MTA-SZTE Research Group on Artificial Intelligence
SZTE Publicatio Repozitórium - SZTE - Repository of PublicationsNot a member yet
32192 research outputs found
Sort by
Germany’s Security Role in Bosnia and Herzegovina, North Macedonia, Kosovo: From Civilian Power to Strategic Actor
Get PDFChallenges of Consolidation and Institutionalisation of Cross-border Cooperation in the Hungarian–Romanian–Serbian border region
Get PDF
A református peregrináció kollektív és személyes emlékezete a kora újkorban
Get PDFThe Collective and Personal Memory of Reformed Peregrination in the Early Modern Period. In the Early Modern Period, Reformed students in Hungary created a complex network. This network helped them to organize their university studies abroad. The memory of the peregrination is documented in ego-documents and other records. The culture of memory was maintained by a complex network of personal and collective elements. The oral tradition played an important role in the system, as much information was preserved by word of mouth. Written sources of memory survive in student lists, friendship books, diaries, and church chronicles. However, traces of historical research that went beyond memory can be found not only in the works of scholars (Péter Bod, Miklós Sinai, István Weszprémi) but also in congregational documents
The importance of community music in society
Get PDFCommunity music is a multifaceted phenomenon that fosters collaboration, social cohesion, and cultural expression through active music engagement within diverse communities. Community music-making is best understood as an inclusive, participatory practice that has the power to transform social dynamics within communities. The literature presents the multifaceted dimensions and potential of community music-making, showing its ability to promote not only artistic expression, but also social coherence, personal growth, and community development. This synthesis of literature underscores the potential for community music to serve as a catalyst for positive change in music education practices, focussing on communal engagement and empowerment rather than solely individual treatment
Correlations Between Colloidal Stability and Peroxidase Activity of Prussian Blue Nanozymes in Salt Solutions
Get PDFBioimpedance Analysis of Cucumber Plants Exposed to Different Nitrogen Doses Under Greenhouse Conditions
Get PDFNitrogen (N) availability is critical for cucumber (Cucumis sativus L.) growth and yield in greenhouse production. In this study, we investigated the effects of different N doses on the bioimpedance spectroscopy (BIS) parameters of cucumber plants (ES.22.17 F1 genotype), focusing on extracellular fluid resistance (R1), intracellular fluid resistance (R2), vacuole fluid resistance (R4), and cell membrane capacitances (Cm, Ct). The results showed that low N supply significantly increased R1 and reduced Cm in the leaves, indicative of decreased nitrate (NO3−) concentration and impaired membrane fluidity. Higher N supply lowered resistance and increased cell membrane capacitance, reflecting improved ion transport and storage efficiency. A strong positive correlation was observed between total N and NO3− content (r = 0.9), while NO3− content negatively correlated with extracellular fluid resistance (R1, r = −0.8) and vacuole fluid resistance (R4, r = −0.9). The optimal N supply for cucumber plants was associated with R1 values of 47,121.07–52,953.93 Ω, R4 values of 0.348–0.529 Ω, and Cm values of 3.149 × 10⁻10–3.781 × 10⁻10 F. These BIS parameters showed high sensitivity to plant N status, highlighting BIS as a promising, minimally invasive technique for real-time nutrient monitoring. By integrating BIS data and horticultural best practices, growers can refine N fertilization strategies for better resource efficiency and potentially higher yields and fruit quality
Artificial Neural Network-based MEMS Accelerometer Array Calibration
Get PDFAccurate calibration of micro-electromechanical systems (MEMS) accelerometers is crucial for enhancing the performance of low-cost inertial measurement units (IMUs). This paper introduces a novel calibration technique that leverages artificial neural networks (ANNs) combined with data from multiple IMUs to increase the accuracy of the calibration. The proposed method involves a calibrated UR robot, which enables the data acquisition of ground truth data for an effective calibration of IMUs. It enhances the calibration accuracy by utilizing the collective measurements from five IMUs within an accelerometer array. Fourteen sets of measurement data were established in dynamic environments using the robotic arm. The ANN-based approach was trained using ten datasets of dynamic measurements, where the trained model is validated against four unseen test data. The ANN-based calibration performance is evaluated by comparing it to standard methods such as ellipsoid fitting method and arithmetic averaging of the sensor outputs. Results demonstrate that the proposed method achieves superior calibration accuracy, with an improvement of 18.2% over the ellipsoid fitting technique and 23.3% over the averaging method. It also shows that fusing accelerometer measurements with Euler angles calculated from acceleration as input data for the ANN provided the best results for the calibration. The findings suggest that integrating ANN models with data fusion from multiple sensors significantly improves the calibration accuracy of MEMS accelerometers, thereby enhancing their potential for use in precise motion sensing applications
