In sports, inertial measurement units are often used to measure the orientation of human body segments. A Madgwick (MW) filter can be used to obtain accurate inertial measurement unit (IMU) orientation estimates. This filter combines two different orientation estimates by applying a correction of the (1) gyroscope-based estimate in the direction of the (2) earth frame-based estimate. However, in sports situations that are characterized by relatively large linear accelerations and/or close magnetic sources, such as wheelchair sports, obtaining accurate IMU orientation estimates is challenging. In these situations, applying the MW filter in the regular way, i.e., with the same magnitude of correction at all time frames, may lead to estimation errors. Therefore, in this study, the MW filter was extended with machine learning to distinguish instances in which a small correction magnitude is beneficial from instances in which a large correction magnitude is beneficial, to eventually arrive at accurate body segment orientations in IMU-challenging sports situations. A machine learning algorithm was trained to make this distinction based on raw IMU data. Experiments on wheelchair sports were performed to assess the validity of the extended MW filter, and to compare the extended MW filter with the original MW filter based on comparisons with a motion capture-based reference system. Results indicate that the extended MW filter performs better than the original MW filter in assessing instantaneous trunk inclination (7.6 vs. 11.7◦ root-mean-squared error, RMSE), especially during the dynamic, IMU-challenging situations with moving athlete and wheelchair. Improvements of up to 45% RMSE were obtained for the extended MW filter compared with the original MW filter. To conclude, the machine learning-based extended MW filter has an acceptable accuracy and performs better than the original MW filter for the assessment of body segment orientation in IMU-challenging sports situations.
DOCUMENT
When studying the acquisition of social-communicative competence, it is important to take students' individual learning theories into account. Increased insight into the role ILTs play can be of help in improving social work education.
DOCUMENT
Situated learning plays a key role in internships and other practice-based learning settings in teacher education. The dominant assumption for a long time has been that the development of teaching competency is advanced most through practical teaching experience and post-lesson conferences between mentor and student teachers. It is through the reflection of teaching and classroom processes that student teachers are believed to develop their professional knowledge. The assistance of such reflection draws on mentor teachers’ teaching expertise. Mentor teachers, however, rarely explicate practical and theory-based knowledge underlying their practice and student teachers are not inclined to search for their mentor teacher’s underlying knowledge. As a consequence, the knowledge underlying effective teaching often remains implicit. The symposium brings together three novel approaches to assist teacher learning, which aim to make knowledge of teaching explicit. To bridge the gap between mentor and student teachers’ instructional concepts, the method of videobased tagging as a pre-requisite to initiate and structure professional dialogue is suggested and researched by van den Bogert, Crasborn, Bruggen and Eindhoven in The Netherlands. The second study by Staub, Waldis, Schatzmann and Futter investigates effects of an intervention with mentor teachers in Switzerland, suggesting the enactment of pre-lesson conferences and/or the use of a core concepts for lesson planning and reflection. A third study involving Germany and Switzerland by Kreis, Schnebel, Wyss, Wagner and Deiringer researches student teachers’ knowledge, beliefs and experiences related to collaborative lesson planning with peers. The shared assumption is that all three approaches enhance explicit communication on teaching and encourage professional dialogues that contribute to teacher learning in significant ways. Eliciting mentor and pre-service teachers’ practical knowledge using teacher-tagged classroom situations Bogert van den, Crasborn, Bruggen van & Jochems) Objectives The present study has a twofold objective. First, elicitation of mentor and pre-service teachers’ conceptualizations of videotaped classroom situations to clarify similarities and differences between practical knowledge of experienced and novice teachers. Second, exploration of ‘collaborative tagging’ as a new method to access mentors and pre-service teachers’ practical knowledge. Theoretical framework Teachers’ practical knowledge underlies overt teaching behavior, and is personal, unique, often tacit, and intertwined with teaching actions (Meijer, Verloop, & Beijaard, 2002). The ability to notice and interpret what is happening in a classroom is a basic aspect of teachers’ practical knowledge (Goodwin, 1994). Experienced teachers are more proficient in this essential