Technologies developed at universities are direct means to conceive a teaching plan for promoting science, technology, engineering and mathematics (STEM) at the K-12 level of education. This work-in-progress develops this notion: We elaborate a teaching plan for K-12 students based on technologies for recording plant bioelectrical activity. The teaching plan sketches hands-on activities, where pupils can self-assemble the electronic components such as the electro-potential sensor, analog-to-digital (ADC) converter, and Arduino board for processing, as designed by research students at Politecnico di Milano. Using our project as a blueprint, we aim to support other educators at universities to promote further STEM and expose pupils to technical developments at universities.

Atrial fibrillation is a prevalent cardiac arrhythmia, significantly increasing the risk of stroke, heart failure, and mortality. Early detection, especially during asymptomatic and paroxysmal stages, is essential for effective intervention. This study explores the application of deep neural networks in simplified ECG screening to enhance population-wide detection of atrial fibrillation. A handheld device, MyDiagnostick, was employed for large-scale ECG data acquisition within a pharmacy-based clinical trial on 7295 subjects aged 65 years and older. Automated diagnosis yielded 6.08% of AF prevalence in the given dataset. The data were then analyzed using a validated deep neural network model for the detection of cardiac arrhythmia in 12-lead ECG data for feature extraction and detection of atrial fibrillation. In addition, we investigate the capabilities of explainable artificial intelligence to provide diagnostic support for cardiologists and assess the feasibility of implementing deep neural networks in wearable devices for continuous monitoring. The study also emphasizes the importance of interpretability in artificial intelligence models for medical applications, leveraging explainable artificial intelligence to highlight ECG segments indicative of atrial fibrillation. Our findings demonstrate the efficacy of deep neural networks in atrial fibrillation detection with an F1-score of 86% vs. 81% of the automated ECG stick analysis and the potential for their integration into wearable technology by successfully reducing the number of weights by 99% without significant loss of accuracy, providing a robust tool for early diagnosis and continuous monitoring of atrial fibrillation.

Promoting science, technology, engineering and mathematics (STEM) education at K-12 level motivates pupils to pursue technical careers at universities, which is of high importance due to skilled labor shortage and other factors. In particular, in Germany the population with a tertiary education level is less than the average in the European Union (35–41 %. Motivating the study of technical careers, this paper features a model for promoting STEM at the K-12 education level by developing joint teaching platforms with students at technical universities. The model is derived from hands-on experience at TU Berlin targeting a climate change topic: As part of student semester projects, Bachelor students integrated a humidity sensor into a drone and conducted atmospheric measurements. The resulting hard and software components provided by the students allowed the preparation of a lesson plan to promote STEM at the K-12 level. In this way, we synergically connect the means from the university with hands-on activities as means to promote STEM topics with K-12 students. The resulting benefits are manifold; students at the university develop technical skills and become part of a social intention to promote STEM topics on the one hand. On the second hand, pre-university students might have first-hand experiences with hardware prototypes and their applicability to relevant topics like climate change surveillance. The developed model may illustrate straightforward means for educators to design lesson plans, including actual practices at university and pre-university levels.

Deep learning has proven effective in several areas, including computer vision, natural language processing, and disease prediction, which can support clinicians in making decisions along the clinical pathway. However, in order to successfully integrate these algorithms into clinical practice, it is important that their decision-making processes are transparent, explainable, and interpretable. Firstly, this tutorial will introduce targeted eXplainable Artificial Intelligence (XAI) methods to address the urgent need for explainability of deep learning in healthcare applications. In particular, it focuses on algorithms for raw biosignals without prior feature extraction that enable medical diagnoses, specifically electrocardiograms (ECG) -- stemming from the heart -- and electroencephalograms (EEG) representing the electrical activity of the brain. Secondly, participants are provided with a comprehensive workflow that includes both data processing and an introduction to relevant network architectures. Subsequently, various XAI methods are described and it is shown, how the resulting relevance attributions can be visualized on biosignals. Finally, two compelling real-world use cases are presented that demonstrate the effectiveness of XAI in analyzing ECG and EEG signals for disease prediction and sleep classification, respectively. In summary, the tutorial will provide the skills required for gaining insight into the decision process of deep neural networks processing authentic clinical biosignal data.

