David S. Johnson

David S. Johnson, Olya Hakobyan, Hanna Drimalla

Machine learning is frequently used in affective computing, but presents challenges due the opacity of state-of-the-art machine learning methods. Because of the impact affective machine learning systems may have on an individual's life, it is important that models be made transparent to detect and mitigate biased decision making. In this regard, affective machine learning could benefit from the recent advancements in explainable artificial intelligence (XAI) research. We perform a structured literature review to examine the use of interpretability in the context of affective machine learning. We focus on studies using audio, visual, or audiovisual data for model training and identified 29 research articles. Our findings show an emergence of the use of interpretability methods in the last five years. However, their use is currently limited regarding the range of methods used, the depth of evaluations, and the consideration of use-cases. We outline the main gaps in the research and provide recommendations for researchers that aim to implement interpretable methods for affective machine learning.

David S. Johnson

Human-AI collaboration is often proposed to improve high-stakes decision-making, yet the influence of increased stakes and imperfect AI on decision-making strategies is not fully understood. Studying such behavior in realistic settings is challenging, as application-grounded evaluations are costly, rely on experts, or lack meaningful consequences for decision errors. To address this, we introduce Blockies, a parametric dataset generator for visual diagnostic tasks, and conduct an empirical study examining how perceived stakes influence reliance calibration and behavior. Results show that raised stakes lead to longer deliberation, but less calibrated reliance, with participants increasingly deferring to incorrect AI advice as decision time increased. These findings highlight that increased effort under higher stakes does not necessarily improve reliance calibration and show the importance of accounting for stakes when evaluating human-AI decision-making.

Zhisen Hu, Dominic Cullen, David S. Johnson et al.

Knee osteoarthritis (OA) is one of the most widespread and burdensome health problems [1-4]. Total knee replacement (TKR) may be offered as treatment for end-stage knee OA. Nevertheless, TKR is an invasive procedure involving prosthesis implantation at the knee joint, and around 10% of patients are dissatisfied following TKR [5,6]. Dissatisfaction is often assessed through patient-reported outcome measures (PROMs) [7], which are usually completed by patients and assessed by health professionals to evaluate the condition of TKR patients. In clinical practice, predicting poor TKR outcomes in advance could help optimise patient selection and improve management strategies. Radiographic knee alignment is an important biomarker for predicting TKR outcomes and long-term joint health. Abnormalities such as femoral or tibial deformities can directly influence surgical planning, implant selection, and postoperative recovery [8,9]. Traditional alignment measurement is manual, time-consuming, and requires long-leg radiographs, which are not always undertaken in clinical practice. Instead, standard anteroposterior (AP) knee radiographs are often the main imaging modality. Automated methods for alignment assessment in standard knee radiographs are potentially clinically valuable for improving efficiency in the knee OA treatment pathway.

David S. Johnson, Wolfgang Lorenz, Michael Taenzer et al.

Research on sound event detection (SED) in environmental settings has seen increased attention in recent years. The large amounts of (private) domestic or urban audio data needed raise significant logistical and privacy concerns. The inherently distributed nature of these tasks, make federated learning (FL) a promising approach to take advantage of largescale data while mitigating privacy issues. While FL has also seen increased attention recently, to the best of our knowledge there is no research towards FL for SED. To address this gap and foster further research in this field, we create and publish novel FL datasets for SED in domestic and urban environments. Furthermore, we provide baseline results on the datasets in a FL context for three deep neural network architectures. The results indicate that FL is a promising approach for SED, but faces challenges with divergent data distributions inherent to distributed client edge devices.