Conceptual Model of Visual Analytics for Hands-on Cybersecurity Training

Ošlejšek, Radek; Rusňák, Vít; Burska, Karolina; Švábenský, Valdemar; Vykopal, Jan; Čegan, Jakub

doi:10.1109/tvcg.2020.2977336

Cited by 13 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The role of the instructors who use these platforms shifts from being an active intermediary between learning content and students to a facilitator of learning who employs the platform and its features. Once a training starts, the instructors monitor students' progress using the insights automatically provided by the platform, such as those presented in [33]. The insights are generated using the methods of learning analytics [34] and educational data mining [35], which leverage data from educational contexts to understand and improve teaching and learning [36], [37].…”

Section: B Environments For Learning Cybersecurity Skillsmentioning

confidence: 99%

Smart Environment for Adaptive Learning of Cybersecurity Skills

Vykopal

Šeda

Švábenský

et al. 2023

IEEE Trans. Learning Technol.

Self Cite

View full text Add to dashboard Cite

Hands-on computing education requires a realistic learning environment that enables students to gain and deepen their skills. Available learning environments, including virtual and physical labs, provide students with real-world computer systems but rarely adapt the learning environment to individual students of various proficiency and background. We designed a unique and novel smart environment for adaptive training of cybersecurity skills. The environment collects a variety of student data to assign a suitable learning path through the training. To enable such adaptiveness, we proposed, developed, and deployed a new tutor model and a training format. We evaluated the learning environment using two different adaptive trainings attended by 114 students of various proficiency. The results show students were assigned tasks with a more appropriate difficulty, which enabled them to successfully complete the training. Students reported that they enjoyed the training, felt the training difficulty was appropriately designed, and would attend more training sessions like these. Instructors can use the environment for teaching any topic involving real-world computer networks and systems because it is not tailored to particular training. We freely released the software along with exemplary training so that other instructors can adopt the innovations in their teaching practice.

show abstract

Section: B Environments For Learning Cybersecurity Skillsmentioning

confidence: 99%

Smart Environment for Adaptive Learning of Cybersecurity Skills

Vykopal

Šeda

Švábenský

et al. 2023

IEEE Trans. Learning Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…2 College of Electrical and control engineering, Shenyang Jianzhu University, Shenyang 110168, China. 3 College of Electrical and control engineering, Shenyang Jianzhu University, Shenyang 110168, China. 4 Software College, Shenyang Normal University, Shenyang 110168, China.…”

Section: Declarationsmentioning

confidence: 99%

“…Therefore, how to evacuate the trapped people safely and rapidly has become the focus of many scholars' research. Earlier, the modeling of large building fire environment mainly includes raster method [1], topological method [2], and visual map method [3]. The topological method can reduce the search space, but there are many limitations such as complex grid establishment and difficult to maintain; the visual map method can simplify the map by removing unnecessary connecting lines, but the search speed is slow and the environment is poorly adapted when there are many obstacles; and the raster method can rasterize irregular obstacles, and at the same time, it is easy to build and save, so it is more commonly used.…”

Section: Introductionmentioning

confidence: 99%

The Escape Path PlanningAlgorithm in Large Building Fires Based on Multiple Fusion Strategies

Gao

Zhang

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Large building fires are currently the most direct and serious type of fire that causes property damage and casualties, and delayed evacuation is one of the important reasons for casualties. Therefore, how to safely and quickly evacuate trapped individuals has become the focus of research by many scholars. Our goal is to propose a robust, universal, and high-precision fire escape path that utilizes minimal human intervention, making the algorithm practical and highly fitting to the scene. Results: This article constructs a framework for evacuating and evacuating fire personnel. Through the drone relay communication platform, multi-source information data collected at the fire scene is synchronously transmitted to the information exchange center, and uploaded to the cloud for real-time processing. In the cloud processing stage, the dynamic path planning method for large-scale building fires that integrates multiple strategies proposed in this article is used to generate escape paths, and the information exchange center is used to guide personnel to evacuate and escape. In addition, the information exchange center synchronizes the comprehensive scheduling of rescue agencies such as fire alarms and emergency centers. Conclusions: This article proposes a dynamic pathfinder path planning method that integrates multiple strategies based on the original FPA. By utilizing the mapping relationship between personnel location and fitness, the path planning problem is transformed into a set sorting problem, shortening escape time and improving path safety; A multi-objective path planning mechanism based on the A * algorithm has been constructed. By defining a dynamic matching degree to adapt to environmental changes, the population density at the exit is reduced, and the algorithm's global search ability and escape efficiency are improved. A cloud server IoT fire evacuation and escape model based on relay communication drones is designed, which utilizes the drone's adaptive height characteristics to ensure communication quality while expanding communication coverage, By using cloud processing to shorten runtime, the superiority of the method was verified through comparative experiments on single objective and multi-objective global path planning under multiple sets of grid maps with different specifications.

show abstract

“…The learning environment has to collect and evaluate the data to be able to perform the task adaptivity. Furthermore, it is recommended to store the training data in a suitable format and visualize them using visual analytics [19]. Next, it can be useful for further development of adaptive learning techniques or for other research directions.…”

Section: E Data Gathering and Evaluationmentioning

confidence: 99%