The emerging concept of multidimensional process mining adopts the ideas of data cubes and OLAP to analyze processes from multiple views. Analysts can split the event log into a set of homogenous sublogs according to its case and event attributes. Process mining techniques are used to create an individual process model for each sublog representing variants of the process. These models can be compared to identify the differences between the variants. Due to the explorative character of the analysis, interactivity is crucial to successfully apply multidimensional process mining. However, current approaches lack interactivity, e.g., they require the analyst to re-perform the analysis steps after changing the view on the data cube. In this paper, we introduce a novel framework to improve the interactivity of multidimensional process mining. As our main contribution, we provide a generic concept for interactive process mining based on a stack of operations.

Multidimensional process mining adopts the concept of data cubes to split event data into a set of homogenous sublogs according to case and event attributes. For each sublog, a separated process model is discovered and compared to other models to identify group-specific differences for the process. For an effective explorative process analysis, performance is vital due to the explorative characteristics of the analysis. We propose to adopt well-established approaches from the data warehouse domain based on relational databases to provide acceptable performance. In this paper, we present the underlying relational concepts of PMCube, a data-warehouse-based approach for multidimensional process mining. Based on a relational database schema, we introduce generic query patterns which map OLAP queries onto SQL to push the operations (i.e. aggregation and filtering) to the database management system. We evaluate the run-time behavior of our approach by a number of experiments. The results show that our approach provides a significantly better performance than the state-of-the-art for multidimensional process mining and scales up linearly with the number of events.

Local energy management and demand response are established methods to raise energy efficiency, to lower the costs for energy supply, and even to help stabilizing the grid. With the emergence of E-Mobility in industrial enterprises the intelligent use of power demand draws significantly increased importance. Due to the time lag of actual energy usage by the vehicles and the energy demand from the grid for charging the batteries of these vehicles new possibilities for load shifting arise. These can be used to optimize the local energy demand curve, to react to RTP-pricing or to offer services to the grid like providing control reserve power. Support of information technology on consumer side is required to effectively make use of these possibilities. Based on a case study of the maritime container terminal altenwerder located in Hamburg and in reference to the electricity market reference architecture a software application is presented that extends the energy management of a flexible consumer with intelligent functions to control the energy demand.

Networked activity trackers have become an important tool for assessing physical activity, as part of behavior change interventions, within epidemiological studies, or driven by personal interest. However the use of activity trackers is often abandoned after a few months, and their effect on health behavior is unclear. We conducted a longitudinal study observing the use of activity trackers by 34 patients recovering from a myocardial infarction. The patients used the tracker continuously for up to more than one year. We observe two usage patterns: Regular use on some but not all days per week is observed for all patients and remains consistent during the usage period. Uninterrupted use on many successive days is observed for some patients only, happens only once per patient, and mostly at the beginning of the use. We hypothesize that the activity tracker is particularly used as a motivational tool by objectively measuring one's physical activity, and only some people use it as a tool for learning one's behavior .

Machine Condition Monitoring (MCM) is an important topic for the reliability of industrial machines in increasingly interconnected production facilities. The analysis of a huge amount of data to get information about the machine's condition is a difficult challenge. Current solutions for these analyses are often very specific, need a lot of manual configuration or are difficult to apply. In this paper, we present a system that uses anomaly detection in data streams to find hints for faulty machines in the data. The basis of this system is a Data stream management system (DSMS), which can handle huge amounts of streaming data and simplifies the definition of analyses. Due to the anomaly detection algorithms, the approach can be applied to a variety of data and scenarios. The outcome is a system that allows live analysis of machine data for MCM.

Multidimensional process mining is an emerging approach that adopts the concept of data cubes to analyze processes from multi- ple views. This enables analysts to split event logs into a set of homoge- nous sublogs according to the case and event attributes. Each sublog is independently analyzed using process mining techniques resulting in an individual process model for each sublog. These models can be compared to identify group-related differences between the process variants. In this paper, we derive a number of general research questions addressed for multidimensional process mining by a literature review. We analyze the requirements for its application and point out its limitations and chal- lenges. We conduct two case studies applying multidimensional process mining in two different use cases to evaluate our findings.

Process mining provides a set of techniques to discover process models from recorded event data or to analyze and improve given process models. Typically, these techniques give a single point of view on the process. However, some domains need to differentiate the process according to the characteristic features of their cases. The healthcare domain, for example, needs to distinguish between different groups of patients, defined by the patients’ properties like age or gender, to get more precise insights into the treatment process. The emerging concept of multidimensional process mining aims to overcome this gap by the notion of data cubes that can be used to spread data over multiple cells. This paper introduces PMCube, a novel approach for multidimensional process mining based on the multidimensional modeling of event logs that can be queried by OLAP operators to mine sophisticated process models. An optional step of consolidation allows to reduce the complexity of results to ease its interpretation. We implemented this approach in a prototype and applied it in a case study to analyze the perioperative processes in a large German hospital.

