Refine
Year of publication
Document Type
- Article (34)
- Doctoral Thesis (22)
- Postprint (9)
- Monograph/Edited Volume (3)
- Working Paper (3)
- Conference Proceeding (2)
- Habilitation Thesis (1)
- Preprint (1)
Keywords
- machine learning (75) (remove)
Institute
- Hasso-Plattner-Institut für Digital Engineering GmbH (16)
- Institut für Biochemie und Biologie (10)
- Institut für Geowissenschaften (8)
- Institut für Umweltwissenschaften und Geographie (8)
- Institut für Physik und Astronomie (6)
- Hasso-Plattner-Institut für Digital Engineering gGmbH (5)
- Mathematisch-Naturwissenschaftliche Fakultät (5)
- Department Linguistik (4)
- Extern (4)
- Fachgruppe Volkswirtschaftslehre (4)
Rapidly growing seismic and macroseismic databases and simplified access to advanced machine learning methods have in recent years opened up vast opportunities to address challenges in engineering and strong motion seismology from novel, datacentric perspectives. In this thesis, I explore the opportunities of such perspectives for the tasks of ground motion modeling and rapid earthquake impact assessment, tasks with major implications for long-term earthquake disaster mitigation.
In my first study, I utilize the rich strong motion database from the Kanto basin, Japan, and apply the U-Net artificial neural network architecture to develop a deep learning based ground motion model. The operational prototype provides statistical estimates of expected ground shaking, given descriptions of a specific earthquake source, wave propagation paths, and geophysical site conditions. The U-Net interprets ground motion data in its spatial context, potentially taking into account, for example, the geological properties in the vicinity of observation sites. Predictions of ground motion intensity are thereby calibrated to individual observation sites and earthquake locations.
The second study addresses the explicit incorporation of rupture forward directivity into ground motion modeling. Incorporation of this phenomenon, causing strong, pulse like ground shaking in the vicinity of earthquake sources, is usually associated with an intolerable increase in computational demand during probabilistic seismic hazard analysis (PSHA) calculations. I suggest an approach in which I utilize an artificial neural network to efficiently approximate the average, directivity-related adjustment to ground motion predictions for earthquake ruptures from the 2022 New Zealand National Seismic Hazard Model. The practical implementation in an actual PSHA calculation demonstrates the efficiency and operational readiness of my model. In a follow-up study, I present a proof of concept for an alternative strategy in which I target the generalizing applicability to ruptures other than those from the New Zealand National Seismic Hazard Model.
In the third study, I address the usability of pseudo-intensity reports obtained from macroseismic observations by non-expert citizens for rapid impact assessment. I demonstrate that the statistical properties of pseudo-intensity collections describing the intensity of shaking are correlated with the societal impact of earthquakes. In a second step, I develop a probabilistic model that, within minutes of an event, quantifies the probability of an earthquake to cause considerable societal impact. Under certain conditions, such a quick and preliminary method might be useful to support decision makers in their efforts to organize auxiliary measures for earthquake disaster response while results from more elaborate impact assessment frameworks are not yet available.
The application of machine learning methods to datasets that only partially reveal characteristics of Big Data, qualify the majority of results obtained in this thesis as explorative insights rather than ready-to-use solutions to real world problems. The practical usefulness of this work will be better assessed in the future by applying the approaches developed to growing and increasingly complex data sets.
Pathogens and animal pests (P&A) are a major threat to global food security as they directly affect the quantity and quality of food. The Southern Amazon, Brazil's largest domestic region for soybean, maize and cotton production, is particularly vulnerable to the outbreak of P&A due to its (sub)tropical climate and intensive farming systems. However, little is known about the spatial distribution of P&A and the related yield losses. Machine learning approaches for the automated recognition of plant diseases can help to overcome this research gap. The main objectives of this study are to (1) evaluate the performance of Convolutional Neural Networks (ConvNets) in classifying P&A, (2) map the spatial distribution of P&A in the Southern Amazon, and (3) quantify perceived yield and economic losses for the main soybean and maize P&A. The objectives were addressed by making use of data collected with the smartphone application Plantix. The core of the app's functioning is the automated recognition of plant diseases via ConvNets. Data on expected yield losses were gathered through a short survey included in an "expert" version of the application, which was distributed among agronomists. Between 2016 and 2020, Plantix users collected approximately 78,000 georeferenced P&A images in the Southern Amazon. The study results indicate a high performance of the trained ConvNets in classifying 420 different crop-disease combinations. Spatial distribution maps and expert-based yield loss estimates indicate that maize rust, bacterial stalk rot and the fall armyworm are among the most severe maize P&A, whereas soybean is mainly affected by P&A like anthracnose, downy mildew, frogeye leaf spot, stink bugs and brown spot. Perceived soybean and maize yield losses amount to 12 and 16%, respectively, resulting in annual yield losses of approximately 3.75 million tonnes for each crop and economic losses of US$2 billion for both crops together. The high level of accuracy of the trained ConvNets, when paired with widespread use from following a citizen-science approach, results in a data source that will shed new light on yield loss estimates, e.g., for the analysis of yield gaps and the development of measures to minimise them.
