Insufficient physical activity presents a significant hazard to overall health, with sedentary lifestyles linked to a variety of health issues. Monitoring physical activity levels allows the recognition of patterns of sedentary behavior and the provision of coaching to meet the recommended physical activity standards. In this paper, we aim to address the problem of reducing the time consuming process of fitting classifiers when generating personalized models for a coaching application. The proposed approach consists of evaluating the effects of clustering participants based on their walking patterns and then recommending a unique model for each group. Each model consists of a random forest classifier with a different number of estimators each. The resulting approach reduces the fitting time considerably while keeping nearly the same classification performance as personalized models.
DOCUMENT
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.
DOCUMENT
Objectives: Emotional eating is recognized as a potential contributor to weight gain. Emotional eaters often hide their problems because of feelings of shame about their behavior, making it challenging to provide them with the necessary support. The introduction of a virtual coach might offer a potential solution in assisting them. To find out whether emotional eaters are receptive to online personalized coaching, we presented emotional eaters with two essential proto-typical problem situations for emotional eaters: “experiencing cravings” and “after giving in to cravings,” and asked them whether they preferred one of the three coaching strategies presented: Validating, Focus-on-Change and Dialectical.Methods: An experimental vignette study (2 × 3 design) was carried out. The vignettes featured two distinct personas, each representing one of the two common problem scenarios experienced by emotional eaters, along with three distinct coaching strategies for each scenario. To identify potential predictors for recognition of problem situations, questionnaires on emotional eating (DEBQ), personality traits (Big-5), well-being (PANAS), and BMI were administrated.Results: A total of 62% of the respondents identified themselves with “after giving in to cravings” and 47% with “experiencing cravings.” BMI, emotional eating and emotional stability appeared to be predictors in recognizing both the problem situations. In “experiencing cravings,” the participating women preferred Dialectical and the Validation coaching strategies. In the “after giving in to cravings” condition, they revealed a preference for the Dialectical and the Focus-on-Change coaching strategies.Conclusion: Using vignettes allowed a less threatening way of bringing up sensitive topics for emotional eaters. The personas representing the problem situations were reasonably well recognized. To further enhance this recognition, it is important for the design and content of the personas to be even more closely related to the typical problem scenarios of emotional eaters, rather than focusing on physical characteristics or social backgrounds. This way, users may be less distracted by these factors. With the knowledge gained about the predictors that may influence recognition of the problem situations, design for coaching can be more customized. The participants represented individuals with high emotional eating levels, enhancing external validity.
DOCUMENT
Obesity has become a major societal problem worldwide [1][2]. The main reason for severe overweight is excessive intake of energy, in relation to the individual needs of a human body. Obesity is associated with poor eating habits and/or a sedentary lifestyle. A significant part of the obese population (40%) belongs to a vulnerable target group of emotional eaters, who overeat due to negative emotions [3]. There is a need for self-management support and personalized coaching to enhance emotional eaters in recognising and self-regulating their emotions.Over the last years, coaching systems have been developed for behavior change support, healthy lifestyle, and physical activity support [4]-[9]. Existing virtual coach applications lack systematic evaluation of coaching strategies and usually function as (tele-)monitoring systems. They are limited to giving general feedback to the user on achieved goals and/or accomplished (online) assignments.Dialectical Behavior Therapy (DBT) focuses on getting more control over one’s ownemotions by reinforcing skills in mindfulness, emotion regulation, and stress tolerance [10]. Emotion regulation is about recognizing and acknowledging emotions and accepting the fact that they come and go. The behavior change strategies within DBT are based on validation and dialectics [11]. Dialectics changes the users’ attitude and behavior by creating incongruence between an attitude and behavior since stimuli or the given information contradict with each other.The ultimate goal of the virtual coach is to raise awareness of emotional eaters on their own emotions, and to enhance a positive change of attitude towards accepting the negative emotions they experience. This should result in a decrease of overeating and giving in to binges. We believe that the integration of the dialectical behavior change strategies and persuasive features from the Persuasive System Design Model by Kukkonen and Harjumaa [12] will enhance the personalization of the virtual coach for this vulnerable group. We aim at developing a personalized virtual coach ‘Denk je zèlf!’ (Dutch for ‘Develop a wise mind and counsel yourself’) providing support for self-regulation of emotions for young obese emotional eaters. This poster presents an eCoaching model and a research study protocol aiming at the validation of persuasive coaching strategies based on behavior change techniques using dialectical strategies. Based on the context (e.g., location), emotional state of the user, and natural language processing, the virtual coach application enables tailoring of the real-time feedback to the individual user. Virtual coach application communicates with the user over a chat timeline and provides personal feedback.The research protocol decribes the two weeks field study on validating persuasive coaching strategies for emotional eaters. Participants (N=30), recruited via a Dutch franchise organization of dietitian nutritionists, specialized in treating emotional eating behaviors, will voluntarily participate in this research study. Participants will be presented with short dialogues (existing questions and answers) and will be asked to select the preferred coaching strategy (validating or a dialectical), according to their (current) emotions. To trigger a certain emotion (e.g., the affect that fits best with the chosen coaching strategy), a set of pictures will be shown to the user that evoke respectively sadness, anger, fear, and disgust [13].Participants will be asked to fill out the demographics data ((nick) name, age, gender, weight, length, place of residence) and three questionnaires: • Dutch Eating Behavior Questionnaire (DEBQ) [14],• Five Factor Personality Inventory (FFPI) [15], • Quality of Life Index Questionnaire [16].This research study aims at answering the following research questions: “Which coaching strategies do users with a specific type of emotional eating behavior benefit most from while consulting their personalized virtual coach?; “Which coaching strategies are optimal for which emotions?” and “Which coaching approach do users prefer in which context, e.g. time of the day, before/after a craving?”
