Lidé na fakultě
PhDr. Viktor Fuglík, Ph.D.

2023, International Journal of Artificial Intelligence in Education, 2023 (33), p. 583-608), ISSN 1560-4292

Student drop-out is one of the most critical issues that higher educational institutions face nowadays. The problem is significant for first-year students. These freshmen are especially at risk of failing due to the transition from different educational settings at high school. Thanks to the massive boom of Information and Communication Technologies, universities have started to collect a vast amount of study- and student-related data. Teachers can use the collected information to support students at risk of failing their studies. At the Faculty of Mechanical Engineering, Czech Technical University in Prague, the situation is no different, and first-year students are a vulnerable group similar to other institutions. The most critical part of the first year is the first exam period. One of the essential skills the student needs to develop is planning for exams. The presented research aims to explore the exam-taking patterns of first-year students. Data of 361 first-year students have been analysed and used to construct “layered” Markov chain probabilistic graphs. The graphs have revealed interesting behavioural patterns within the groups of successful and unsuccessful students.

Článek v periodiku excerpovaném databází Scopus

2021, Future Generation Computer Systems, 125, p. 661-671), ISSN 0167-739X

The Faculty of Mechanical Engineering, Czech Technical University in Prague (FME) faces a significant student drop-out in the first-year bachelor programme, which is an actual problem for many higher education institutions. Metacognitive processes play a vital role in self-regulated learning. Students become active participants in their learning, and one critical aspect of higher education studies is planning and time management. The exam taking behaviour is in the context of the FME manifestation of the time management skills of each student; thus, the exam-taking patterns may help identify at-risk students. To evaluate the importance of exam behaviour patterns, we conducted three experiments. Identification of students passing or failing the first study year has been conducted using four different machine learning models. The exam taking behaviour patterns increase the prediction F-measure significantly for the class of failing students (approximately 0.3 increase). Moreover, the approach based on student behaviour enabled us to identify the critical exam-taking patterns, which further helps the lecturers identify at-risk students and improve their time management skills and chances to pass the first academic year.

Článek v periodiku excerpovaném SCI Expanded

2020, LAK '20: Proceedings of the Tenth International Conference on Learning Analytics & Knowledge, New York, ACM), p. 124-128), ISBN 978-1-4503-7712-6

At present, universities collect study-related data about their students. This information can be used to support students at risk of failing their studies. At the Faculty of Mechanical Engineering (FME), Czech Technical University in Prague (CTU), the group of the first-year students is the most vulnerable. The most critical part of the first year is the winter exam period when students usually divide into those who will pass and fail. One of the most important abilities, students need to learn, is exam planning, and our research aims at the exploration of the exam strategies of successful students. These strategies can be used for improving first-year students retention. The outgoing research on the analysis of exam strategies of the first-year students in the academic year 2017/2018 is reported. From a total of 361 first-year students, successful students have been selected. The successful student is the one who finished all three mandatory exams before the end of the first exam period. From the exam sequences of 153 selected students, a "layered" Markov chain probabilistic model has been constructed. It uncovered the most common exam strategies taken by those students.

Stať ve sborníku z prestižní konf.

2019, Transforming Learning with Meaningful Technologies, Cham, Springer), p. 587-590), ISBN 978-3-030-29735-0, ISSN 0302-9743

Almost all higher educational institutions use Virtual Learning Environments (VLE) for the delivery of educational content to the students. Those systems collect information about student behaviour, and university can take advantage of analysing such data to model and predict student outcomes. Our work aims at discovering whether there exists a direct connection between the intensity of VLE behaviour represented as recorded student activities and their study outcomes and analyse how intense this connection is. For that purpose, we employed the clustering method to divide students into so-called VLE intensity groups and compared formed groups (clusters) with the student outcomes in the course. Our analysis has been performed using Open University Learning Analytics dataset (OULAD).

Stať ve sborníku z prestižní konf.

