Security threats, among other intrusions affecting the availability, confidentiality and integrity of IT resources and services, are spreading fast and can cause serious harm to organizations. Intrusion detection has a key role in capturing intrusions. In particular, the application of machine learning methods in this area can enrich the intrusion detection efficiency. Various methods, such as pattern recognition from event logs, can be applied in intrusion detection. The main goal of our research is to present a possible intrusion detection approach using recent machine learning techniques. In this paper, we suggest and evaluate the usage of stacked ensembles consisting of neural network (SNN) and autoen-coder (AE) models augmented with a tree-structured Parzen estimator hyperparameter optimization approach for intrusion detection. The main contribution of our work is the application of advanced hyperparameter optimization and stacked ensembles together.We conducted several experiments to check the effectiveness of our approach. We used the NSL-KDD dataset, a common benchmark dataset in intrusion detection, to train our models. The comparative results demonstrate that our proposed models can compete with and, in some cases, outperform existing models.
Higher education has a number of key roles to play in accelerating progress toward sustainability goals. It has a responsibility to provide and teach curricula that are tailored to labor market needs, to help change people’s attitudes and motivation toward sustainability, and to reduce inequalities between different students. Course leaders and developers of curricula should monitor and assess these needs in order to improve their curricula from time to time. In the present work, we describe a data-driven approach based on text-mining techniques to identify the competences required for a given position based on job advertisements. To demonstrate the usefulness of our suggested method, the supply chain management occupation was selected as the supply chain is a constantly changing domain that is highly affected by green activities and initiatives, and the COVID-19 pandemic strongly influenced this sector, as well. This data-driven process allowed the identification of required soft and hard skills contained in job descriptions. However, it was found that some important concepts of green supply chain management, such as repair and refurbishment, were only marginally mentioned in the job advertisements. Therefore, in addition to labor market expectations, a business process model from relevant green supply chain management literature was developed to complement the required competences. The given new techniques can support the paradigm shift toward sustainable development and help curriculum developers and decision makers assess labor market needs in the area of sustainability skills and competences. The given result can serve as an input of outcome-based training development to design learning objective-based teaching materials.
Blockchain technology creates the possibility for developing knowledge-intensive goods. Only a few studies in Affordance theory deal with investigating blockchain. This paper aims to discover affordances in blockchain when designing an AI-based financial recommendation system as a decision support system. The design thinking methodology was extended with machine learning and business process modelling to discover financial offerings, digital objects to be tokenised, advantages gained from the tracing affordances and consensus mechanism, and the role of smart contracts for each persona. The implementation of discovered blockchain-based applications requires a multichain framework to meet the requirements of design affordances.
25 September 2020 in International Journal of Serious Games
This paper presents a study on data retrieved from a gamified team building application, which promotes employees’ joint sport activities. The aim of this work is to identify and evaluate behavior usage patterns, and user engagement indicators based on interaction data gained from the application and to determine key factors affecting engagement levels. In order to determine behavioral patterns, users have been tested for system use, for participation at events and competitions, and for having tendency in social interactions. The study classified three typologies of engaged users: the Achievers who are motivated by the reward of achieving long-term goals, the Socializers who enjoy interacting with others and the Conquerors who like struggling until they eventually achieve victory by defeating others. We were also able to reveal additional influencing factors beyond personal behavior patterns like the corporate culture and the importance of the ‘organizers’.
13 March 2018 in Vezetéstudomány / Budapest Management Review