This paper sheds new light on the role of communication for cartel formation. Using machine learning to evaluate free-form chat communication among firms in a laboratory experiment, we identify typical communication patterns for both explicit cartel formation and indirect attempts to collude tacitly. We document that firms are less likely to communicate explicitly about price fixing and more likely to use indirect messages when sanctioning institutions are present. This effect of sanctions on communication reinforces the direct cartel-deterring effect of sanctions as collusion is more difficult to reach and sustain without an explicit agreement. Indirect messages have no, or even a negative, effect on prices.
The intensity of cosmic radiation may differ over five orders of magnitude within a few hours or days during the Solar Particle Events (SPEs), thus increasing for several orders of magnitude the probability of Single Event Upsets (SEUs) in space-borne electronic systems. Therefore, it is vital to enable the early detection of the SEU rate changes in order to ensure timely activation of dynamic radiation hardening measures. In this paper, an embedded approach for the prediction of SPEs and SRAM SEU rate is presented. The proposed solution combines the real-time SRAM-based SEU monitor, the offline-trained machine learning model and online learning algorithm for the prediction. With respect to the state-of-the-art, our solution brings the following benefits: (1) Use of existing on-chip data storage SRAM as a particle detector, thus minimizing the hardware and power overhead, (2) Prediction of SRAM SEU rate one hour in advance, with the fine-grained hourly tracking of SEU variations during SPEs as well as under normal conditions, (3) Online optimization of the prediction model for enhancing the prediction accuracy during run-time, (4) Negligible cost of hardware accelerator design for the implementation of selected machine learning model and online learning algorithm. The proposed design is intended for a highly dependable and self-adaptive multiprocessing system employed in space applications, allowing to trigger the radiation mitigation mechanisms before the onset of high radiation levels.
Forest microclimate can buffer biotic responses to summer heat waves, which are expected to become more extreme under climate warming. Prediction of forest microclimate is limited because meteorological observation standards seldom include situations inside forests.
We use eXtreme Gradient Boosting - a Machine Learning technique - to predict the microclimate of forest sites in Brandenburg, Germany, using seasonal data comprising weather features.
The analysis was amended by applying a SHapley Additive explanation to show the interaction effect of variables and individualised feature attributions.
We evaluate model performance in comparison to artificial neural networks, random forest, support vector machine, and multi-linear regression.
After implementing a feature selection, an ensemble approach was applied to combine individual models for each forest and improve robustness over a given single prediction model.
The resulting model can be applied to translate climate change scenarios into temperatures inside forests to assess temperature-related ecosystem services provided by forests.
The present paper proposes a novel approach for equilibrium selection in the infinitely repeated prisoner’s dilemma where players can communicate before choosing their strategies. This approach yields a critical discount factor that makes different predictions for cooperation than the usually considered sub-game perfect or risk dominance critical discount factors. In laboratory experiments, we find that our factor is useful for predicting cooperation. For payoff changes where the usually considered factors and our factor make different predictions, the observed cooperation is consistent with the predictions based on our factor.
A review of source models to further the understanding of the seismicity of the Groningen field
(2022)
The occurrence of felt earthquakes due to gas production in Groningen has initiated numerous studies and model attempts to understand and quantify induced seismicity in this region. The whole bandwidth of available models spans the range from fully deterministic models to purely empirical and stochastic models. In this article, we summarise the most important model approaches, describing their main achievements and limitations. In addition, we discuss remaining open questions and potential future directions of development.
