000 Informatik, Informationswissenschaft, allgemeine Werke
Refine
Year of publication
Document Type
- Article (212)
- Other (117)
- Doctoral Thesis (88)
- Postprint (12)
- Part of a Book (11)
- Conference Proceeding (11)
- Monograph/Edited Volume (5)
- Master's Thesis (4)
- Review (2)
- Habilitation Thesis (1)
Keywords
- MOOC (39)
- e-learning (35)
- Digitale Bildung (34)
- Kursdesign (33)
- Micro Degree (33)
- Online-Lehre (33)
- Onlinekurs (33)
- Onlinekurs-Produktion (33)
- digital education (33)
- micro degree (33)
Institute
- Hasso-Plattner-Institut für Digital Engineering GmbH (230)
- Institut für Informatik und Computational Science (94)
- Hasso-Plattner-Institut für Digital Engineering gGmbH (80)
- Wirtschaftswissenschaften (24)
- Institut für Physik und Astronomie (8)
- Universitätsbibliothek (5)
- Institut für Mathematik (4)
- Fachgruppe Betriebswirtschaftslehre (3)
- Department Linguistik (2)
- Fachgruppe Volkswirtschaftslehre (2)
Deep metric learning employs deep neural networks to embed instances into a metric space such that distances between instances of the same class are small and distances between instances from different classes are large. In most existing deep metric learning techniques, the embedding of an instance is given by a feature vector produced by a deep neural network and Euclidean distance or cosine similarity defines distances between these vectors. This paper studies deep distributional embeddings of sequences, where the embedding of a sequence is given by the distribution of learned deep features across the sequence. The motivation for this is to better capture statistical information about the distribution of patterns within the sequence in the embedding. When embeddings are distributions rather than vectors, measuring distances between embeddings involves comparing their respective distributions. The paper therefore proposes a distance metric based on Wasserstein distances between the distributions and a corresponding loss function for metric learning, which leads to a novel end-to-end trainable embedding model. We empirically observe that distributional embeddings outperform standard vector embeddings and that training with the proposed Wasserstein metric outperforms training with other distance functions.
A central insight from psychological studies on human eye movements is that eye movement patterns are highly individually characteristic. They can, therefore, be used as a biometric feature, that is, subjects can be identified based on their eye movements. This thesis introduces new machine learning methods to identify subjects based on their eye movements while viewing arbitrary content. The thesis focuses on probabilistic modeling of the problem, which has yielded the best results in the most recent literature. The thesis studies the problem in three phases by proposing a purely probabilistic, probabilistic deep learning, and probabilistic deep metric learning approach. In the first phase, the thesis studies models that rely on psychological concepts about eye movements. Recent literature illustrates that individual-specific distributions of gaze patterns can be used to accurately identify individuals. In these studies, models were based on a simple parametric family of distributions. Such simple parametric models can be robustly estimated from sparse data, but have limited flexibility to capture the differences between individuals. Therefore, this thesis proposes a semiparametric model of gaze patterns that is flexible yet robust for individual identification. These patterns can be understood as domain knowledge derived from psychological literature. Fixations and saccades are examples of simple gaze patterns. The proposed semiparametric densities are drawn under a Gaussian process prior centered at a simple parametric distribution. Thus, the model will stay close to the parametric class of densities if little data is available, but it can also deviate from this class if enough data is available, increasing the flexibility of the model. The proposed method is evaluated on a large-scale dataset, showing significant improvements over the state-of-the-art. Later, the thesis replaces the model based on gaze patterns derived from psychological concepts with a deep neural network that can learn more informative and complex patterns from raw eye movement data. As previous work has shown that the distribution of these patterns across a sequence is informative, a novel statistical aggregation layer called the quantile layer is introduced. It explicitly fits the distribution of deep patterns learned directly from the raw eye movement data. The proposed deep learning approach is end-to-end learnable, such that the deep model learns to extract informative, short local patterns while the quantile layer learns to approximate the distributions of these patterns. Quantile layers are a generic approach that can converge to standard pooling layers or have a more detailed description of the features being pooled, depending on the problem. The proposed model is evaluated in a large-scale study using the eye movements of subjects viewing arbitrary visual input. The model improves upon the standard pooling layers and other statistical aggregation layers proposed in the literature. It also improves upon the state-of-the-art eye movement biometrics by a wide margin. Finally, for the model to identify any subject — not just the set of subjects it is trained on — a metric learning approach is developed. Metric learning learns a distance function over instances. The metric learning model maps the instances into a metric space, where sequences of the same individual are close, and sequences of different individuals are further apart. This thesis introduces a deep metric learning approach with distributional embeddings. The approach represents sequences as a set of continuous distributions in a metric space; to achieve this, a new loss function based on Wasserstein distances is introduced. The proposed method is evaluated on multiple domains besides eye movement biometrics. This approach outperforms the state of the art in deep metric learning in several domains while also outperforming the state of the art in eye movement biometrics.
