The standing long jump (SLJ) is a test used to evaluate lower limb strength and function. In addition to jump distance, evaluating stability during the jump is also important. This study investigates stability classification in SLJ by analysing the rotational movements of the lower limbs. Inertial sensors were used to collect kinematic data from 10 healthy subjects. Segment and joint angles were derived based on angular velocities in the sagittal plane. Functional principal component analysis (fPCA) was performed on two datasets: joint angles (MfPCAjoint) and segment angles (MfPCAsegment). The resulting fPCA scores were used as inputs for support vector machine classifiers. The classification accuracy was 86% for MfPCAjoint and 85% for MfPCAsegment, with MfPCAjoint also showing more consistent performance metrics. These results suggest that fPCA scores can effectively describe stability, although a larger dataset is necessary for further validation.

Standing long jump (SLJ) represents a common exercise for assessing the physical abilities of both children and adults. In practice, the performance is usually evaluated by jump distance, while other aspects of the technique are often ignored. This study proposed a visualisation method of the SLJ movement pattern using the principal component analysis (PCA). Nine healthy students, divided into two groups based on their history of playing sports, participated in the collection of kinematic parameters of the lower and upper extremities during the performance of SLJ. The 2D PCA-based cyclograms were constructed and compared between subjects and groups. The results showed that all cyclograms had a similar shape with slight variations between subjects. The repeatability of the cyclogram forming was confirmed, as well as the representation of the existing symmetry in the body motion of the SLJ. As such, the proposed visualisation method has the potential for monitoring the processes of rehabilitation, training, and overall assessment of an individual's technique.

Facial expressions provide a fundamental means for communication, and with an unlimited number of nuances in emotion portrayal, it is important to understand how emotion recognition works. In this paper, 10 participants (5 female and 5 male) were shown 4 blocks of images (each having 36 images) of faces portraying emotions: neutral, happiness, sadness, anger, fear and disgust. The first two blocks displayed regular images of faces, the other two showed upside-down images. Their performance and eye movements were monitored using an eye-tracking device. By analyzing the recognition accuracy, the time spent and the number of fixations for each image, the influence of participant gender, image modifications, and attributes of actors was assessed. The results show an overall recognition accuracy of around 80 %, with female participants having an overall higher recognition accuracy. Happiness was shown to be the best-recognised emotion, with sadness being the one most often misinterpreted. This conclusion was also shown in the eye-tracking metrics, with sadness being the most frequent emotion for the high-valued outliers.