For chess players to sharpen their tactical skills effectively, they train on chess puzzles with a fitting difficulty level. This paper presents an approach to estimate the difficulty level of chess puzzles using a deep neural network. The proposed approach achieved second place in the IEEE BigData Cup 2024 competition: Predicting chess puzzle difficulty. For the design of our network architecture, we take inspiration from the human problem-solving process for chess puzzles. We train the model to predict the correct move as an auxiliary task to improve the training process. We also predict themes, which are patterns in chess puzzles as a second auxiliary task. Finally, we use the uncertainty in the position, i.e. how incorrect the model’s move prediction is, as a further input to guide the estimation of the puzzle difficulty.

Multiplayer games with social aspects vary widely regarding client design, e.g., point of view or camera perspective. While design paradigms usually arise from gold standards that are set by previously successful games in the industry, the impact of such paradigms is under-researched for games that serve as scientific instruments, e.g., to research social behavior. Intending to investigate how such games should be designed, we built two multiplayer clients with the same game logic, one using a first-person point of view, while the other includes a top-down camera perspective. Then, we conducted an online user study in which players tested these game clients in extensive multiplayer sessions. Analyzing speech time, in-game logs, questionnaires, and qualitative feedback, we look at the perspectives’ impact on player behavior, engagement, and game experience in a scientific or "serious games" context. In addition, we have made our designed game UNISON and both clients available as open source to facilitate future empirical social science research.

Difficulty adjustment in practice exercises has been shown to be beneficial for learning. However, previous research has mostly investigated close-ended tasks, which do not offer the students multiple ways to reach a valid solution. Contrary to this, in order to learn in an open-ended learning task, students need to effectively explore the solution space as there are multiple ways to reach a solution. For this reason, the effects of difficulty adjustment could be different for open-ended tasks. To investigate this, as our first contribution, we compare different methods of difficulty adjustment in a user study conducted with 86 participants. Furthermore, as the practice behavior of the students is expected to influence how well the students learn, we additionally look at their practice behavior as a post-hoc analysis. Therefore, as a second contribution, we identify different types of practice behavior and how they link to students’ learning outcomes and subjective evaluation measures as well as explore the influence the difficulty adjustment methods have on the practice behaviors. Our results suggest the usefulness of taking into account the practice behavior in addition to only using the practice performance to inform adaptive intervention and difficulty adjustment methods.

Virtual surgical training systems are crucial for enabling mental preparation, supporting decision-making, and improving surgical skills. Many virtual surgical training environments focus only on training for a specific medical skill and take place in a single virtual room. However, surgical education and training include the planning of procedures as well as interventions in the operating room context. Moreover, collaboration among surgeons and other medical professionals is only applicable to a limited extent. This work presents a collaborative VR environment similar to a virtual teaching hospital to support surgical training and interprofessional collaboration in a co-located or remote environment. The environment supports photo-realistic avatars and scenarios ranging from planning to training procedures in the virtual operating room. It includes a lobby, a virtual surgical planning room with four surgical planning stations, laparoscopic liver surgery training with the integration of laparoscopic surgical instruments, and medical training scenarios for interprofessional team training in a virtual operating room. Each component was evaluated by domain experts as well as in a series of user studies, providing insights on usability, usefulness, and potential research directions. The proposed environment may serve as a foundation for future medical training simulators.

One of the biggest challenges in using ultrasound (US) is learning to create a spatial mental model of the interior of the scanned object based on the US image and the probe position. As intraoperative ultrasound (IOUS) cannot be easily trained on patients, we present LiVRSono, an immersive VR application to train this skill. The immersive environment, including an US simulation with patientspecific data as well as haptics to support hand-eye coordination, provides a realistic setting. Four clinically relevant training scenarios were identified based on the described learning goal and the workflow of IOUS for liver. The realism of the setting and the training scenarios were evaluated with eleven physicians, of which six participants are experts in IOUS for liver and five participants are potential users of the training system. The setting, handling of the US probe, and US image were considered realistic enough for the learning goal. Regarding the haptic feedback, a limitation is the restricted workspace of the input device. Three of the four training scenarios were rated as meaningful and effective. A pilot study regarding learning outcome shows positive results, especially with respect to confidence and perceived competence. Besides the drawbacks of the input device, our training system provides a realistic learning environment with meaningful scenarios to train the creation of a mental 3D model when performing IOUS. We also identified important improvements to the training scenarios to further enhance the training experience.

With advances in reinforcement learning (RL), agents are now being developed in high-stakes application domains such as healthcare and transportation. Explaining the behavior of these agents is challenging, as they act in large state spaces, and their decision-making can be affected by delayed rewards. In this paper, we explore a combination of explanations that attempt to convey the global behavior of the agent and local explanations which provide information regarding the agent's decision-making in a particular state. Specifically, we augment strategy summaries that demonstrate the agent's actions in a range of states with saliency maps highlighting the information it attends to. Our user study shows that intelligently choosing what states to include in the summary (global information) results in an improved analysis of the agents. We find mixed results with respect to augmenting summaries with saliency maps (local information).