LINK
Human Digital Twins are an emerging type of Digital Twin used in healthcare to provide personalized support. Following this trend, we intend to elevate our virtual fitness coach, a coaching platform using wearable data on physical activity, to the level of a personalized Human Digital Twin. Preliminary investigations revealed a significant difference in performance, as measured by prediction accuracy and F1-score, between the optimal choice of machine learning algorithms for generalized and personalized processing of the available data. Based on these findings, this survey aims to establish the state of the art in the selection and application of machine learning algorithms in Human Digital Twin applications in healthcare. The survey reveals that, unlike general machine learning applications, there is a limited body of literature on optimization and the application of meta-learning in personalized Human Digital Twin solutions. As a conclusion, we provide direction for further research, formulated in the following research question: how can the optimization of human data feature engineering and personalized model selection be achieved in Human Digital Twins and can techniques such as meta-learning be of use in this context?
DOCUMENT
The first year of study is very exciting for many students. Everything is new: the school, your schedule, the teachers, and your fellow students. How can a university ensure a smooth transition for first-year students? For this, Inholland launched the Students for Students (S4S) project in the 2019-2020 academic year. In this project, second-year students (studentcoaches) support first-year students with their studies. They do this based on their own experience and the training they receive during their year as studentcoaches. Research shows that peer-mentoring is very successful in aiding first-year students through their first year of the study program. Peer-mentoring has the potential to increase well-being, social bonding, the feeling of belonging, and student resilience. It also ensures smoother academic integration, as peer-mentoring focuses on developing academic skills as well. Additionally, a studentcoach is often a low threshold point of contact for students where they can go with questions.
DOCUMENT
The aim of this paper is to design and test a smartphone application which supports personalized running experiences for less experienced runners. As a result of a multidisciplinary three-step design approach Inspirun was developed. Inspirun is a personalized running-application for Android smartphones that aims to fill the gap between running on your own (static) schedule, and having a personal trainer that accommodates the schedule to your needs and profile. With the use of GPS and Bluetooth heart rate monitor support, a user's progress gets tracked. The application adjusts the training schedule after each training session, motivating the runner without a real life coach. Results from three user studies are promising; participants were very satisfied with the personalized approach, both in the profiling and de adaptation of their training scheme.
DOCUMENT
There is a growing number of eHealth interventionsaiming at enhancing lifestyle to address obesity. However, theexisting interventions do not take the emotional aspects ofobesity into account. Forty percent of the overweightpopulation is an emotional eater. Emotional eaters gain weightbecause of poor emotion regulation, not just due to bad eatinghabits. We aim at developing a personalized virtual coach‘Denk je zèlf!’ providing support for self-regulation ofemotions for young obese emotional eaters. This paperpresents an eCoaching model and a research study protocolaiming at the validation of persuasive coaching strategies basedon behavior change techniques. Ultimately, we aim atdesigning a personalized eCoaching framework, allowing us tooptimally translate successful behavior change mechanismsand techniques, such as dialectical strategies, into personalizedpersuasive coaching strategies.
DOCUMENT
Self-management is widely seen as a viable contribution to sustainable health care as it allows to promote physical and mental well-being. A promising approach to promoting a healthy lifestyle is the deployment of personalized virtual coaches, especially in combination with the latest developments in the fields of Data Science and Artificial Intelligence. This paper presents a framework for a virtual coaching system, as well as a use case in which parts of this framework are applied. The virtual coach in the use case aims to encourage customer contact center employees to protect their mental health. This article outlines one part of the use-case in particular, viz. how to promote employee autonomy and supervisor support by, inter alia, monitoring employees’ levels of emotional exhaustion. Current systems focus on providing users with insight in their health status or behavior, the authors developed the functional architecture for a system that can be implemented for different goals and generates personalized, real-time advice based on the combination of user preferences, motivational success and predicted user behavior.
DOCUMENT
Just what and how eight experienced teachers in four coaching dyads learned during a 1-year reciprocal peer coaching trajectory was examined in the present study. The learning processes were mapped by providing a detailed description of reported learning activities, reported learning outcomes, and the relations between these two. The sequences of learning activities associated with a particular type of learning outcome were next selected, coded, and analyzed using a variety of quantitative methods. The different activity sequences undertaken by the teachers during a reciprocal peer coaching trajectory were found to trigger different aspects of their professional development.
DOCUMENT