Despite their remarkable performance, deep neural networks remain unadopted in clinical practice, which is considered to be partially due to their lack of explainability. In this work, we apply explainable attribution methods to a pre-trained deep neural network for abnormality classification in 12-lead electrocardiography to open this "black box" and understand the relationship between model prediction and learned features. We classify data from two public databases (CPSC 2018, PTB-XL) and the attribution methods assign a "relevance score" to each sample of the classified signals. This allows analyzing what the network learned during training, for which we propose quantitative methods: average relevance scores over a) classes, b) leads, and c) average beats. The analyses of relevance scores for atrial fibrillation and left bundle branch block compared to healthy controls show that their mean values a) increase with higher classification probability and correspond to false classifications when around zero, and b) correspond to clinical recommendations regarding which lead to consider. Furthermore, c) visible P-waves and concordant T-waves result in clearly negative relevance scores in atrial fibrillation and left bundle branch block classification, respectively. Results are similar across both databases despite differences in study population and hardware. In summary, our analysis suggests that the DNN learned features similar to cardiology textbook knowledge.

What are recent topics in engineering education research addressed by the German scientific community? What are current trends, loose ends, and open directions? Is the research conducted locally or in networks across institutions? Following these questions, we aim to seize the German research community's trends, research directions, and contexts. We survey a systematic literature review covering publications of German researchers published in education-related conferences and jour-nals affiliated to IEEE between 2019 and 2022, resulting in 205 contributions in total. We analyze these works and illustrate results as contributions per topic, authors per institution, and the cross-work between institutions. The most prevalent topics turned out to be educational research, followed by curriculum design and remote instruction. Distinguishable, the German community also rehearse research for the K-12 level and develop Gamification techniques with the 18 % of contributions. Furthermore, we observe teams of three authors per contribution on average, and approximately 15 % of contributions are in collaboration among different institutions. On the basis of the literature review, we additionally provide our in-depth viewpoint discussing potential directions for German researchers and open a debate for best practices in supporting research on educational topics. We elaborate on effective means for promoting educational research in the community, more accessibility to learning technologies, and promotion of cross-work among institutions for further steeping the teaching research community within the IEEE.

The continuing interest in unobtrusive electrocardiography requires the development of algorithms, compensating for an increased number of artifacts. In previous work, we proposed a framework for robust parameter estimation of signals following a piecewise Gaussian derivative model, well suited for describing all waves of a heartbeat. The framework is based on a numeric and analytic representation of applying the Wavelet Transform at arbitrary scale to the input model. For robustly estimating model parameters, it processes lines of zero-crossings in scale-space, showing high accuracy for various noise models in synthetic signals. An initial evaluation with electrocardiography signals revealed that our basic classifier for identifying the correct lines often fails, leading to false parameter estimates. In this work, we propose a general delineation method based on a solid mathematical framework that treats each heartbeat, wave and fiducial point in the same way, tailored only by intuitive parameters and not relying on any heuristically found decision rules. The steps include a novel line classifier based on pre-filtering using domain knowledge, followed by an exhaustive search among all possible combinations of zero-crossing lines and an error-measure quantifying their agreement with the model. The combination with highest agreement is processed by the parameter estimation framework, customized to the computation of all nine fiducial points. Evaluation using the expert-annotated QT database, shows high sensitivity (P: 99.91%, QRS: 99.92%, T: 99.89%) and mean errors below 1 ms for all onset and offset fiducial points. The proposed combination of line classification and parameter estimation is well suited for delineating electrocardiograms.