perceptional process than novice teachers (Berliner, 2001; Sabers, Cushing, & Berliner, 1991). Consequently, proficient teachers may facilitate the professional development of novices. However, mentor teachers rarely explicate practical knowledge underlying their teaching practice (Edwards & Protheroe, 2004), and most pre-service teachers are not inclined to search for their mentor teacher’s practical knowledge (Penny, Harley, & Jessop, 1996). Hence, in this study we explored ‘collaborative tagging’ (Mika, 2005): a method where many people independently attach keywords called tags to e.g. videos, for categorization and fast future retrieval. Collaborative tagging has gained popularity since 2004 (Hammond, Hannay, Lund, & Scott, 2005), indicating the willingness and ease with which this activity is undertaken. In other studies (Cattuto, Benz, Hotho, & Stumme, 2008; Mika, 2005) network analysis of the co-occurrence of tags revealed the semantic relationships between the tags; a bottom-up taxonomy, or a so called folksonomy (Vander Wal, 2004). In this study, collaborative tagging was applied to explore the structure of teachers’ knowledge and compare conscious aspects of mentor and pre-service teachers’ practical knowledge. The main research questions were: • Which concepts do mentor- and pre-service teachers use to tag videotaped classroom situations? • To what extent do the generated tags and the relations between them differ between mentor- and pre-service teachers? • To what extent is collaborative tagging is helpful in gaining access to conscious aspects of mentors and pre-service teachers’ practical knowledge? Method Participants were 100 mentor-teachers and 100 pre-service teachers. The participants each ‘tagged” five video-fragments of different classroom situations. Data were analyzed with UCINET software as proposed by Mika (2005). Co-occurrences of tags were computed. Familiar measures of social network analysis (e.g. clustering coefficients, and (local) betweenness centrality) were used to describe each folksonomy, and to compare pre-service and mentor teachers’ networks of tags. Results and significance The study established that tagging is a promising new method to elicit teachers’ practical knowledge. The resulting folksonomies clarified similarities and differences between mentors’ and pre-service teachers’ practical knowledge. Results indicate that experienced teachers use more detailed and specific tags than pre-service teachers. This method makes a significant contribution to the methodology of the study of teachers’ practical knowledge. Folksonomies not only elicit individual teachers’ practical knowledge but enable researchers to discern common element’s in teachers’ practical knowledge. Moreover, in teacher education, folksonomies are helpful to initiate and structure professional dialogue between pre-service and mentor teachers.
DOCUMENT
Nederland kent ongeveer 220.000 bedrijfsongevallen per jaar (met 60 mensen die overlijden). Vandaar dat elke werkgever verplicht is om bedrijfshulpverlening (BHV) te organiseren, waaronder BHV-trainingen. Desondanks brengt slechts een-derde van alle bedrijven de arbeidsrisico’s in kaart via een Risico-Inventarisatie & Evaluatie (RI&E) en blijft het aandeel werknemers met een arbeidsongeval hoog. Daarom wordt er continu geïnnoveerd om BHV-trainingen te optimaliseren, o.a. door middel van Virtual Reality (VR). VR is niet nieuw, maar is wel doorontwikkeld en betaalbaarder geworden. VR biedt de mogelijkheid om veilige realistische BHV-noodsimulaties te ontwikkelen waarbij de cursist het gevoel heeft daar echt te zijn. Ondanks de toename in VR-BHV-trainingen, is er weinig onderzoek gedaan naar het effect van VR in BHV-trainingen en zijn resultaten tegenstrijdig. Daarnaast zijn er nieuwe technologische ontwikkelingen die het mogelijk maken om kijkgedrag te meten in VR m.b.v. Eye-Tracking. Tijdens een BHV-training kan met Eye-Tracking gemeten worden hoe een instructie wordt opgevolgd, of cursisten worden afgeleid en belangrijke elementen (gevaar en oplossingen) waarnemen tijdens de simulatie. Echter, een BHV-training met VR en Eye-Tracking (interacties) bestaat niet. In dit project wordt een prototype ontwikkeld waarin Eye-Tracking wordt verwerkt in een 2021 ontwikkelde VR-BHV-training, waarin noodsituaties zoals een kantoorbrand worden gesimuleerd (de BHVR-toepassing). Door middel van een experiment zal het prototype getest worden om zo voor een deel de vraag te beantwoorden in hoeverre en op welke manier Eye-Tracking in VR een meerwaarde biedt voor (RI&E) BHV-trainingen. Dit project sluit daarmee aan op het missie-gedreven innovatiebeleid ‘De Veiligheidsprofessional’ en helpt het MKB dat vaak middelen en kennis ontbreekt voor onderzoek naar effectiviteit rondom innovatieve-technologieën in educatie/training. Het project levert onder meer een prototype op, een productie-rapport en onderzoeks-artikel, en staat open voor nieuwe deelnemers bij het schrijven van een grotere aanvraag rondom de toepassing en effect van VR en Eye-Tracking in BHV-trainingen.
