http://hdl.handle.net/20.500.14044/33788 2026-07-26T15:13:07Z http://hdl.handle.net/20.500.14044/32851 Priority Decision Rules with a Fuzzy MCDM Approach for Solving Flexible Job Shop Problem: A Real Case Study of Optimizing Manufacturing Stanković, Aleksandar; Petrović, Goran The Flexible Job Shop Problem (FJSP) represents a significant challenge in the field of planning due to its complexity and the constant need for problem-solving in the market. It should be emphasized that FJSP is one of the most difficult NP problems in combinatorial optimization. One of the key factors in maintaining the competitiveness of small and medium enterprises in the market is increasing productivity while minimizing costs and manufacturing time. This paper proposes a multi-criteria approach, whose main role is job prioritization and FJSP optimization using a metaheuristic algorithm in a specific case study of a furniture manufacturing company. To determine the weight coefficients, two methods, the fuzzy Analytic Hierarchy Process (FAHP) and the fuzzy Full Consistency Method (FFUCOM), were integrated, while the fuzzy Weighted Aggregated Sum Product Assessment (FWASPAS) method was used for job ranking. As the next step in the study, the NSGA II algorithm was applied to optimize FJSP. Based on the conducted case study and production optimization, experimental results demonstrated the success of the proposed methodology and improved the organization of production resources after job prioritization. 2025-01-01T00:00:00Z http://hdl.handle.net/20.500.14044/32241 Hierarchical Knowledge Graphs and their Application Siklósi, István The transformation of the world's knowledge from poorly structured texts, to well-structured knowledge graphs (KG) is a common practice. KGs are well-suited for AI applications, but their human representation can pose challenges for clarity and navigation, especially when dealing with a large number of elements. To address the issue, we propose the introduction of a new type of diagram known as the Hierarchical Knowledge Graph (HKG). Based on the models of cognitive psychology, the HKG has the potential to enhance the use of KGs and ontologies in educational contexts, as it can serve as presentable lecture notes and an alternative to traditional textbooks. This article presents a novel prototype of an application. 2025-01-01T00:00:00Z http://hdl.handle.net/20.500.14044/32240 Social and Sexual Robots: Technological Development, Social Acceptance and Ethical Challenges Nagy, Enikő Japanese society is characterised by a unique technological development and openness to it, which has allowed the development of sexual and social robots. This article provides an overview of the technological development, social acceptance and ethical challenges of passion machines. It presents recent technological advances in the field of intimate robots and analyses their impact on human-machine interaction and individual sexual experiences. In addition, it examines the reactions and attitudes of societies towards these technologies, including acceptance, debates and possible protests. The abstract concludes with a discussion of the ethical issues that arise with the development of this type of technology, and draws attention to the importance of protecting human rights and social norms in this dynamically changing environment. 2025-01-01T00:00:00Z http://hdl.handle.net/20.500.14044/32238 A Comparison of Neural Networks and Fuzzy Inference Systems for the Identification of Magnetic Disturbances in Mobile Robot Localization Stefanoni, Massimo; Takács, Márta; Odry, Ákos; Sarcevic, Peter Three-axis magnetometers are widely used in the field of localization in both outdoor and indoor environments. However, magnetic field measurements are disturbed by the presence of metallic objects due to the soft and hard-iron effects. To neglect these effects, a compensation technique is required, and, in this article, different solutions are proposed and evaluated to compensate for the disturbance effects of metallic objects with known fingerprints. These techniques exploit an already presented concept in the literature that is able to provide the compensation values of a known detected object using the distance and angle as inputs to a single hidden layer Artificial Neural Network (ANN). In this work, unlike the original proposal, each new presented technique exploits a modified or a different soft computing tool, such as a double hidden ANN, a Fuzzy Inference System (FIS), and an Adaptive Neural FIS (ANFIS). The techniques were tested with real measurements of three different objects, and the performances of the techniques were compared using the maximum errors, the Mean Absolute Errors (MAEs) of every single component, and the total MAEs. Overall, among them, only the ANN techniques and the ANFIS provided acceptable results. More precisely, the former provided maximum errors in the range between 0.3 μT and 3.8 μT, and MAEs in the order of 0.07 μT, whereas the latter was the one that provided the best performance, giving a residual maximum error in the order of 10 -3 μT and an MAE in the order of 10 -5 μT. 2025-01-01T00:00:00Z