PyFin-sentiment
(2023)
Responding to the poor performance of generic automated sentiment analysis solutions on domain-specific texts, we collect a dataset of 10,000 tweets discussing the topics of finance and investing. We manually assign each tweet its market sentiment, i.e., the investor’s anticipation of a stock’s future return. Using this data, we show that all existing sentiment models trained on adjacent domains struggle with accurate market sentiment analysis due to the task’s specialized vocabulary. Consequently, we design, train, and deploy our own sentiment model. It outperforms all previous models (VADER, NTUSD-Fin, FinBERT, TwitterRoBERTa) when evaluated on Twitter posts. On posts from a different platform, our model performs on par with BERT-based large language models. We achieve this result at a fraction of the training and inference costs due to the model’s simple design. We publish the artifact as a python library to facilitate its use by future researchers and practitioners.
Averting today's loss of biodiversity and ecosystem services can be achieved through conservation efforts, especially of keystone species. Giraffes (Giraffa camelopardalis) play an important role in sustaining Africa's ecosystems, but are 'vulnerable' according to the IUCN Red List since 2016. Monitoring an animal's behavior in the wild helps to develop and assess their conservation management. One mechanism for remote tracking of wildlife behavior is to attach accelerometers to animals to record their body movement. We tested two different commercially available high-resolution accelerometers, e-obs and Africa Wildlife Tracking (AWT), attached to the top of the heads of three captive giraffes and analyzed the accuracy of automatic behavior classifications, focused on the Random Forests algorithm. For both accelerometers, behaviors of lower variety in head and neck movements could be better predicted (i.e., feeding above eye level, mean prediction accuracy e-obs/AWT: 97.6%/99.7%; drinking: 96.7%/97.0%) than those with a higher variety of body postures (such as standing: 90.7-91.0%/75.2-76.7%; rumination: 89.6-91.6%/53.5-86.5%). Nonetheless both devices come with limitations and especially the AWT needs technological adaptations before applying it on animals in the wild. Nevertheless, looking at the prediction results, both are promising accelerometers for behavioral classification of giraffes. Therefore, these devices when applied to free-ranging animals, in combination with GPS tracking, can contribute greatly to the conservation of giraffes.
Background:
Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models.
Methods:
For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases.
Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning
can then be deployed to classify specific behaviour and mental health patterns.
Results:
We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through
rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project.
Conclusions:
This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns
of unknown effects.
Für die Entwicklung professioneller Handlungskompetenzen angehender Lehrkräfte stellt die Unterrichtsreflexion ein wichtiges Instrument dar, um Theoriewissen und Praxiserfahrungen in Beziehung zu setzen. Die Auswertung von Unterrichtsreflexionen und eine entsprechende Rückmeldung stellt Forschende und Dozierende allerdings vor praktische wie theoretische Herausforderungen. Im Kontext der Forschung zu Künstlicher Intelligenz (KI) entwickelte Methoden bieten hier neue Potenziale. Der Beitrag stellt überblicksartig zwei Teilstudien vor, die mit Hilfe von KI-Methoden wie dem maschinellen Lernen untersuchen, inwieweit eine Auswertung von Unterrichtsreflexionen angehender Physiklehrkräfte auf Basis eines theoretisch abgeleiteten Reflexionsmodells und die automatisierte Rückmeldung hierzu möglich sind. Dabei wurden unterschiedliche Ansätze des maschinellen Lernens verwendet, um modellbasierte Klassifikation und Exploration von Themen in Unterrichtsreflexionen umzusetzen. Die Genauigkeit der Ergebnisse wurde vor allem durch sog. Große Sprachmodelle gesteigert, die auch den Transfer auf andere Standorte und Fächer ermöglichen. Für die fachdidaktische Forschung bedeuten sie jedoch wiederum neue Herausforderungen, wie etwa systematische Verzerrungen und Intransparenz von Entscheidungen. Dennoch empfehlen wir, die Potenziale der KI-basierten Methoden gründlicher zu erforschen und konsequent in der Praxis (etwa in Form von Webanwendungen) zu implementieren.
The Security Operations Center (SOC) represents a specialized unit responsible for managing security within enterprises. To aid in its responsibilities, the SOC relies heavily on a Security Information and Event Management (SIEM) system that functions as a centralized repository for all security-related data, providing a comprehensive view of the organization's security posture. Due to the ability to offer such insights, SIEMS are considered indispensable tools facilitating SOC functions, such as monitoring, threat detection, and incident response.
