000 Informatik, Informationswissenschaft, allgemeine Werke
Refine
Document Type
- Article (49)
- Other (24)
- Doctoral Thesis (2)
- Review (2)
- Monograph/Edited Volume (1)
- Conference Proceeding (1)
- Postprint (1)
Is part of the Bibliography
- yes (80)
Keywords
- performance (3)
- run time analysis (3)
- theory (3)
- Algorithms (2)
- BIM (2)
- Big Data (2)
- Machine learning (2)
- data profiling (2)
- fabrication (2)
- genetic programming (2)
Institute
- Hasso-Plattner-Institut für Digital Engineering gGmbH (80) (remove)
Ubiquitous computing has proven its relevance and efficiency in improving the user experience across a myriad of situations. It is now the ineluctable solution to keep pace with the ever-changing environments in which current systems operate. Despite the achievements of ubiquitous computing, this discipline is still overlooked in business process management. This is surprising, since many of today’s challenges, in this domain, can be addressed by methods and techniques from ubiquitous computing, for instance user context and dynamic aspects of resource locations. This paper takes a first step to integrate methods and techniques from ubiquitous computing in business process management. To do so, we propose discovering commute patterns via process mining. Through our proposition, we can deduce the users’ significant locations, routes, travel times and travel modes. This information can be a stepping-stone toward helping the business process management community embrace the latest achievements in ubiquitous computing, mainly in location-based service. To corroborate our claims, a user study was conducted. The significant places, routes, travel modes and commuting times of our test subjects were inferred with high accuracies. All in all, ubiquitous computing can enrich the processes with new capabilities that go beyond what has been established in business process management so far.
Evaluating creativity of verbal responses or texts is a challenging task due to psychometric issues associated with subjective ratings and the peculiarities of textual data. We explore an approach to objectively assess the creativity of responses in a sentence generation task to 1) better understand what language-related aspects are valued by human raters and 2) further advance the developments toward automating creativity evaluations. Over the course of two prior studies, participants generated 989 four-word sentences based on a four-letter prompt with the instruction to be creative. We developed an algorithm that scores each sentence on eight different metrics including 1) general word infrequency, 2) word combination infrequency, 3) context-specific word uniqueness, 4) syntax uniqueness, 5) rhyme, 6) phonetic similarity, and similarity of 7) sequence spelling and 8) semantic meaning to the cue. The text metrics were then used to explain the averaged creativity ratings of eight human raters. We found six metrics to be significantly correlated with the human ratings, explaining a total of 16% of their variance. We conclude that the creative impression of sentences is partly driven by different aspects of novelty in word choice and syntax, as well as rhythm and sound, which are amenable to objective assessment.
Generating a novel and descriptive caption of an image is drawing increasing interests in computer vision, natural language processing, and multimedia communities. In this work, we propose an end-to-end trainable deep bidirectional LSTM (Bi-LSTM (Long Short-Term Memory)) model to address the problem. By combining a deep convolutional neural network (CNN) and two separate LSTM networks, our model is capable of learning long-term visual-language interactions by making use of history and future context information at high-level semantic space. We also explore deep multimodal bidirectional models, in which we increase the depth of nonlinearity transition in different ways to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, multi-scale, and vertical mirror are proposed to prevent over-fitting in training deep models. To understand how our models "translate" image to sentence, we visualize and qualitatively analyze the evolution of Bi-LSTM internal states over time. The effectiveness and generality of proposed models are evaluated on four benchmark datasets: Flickr8K, Flickr30K, MSCOCO, and Pascal1K datasets. We demonstrate that Bi-LSTM models achieve highly competitive performance on both caption generation and image-sentence retrieval even without integrating an additional mechanism (e.g., object detection, attention model). Our experiments also prove that multi-task learning is beneficial to increase model generality and gain performance. We also demonstrate the performance of transfer learning of the Bi-LSTM model significantly outperforms previous methods on the Pascal1K dataset.
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.
Interactive Close-Up Rendering for Detail plus Overview Visualization of 3D Digital Terrain Models
(2019)
This paper presents an interactive rendering technique for detail+overview visualization of 3D digital terrain models using interactive close-ups. A close-up is an alternative presentation of input data varying with respect to geometrical scale, mapping, appearance, as well as Level-of-Detail (LOD) and Level-of-Abstraction (LOA) used. The presented 3D close-up approach enables in-situ comparison of multiple Regionof-Interests (ROIs) simultaneously. We describe a GPU-based rendering technique for the image-synthesis of multiple close-ups in real-time.
A fundamental task in 3D geovisualization and GIS applications is the visualization of vector data that can represent features such as transportation networks or land use coverage. Mapping or draping vector data represented by geometric primitives (e.g., polylines or polygons) to 3D digital elevation or 3D digital terrain models is a challenging task. We present an interactive GPU-based approach that performs geometry-based draping of vector data on per-frame basis using an image-based representation of a 3D digital elevation or terrain model only.
Mary, Hugo, and Hugo*
(2020)
Distributed data-parallel processing systems like MapReduce, Spark, and Flink are popular for analyzing large datasets using cluster resources. Resource management systems like YARN or Mesos in turn allow multiple data-parallel processing jobs to share cluster resources in temporary containers. Often, the containers do not isolate resource usage to achieve high degrees of overall resource utilization despite overprovisioning and the often fluctuating utilization of specific jobs. However, some combinations of jobs utilize resources better and interfere less with each other when running on the same shared nodes than others. This article presents an approach for improving the resource utilization and job throughput when scheduling recurring distributed data-parallel processing jobs in shared clusters. The approach is based on reinforcement learning and a measure of co-location goodness to have cluster schedulers learn over time which jobs are best executed together on shared resources. We evaluated this approach over the last years with three prototype schedulers that build on each other: Mary, Hugo, and Hugo*. For the evaluation we used exemplary Flink and Spark jobs from different application domains and clusters of commodity nodes managed by YARN. The results of these experiments show that our approach can increase resource utilization and job throughput significantly.
Cloud Storage Broker (CSB) provides value-added cloud storage service for enterprise usage by leveraging multi-cloud storage architecture. However, it raises several challenges for managing resources and its access control in multiple Cloud Service Providers (CSPs) for authorized CSB stakeholders. In this paper we propose unified cloud access control model that provides the abstraction of CSP's services for centralized and automated cloud resource and access control management in multiple CSPs. Our proposal offers role-based access control for CSB stakeholders to access cloud resources by assigning necessary privileges and access control list for cloud resources and CSB stakeholders, respectively, following privilege separation concept and least privilege principle. We implement our unified model in a CSB system called CloudRAID for Business (CfB) with the evaluation result shows it provides system-and-cloud level security service for cfB and centralized resource and access control management in multiple CSPs.
The rapid digitalization of the Facility Management (FM) sector has increased the demand for mobile, interactive analytics approaches concerning the operational state of a building. These approaches provide the key to increasing stakeholder engagement associated with Operation and Maintenance (O&M) procedures of living and working areas, buildings, and other built environment spaces. We present a generic and fast approach to process and analyze given 3D point clouds of typical indoor office spaces to create corresponding up-to-date approximations of classified segments and object-based 3D models that can be used to analyze, record and highlight changes of spatial configurations. The approach is based on machine-learning methods used to classify the scanned 3D point cloud data using 2D images. This approach can be used to primarily track changes of objects over time for comparison, allowing for routine classification, and presentation of results used for decision making. We specifically focus on classification, segmentation, and reconstruction of multiple different object types in a 3D point-cloud scene. We present our current research and describe the implementation of these technologies as a web-based application using a services-oriented methodology.