BME MDA - a Műegyetem Digitális Archivuma
Not a member yet
47877 research outputs found
Sort by
Evaluating Machine Learning Algorithms for Effective Network Protocol Classification
No full textThe current study illustrates the effectiveness of machine learning for the classification of protocols. Many critical operations on the network need to be observed, such as traffic analysis, quality of services, and traffic optimization. Given the emerging complexity of the network environment, it has become a challenge for a traditional classifier to deal with encrypted traffic and dynamic port assignment by data traffic. In the current study, three machine learning models were used and examined, named Decision Tree (TD), Random Forest (RF), and Naive Bayes(NB), which were evaluated based on metrics such as precision, precision, recall, and F1 score. The results indicated that both the Random Forest and the Decision tree outperform the NB, the highest achievement of the accuracy was for Random Forest with 96 %. This work shows the potential of using machine learning for the management of modern networks and provides the foundation for further studie
Determination of traffic load induced accumulating permanent strains of granular soils under flexible pavement structures
Full text link
Asset Administration Shell Integration for Iot Sensors: An Automated Process for Precast Concrete Elements
No full textInternet of Things (IoT) enabled sensors are becoming increasingly ubiquitous and solidify the foundation on which digital twins can depict the current state of an actual physical “thing” in the real world. In the context of this paper, the authors present the developed automated process for integrating IoT sensors into the Asset Administration Shell (AAS) as the representation of a digital twin of precast concrete elements. The emphasis is on the early phases of the product lifecycle, namely product development, production, and quality assurance, with an outlook on how this integration benefits the subsequent lifecycle phases.
The concept differentiates between active and passive IoT devices, as well as how their specifics influence the integration process into the AAS. The critical moments of the concept are just before the instance of the product type (i.e. the specific concrete element) is instantiated for the first time during the start of production and when the identifying component (i.e. RFID tag or IoT sensor) is connected physically and digitally to the product in production. Given the vast diversity of embedded systems used as IoT devices, the concrete element's AAS may simply reference the embedded IoT device's AAS, or it may include the device's data into its own AAS, making the embedded device a "co-managed asset." A physical demonstrator shows the capability of the proposed approach and the way of integrating the gathered data into both IoT platforms and building information models (BIM) for the as-built state.
The paper concludes with a discussion of the future steps in development and prospective transfer alternatives, as well as a reflection on the functional gains achieved through the use of the AAS
Játékosított tanulás a szervezetben: A Games for Business online oktató platform felhasználó-központú vizsgálata
No full text