Despite advancements in big data architectures and analytics, most SIEMs fall short of keeping pace. Architecturally, they function merely as log search engines, lacking the support for distributed large-scale analytics. Analytically, they rely on rule-based correlation, neglecting the adoption of more advanced data science and machine learning techniques.
This thesis first proposes a blueprint for next-generation SIEM systems that emphasize distributed processing and multi-layered storage to enable data mining at a big data scale. Next, with the architectural support, it introduces two data mining approaches for advanced threat detection as part of SOC operations.
First, a novel graph mining technique that formulates threat detection within the SIEM system as a large-scale graph mining and inference problem, built on the principles of guilt-by-association and exempt-by-reputation. The approach entails the construction of a Heterogeneous Information Network (HIN) that models shared characteristics and associations among entities extracted from SIEM-related events/logs. Thereon, a novel graph-based inference algorithm is used to infer a node's maliciousness score based on its associations with other entities in the HIN. Second, an innovative outlier detection technique that imitates a SOC analyst's reasoning process to find anomalies/outliers. The approach emphasizes explainability and simplicity, achieved by combining the output of simple context-aware univariate submodels that calculate an outlier score for each entry.
Both approaches were tested in academic and real-world settings, demonstrating high performance when compared to other algorithms as well as practicality alongside a large enterprise's SIEM system.
This thesis establishes the foundation for next-generation SIEM systems that can enhance today's SOCs and facilitate the transition from human-centric to data-driven security operations.
The near-Earth space environment is a highly complex system comprised of several regions and particle populations hazardous to satellite operations. The trapped particles in the radiation belts and ring current can cause significant damage to satellites during space weather events, due to deep dielectric and surface charging. Closer to Earth is another important region, the ionosphere, which delays the propagation of radio signals and can adversely affect navigation and positioning. In response to fluctuations in solar and geomagnetic activity, both the inner-magnetospheric and ionospheric populations can undergo drastic and sudden changes within minutes to hours, which creates a challenge for predicting their behavior. Given the increasing reliance of our society on satellite technology, improving our understanding and modeling of these populations is a matter of paramount importance.
In recent years, numerous spacecraft have been launched to study the dynamics of particle populations in the near-Earth space, transforming it into a data-rich environment. To extract valuable insights from the abundance of available observations, it is crucial to employ advanced modeling techniques, and machine learning methods are among the most powerful approaches available. This dissertation employs long-term satellite observations to analyze the processes that drive particle dynamics, and builds interdisciplinary links between space physics and machine learning by developing new state-of-the-art models of the inner-magnetospheric and ionospheric particle dynamics.
The first aim of this thesis is to investigate the behavior of electrons in Earth's radiation belts and ring current. Using ~18 years of electron flux observations from the Global Positioning System (GPS), we developed the first machine learning model of hundreds-of-keV electron flux at Medium Earth Orbit (MEO) that is driven solely by solar wind and geomagnetic indices and does not require auxiliary flux measurements as inputs. We then proceeded to analyze the directional distributions of electrons, and for the first time, used Fourier sine series to fit electron pitch angle distributions (PADs) in Earth's inner magnetosphere. We performed a superposed epoch analysis of 129 geomagnetic storms during the Van Allen Probes era and demonstrated that electron PADs have a strong energy-dependent response to geomagnetic activity. Additionally, we showed that the solar wind dynamic pressure could be used as a good predictor of the PAD dynamics. Using the observed dependencies, we created the first PAD model with a continuous dependence on L, magnetic local time (MLT) and activity, and developed two techniques to reconstruct near-equatorial electron flux observations from low-PA data using this model.
The second objective of this thesis is to develop a novel model of the topside ionosphere. To achieve this goal, we collected observations from five of the most widely used ionospheric missions and intercalibrated these data sets. This allowed us to use these data jointly for model development, validation, and comparison with other existing empirical models. We demonstrated, for the first time, that ion density observations by Swarm Langmuir Probes exhibit overestimation (up to ~40-50%) at low and mid-latitudes on the night side, and suggested that the influence of light ions could be a potential cause of this overestimation. To develop the topside model, we used 19 years of radio occultation (RO) electron density profiles, which were fitted with a Chapman function with a linear dependence of scale height on altitude. This approximation yields 4 parameters, namely the peak density and height of the F2-layer and the slope and intercept of the linear scale height trend, which were modeled using feedforward neural networks (NNs). The model was extensively validated against both RO and in-situ observations and was found to outperform the International Reference Ionosphere (IRI) model by up to an order of magnitude. Our analysis showed that the most substantial deviations of the IRI model from the data occur at altitudes of 100-200 km above the F2-layer peak. The developed NN-based ionospheric model reproduces the effects of various physical mechanisms observed in the topside ionosphere and provides highly accurate electron density predictions.
