetic flux are processed in the frequency domain and a feature selection stage is employed to pinpoint the most informative components to further be fed to a classifier that performs the assessment of the motor circuit. The results are promising, indicating that short circuit detection as well as quantification is feasible using noninvasive techniques
Why Fuzzy Cognitive Maps Are Efficient
No full textIn many practical situations, the relation between the experts’ degrees of confidence in different related statements is well described by Fuzzy Cognitive Maps (FCM). This empirical success is somewhat puzzling, since from the mathematical viewpoint, each FCM relation corresponds to a simplified one-neuron neural network, and it is well known that to adequately describe relations, we need multiple neurons. In this paper, we show that the empirical success of FCM can be explained if we take into account that human’s subjective opinions follow Miller’s seven plus minus two law
Strategies to Enhance Students' Capabilities of Abstract Thinking - the Use of Case in Different Learning Situations
No full text- …