Receiving the first “Rijbewijs” is always an exciting moment for any teenager, but, this also comes with considerable risks. In the Netherlands, the fatality rate of young novice drivers is five times higher than that of drivers between the ages of 30 and 59 years. These risks are mainly because of age-related factors and lack of experience which manifests in inadequate higher-order skills required for hazard perception and successful interventions to react to risks on the road. Although risk assessment and driving attitude is included in the drivers’ training and examination process, the accident statistics show that it only has limited influence on the development factors such as attitudes, motivations, lifestyles, self-assessment and risk acceptance that play a significant role in post-licensing driving. This negatively impacts traffic safety. “How could novice drivers receive critical feedback on their driving behaviour and traffic safety? ” is, therefore, an important question. Due to major advancements in domains such as ICT, sensors, big data, and Artificial Intelligence (AI), in-vehicle data is being extensively used for monitoring driver behaviour, driving style identification and driver modelling. However, use of such techniques in pre-license driver training and assessment has not been extensively explored. EIDETIC aims at developing a novel approach by fusing multiple data sources such as in-vehicle sensors/data (to trace the vehicle trajectory), eye-tracking glasses (to monitor viewing behaviour) and cameras (to monitor the surroundings) for providing quantifiable and understandable feedback to novice drivers. Furthermore, this new knowledge could also support driving instructors and examiners in ensuring safe drivers. This project will also generate necessary knowledge that would serve as a foundation for facilitating the transition to the training and assessment for drivers of automated vehicles.
Electronic Sports (esports) is a form of digital entertainment, referred to as "an organised and competitive approach to playing computer games". Its popularity is growing rapidly as a result of an increased prevalence of online gaming, accessibility to technology and access to elite competition.Esports teams are always looking to improve their performance, but with fast-paced interaction, it can be difficult to establish where and how performance can be improved. While qualitative methods are commonly employed and effective, their widespread use provides little differentiation among competitors and struggles with pinpointing specific issues during fast interactions. This is where recent developments in both wearable sensor technology and machine learning can offer a solution. They enable a deep dive into player reactions and strategies, offering insights that surpass traditional qualitative coaching techniquesBy combining insights from gameplay data, team communication data, physiological measurements, and visual tracking, this project aims to develop comprehensive tools that coaches and players can use to gain insight into the performance of individual players and teams, thereby aiming to improve competitive outcomes. Societal IssueAt a societal level, the project aims to revolutionize esports coaching and performance analysis, providing teams with a multi-faceted view of their gameplay. The success of this project could lead to widespread adoption of similar technologies in other competitive fields. At a scientific level, the project could be the starting point for establishing and maintaining further collaboration within the Dutch esports research domain. It will enhance the contribution from Dutch universities to esports research and foster discussions on optimizing coaching and performance analytics. In addition, the study into capturing and analysing gameplay and player data can help deepen our understanding into the intricacies and complexities of teamwork and team performance in high-paced situations/environments. Collaborating partnersTilburg University, Breda Guardians.
