Institut für Wirtschaftsinformatik (IIS)
Refine
Keywords
- Analyse (1)
- Baye´sche-Statistik (1)
- Datenerhebung auf Keyword-Ebene (1)
- Erhebung (1)
- Graphen (1)
- Netzwerkanalyse (1)
- Netzwerke (1)
- Online-Marketing (1)
- Robustheit (1)
- Umfrage (1)
Institute
Detecting and assessing road damages for autonomous driving utilizing conventional vehicle sensors
(2021)
Environmental perception is one of the biggest challenges in autonomous driving to move inside complex traffic situations properly. Perceiving the road's condition is necessary to calculate the drivable space; in manual driving, this is realized by the human visual cortex. Enabling the vehicle to detect road conditions is a critical and complex task from many perspectives. The complexity lies on the one hand in the development of tools for detecting damage, ideally using sensors already installed in the vehicle, and on the other hand, in integrating detected damages into the autonomous driving task and thus into the subsystems of autonomous driving. High-Definition Feature Maps, for instance, should be prepared for mapping road damages, which includes online and in-vehicle implementation. Furthermore, the motion planning system should react based on the detected damages to increase driving comfort and safety actively. Road damage detection is essential, especially in areas with poor infrastructure, and should be integrated as early as possible to enable even less developed countries to reap the benefits of autonomous driving systems. Besides the application in autonomous driving, an up-to-date solution on assessing road conditions is likewise desirable for the infrastructure planning of municipalities and federal states to make optimal use of the limited resources available for maintaining infrastructure quality. Addressing the challenges mentioned above, the research approach of this work is pragmatic and problem-solving. In designing technical solutions for road damage detection, we conduct applied research methods in engineering, including modeling, prototyping, and field studies. We utilize design science research to integrate road damages in an end-to-end concept for autonomous driving while drawing on previous knowledge, the application domain requirements, and expert workshops. This thesis provides various contributions to theory and practice. We design two individual solutions to assess road conditions with existing vehicle sensor technology. The first solution is based on calculating the quarter-vehicle model utilizing the vehicle level sensor and an acceleration sensor. The novel model-based calculation measures the road elevation under the tires, enabling common vehicles to assess road conditions with standard hardware. The second solution utilizes images from front-facing vehicle cameras to detect road damages with deep neural networks. Despite other research in this area, our algorithms are designed to be applicable on edge devices in autonomous vehicles with limited computational resources while still delivering cutting-edge performance. In addition, our analyses of deep learning tools and the introduction of new data into training provide valuable opportunities for researchers in other application areas to develop deep learning algorithms to optimize detection performance and runtime. Besides detecting road damages, we provide novel algorithms for classifying the severity of road damages to deliver additional information for improved motion planning. Alongside the technical solutions, we address the lack of an end-to-end solution for road damages in autonomous driving by providing a concept that starts from data generation and ends with servicing the vehicle motion planning. This includes solutions for detecting road damages, assessing their severity, aggregating the data in the vehicle and a cloud platform, and making the data available via that platform to other vehicles. Fundamental limitations in this dissertation are due to boundaries in modeling. Our pragmatic approach simplifies reality, which always distorts the degree of truth in the result. This affects the model building of the quarter-vehicle and deep learning. Further limitations occur in the end-to-end concept. This represents the integration of road damages in the autonomous driving task but does not detail the aggregation modules and interfaces of the subsystems. The completion of this work does not conclude the topic of road damage detection and assessment in autonomous driving. Research must continue to optimize the proposed solutions and test them on a widespread basis in the real world. Furthermore, the sensor fusion of different approaches is fascinating in order to combine the advantages of individual systems. Integrating the end-to-end concept into the ecosystem of an autonomous vehicle is another fascinating field, taking interfaces and cloud platforms into account.
Extracting meaningful representations of data is a fundamental problem in machine learning. Those representations can be viewed from two different perspectives. First, there is the representation of data in terms of the number of data points. Representative subsets that compactly summarize the data without superfluous redundancies help to reduce the data size. Those subsets allow for scaling existing learning algorithms up without approximating their solution. Second, there is the representation of every individual data point in terms of its dimensions. Often, not all dimensions carry meaningful information for the learning task, or the information is implicitly embedded in a low-dimensional subspace. A change of representation can also simplify important learning tasks such as density estimation and data generation. This thesis deals with the aforementioned views on data representation and contributes to them. We first focus on computing representative subsets for a matrix factorization technique called archetypal analysis and the setting of optimal experimental design. For these problems, we motivate and investigate the usability of the data boundary as a representative subset. We also present novel methods to efficiently compute the data boundary, even in kernel-induced feature spaces. Based on the coreset principle, we derive another representative subset for archetypal analysis, which provides additional theoretical guarantees on the approximation error. Empirical results confirm that all compact representations of data derived in this thesis perform significantly better than uniform subsets of data. In the second part of the thesis, we are concerned with efficient data representations for density estimation. We analyze spatio-temporal problems, which arise, for example, in sports analytics, and demonstrate how to learn (contextual) probabilistic movement models of objects using trajectory data. Furthermore, we highlight issues of interpolating data in normalizing flows, a technique that changes the representation of data to follow a specific distribution. We show how to solve this issue and obtain more natural transitions on the example of image data.
