The literature contains very few publications on the application of Process Mining methods for the analysis of event logs in Enterprise Collaboration Systems (ECS). This is not surprising because the analysis of digital support for collaborative work is extremely intricate due to various challenges relating to a lack of data access, poor data quality, unstructured processes and a lack of descriptive models. This article reports on the findings from an Action Design Research (ADR) project. The ADR team had access to a large instance of an operational ECS with more than 3000 users. The event log contains several million entries. Together with the platform’s operating team, intensive research was carried out over a period of six years on ways of analysing user activities on the platform. Several cycles were run to develop new methods and computational techniques to decipher the event logs and meaningfully describe the processes recorded in them. Thanks to the close collaboration between the researchers and the operators of the collaboration platform, it was possible to compare the real-world processes carried out in the platform with the processes discovered using a novel method for Social Process Mining (SPM). The result is a pattern analysis that discovers patterns in processes that have a high degree of correspondence with the real-world scenes of collaborative work. The research work has now reached a point where other software products are included (multi-system analysis) and a catalogue of collaborative work situations (scenes) has been developed to describe the process patterns that result from the Process Mining and graph-based analysis techniques.

Künstliche Intelligenz (KI) hat sich in den letzten Jahren in der Gesellschaft stark ver-breitet und auch in Unternehmen einen zunehmenden Einsatz gefunden. Bekannt für den Einsatz sind meistens große internationale Konzerne, welche eine führende Position in den Märkten einnehmen. Um Deutschland als KI-Standort zu stärken, hat deshalb die Bundesregierung 2018 beschlossen, mit 5 Milliarden Euro deutsche Unternehmen in der Verwendung von KI zu fördern. Stand September 2021 wurden von diesen allerdings nur 346 Millionen abgerufen, wodurch sich die Frage stellt, wie besonders kleine und mittlere Unternehmen (KMUs) in Deutschland mit dem Thema KI umgehen. Ziel dieser Arbeit ist es deshalb, die Perspektive der KMUs auf Akzeptanzkriterien, Hindernisse und Potenziale des Einsatzes von KI zu untersuchen. Um die Forschungs-fragen zu beantworten, wurde eine qualitative Interviewstudie mit fünf KMUs durchge-führt, welche im Anschluss mit dem Ansatz der qualitativen Inhaltsanalyse nach May-ring ausgewertet wurde. Die Arbeit zeigt, dass Unternehmen ein großes Interesse am Thema KI haben und sich der Einsatz immer weiter verbreitet. KMUs sehen viel Potenzial durch den Einsatz der neuen Technologie, sehen aber noch einige Hindernisse, die es zu überwinden gilt.

