The goal of this contribution is to gather and to critically analyze recent evidence regarding the potential of exergaming for Parkinson’s disease (PD) rehabilitation and to provide an up-to-date analysis of the current state of studies on exergame-based therapy in PD patients. We performed our search based on the conclusions of a previous systematic review published in 2014. Inclusion criteria were articles published in the indexed databases Pubmed, Scopus, Sciencedirect, IEEE and Cochrane published since January 1, 2014. Exclusion criteria were papers with a target group other than PD patients exclusively, or contributions not based on exergames. Sixty-four publications out of 525 matches were selected. The analysis of the 64 selected publications confirmed the putative improvement in motor skills suggested by the results of the previous review. The reliability and safety of both Microsoft Kinect and Wii Balance Board in the proposed scenarios was further confirmed by several recent studies. Clinical trials present better (n = 5) or similar (n = 3) results than control groups (traditional rehabilitation or regular exercise) in motor (TUG, BBS) and cognitive (attention, alertness, working memory, executive function), thus emphasizing the potential of exergames in PD. Pilot studies (n = 11) stated the safety and feasibility of both Microsoft Kinect and Wii Balance Board, potentially in home scenarios as well. Technical papers (n = 30) stated the reliability of balance and gait data captured by both devices. Related meta-analyses and systematic reviews (n = 15) further support these statements, generally citing the need for adaptation to patient’s skills and new input devices and sensors as identified gaps. Recent evidence indicates exergame-based therapy has been widely proven to be feasible, safe, and at least as effective as traditional PD rehabilitation. Further insight into new sensors, best practices and different cognitive stadiums of PD (such as PD with Mild Cognitive Impairment), as well as task specificity, are required. Also, studies linking game parameters and results with traditional assessment methods, such as UPDRS scores, are required. Outcomes for randomized controlled trials (RCTs) should be standardized, and follow-up studies are required, particularly for motor outcomes.

Automatic grading models are valued for the time and effort saved during the instruction of large student bodies. Especially with the increasing digitization of education and interest in large-scale standardized testing, the popularity of automatic grading has risen to the point where commercial solutions are widely available and used. However, for short answer formats, automatic grading is challenging due to natural language ambiguity and versatility. While automatic short answer grading models are beginning to compare to human performance on some datasets, their robustness, especially to adversarially manipulated data, is questionable. Exploitable vulnerabilities in grading models can have far-reaching consequences ranging from cheating students receiving undeserved credit to undermining automatic grading altogether—even when most predictions are valid. In this paper, we devise a black-box adversarial attack tailored to the educational short answer grading scenario to investigate the grading models’ robustness. In our attack, we insert adjectives and adverbs into natural places of incorrect student answers, fooling the model into predicting them as correct. We observed a loss of prediction accuracy between 10 and 22 percentage points using the state-of-the-art models BERT and T5. While our attack made answers appear less natural to humans in our experiments, it did not significantly increase the graders’ suspicions of cheating. Based on our experiments, we provide recommendations for utilizing automatic grading systems more safely in practice.

Location-based games (LBGs) are based on digital representations of our surroundings and the spaces we inhabit. These digital twins of the real world, real world metaverses, are subsequently augmented by imaginary game content. However, the virtual reconstruction of the world inevitably emphasises some aspects of reality and disregards others. In this work we explore and discuss the elements of reality that are included, and omitted, in popular commercial LBGs. We focus on eight popular contemporary LBGs from five different developers and investigate their connections to the real world. Subsequently, we compare the identified real world features of the LBGs to the landscape dimensions of the widely adopted Landscape Character Assessment framework. The findings show that settlement, hydrology, climate and land cover are the most commonly incorporated landscape dimensions, albeit in low fidelity. By contrast, dimensions, such as geology, soils and enclosure were not represented in the observed LBGs. In addition, we discovered several anthropogenic and cultural aspects, such as land ownership and time depth that are implicitly included in some commercial LBGs, notably in the Niantic Wayfarer system providing unique high-fidelity data of cultural and historical locations. Overall, we find only little variance within landscape dimensions between the observed commercial LBGs. Our findings open discussions on choices regarding the virtual representation of the real world in systems, such as LBGs, navigational software and a reality-based metaverse.

Educational automatic question generation (AQG) is often unable to realize its full potential in educational applications due to insufficient training data. For this reason, current research relies on noneducational question answering datasets for system training and evaluation. However, noneducational training data may comprise different language patterns than educational data. Consequently, the research question of whether models trained on noneducational datasets transfer well to the educational AQG task arises. In this work, we investigate the AQG subtask of answer selection, which aims to extract meaningful answers for the questions to be generated. We train and evaluate six modern and well-established BERT-based machine learning model architectures on two widely used noneducational datasets. Furthermore, we introduce a novel, midsized educational dataset for answer selection called TQA-A. TQA-A is used to investigate the transfer capabilities of the noneducational models to the educational domain. In terms of phrase-level evaluation metrics, noneducational models perform similar to models trained directly on the novel educational TQA-A dataset, although trained with considerably more training data. Moreover, models trained directly on TQA-A select fewer named entity-based and more verb-based answers than noneducational models. This provides evidence for differences in noneducational and educational answer selection tasks.

Background: Many studies have shown a direct relationship between physical activity and health. It has also been shown that the average fitness level in Western societies is lower than recommended by the World Health Organization. One tool that can be used to increase physical activity for individual people is exergaming, that is, serious games that motivate players to do physical exercises. Objective: This scoping review of recent studies regarding exergame efficacy aims to evaluate which sensing modalities are used to assess exergame efficacy as well as motion quality. We also analyze how the collected motion sensing data is being leveraged with respect to exergame efficacy and motion quality assessment. Methods: We conducted 2 extensive and systematic searches of the ACM Digital Library and the PubMed database, as well as a single search of the IEEE Xplore database, all according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement. Overall, 343 studies were assessed for eligibility by the following criteria: The study should be peer-reviewed; the year of publication should be between 2015 and 2023; the study should be available in English or German; the study evaluates the efficacy of at least 1 exergame; sensor data is recorded during the study and is used for evaluation; and the study is sufficiently described to extract information on the exergames, sensors, metrics, and results. Results: We found 67 eligible studies, which we analyzed with regard to sensor usage for both efficacy evaluation and motion analysis. Overall, heart rate (HR) was the most commonly used vital sign to evaluate efficacy (n=52), while the Microsoft Kinect was the most commonly used exergame sensor (n=26). The results of the analysis show that the sensors used in the exergames and the sensors used in the evaluation are, in most cases, mutually exclusive, with motion quality rarely being considered as a metric. Conclusions: The lack of motion quality assessment is identified as a problem both for the studies and the exergames themselves since incorrectly executed motions can reduce an exergame’s effectiveness and increase the risk of injury. Here we propose how to use the same sensors both as input for the exergame and to assess motion quality by presenting recent developments in motion recognition and sensing.