Motivation: Maximizing the value from data has become a key challenge for companies as it helps improve operations and decision making, enhances products and services, and, ultimately, leads to new business models. The latter two have been investigated by scholars as part of an emerging research field on data-driven business model innovation. While enterprise architecture (EA) management and modeling have proven their value for IT-related projects, the support of enterprise architecture for data-driven business models (DDBMs) is a rather new and unexplored field. We argue that the current understanding of the intersection of data-driven business model innovation and enterprise architecture is incomplete because of five challenges that have not been addressed in existing research: (1) lack of knowledge of how companies design and realize data-driven business models from a process perspective, (2) lack of knowledge on the implementation phase of data-driven business models, (3) lack of knowledge on the potential support enterprise architecture modeling and management can provide to data-driven business model endeavors, (4) lack of knowledge on how enterprise architecture modeling and management support data-driven business model design and realization in practice, (5) lack of knowledge on how to deploy data-driven business models. We address these challenges by examining how enterprise architecture modeling and management can benefit data-driven business model innovation.
Research Approach: Addressing the challenges mentioned above, the mixed-method approach of this thesis draws on a systematic literature review, qualitative empirical research as well as the design science research paradigm. We conducted a systematic literature search on data-driven business models and enterprise architecture. Considering the novelty of data-driven business models for academia and practice, we conducted explorative qualitative research to explain “why” and “how” companies embark on realizing data-driven business models. Throughout these studies, the primary data source was semi-structured interviews. In order to provide an artifact for DDBM innovation, we developed a theory for design and action. The data-driven business model innovation artifact was inductively developed in two design iterations based on the design science paradigm and the design science research framework.
Contribution: This thesis provides several contributions to theory and practice. We identified a clear gap in previous research efforts and derived 42 data-driven business model-related EA concerns. In order to address the identified literature gap, we provide empirical evidence for data-driven business model innovation. Four pathways of data-driven business model design and realization were identified. Along these pathways, an overview of EA application areas was derived from the empirical and theoretical findings. With the aim of supporting practitioners in data-driven business model innovation, this thesis was concerned with the development of a reference model. The reference model for data-driven business model innovation provides a broad view and applies enterprise architecture, where appropriate. This thesis provides five recommendations for practitioners realizing data-driven business models that address the demand for support in data-driven business model innovation.
Limitations: Several limitations must be considered. We acknowledge the threat to validity based on the fact that the thesis was written over the span of two years. As DDBMs are an emerging phenomenon in the literature, our thoughts on the underlying concepts have also evolved. Our ideas evolved to include a wider range of literature, different terminology, and a broader empirical foundation. We have gathered and analyzed the extended literature on EA and DDBM interconnectivity. However, the selection of keywords restricts the set of results. The data stem from a limited number of organizations and industries; thus, our conceptual developments need further testing to ensure generalizability.
Future Research: This thesis suggests several fruitful research avenues. Complementing the current concepts with additional data and quantitative research methods could address the existing threats to validity. A deeper understanding of data-driven business model innovation pathways, in the light of the detailed methods per pathway, would enhance the knowledge on this topic. Future research could focus on conducting additional design cycles for the data-driven business model innovation reference model. It would be interesting to enrich the findings of this thesis with quantitative data on correlations in data-driven business model innovation and enterprise architecture support. Furthermore, investigating a single case study and exploring new application fields of enterprise architecture in the data-driven business model innovation context would benefit research and practice would benefit.
Mental health is an important factor in an individuals’ life - more than 300 million individuals suffered from depression in 2015. Online-based interventions have been developed for the treatment of various mental disorders. These types of interventions
have proven their efficacy and can lead to positive outcomes for suffering patients. During these interventions, a large amount of patient-specific data is gathered that can be utilized to increase treatment outcomes by informing decision-making processes of psychotherapists, experts in the field, and patients.