Efficient Cochlear Implant (CI) surgery requires prior knowledge of the cochlea’s size and its characteristics. This information helps to select suitable implants for different patients. Registered and fused images helps doctors by providing more informative image that takes advantages of different modalities. The cochlea’s small size and complex structure, in addition to the different resolutions and head positions during imaging, reveals a big challenge for the automated registration of the different image modalities. To obtain an automatic measurement of the cochlea length and the volume size, a segmentation method of cochlea medical images is needed. The goal of this dissertation is to introduce new practical and automatic algorithms for the human cochlea multi-modal 3D image registration, fusion, segmentation and analysis. Two novel methods for automatic cochlea image registration (ACIR) and automatic cochlea analysis (ACA) are introduced. The proposed methods crop the input images to the cochlea part and then align the cropped images to obtain the optimal transformation. After that, this transformation is used to align the original images. ACIR and ACA use Mattes mutual information as similarity metric, the adaptive stochastic gradient descent (ASGD) or the stochastic limited memory Broyden–Fletcher–Goldfarb–Shanno (s-LBFGS) optimizer to estimate the parameters of 3D rigid transform. The second stage of nonrigid registration estimates B-spline coefficients that are used in an atlas-model-based segmentation to extract cochlea scalae and the relative measurements of the input image. The image which has segmentation is aligned to the input image to obtain the non-rigid transformation. After that the segmentation of the first image, in addition to point-models are transformed to the input image. The detailed transformed segmentation provides the scala volume size. Using the transformed point-models, the A-value, the central scala lengths, the lateral and the organ of corti scala tympani lengths are computed. The methods have been tested using clinical 3D images of total 67 patients: from Germany (41 patients) and Egypt (26 patients). The atients are of different ages and gender. The number of images used in the experiments is 217, which are multi-modal 3D clinical images from CT, CBCT, and MRI scanners. The proposed methods are compared to the state of the arts ptimizers related medical image registration methods e.g. fast adaptive stochastic gradient descent (FASGD) and efficient preconditioned tochastic gradient descent (EPSGD). The comparison used the root mean squared distance (RMSE) between the ground truth landmarks and the resulted landmarks. The landmarks are located manually by two experts to represent the round window and the top of the cochlea. After obtaining the transformation using ACIR, the landmarks of the moving image are transformed using the resulted transformation and RMSE of the transformed landmarks, and at the same time the fixed image landmarks are computed. I also used the active length of the cochlea implant electrodes to compute the error aroused by the image artifact, and I found out an error ranged from 0.5 mm to 1.12 mm. ACIR method’s RMSE average was 0.36 mm with a standard deviation (SD) of 0.17 mm. The total time average required for registration of an image pair using ACIR was 4.62 seconds with SD of 1.19 seconds. All experiments are repeated 3 times for justifications. Comparing the RMSE of ACIR2017 and ACIR2020 using paired T-test shows no significant difference (p-value = 0.17). The total RMSE average of ACA method was 0.61 mm with a SD of 0.22 mm. The total time average required for analysing an image was 5.21 seconds with SD of 0.93 seconds. The statistical tests show that there is no difference between the results from automatic A-value method and the manual A-value method (p-value = 0.42). There is no difference also between length’s measurements of the left and the right ear sides (p-value > 0.16). Comparing the results from German and Egypt dataset shows there is no difference when using manual or automatic A-value methods (p-value > 0.20). However, there is a significant difference when using ACA2000 method between the German and the Egyptian results (p-value < 0.001). The average time to obtain the segmentation and all measurements was 5.21 second per image. The cochlea scala tympani volume size ranged from 38.98 mm3 to 57.67 mm3 . The combined scala media and scala vestibuli volume size ranged from 34.98 mm 3 to 49.3 mm 3 . The overall volume size of the cochlea should range from 73.96 mm 3 to 106.97 mm 3 . The lateral wall length of scala tympani ranged from 42.93 mm to 47.19 mm. The organ-of-Corti length of scala tympani ranged from 31.11 mm to 34.08 mm. Using the A-value method, the lateral length of scala tympani ranged from 36.69 mm to 45.91 mm. The organ-of-Corti length of scala tympani ranged from 29.12 mm to 39.05 mm. The length from ACA2020 method can be visualised and has a well-defined endpoints. The ACA2020 method works on different modalities and different images despite the noise level or the resolution. In the other hand, the A-value method works neither on MRI nor noisy images. Hence, ACA2020 method may provide more reliable and accurate measurement than the A-value method. The source-code and the datasets are made publicly available to help reproduction and validation of my result.

Der Industriestandard Decision Model and Notation (DMN) ermöglicht seit 2015 eine neue Art der Formalisierung von Geschäftsregeln. Hier werden Regeln in sogenannten Entscheidungstabellen modelliert, die durch Eingabespalten und Ausgabespalten definiert sind. Zudem sind Entscheidungen in graphartigen Strukturen angeordnet (DRD Ebene), die Abhängigkeiten unter diesen erzeugen. Nun können, mit gegebenen Input, Entscheidungen von geeigneten Systemen angefragt werden. Aktivierte Regeln produzieren dabei einen Output für die zukünftige Verwendung. Jedoch erzeugen Fehler während der Modellierung fehlerhafte Modelle, die sowohl in den Entscheidungstabellen als auch auf der DRD Ebene auftreten können. Nach der Design Science Research Methodology fokus\-siert diese Arbeit eine Implementierung eines Verifikationsprototyps für die Erkennung und Lösung dieser Fehler während der Modellierungsphase. Die vorgestellten Grundlagen liefern die notwendigen theoretischen Grundlagen für die Entwicklung des Tools. Diese Arbeit stellt außerdem die Architektur des Werkzeugs und die implementierten Verifikationsfähigkeiten vor. Abschließend wird der erstellte Prototyp evaluiert.

Business Process Querying (BPQ) is a discipline in the field of Business Process Man- agement which helps experts to understand existing process models and accelerates the development of new ones. Its queries can fetch and merge these models, answer questions regarding the underlying process, and conduct compliance checking in return. Many languages have been deployed in this discipline but two language types are dominant: Logic-based languages use temporal logic to verify models as finite state machines whereas graph-based languages use pattern matching to retrieve subgraphs of model graphs directly. This thesis aims to map the features of both language types to features of the other to identify strengths and weaknesses. Exemplarily, the features of Computational Tree Logic (CTL) and The Diagramed Modeling Language (DMQL) are mapped to one another. CTL explores the valid state space and thus is better for behavioral querying. Lacking certain structural features and counting mechanisms it is not appropriate to query structural properties. In contrast, DMQL issues structural queries and its patterns can reconstruct any CTL formula. However, they do not always achieve exactly the same semantic: Patterns treat conditional flow as sequential flow by ignoring its conditions. As a result, retrieved mappings are invalid process execution sequences, i.e. false positives, in certain scenarios. DMQL can be used for behavioral querying if these are absent or acceptable. In conclusion, both language types have strengths and are specialized for different BPQ use cases but in certain scenarios graph-based languages can be applied to both. Integrating the evaluation of conditions would remove the need for logic-based languages in BPQ completely.