We present a Virtual and Augmented Reality multi-user prototype of a learning environment for liver anatomy education. Our system supports various training scenarios ranging from small learning groups to classroom-size education, where students and teachers can participate in virtual reality, augmented reality, or via desktop PCs. In an iterative development process with surgeons and teachers, a virtual organ library was created. Nineteen liver data sets were used comprising 3D surface models, 2D image data, pathology information, diagnosis and treatment decisions. These data sets can interactively be sorted and investigated individually regarding their volumetric and meta information. The three participation modes were evaluated within a user study with surgery lecturers (5) and medical students (5). We assessed the usability and presence using questionnaires. Additionally, we collected qualitative data with semistructured interviews. A total of 435 individual statements were recorded and summarized to 49 statements. The results show that our prototype is usable, induces presence, and potentially support the teaching of liver anatomy and surgery in the future.

With advances in reinforcement learning (RL), agents are now being developed in high-stakes application domains such as healthcare and transportation. Explaining the behavior of these agents is challenging, as the environments in which they act have large state spaces, and their decision-making can be affected by delayed rewards, making it difficult to analyze their behavior. To address this problem, several approaches have been developed. Some approaches attempt to convey the global behavior of the agent, describing the actions it takes in different states. Other approaches devised local explanations which provide information regarding the agent's decision-making in a particular state. In this paper, we combine global and local explanation methods, and evaluate their joint and separate contributions, providing (to the best of our knowledge) the first user study of combined local and global explanations for RL agents. Specifically, we augment strategy summaries that extract important trajectories of states from simulations of the agent with saliency maps which show what information the agent attends to. Our results show that the choice of what states to include in the summary (global information) strongly affects people's understanding of agents: participants shown summaries that included important states significantly outperformed participants who were presented with agent behavior in a set of world-states that are likely to appear during gameplay. We find mixed results with respect to augmenting demonstrations with saliency maps (local information), as the addition of saliency maps, in the form of raw heat maps, did not significantly improve performance in most cases. However, we do find some evidence that saliency maps can help users better understand what information the agent relies on during its decision-making, suggesting avenues for future work that can further improve explanations of RL agents.

Underwater sounds provide essential information for marine researchers to study sea mammals.During long-term studies large amounts of sound signals are being recorded using hydrophones.To facilitate the time consuming process of manually evaluating the recorded data, computational systems are often employed.Recent approaches utilize Convolutional Neural Networks (CNNs) to analyze spectrograms extracted from the audio signal.In this paper we explore the potential of relevance analysis to enhance the performance of existing CNN approaches.For this purpose, we present a fusion system that utilizes intermediate outputs of three state of the art CNNs, which are fine tuned to recognize whale sounds in spectrograms.Hereby we use Explainable Artificial Intelligence (XAI) to asses the relevance of each feature within the obtained representations.Based on those relevance values, we create novel masking algorithms to extract significant subsets of respective representations.These subsets are used to train an ensemble of classification systems that are serving as input for the final fusion step.We observe that a classification system can benefit from the inclusion of Relevance-based Feature Masking in terms of improved performance and reduced input dimensionality.The presented work is part of the INTERSPEECH 2019 Computational Paralinguistics Challenge.

While the research area of artificial intelligence benefited from increasingly sophisticated machine learning techniques in recent years, the resulting systems suffer from a loss of transparency and comprehensibility. This development led to an on-going resurgence of the research area of explainable artificial intelligence (XAI) which aims to reduce the opaqueness of those black-box-models. However, much of the current XAI-Research is focused on machine learning practitioners and engineers while omitting the specific needs of end-users. In this paper, we examine the impact of virtual agents within the field of XAI on the perceived trustworthiness of autonomous intelligent systems. To assess the practicality of this concept, we conducted a user study based on a simple speech recognition task. As a result of this experiment, we found significant evidence suggesting that the integration of virtual agents into XAI interaction design leads to an increase of trust in the autonomous intelligent system.

The permanent magnet synchronous motor (PMSM) is widely used in highly utilised automotive traction drives and other industrial applications. With regards to the device life-time, safe operation and control performance, the magnet temperature is of great interest. Since a direct magnet temperature measurement is not feasible in most cases, this contribution gives a review on state-of-the-art model-based magnet temperature determination methods in PMSM. In this context, the existing publications can be classified into thermal models, flux observers and voltage signal injection approaches. Firstly, brief introductions of these methods are given, followed by a direct comparison regarding drawbacks and benefits. Finally, this contribution concludes with an outlook of potential further investigations in this research field.