Enterprise Resource Planning (ERP) system customization is often necessary because companies have unique processes that provide their competitive advantage. Despite new technological advances such as cloud computing or model-driven development, technical ERP customization options are either outdated or ambiguously formulated in the scientific literature. Using a systematic literature review (SLR) that analyzes 137 definitions from 26 papers, the result is an analysis and aggregation of technical customization types by providing clearance and aligning with future organizational needs. The results show a shift from ERP code modification in on-premises systems to interface and integration customization in cloud ERP systems, as well as emerging technological opportunities as a way for customers and key users to perform system customization. The study contributes by providing a clear understanding of given customization types and assisting ERP users and vendors in making customization decisions.
During a crisis event, social media enables two-way communication and many-to-many information broadcasting, browsing others’ posts, publishing own content, and public commenting. These records can deliver valuable insights to approach problematic situations effectively. Our study explores how social media communication can be analyzed to understand the responses to health crises better. Results based on nearly 800 K tweets indicate that the coping and regulation foci framework holds good explanatory power, with four clusters salient in public reactions: 1) “Understanding” (problem-promotion); 2) “Action planning” (problem-prevention); 3) “Hope” (emotion-promotion) and 4) “Reassurance” (emotion-prevention). Second, the inter-temporal analysis shows high volatility of topic proportions and a shift from self-centered to community-centered topics during the course of the event. The insights are beneficial for research on crisis management and practicians who are interested in large-scale monitoring of their audience for well-informed decision-making.
Digital inclusion
(2021)
In this thesis, we tackle two social disruptions: recent refugee waves in Germany and the COVID-19 pandemic. We focus on the use of information and communication technology (ICT) as a key means of alleviating these disruptions and promoting social inclusion. As social disruptions typically lead to frustration and fragmentation, it is essential to ensure the social inclusion of individuals and societies during such times.
In the context of the social inclusion of refugees, we focus on the Syrian refugees who arrived in Germany as of 2015, as they form a large and coherent refugee community. In particular, we address the role of ICTs in refugees’ social inclusion and investigate how different ICTs (especially smartphones and social networks) can foster refugees’ integration and social inclusion. In the context of the COVID-19 pandemic, we focus on the widespread unconventional working model of work from home (WFH). Our research here centers on the main constructs of WFH and the key differences in WFH experiences based on personal characteristics such as gender and parental status.
We reveal novel insights through four well-established research methods: literature review, mixed methods, qualitative method, and quantitative method. The results of our research have been published in the form of eight articles in major information systems venues and journals. Key results from the refugee research stream include the following: Smartphones represent a central component of refugee ICT use; refugees view ICT as a source of information and power; the social connectedness of refugees is strongly correlated with their Internet use; refugees are not relying solely on traditional methods to learn the German language or pursue further education; the ability to use smartphones anytime and anywhere gives refugees an empowering feeling of global connectedness; and ICTs empower refugees on three levels (community participation, sense of control, and self-efficacy).
Key insights from the COVID-19 WFH stream include: Gender and the presence of children under the age of 18 affect workers’ control over their time, technology usefulness, and WFH conflicts, while not affecting their WFH attitudes; and both personal and technology-related factors affect an individual’s attitude toward WFH and their productivity. Further insights are being gathered at the time of submitting this thesis.