2018, Lifelong Technology-Enhanced Learning. EC-TEL 2018., Springer, Cham), p. 575-578), ISBN 978-3-319-98571-8, ISSN 0302-9743

Nowadays, the higher education institutions experience the problem of the student drop-out. In response to this problem, universities started employing analytical dashboards and educational data mining methods such as machine learning, to detect students at risk of failing their studies. In this paper, we present interactive web-based Learning Analytics dashboard - Analyst, which has been successfully deployed at Faculty of Mechanical Engineering (FME), Czech Technical University in Prague. The dashboard provides academic teaching staff with the opportunity to analyse student-related data from various sources in multiple ways to identify those, who might have difficulties to complete their degree. For this purpose, multiple analytical dashboard views have been implemented. It includes summary statistic, study progression graph, and credit completion probabilities graph. In addition, users have the option to export all analysis related graphs for the future use. Based on the outcomes provided by the Analyst, the university successfully ran the interventions on the selected at-risk students and significantly increased the retention rate in the first study year.

Stať ve sborníku z prestižní konf.

2018, Lifelong Technology-Enhanced Learning. EC-TEL 2018., Springer, Cham), p. 166-171), ISBN 978-3-319-98571-8, ISSN 0302-9743

With the rapid advancement of Virtual Learning Environments (VLE) in higher education, the amount of available student data grows. Universities collect the information about students, their demographics, their study results and their behaviour in the online environment. By applying modelling and predictive analysis methods it is possible to predict student outcome or detect bottlenecks in course design. Our work aims at statistical simulation of student behaviour in the VLE in order to identify behavioural patterns leading to drop-out or passive withdrawal i.e. the state when a student is not studying, but he has not actively withdrawn from studies. For that purpose, the method called Markov chain modelling has been used. Recorded student activities in VLE (VLE logs) has been used for constructing of probabilistic representation that students will perform some activity in the next week based on their activities in the current week. The result is an instance of the family of absorbing Markov chains, which can be analysed using the property called time to absorption. The preliminary results show that interesting patterns in student VLE behaviour can be uncovered, especially when combined with the information about submission of the first assessment. Our analysis has been performed using Open University Learning Analytics dataset (OULAD) and research notes are available online (https://bit.ly/2JrY5zv) .

Stať ve sborníku z prestižní konf.

2016

Popis analýzy informačního obsahu dat, které bylo možno vzdáleně vyčíst z vozidlových jednotek při zkušebním provozu v rámci projektu TA04020797.

Výzkumná zpráva v češtině

2016, HARMO 2016 - 17th International Conference on Harmonisation within Atmospheric Dispersion Modelling for Regulatory Purposes, Proceedings, Budapest, Hungarian Meteorological Service), p. 117-120), ISBN 9789639931107

High-quality emission data are of utmost importance for the reliable outputs of air quality models. AQ models require speciated hourly emissions, whereas emission inventories are constructed on annual basis and include only main pollutants. For the time disaggregation simple and constant monthly, daily, and hourly factors are usually used. Likewise, chemical speciations are usually based on outputs of very few and sometimes quite old reports and do not necessarily correspond to the situation in the country of interest. For the emission processing itself many scientific groups use SMOKE pre-processor, due its availability and since it is fitted for the WRF and CMAQ models. Nevertheless, its application for non-US countries can be quite complicated due to different data and metadata structure. Our project focusses on two aims: 1) The derivation of the time and speciation profiles specific for the Czech Republic. For this purpose, we analyse continuous emission measurements from the large stationary sources, temperature and behaviour dependency of the household heating emission, and the data available in the extensive Czech emission database REZZO. For the transport we managed to access data from the Electronic Control Units (ECU) of the vehicular fleet maintained by the SHERLOG company. These unique data give us information on engine state, fuel consumption, and driving styles from the real traffic flow. 2) The construction of a flexible emission processor for AQ models based on the freely available software.

Stať ve sborníku z prestižní konf. (Scopus)

2016

Zpráva popisuje architekturu a jednotlivé součásti navrhovaného emisního modelu. Dále obsahuje popis propojení jednotlivých submodulů a toky a formáty dat.

Výzkumná zpráva v češtině