This dissertation provides an extensive study of geospace dynamics, and the main results of this work contribute to the improvement of models of plasma populations in the near-Earth space environment.
Volcanoes are one of the Earth’s most dynamic zones and responsible for many changes in our planet. Volcano seismology aims to provide an understanding of the physical processes in volcanic systems and anticipate the style and timing of eruptions by analyzing the seismic records. Volcanic tremor signals are usually observed in the seismic records before or during volcanic eruptions. Their analysis contributes to evaluate the evolving volcanic activity and potentially predict eruptions. Years of continuous seismic monitoring now provide useful information for operational eruption forecasting. The continuously growing amount of seismic recordings, however, poses a challenge for analysis, information extraction, and interpretation, to support timely decision making during volcanic crises. Furthermore, the complexity of eruption processes and precursory activities makes the analysis challenging.
A challenge in studying seismic signals of volcanic origin is the coexistence of transient signal swarms and long-lasting volcanic tremor signals. Separating transient events from volcanic tremors can, therefore, contribute to improving our understanding of the underlying physical processes. Some similar issues (data reduction, source separation, extraction, and classification) are addressed in the context of music information retrieval (MIR). The signal characteristics of acoustic and seismic recordings comprise a number of similarities. This thesis is going beyond classical signal analysis techniques usually employed in seismology by exploiting similarities of seismic and acoustic signals and building the information retrieval strategy on the expertise developed in the field of MIR.
First, inspired by the idea of harmonic–percussive separation (HPS) in musical signal processing, I have developed a method to extract harmonic volcanic tremor signals and to detect transient events from seismic recordings. This provides a clean tremor signal suitable for tremor investigation along with a characteristic function suitable for earthquake detection. Second, using HPS algorithms, I have developed a noise reduction technique for seismic signals. This method is especially useful for denoising ocean bottom seismometers, which are highly contaminated by noise. The advantage of this method compared to other denoising techniques is that it doesn’t introduce distortion to the broadband earthquake waveforms, which makes it reliable for different applications in passive seismological analysis. Third, to address the challenge of extracting information from high-dimensional data and investigating the complex eruptive phases, I have developed an advanced machine learning model that results in a comprehensive signal processing scheme for volcanic tremors. Using this method seismic signatures of major eruptive phases can be automatically detected. This helps to provide a chronology of the volcanic system. Also, this model is capable to detect weak precursory volcanic tremors prior to the eruption, which could be used as an indicator of imminent eruptive activity. The extracted patterns of seismicity and their temporal variations finally provide an explanation for the transition mechanism between eruptive phases.
Background and objectives
AKI treated with dialysis initiation is a common complication of coronavirus disease 2019 (COVID-19) among hospitalized patients. However, dialysis supplies and personnel are often limited.
Design, setting, participants, & measurements
Using data from adult patients hospitalized with COVID-19 from five hospitals from theMount Sinai Health System who were admitted between March 10 and December 26, 2020, we developed and validated several models (logistic regression, Least Absolute Shrinkage and Selection Operator (LASSO), random forest, and eXtreme GradientBoosting [XGBoost; with and without imputation]) for predicting treatment with dialysis or death at various time horizons (1, 3, 5, and 7 days) after hospital admission. Patients admitted to theMount Sinai Hospital were used for internal validation, whereas the other hospitals formed part of the external validation cohort. Features included demographics, comorbidities, and laboratory and vital signs within 12 hours of hospital admission.
