Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.
Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88–0.99, and mean F1-score = 0.90, range = 0.87–0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.
Many studies have shown that self-controlled feedback is beneficial for learning motor tasks, andthat learners prefer to receive feedback after supposedly good trials. However, to date all studiesconducted on self-controlled learning have used individual tasks and mainly relatively simpleskills. Therefore, the aim of this study was to examine self-controlled feedback on tactical skills insmall-sided soccer games. Highly talented youth soccer players were assigned to a self-control oryoked group and received video feedback on their o ffensive performance in 3 vs. 2 small-sidedgames. The results showed that the self-control group requested feedback mostly after good trials,that is, after they scored a goal. In addition, the perceived performance of the self-control groupwas higher on feedback than on no-feedback trials. Analyses of the conversations around thevideo feedback revealed that the players and coach discussed good and poor elements of per-formance and how to improve it. Although the coach had a major role in these conversations, theplayers of the self-control group spoke more and showed more initiative compared to the yokedgroup. The results revealed no significant beneficial effect of self-controlled feedback on per-formance as judged by the coach. Overall, the findings suggest that in such a complex situation assmall-sided soccer games, self-controlled feedback is used both to confirm correct performanceelements and to determine and correct errors, and that self-controlled learning stimulates theinvolvement of the learner in the learning process.
Leerkrachten van basisscholen ervaren handelingsverlegenheid bij het lesgeven aan leerlingen met autisme spectrum stoornis (ASS). Dit is een urgent probleem, want sinds de invoering van de Wet Passend onderwijs in 2014 zijn leerkrachten in het regulier onderwijs zelf verantwoordelijk voor het aanbieden van een passend onderwijsaanbod voor alle kinderen en worden leerkrachten in het speciaal (basis-)onderwijs geconfronteerd met zwaardere problematiek. Bovenstaande sluit aan bij de thema?s ?adaptief onderwijzen? en ?talentontwikkeling?, die hoog op de agenda staan van landelijke en regionale onderwijsinstellingen. De vraag die leerkrachten stellen is: Hoe zorg ik ervoor dat kinderen met ASS zelfstandig werken in de klas, zodat zij het optimale halen uit zichzelf en mee kunnen komen met de rest van de klas? Een voorbeeld van deze vraag is te vinden op zien op deze video: https://vimeo.com/138308381 (Wachtwoord: Raak040915). Om deze vraag te beantwoorden, wordt in dit project de TalentenKracht werkwijze uitgewerkt. Hiermee leert de leerkracht de verborgen talenten boven te halen bij de leerling met ASS en tegelijkertijd het talent bij zichzelf om de leerling met ASS adequaat te kunnen coachen. Hierdoor ontstaat een positieve talentspiraal. Het project wordt uitgevoerd door een consortium bestaande uit de schoolbesturen van RENN4 Noord-Nederland, SCSOG Groningen en COG Assen, het lectoraat Leren en Gedrag ingebed in het Lectoraat Integraal Jeugdbeleid (IJB), de Pedagogische Academie en Toegepaste Psychologie van de Hanzehogeschool Groningen, Orthopedagogiek van de Rijksuniversiteit Groningen en de onderzoeksafdeling van RENN4. Na afloop van dit project kunnen leerkrachten een positieve talentspiraal op gang brengen in de dagelijkse klassenpraktijk. Ook hebben zij de beschikking over een methode netwerkleren, waarmee op een duurzame manier gewerkt kan worden aan professionalisering wat betreft het werken met kinderen met ASS. Via diverse kanalen wordt de kennis beschikbaar gesteld voor een bredere groep scholen en het onderwijs- en onderzoeksveld.
