Video-based physical training has gained popularity over the years, among both sports practitioners and HCI researchers, whose works ranged from offering computer-assisted solutions for self-correction, to enhancing the learning experience of trainees. This thesis focused on the latter, by investigating the communicative potential of three categories of visual coaching cues and their impact on movement learning, as well as by deriving methodological considerations for similar works. This thesis adopted a Research through Design approach to investigate, from a trainee-centred perspective, three sets of cues: A) abstract visual metaphors (arrows, lines, angles); B) body highlights; and C) material visual metaphors (imagined 3D objects). The cues were informed by a professional trainer’s insights and relevant literature, and were tested with ten participants throughout the course of three sessions. Their reflections were gathered through interviews. The subsequent thematic analysis generated 1) insights on the individual cues (such as their role as reminders, their impact on imagery, and the movement qualities they were able to portray), and 2) design and methodological considerations for future works (such as the importance of involving a professional trainer, clearly defining the learning outcomes of a video session, and choosing the appropriate visual cues).

Title: Bodyweight training in individuals with spinal cord injuries and the possibilities in usage of outdoor gyms in Prague Objectives: The aim of this diploma thesis was to compile a methodical series of bodyweight exercises suitable for people after spinal cord injury. It was also found out which of the Prague outdoor gyms are suitable for performing exercises from this methodical series and thus also for people using a wheelchair. Methods: The method of theoretical-critical analysis was used to compile the methodical series. Theoretical knowledge was applied in the selection and description of exercises. The methodical series is divided into groups of pulling and pushing exercises. Each of them contains descriptions of exercises, their modifications and photographs. Outdoor gyms was deliberately selected for research and quantitatively evaluated in the table. Selected outdoor gyms evaluated as suitable were qualitatively commented and supplemented with photographs. Results: The methodical series contains 12 exercises and photographs. In the description of the exercises, attention is paid to the key points in the implementation, the possibility of regression and progression of the exercise and the goal of the exercise. After the analysis of 39 Prague outdoor gyms, 12 suitable outdoor gyms were...

This thesis explores the feasibility of developing an affordable and easy-to-use feed- back system that leverages information from multiple inertial measurement units (IMUs) to identify mistakes during upper body bodyweight training and provide real-time feedback to the user. To develop the system, a human-centered approach was used, which involved conducting semi-structured interviews with movement ex- perts and a workshop with targeted end-users to understand their needs. The study also involved 12 volunteers who performed push-ups, tricep dips, and planks cor- rectly and then made specific mistakes intentionally while wearing five IMUs. Binary and multiclass classifiers were developed to classify the exercise technique. The re- sults showed that personalized multiclass classifiers produced good to excellent quality results, while global classification techniques performed poorly. Additionally, an increased number of sensors did not always lead to improved classification re- sults, and the placement of the sensors could have a significant impact. The user in- put and evaluation of the feedback system pinpointed the need for customization and accessibility in the design. This thesis contributes to the development of a feedback system that can help users identify mistakes in their upper body bodyweight exer- cises and improve their form and technique. / Denna avhandling utforskar genomförbarheten att utveckla ett prisvärt och lättan- vänt feedbacksystem som utnyttjar information från flera inertiella mätenheter (IMU: er) för att identifiera misstag under överkroppsövningar med egen kroppsvikt och ge användaren realtidsfeedback. För att utveckla systemet användes en human- centrerad metod, som innefattade semistrukturerade intervjuer med rörelseexperter och en workshop med målinriktade slutanvändare för att förstå deras behov. Studien inkluderade också 12 frivilliga som utförde armhävningar, tricep dips och plankor korrekt och sedan medvetet gjorde specifika misstag medan de bar på fem IMU: er. Binära och flerklassklassificerare utvecklades för att klassificera övningstekniken. Resultaten visade att personliga flerklassklassificerare producerade bra till utmärkta resultat, medan globala klassificeringstekniker presterade dåligt. Dessutom ledde ett ökat antal sensorer inte alltid till förbättrade klassificeringsresultat, och placeringen av sensorerna kunde ha en betydande påverkan. Användarinput och utvärdering av feedbacksystemet pekade på behovet av anpassning och tillgänglighet i designen. Denna avhandling bidrar till utvecklingen av ett feedbacksystem som kan hjälpa an- vändare att identifiera misstag i sina överkroppsövningar med egen kroppsvikt och förbättra sin form och teknik.