Results
A total of 6093 patients (2442 in training and 3651 in external validation) were included in the final cohort. Of the different modeling approaches used, XGBoost without imputation had the highest area under the receiver operating characteristic (AUROC) curve on internal validation (range of 0.93-0.98) and area under the precisionrecall curve (AUPRC; range of 0.78-0.82) for all time points. XGBoost without imputation also had the highest test parameters on external validation (AUROC range of 0.85-0.87, and AUPRC range of 0.27-0.54) across all time windows. XGBoost without imputation outperformed all models with higher precision and recall (mean difference in AUROC of 0.04; mean difference in AUPRC of 0.15). Features of creatinine, BUN, and red cell distribution width were major drivers of the model's prediction.
Conclusions
An XGBoost model without imputation for prediction of a composite outcome of either death or dialysis in patients positive for COVID-19 had the best performance, as compared with standard and other machine learning models.
Reflexion und Reflexivität
(2023)
Reflexion gilt in der Lehrkräftebildung als eine Schlüsselkategorie der professionellen Entwicklung. Entsprechend wird auf vielfältige Weise die Qualität reflexionsbezogener Kompetenzen untersucht. Eine Herausforderung hierbei kann in der Annahme bestehen, von der Analyse schriftlicher Reflexionen unmittelbar auf die Reflexivität einer Person zu schließen, da Reflexion stets kontextspezifisch als Abbild reflexionsbezogener Argumentationsprozesse angesehen werden sollte und reflexionsbezogenen Dispositionen unterliegt. Auch kann die Qualität einer Reflexion auf mehreren Dimensionen bewertet werden, ohne quantifizierbare, absolute Aussagen treffen zu können.
Daher wurden im Rahmen einer Physik-Videovignette N = 134 schriftliche Fremdreflexionen verfasst und kontextspezifische reflexionsbezogene Dispositionen erhoben. Expert*innen erstellten theoriegeleitet Qualitätsbewertungen zur Breite, Tiefe, Kohärenz und Spezifität eines jeden Reflexionstextes. Unter Verwendung computerbasierter Klassifikations- und Analyseverfahren wurden weitere Textmerkmale erhoben. Mittels explorativer Faktorenanalyse konnten die Faktoren Qualität, Quantität und Deskriptivität gefunden werden. Da alle konventionell eingeschätzten Qualitätsbewertungen durch einen Faktor repräsentiert wurden, konnte ein maximales Qualitätskorrelat kalkuliert werden, zu welchem jede schriftliche Fremdreflexion im Rahmen der vorliegenden Vignette eine computerbasiert bestimmbare Distanz aufweist. Diese Distanz zum maximalen Qualitätskorrelat konnte validiert werden und kann die Qualität der schriftlichen Reflexionen unabhängig von menschlichen Ressourcen quantifiziert repräsentieren. Abschließend konnte identifiziert werden, dass ausgewählte Dispositionen in unterschiedlichem Maße mit der Reflexionsqualität zusammenhängen. So konnten beispielsweise bezogen auf das Physik-Fachwissen minimale Zusammenhänge identifiziert werden, wohingegen Werthaltung sowie wahrgenommene Unterrichtsqualität eng mit der Qualität einer schriftlichen Reflexion in Verbindung stehen können.
Es wird geschlussfolgert, dass reflexionsbezogene Dispositionen moderierenden Einfluss auf Reflexionen nehmen können. Es wird empfohlen bei der Erhebung von Reflexion mit dem Ziel der Kompetenzmessung ausgewählte Dispositionen mit zu erheben. Weiter verdeutlicht diese Arbeit die Möglichkeit, aussagekräftige Quantifizierungen auch in der Analyse komplexer Konstrukte vorzunehmen. Durch computerbasierte Qualitätsabschätzungen können objektive und individuelle Analysen und differenzierteres automatisiertes Feedback ermöglicht werden.
Background:
COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking.
Objective:
The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points.
Methods:
We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions.
Results:
Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction.
Conclusions:
We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.
Casualties and damages from urban pluvial flooding are increasing. Triggered by short, localized, and intensive rainfall events, urban pluvial floods can occur anywhere, even in areas without a history of flooding. Urban pluvial floods have relatively small temporal and spatial scales. Although cumulative losses from urban pluvial floods are comparable, most flood risk management and mitigation strategies focus on fluvial and coastal flooding. Numerical-physical-hydrodynamic models are considered the best tool to represent the complex nature of urban pluvial floods; however, they are computationally expensive and time-consuming. These sophisticated models make large-scale analysis and operational forecasting prohibitive. Therefore, it is crucial to evaluate and benchmark the performance of other alternative methods.
