Contributions in Merlin

null

Cerebral blood flow differs between migraine patients and healthy controls during attack and the interictal period. This study compares the brain perfusion of episodic migraine patients and healthy controls and investigates the influence of anodal transcranial direct current stimulation (tDCS) over the occipital cortex. We included healthy adult controls and episodic migraineurs. After a 28-day baseline period and the baseline visit, migraine patients received daily active or sham anodal tDCS over the occipital lobe for 28 days. All participants underwent a MRI scan at baseline; migraineurs were also scanned shortly after the stimulation period and about five months later. At baseline, brain perfusion of migraine patients and controls differed in several areas; among the stimulated areas, perfusion was increased in the cuneus of healthy controls. At the first visit, the active tDCS group had an increased blood flow in regions processing visual stimuli and a decreased perfusion in other areas. Perfusion did not differ at the second follow-up visit. The lower perfusion level in migraineurs in the cuneus indicates a lower preactivation level. Anodal tDCS over the occipital cortex increases perfusion of several areas shortly after the stimulation period, but not 5 months later. An increase in the cortical preactivation level could mediate the transient reduction of the migraine frequency.Trial registration: NCT03237754 (registered at clincicaltrials.gov; full date of first trial registration: 03/08/2017).

This paper presents Fedstellar, a platform for training decentralized Federated Learning (FL) models in heterogeneous topologies in terms of the number of federation participants and their connections. Fedstellar allows users to build custom topologies, enabling them to control the aggregation of model parameters in a decentralized manner. The platform offers a Web application for creating, managing, and connecting nodes to ensure data privacy and provides tools to measure, monitor, and analyze the performance of the nodes. The paper describes the functionalities of Fedstellar and its potential applications. To demonstrate the applicability of the platform, different use cases are presented in which decentralized, semi-decentralized, and centralized architectures are compared in terms of model performance, convergence time, and network overhead when collaboratively classifying hand-written digits using the MNIST dataset.

Investors perceive stocks of companies with fluent names as more profitable. This perception may result from two different channels: a direct, non-deliberate affect toward fluent names or a deliberate interpretation of fluent names as a signal for company quality. We use preregistered experiments to disentangle these channels and test their limitations. Our results indicate the existence of a significant non-deliberate fluency effect, while the deliberate fluency effect can be activated and deactivated in boundary cases. Both effects are consistent across different groups of participants. However, whereas the fluency effect is strong in isolation, it has limitations when investors are confronted with additional information about the stock.

We show that banks cross-sell future deposits and loans to existing household depositors. A bank is 20-percentage-points more likely to sell a loan to an existing depositor than to an otherwise comparable household. Existing depositors pay a premium when borrowing, and we find no indication that banks obtain an informational advantage on such borrowers, suggesting that the cross-selling is driven more by demand than by supply complementarities. These demand complementarities are in turn driven more by stickiness rather than by unobserved persistent preferences. Finally, banks internalize future cross-selling potential when setting deposit rates.

When a sample combines data from two or more groups, multivariate regression yields a matrix-weighted average of the group-specific coefficient vectors. However, it is possible that the weighted average of a specific coefficient falls outside the range of the group-specific coefficients, and it may even have a different sign compared to both group-level coefficients, a manifestation of Simpson’s paradox. The result of the combined regression is then prone to misinterpretation. The purpose of this paper is to raise awareness of this problem and to state conditions under which such non-convex weighting or sign reversal can arise, for a model with two regressors and two groups. Two illustrative examples, an investment equation estimated with panel data, and a cross-sectional earnings equation for men and women, highlight the relevance of these findings for applied work.

Artificial intelligence (AI) is becoming increasingly important as the amount of digital data grows. However, AI systems are often opaque and perceived as black boxes, which has a negative impact on user acceptance and trust. We see this in healthcare, where despite the great potential of AI, a lack of understanding and trust has held back physicians from adopting it. One way to address these issues is through Explainable AI (XAI), which focuses on understanding and interpreting AI behavior. In this thesis, we want to contribute to XAI by developing a visual analytics system called VisAIExplorer. We want to find out how an interactive visual analytics system can be designed to explain machine learning models to novice machine learning users, and what types of visualizations within the system can help to build understanding. The goal of VisAIExplorer is to explain the two models, logistic regression and hierarchical clustering, to novice machine learning users by providing various visualizations and support throughout the work process. The machine learning models are trained on a medical dataset about strokes, as healthcare professionals could benefit from a better understanding and increased trust in AI systems. By improving transparency and user support, VisAIExplorer aims to overcome the limitations of existing AI tools and promote more explainability in AI. The thesis includes a literature review, system development, evaluation, and suggestions for future improvements.

Today, most of the research in neural machine translation (NMT) focuses on 20 of the world’s 7,000 languages. The scarcity of training data is a substantial bottleneck to research in most of the remaining languages. Tulu is one such low-resource language, spoken by fewer than two million people in the southern part of India. To address this limitation, this thesis attempts to develop an NMT model that can translate between English and Tulu. The technique used here is inspired by a method called NMT-Adapt, which adapts a translation model trained on a related high-resource language to translate the low-resource language. This is done using only monolingual data in the low-resource language, and a combination of iterative methods including ‘back-translation’ and ‘denoising autoencoding’. The related high-resource language used in this work is another south Indian language called Kannada, which has abundant training data and is closely related to Tulu. Monolingual Tulu data scraped from articles on the Tulu language Wikipedia was used in combination with an English-Kannada NMT model for achieving the task. This work also introduces a benchmark dataset for Tulu consisting of 1,300 sentences. The results demonstrate that the model is able to translate Tulu to English reasonably well. Although English to Tulu translation needs improvement, there is no other translation model for translating from English to Tulu for comparison.

The purpose of this thesis is the development and evaluation of a spoken pedagogical conversational agent (PCA) which can carry out complete telephone calls in the context of a corporate identity (CI) training. The term CI refers the overall self-image of an organization regarding its corporate personality and reflects how an organization is perceived by both internal and external stakeholders. One aspect of the overarching study about CI in public administrations of two German communes is service on the telephone, which aims at giving employees an opportunity to train and improve their skills in different areas such as active listening, issue solving, or de-escalation on the telephone. Besides the implementation of effective telephone exercises, the focus is on the personalization abilities of the PCA such as complete simulated conversations and feedback generation, which is accomplished by making use of recent language models such as the state-of-the-art ChatGPT model by OpenAI. How these models can be used in this organizational context is a relatively new area of study and not much research exists about this yet. Furthermore, the effects of personalization on the users such as social presence and interaction quality is examined. To accomplish this, requirements are established based on an iterative process considering stakeholder input and related work surrounding institutional talk, workplace learning, and conversational agents. Then, the technologies are selected consisting of different components such as speech-to-text and text-to-speech engines. During development a major focus is on prompt engineering which aims at providing optimal instructions for the language model to generate an optimal response. Finally, a functioning PCA is implemented and deployed in a CI training with real employees of two public administrations. Following the training, an evaluation is carried out consisting of different surveys and interviews, which are used in the analysis of the PCA. The results show that a PCA in this context can be personalized in various ways by utilizing novel language models such as ChatGPT. Furthermore, the evidence indicates that the personalization can potentially lead to an increased social presence and higher interaction quality. In a final step, the personalization of the PCA, problematic aspects, and challenges are discussed, resulting in derived design principles. The further development of the PCA can make use of these insights as a foundation regarding different technical and sociotechnical aspects.