The geopolitical dependency on oil and gas, looming threats of climate change, social and environmental costs of mining, or the prospect to address business opportunities in a large and growingmarket—there aremany reasons to redress our fossil-based energy systems. In fact, energy topics have become a top priority of our society, and decision makers around the world have committed themselves to ambitious development targets towards a sustainable energy supply and use. To attain this goal, two dominant, complementary paths are treaded: the expansion of renewable energy sources and improvements in energy efficiency across all sectors. Both

Conventional database management systems are usually not capable to deal with continuous processing of potentially infinite data streams. Therefore, special data stream management systems and frameworks are developed. They use continuous queries which produce also streams as results, so that static visualization is not feasible, since the results are changing constantly. To handle this, we developed a dashboard concept, which we want to propose in this demonstration. A dashboard can be considered as an control or monitoring panel for real time data stream results. The user is free to define and configure individual dashboard parts. Each part is connected to a (user defined) continuous query, whose results are received and visualized in real-time. In this demonstration, we provide different data stream sources, continuous queries and dashboard parts. With them, the user can compose his own individual presentation of his processing results.

Process mining techniques allow process analysts to generate process models from recorded event logs. Typically, process mining considers the event log as a whole and creates a single model reflecting its behavior. However, the process may be influenced by several characteristics of the process instances, e.g., by the individual characteristics of a patient in the healthcare domain like age and sex. This leads to a wide range of process variations which can end up in complex and confusing models, blurring the behavior of specific process variants. Multidimensional process mining (MPM) aims to overcome this limitation by the notion of data cubes, spreading the data over multiple cells, each representing a group of cases with similar characteristics. This allows for the creation of separated process models for a homogenous set of cases. In this paper, we introduce PMCube Explorer, a novel tool for MPM, that allows for the analysis of a process from various views. It enables the analyst to specify OLAP queries to extract multiple cells from the data warehouse. Each cell contains a subset of event data which are mined separately to discover independent process models. To deal with the potentially high amount of resulting models, our tool provides some distinctive features like the visualization of model differences or the consolidation of multiple process models. We applied our tool in a case study to analyze the perioperative processes in a large German hospital.

Process mining automatically generates process models from event logs. In multidimensional process mining, these models can be analyzed from various viewpoints by clustering event traces according to their attributes, e.g. age or region of the patient for a healthcare process. For each cluster, a distinct process model is calculated. Since these models are supposed to be identical in most parts, differences between them are hard to spot. Therefore, a tool for emphasizing these differences is needed. To face the different challenges presented by multidimensional process mining like the representational bias, such an approach has to be customizable to support different modeling languages and different layout and differencing algorithms. This paper presents a generic approach to calculate and visualize differences between process models which can be used to compare models in multidimensional process mining.

Tactical decisions profoundly characterize team sports like soccer or basketball. Analyses of matches and training sessions (e.g., mileage or pass completion rate of a player) become more and more important for those tactical decisions. Most of the analyses are video-based, resulting in high operating expenses. Additionally, a highly specialized system with a huge amount of system resources like processors and memory is needed. Typically, analysts present the results of the video data analysis in time-outs (e.g., in the half-time break of a soccer match). However, coaches often desire to view statistics in real-time during the match. In this paper, we demonstrate Herakles , a system for live sport analysis using streaming sensor data and a Peer-to-Peer network of conventional and low-cost private machines. Since sensor data is typically of high volume and velocity, Herakles uses OdysseusP2P , a distributed data stream management system, for processing these streams in real-time. Since the results of the data stream processing are intended for coaches, the front-end of Herakles is an application for mobile devices like smartphones or tablets. With Herakles, a coach is able to view individual sport statistics during the game at the sideline to make immediate tactical decisions.

The development of algorithms for online Collaborative Filtering (CF) in the past few years enables to add new rating data to existing models. The Recommender System (RecSys) task changes from calculating recommendations from a static and finite dataset to continuously processing rating data. Instead of using stream processing frameworks to implement CF algorithms, we present a prototype that extends the open source Data Stream Management System (DSMS) Odysseus in a generic and domain-independent way. The user can build a custom RecSys that benefits from existing DSMS features by defining a continuous query with a declarative query language.

From our ongoing project, we present the collected requirements and business drivers from the energy industry imposed upon analytical information systems, specifically in the case of a contribution margin control as part of electricity trading. As a solution, we introduce our architecture for business intelligence in the cloud and apply these in the afore mentioned use case in the form of a research prototype. We provide the current implementation status at an early stage, on one hand to increase the transparency of the still young field of business intelligence in the cloud, and on the other hand to demonstrate the development potential of the technology for the energy sector.