The findings of this cumulative thesis are represented in three research articles. The first study evaluates two topographic-based methods to map urban pluvial flooding, fill–spill–merge (FSM) and topographic wetness index (TWI), by comparing them against a sophisticated hydrodynamic model. The FSM method identifies flood-prone areas within topographic depressions while the TWI method employs maximum likelihood estimation to calibrate a TWI threshold (τ) based on inundation maps from the 2D hydrodynamic model. The results point out that the FSM method outperforms the TWI method. The study highlights then the advantage and limitations of both methods.
Data-driven models provide a promising alternative to computationally expensive hydrodynamic models. However, the literature lacks benchmarking studies to evaluate the different models' performance, advantages and limitations. Model transferability in space is a crucial problem. Most studies focus on river flooding, likely due to the relative availability of flow and rain gauge records for training and validation. Furthermore, they consider these models as black boxes. The second study uses a flood inventory for the city of Berlin and 11 predictive features which potentially indicate an increased pluvial flooding hazard to map urban pluvial flood susceptibility using a convolutional neural network (CNN), an artificial neural network (ANN) and the benchmarking machine learning models random forest (RF) and support vector machine (SVM). I investigate the influence of spatial resolution on the implemented models, the models' transferability in space and the importance of the predictive features. The results show that all models perform well and the RF models are superior to the other models within and outside the training domain. The models developed using fine spatial resolution (2 and 5 m) could better identify flood-prone areas. Finally, the results point out that aspect is the most important predictive feature for the CNN models, and altitude is for the other models.
While flood susceptibility maps identify flood-prone areas, they do not represent flood variables such as velocity and depth which are necessary for effective flood risk management. To address this, the third study investigates data-driven models' transferability to predict urban pluvial floodwater depth and the models' ability to enhance their predictions using transfer learning techniques. It compares the performance of RF (the best-performing model in the previous study) and CNN models using 12 predictive features and output from a hydrodynamic model. The findings in the third study suggest that while CNN models tend to generalise and smooth the target function on the training dataset, RF models suffer from overfitting. Hence, RF models are superior for predictions inside the training domains but fail outside them while CNN models could control the relative loss in performance outside the training domains. Finally, the CNN models benefit more from transfer learning techniques than RF models, boosting their performance outside training domains.
In conclusion, this thesis has evaluated both topographic-based methods and data-driven models to map urban pluvial flooding. However, further studies are crucial to have methods that completely overcome the limitation of 2D hydrodynamic models.
Decubitus is one of the most relevant diseases in nursing and the most expensive to treat. It is caused by sustained pressure on tissue, so it particularly affects bed-bound patients. This work lays a foundation for pressure mattress-based decubitus prophylaxis by implementing a solution to the single-frame 2D Human Pose Estimation problem.
For this, methods of Deep Learning are employed. Two approaches are examined, a coarse-to-fine Convolutional Neural Network for direct regression of joint coordinates and a U-Net for the derivation of probability distribution heatmaps.
We conclude that training our models on a combined dataset of the publicly available Bodies at Rest and SLP data yields the best results. Furthermore, various preprocessing techniques are investigated, and a hyperparameter optimization is performed to discover an improved model architecture.
Another finding indicates that the heatmap-based approach outperforms direct regression.
This model achieves a mean per-joint position error of 9.11 cm for the Bodies at Rest data and 7.43 cm for the SLP data.
We find that it generalizes well on data from mattresses other than those seen during training but has difficulties detecting the arms correctly.
Additionally, we give a brief overview of the medical data annotation tool annoto we developed in the bachelor project and furthermore conclude that the Scrum framework and agile practices enhanced our development workflow.
On 21 April 2021, the European Commission presented its long-awaited proposal for a Regulation “laying down harmonized rules on Artificial Intelligence”, the so-called “Artificial Intelligence Act” (AIA). This article takes a critical look at the proposed regulation. After an introduction (1), the paper analyzes the unclear preemptive effect of the AIA and EU competences (2), the scope of application (3), the prohibited uses of Artificial Intelligence (AI) (4), the provisions on high-risk AI systems (5), the obligations of providers and users (6), the requirements for AI systems with limited risks (7), the enforcement system (8), the relationship of the AIA with the existing legal framework (9), and the regulatory gaps (10). The last section draws some final conclusions (11).