Stefan Luettgen's research while affiliated with Technische Universität Darmstadt and other places

Publications (8)

Conference Paper
In process mining, many tasks use a simplified representation of a single case to perform tasks like trace clustering, anomaly detection, or subset identification. These representations may capture the control flow of the process as well as the context a case is executed in. However, most of these representations are hand-crafted, which is very tim...
Chapter
The execution of a business process is often determined by the surrounding context, e.g., department, product, or other attributes an event provides. Process discovery mainly focuses on the executed activities, although the context of a case may be needed to accurately represent a process instance, e.g., for clustering, prediction, or anomaly detec...
Preprint
Full-text available
The execution of a business process is often determined by the surrounding context, e.g., department, product, or other attributes an event provides. Process discovery mainly focuses on the executed activities , although the context of a case may be needed to accurately represent a process instance, e.g., for clustering, prediction, or anomaly dete...
Article
In this paper, we introduce BINet, a neural network architecture for real-time multi-perspective anomaly detection in business process event logs. BINet is designed to handle both the control flow and the data perspective of a business process. Additionally, we propose a set of heuristics for setting the threshold of an anomaly detection algorithm...
Preprint
Full-text available
In this paper, we introduce BINet, a neural network architecture for real-time multi-perspective anomaly detection in business process event logs. BINet is designed to handle both the control flow and the data perspective of a business process. Additionally, we propose a set of heuristics for setting the threshold of an anomaly detection algorithm...
Article
Full-text available
Businesses are naturally interested in detecting anomalies in their internal processes, because these can be indicators for fraud and inefficiencies. Within the domain of business intelligence, classic anomaly detection is not very frequently researched. In this paper, we propose a method, using autoencoders, for detecting and analyzing anomalies o...
Article
Full-text available
Manipulation tasks often require robots to recognize interactions between objects. For example, a robot may need to determine if it has grasped an object properly or if one object is resting on another in a stable manner. These interactions usually depend on the contacts between the objects, with different distributions of contacts affording differ...

Citations

... They conducted comparative experiments using the K-means algorithm, and in their study, the four proposed embedding methods showed improved performance relative to other embedding methods. In studies applying deep learning to process mining domains, the vectorized embedding method of de Koninck, Vanden Broucke, and De Weerdt [34] has been widely used [35]- [37]. Ni [35] performed a study that automatically recommended the medical procedure best suited to a patient's condition. ...
... The deviation of a trace is determined using the error the autoencoder makes in predicting the trace. [14] further develops the application of neural networks to event data by training a recurrent neural network to predict the next event in integer-encoding based on the current event in a trace. The aggregate likelihood of predicting the correct events is used to detect deviations. ...
... Process-agnostic and non-interpretable. [13] encodes traces in event data using one-hot encoding and train autoencoder neural network with them. The deviation of a trace is determined using the error the autoencoder makes in predicting the trace. ...
... Deep reinforcement learning (RL) has witnessed remarkable progress over the last years, particularly in domains such as video games or other synthetic toy settings [1][2][3]. On the other hand, applying deep RL on real-world grounded robotic setup such as learning seemingly simple dexterous manipulation tasks in multi-object settings is still confronted with many fundamental limitations being the focus of many recent works [4][5][6][7][8][9][10][11]. The reinforcement learning problem in robotics setups is much more challenging [12]. ...
... 3. This paper builds on two previous conference papers on contact kernels (Kroemer and Peters 2014;Leischnig et al. 2015). In this paper, we extend our research to using the kernel in a clustering framework. ...