Physical fitness presents a significant challenge in ensuring proper exercise posture. Individuals who work out need help maintaining correct exercise posture during their workouts. Maintaining correct form is critical for ensuring the safety and effectiveness of fitness routines. Yet, it is often challenging for individuals to keep proper form without professional guidance, which usually comes at expensive costs. The paper presents a novel method that utilizes the capabilities of YOLOv7 and a primary web camera to offer immediate feedback and correction on body posture during gym activities. Such a method empowers individuals to correct themselves and promotes motivation even without the presence of a professional trainer. This system has been developed to provide immediate, personalized feedback for various fitness exercises. It efficiently counts repetitions and provides textual guidance for improvement, tailored to the specific requirements of fitness enthusiasts. To determine the efficacy of our technology, we carried out a user study in a controlled laboratory setting simulating a gym environment. The study compares our interactive system with the traditional training method, involving participants of varied fitness levels. It showed significant improvements in exercise technique with real-time feedback. These findings are crucial for AI-supported training systems in strength training, underscoring the need for adaptive technologies for different user experiences. The research contributes to human-computer interaction and fitness technology discussions, highlighting interactive models’ potential to augment and sometimes replicate personal training benefits in exercise form and posture improvement.

The aim to support learning communities by Web 2.0 technology leads to their investigation through the prism of learning theories. However, self-observation and self-modeling requires appropriate tools and skills. In this paper we focus on users of a forum platform and propose several tools that perform community detection, social network analysis, text mining, natural language processing, and clustering. The outcomes serve as inputs for community models that are automatically established using the i * information modeling approach. Stakeholders can recognize issues in their communities by visual analytics of the models. Based on this, they can refine community learning processes and community environments by retrieving new community requirements from the models. The process of model establishment was evaluated by experts in i * information modeling and the results show their acceptance of the proposed techniques. This solution enables also support of various well-known modeling approaches (like IMS Learning Design).

In this paper we attempt to address the issue of supporting self-regulation by Personal Learning Environments (PLE), which provide the learner with a freedom to design and compose his or her learning environment according to personal preferences and context demands. Psychology and neuroscience offer a lot of highly relevant results that should be taken into account. We report on our experiments mainly with PhD students, which represent a community of advanced learners. This needs to be considered when interpreting their feedback, as for most of the learners is self-regulation even more challenging. Even students at this high level appreciate pedagogical support in the learning process.

Psycho-pedagogical theories have a high impact on learning. Our aim is to analyze results of behavioral and cognitive psychology to help designers of learning experiences with specification of requirements. We have reviewed literature on human decision making processes, organized a survey and a workshop with PhD students to collect various opinions on these issues, and here we summarize the outcomes.

When Internet users search for information, surf on websites or discuss with others, their actions are driven by certain goals. Extraction of users' goals can enable higher effectiveness and accuracy of web services. Supporting users in based on their goals can be highly beneficial, especially supporting of learners in the preparation for an exam as a learning process, Different phases of learning are identified when users learn collaboratively. We scrutinize how goals are constructed and achieved within a community, examining not only social activities based on patterns of behavior, but also emotions and intents users express in their posts. As a result we elicit users' goals. We achieved good accuracy in defining emotions of users and recognizing their intents and social patterns in our case. Here we discuss how the obtained results contribute to mining of learning community goals.

This paper describes an experiment investigating interactions in a big forum in order to support students in learning English. Groups of collaborating users form communities that generate a lot of data that can be analyzed. We distinguish different phases of the self-regulated learning process and aim to identify them in learners' activities. Then we attempt to recognize patterns of their behavior and consequently their roles in a community. Based on this analysis we try to explain a success or failure of a community. We conclude that heterogeneity of members helps a learning community to function.

Social software is used widely in organizational knowledge management and professional learning. The PROLEARN network of excellence appreciates the trend of lowering the barriers between knowledge and learning management strategies for organizations and individuals. But, companies should not underestimate the needs for systematic support based on sound theories and technologies. We illustrate the requirements by examples and research issues for collaborative adaptive learning platforms for workplace learning in organizations

In this paper we deal with knowledge representation in the area of learning design and adaptive learning. Specification of concrete instances is usually context-dependent and does not support reusability very well, thus we need to represent the knowledge that could help us in generating the instances dynamically.

In this paper, we have focused on using a multi-agent system in e-learning environments with the aim to facilitate the adaptation processes, as well as to enable better way of achieving the e-learning goals. Because we are dealing with the stereotypes of e-learners, having in mind emotional intelligence concepts to help in adaptation to e-learners' real needs and known preferences, we called this system eQ. The focus of the eQ multi-agent system is on the BDI agent rational model, which can be directly used to implement the proposed adaptation strategy, known as the FOSP method.

The ability to relate abstract knowledge to real-world experiences is indispensable in the modern society. Therefore the construction of knowledge from real-world contexts is a major issue of education. This issue is not supported by the current learning management systems. In the RAFT project we develop a system to support remote accessible field trips. One of its applications, the mobile collector, facilitates constructivistic learning processes in real-world contexts.