This thesis contributes to the discussion within the information systems community regarding how to use different ICT solutions to promote the social inclusion of refugees in their new communities and foster an inclusive society. It also adds to the growing body of research on COVID-19, in particular on the sudden workplace transformation to WFH. The insights gathered in this thesis reveal theoretical implications and future opportunities for research in the field of information systems, practical implications for relevant stakeholders, and social implications related to the refugee crisis and the COVID-19 pandemic that must be addressed.
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.
Parsing of argumentative structures has become a very active line of research in recent years. Like discourse parsing or any other natural language task that requires prediction of linguistic structures, most approaches choose to learn a local model and then perform global decoding over the local probability distributions, often imposing constraints that are specific to the task at hand. Specifically for argumentation parsing, two decoding approaches have been recently proposed: Minimum Spanning Trees (MST) and Integer Linear Programming (ILP), following similar trends in discourse parsing. In contrast to discourse parsing though, where trees are not always used as underlying annotation schemes, argumentation structures so far have always been represented with trees. Using the ‘argumentative microtext corpus’ [in: Argumentation and Reasoned Action: Proceedings of the 1st European Conference on Argumentation, Lisbon 2015 / Vol. 2, College Publications, London, 2016, pp. 801–815] as underlying data and replicating three different decoding mechanisms, in this paper we propose a novel ILP decoder and an extension to our earlier MST work, and then thoroughly compare the approaches. The result is that our new decoder outperforms related work in important respects, and that in general, ILP and MST yield very similar performance.
With the recent growth of sensors, cloud computing handles the data processing of many applications. Processing some of this data on the cloud raises, however, many concerns regarding, e.g., privacy, latency, or single points of failure. Alternatively, thanks to the development of embedded systems, smart wireless devices can share their computation capacity, creating a local wireless cloud for in-network processing. In this context, the processing of an application is divided into smaller jobs so that a device can run one or more jobs.
The contribution of this thesis to this scenario is divided into three parts. In part one, I focus on wireless aspects, such as power control and interference management, for deciding which jobs to run on which node and how to route data between nodes. Hence, I formulate optimization problems and develop heuristic and meta-heuristic algorithms to allocate wireless and computation resources. Additionally, to deal with multiple applications competing for these resources, I develop a reinforcement learning (RL) admission controller to decide which application should be admitted. Next, I look into acoustic applications to improve wireless throughput by using microphone clock synchronization to synchronize wireless transmissions.
In the second part, I jointly work with colleagues from the acoustic processing field to optimize both network and application (i.e., acoustic) qualities. My contribution focuses on the network part, where I study the relation between acoustic and network qualities when selecting a subset of microphones for collecting audio data or selecting a subset of optional jobs for processing these data; too many microphones or too many jobs can lessen quality by unnecessary delays. Hence, I develop RL solutions to select the subset of microphones under network constraints when the speaker is moving while still providing good acoustic quality. Furthermore, I show that autonomous vehicles carrying microphones improve the acoustic qualities of different applications. Accordingly, I develop RL solutions (single and multi-agent ones) for controlling these vehicles.
In the third part, I close the gap between theory and practice. I describe the features of my open-source framework used as a proof of concept for wireless in-network processing. Next, I demonstrate how to run some algorithms developed by colleagues from acoustic processing using my framework. I also use the framework for studying in-network delays (wireless and processing) using different distributions of jobs and network topologies.
In this work we tackle the problem of checking strong equivalence of logic programs that may contain local auxiliary atoms, to be removed from their stable models and to be forbidden in any external context. We call this property projective strong equivalence (PSE). It has been recently proved that not any logic program containing auxiliary atoms can be reformulated, under PSE, as another logic program or formula without them – this is known as strongly persistent forgetting. In this paper, we introduce a conservative extension of Equilibrium Logic and its monotonic basis, the logic of Here-and-There, in which we deal with a new connective ‘|’ we call fork. We provide a semantic characterisation of PSE for forks and use it to show that, in this extension, it is always possible to forget auxiliary atoms under strong persistence. We further define when the obtained fork is representable as a regular formula.