In dieser Arbeit wird eine exible, erweiterbare und dom an-enunbh angige Integration von Online-RecSys-Funktionen inein Datenstrommanagementsystem (DSMS) vorgestellt. Da-zu werden neue logische Operatoren eingef uhrt, mit der Nut-zer eines DSMS auf einer abstrakten Ebene RecSys-Funk-tionen nutzen k onnen. Des Weiteren wird eine beispielhafteRealisierung durch physische Operatoren vorgestellt, wie sieaus den logischen Operatoren durch Transformationsregelnerzeugt werden kann. Durch dieses Konzept k onnen Benut-zer ein RecSys mit Hilfe einer Anfragesprache auf die do-m anenspezi schen Bed urfnisse anpassen und mit anderenFunktionen eines DSMS kombinieren. Des Weiteren bringtein DSMS einige Eigenschaften (z.B. Anfrageplanoptimie-rung, Fragmentierung, Scheduling etc.) mit, von denen einOnline-RecSys pro tieren kann. Die Flexibilit at eines DSMSerm oglicht den Vergleich und die Evaluation verschiedenerRecSys-Algorithmen durch den Benutzer.

Recommender-Systeme (RecSys) findet man in vielen Informationssystemen. Das Ziel eines RecSys ist das Interesse eines Benutzers an bestimmten Objekten (engl. item) vorherzusagen, um aus einer grosen Menge an Objekten diejenigen dem Benutzer zu empfehlen, fur die das vorhergesagte Interesse des Benutzers am grosten ist. Die zu empfehlenden Objekte konnen zum Beispiel Produkte, Filme/Videos, Musikstucke, Dokumente, Point of Interests etc. sein. Das Interesse eines Benutzers an einem Objekt wird durch eine Bewertung (engl. rating) quantifiziert. Die Bewertung kann explizit durch den Benutzer angegeben (der Benutzer wird dazu aufgefordert, ein bestimmtes Objekt zu bewerten) oder implizit vom Verhalten des Benutzers abgeleitet werden (im einfachsten Fall durch eine binare Bewertung: Objekt genutzt vs. nicht genutzt). Mit Methoden des maschinellen Lernens wird aus bekannten Bewertungen ein Modell trainiert, dass unbekannte Bewertungen vorhersagen kann. Fur die Bestimmung der Empfehlungsmenge werden die Bewertungen aller unbewerteten Objekte fur einen Benutzer vorhergesagt und die best-bewerteten Objekte empfohlen.

Überlast bedeutet, dass an ein System mehr Anforderungen gestellt werden, als es erfüllen kann. Im schlechtesten Fall ist es nicht mehr ansprechbar oder stürzt ab. Für Datenbankmanagementsysteme (DBMS) existiert eine spezielle Komponente, Admission Control (AC) genannt, welche die Systemlast überwacht, eintreffende Anfragen vor deren Ausführung überprüft und ggfs. zurückstellt. Für kontinuierliche Anfragen, welche permanent ausgeführt werden, reicht diese Art von AC jedoch nicht aus: Es kann zur Konfliktlösung nicht mehr auf die Terminierung einer Anfrage gewartet werden. Zudem ist die Verarbeitung datengetrieben, d. h. Umfang und Inhalt der Daten können stark variieren. Diese Arbeit stellt ein Konzept vor, wie eine flexible und anpassbare AC-Komponente für kontinuierliche Anfragen auf Basis eines Event-Condition-Action-Modells (ECA) umgesetzt werden kann. Zur Regeldefinition wird die einfache Sprache CADL vorgestellt, die eine hohe Flexibilität und Anpassbarkeit der kontinuierlichen AC an konkrete Systeme und Hardware erlaubt. Die Evaluation zeigt mittels Odysseus, einem Framework für Datenstrommanagementsysteme, dass das Konzept effizient funktioniert und effektiv zur Lastkontrolle und Ergreifung von Maßnahmen zur Lastreduktion eingesetzt werden kann.

Für die Verteilung kontinuierlicher Anfragen in verteilten Datenstrommanagementsystemen gibt es je nach Netzwerkarchitektur und Anwendungsfall unterschiedliche Strategien. Es ist u.U. nachteilig, sich auf eine Strategie festzulegen, besonders wenn sich Netzwerkarchitektur oder Anwendungsfall ändern. In dieser Arbeit wird ein Ansatz für eine flexible und erweiterbare Anfrageverteilung in verteilten Datenstrommanagementsystemen vorgestellt. Der Ansatz umfasst drei Schritte: 1) Partitionierung, 2) Modifikation und 3) Allokation. Bei der Partitionierung wird eine kontinuierliche Anfrage in disjunkte Teilanfragen zerlegt. Die optionale Modifikation erlaubt es, Mechanismen wie Fragmentierung oder Replikation zu verwenden. Bei der Allokation werden die einzelnen Teilanfragen schließlich Knoten im Netzwerk zugewiesen, um dort ausgeführt zu werden.