The articles included in this dissertation focus on the analysis of such data collected in digital psychological treatments by using machine learning approaches. This dissertation utilizes various machine learning methods such as Bayesian models, regularization techniques, or decision trees to predict different psychological factors, such as mood or self-esteem, dropout of patients, or treatment outcomes and costs. These models are evaluated using a variety of performance metrics, for example, receiver operating characteristics curve, root mean square error, or specialized performance metrics for Bayesian inference. These types of analyses can support decision- making for psychologists and patients, which can, in turn, lead to better recommendations and subsequently to increased outcomes for patients and simultaneously more insight about the interplay between psychological factors. The contribution of this interdisciplinary dissertation is manifold and can be classified at the intersection of Information Systems, health economics, and psychology. The analysis of user journey data has not yet been fully examined in the field of psychological research. A process for this endeavor is developed and a technical implementation is provided for the research community. The application of machine learning in this context is still in its infancy. Thus, another contribution is the exploration and application of machine learning techniques for the revelation of correlations between psychological factors or characteristics and treatment outcomes as well as their prediction. Additionally, economic factors are predicted to develop a process for treatment type recommendations. This approach can be utilized for finding the optimal treatment type for patients on an individual level considering predicted treatment outcomes and costs. By evaluating the predictive accuracy of multiple machine learning techniques based on various performance metrics, the importance of considering heterogeneity among patients’ behavior and affect is highlighted in some articles. Furthermore, the potential of machine learning-based decision support systems in clinical practice has been examined from a psychotherapists’ point of view.
Analysis of user behavior
(2020)
Online behaviors analysis consists of extracting patterns from server-logs.
The works presented here were carried out within the “mBook” project which aimed to develop indicators of the quantity and quality of the learning process of pupils from their usage of an eponymous electronic textbook for History. In this thesis, we investigate several models that adopt different points of view on the data. The studied methods are either well established in the field of pattern mining or transferred from other fields of machine learning and data-mining.
We improve the performance of archetypal analysis in large dimensions and apply it to unveil correlations between visibility time of particular objects in the e-textbook and pupils’ motivation. We present next two models based on mixtures of Markov chains. The first extracts users’weekly browsing patterns. The second is designed to process essions at a fine resolution, which is sine qua non to reveal the significance of scrolling behaviors. We also propose a new paradigm for online behaviors analysis that interprets sessions as trajectories within the page-graph. In this respect, we establish a general framework for the study of similarity measures between spatio-temporal trajectories, for which the study of sessions is a particular case. Finally, we construct two centroid-based clustering methods using neural networks and thus lay the foundations for unsupervised behaviors analysis using neural networks.
Keywords: online behaviors analysis, educational data mining, Markov models, archetypal analysis, spatio-temporal trajectories, neural network
Network analysis methods have long been used in the social sciences. About 25 years ago, these methods gained popularity in various other domains and many real-world phenomena have been modeled using networks. Well-known examples include (online) social networks, economic networks, web graphs, metabolic networks, infrastructure networks, and many more.
Technological development made it possible to store and process data on a scale not imaginable decades ago — a development that also includes network data. A particular characteristic of network data is that, unlike standard data, the objects of interest, called nodes, have relationships to (possibly all) other objects in the network. Collecting empirical data is often complicated and cumbersome, hence, the observed data are typically incomplete and might also contain other types of errors. Because of the interdependent structure of network data, these errors have a severe impact on network analysis methods.
This cumulative dissertation is about the impact of erroneous network data on centrality measures, which are methods to assess the position of an object, for example a person, with respect to all other objects in a network. Existing studies have shown that even small errors can substantially alter these positions. The impact of errors on centrality measures is typically quantified using a concept called robustness.
The articles included in this dissertation contribute to a better understanding of the robustness of centrality measures in several aspects. It is argued why the robustness needs to be estimated and a new method is proposed. This method allows researchers to estimate the robustness of a centrality measure in a specific network and can be used as a basis for decision making. The relationship between network properties and the robustness of centrality measures is analyzed. Experimental and analytical approaches show that centrality measures are often more robust in networks with a larger average degree. The study of the impact of non-random errors on the robustness suggests that centrality measures are often more robust if missing nodes are more likely to belong to the same community compared to missingness completely at random. For the development of imputation procedures based on machine learning techniques, a process for the evaluation of node embedding methods is proposed.
Online marketing, especially Paid Search Advertising, has become one of the most important paid media channels for companies to sell their products and services online. Despite being under intensive examination by a number of researchers for several years, this topic still offers interesting opportunities to contribute to the com- munity, particularly because of its large economic impact and practical relevance as well as the detailed and widely unfiltered view of consumer behavior that such marketing offers. To provide answers to some of the important questions from advertisers in this con- text, I present four papers in my thesis, in which I extend previous works on optimization topics such as click and conversion prediction. I apply and extend methods from other fields of research to specific problems in Paid Search. After a short introduction, I start with a paper in which we illustrate a new method that helps advertisers to predict conversion probabilities in Paid Search using sparse keyword- level data. We address one of the central problems in Paid search advertising, which is optimizing own investments in this channel by placing bids in keyword auctions. In many cases, evaluations and decisions are made with extremely sparse data, al- though anecdotal evidence suggests that online marketing is a typical
