Autor*innen mit den meisten Dokumenten
Auflistung nach:
Neueste Veröffentlichungen
- ZeitschriftenartikelProcess Mining for Six Sigma(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Graafmans, Teun; Turetken, Oktay; Poppelaars, Hans; Fahland, DirkProcess mining offers a set of techniques for gaining data-based insights into business processes from event logs. The literature acknowledges the potential benefits of using process mining techniques in Six Sigma-based process improvement initiatives. However, a guideline that is explicitly dedicated on how process mining can be systematically used in Six Sigma initiatives is lacking. To address this gap, the Process Mining for Six Sigma (PMSS) guideline has been developed to support organizations in systematically using process mining techniques aligned with the DMAIC (Define-Measure-Analyze-Improve-Control) model of Six Sigma. Following a design science research methodology, PMSS and its tool support have been developed iteratively in close collaboration with experts in Six Sigma and process mining, and evaluated by means of focus groups, demonstrations and interviews with industry experts. The results of the evaluations indicate that PMSS is useful as a guideline to support Six Sigma-based process improvement activities. It offers a structured guideline for practitioners by extending the DMAIC-based standard operating procedure. PMSS can help increasing the efficiency and effectiveness of Six Sigma-based process improving efforts. This work extends the body of knowledge in the fields of process mining and Six Sigma, and helps closing the gap between them. Hence, it contributes to the broad field of quality management.
- ZeitschriftenartikelMachine Learning in Business Process Monitoring: A Comparison of Deep Learning and Classical Approaches Used for Outcome Prediction(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Kratsch, Wolfgang; Manderscheid, Jonas; Röglinger, Maximilian; Seyfried, JohannesPredictive process monitoring aims at forecasting the behavior, performance, and outcomes of business processes at runtime. It helps identify problems before they occur and re-allocate resources before they are wasted. Although deep learning (DL) has yielded breakthroughs, most existing approaches build on classical machine learning (ML) techniques, particularly when it comes to outcome-oriented predictive process monitoring. This circumstance reflects a lack of understanding about which event log properties facilitate the use of DL techniques. To address this gap, the authors compared the performance of DL (i.e., simple feedforward deep neural networks and long short term memory networks) and ML techniques (i.e., random forests and support vector machines) based on five publicly available event logs. It could be observed that DL generally outperforms classical ML techniques. Moreover, three specific propositions could be inferred from further observations: First, the outperformance of DL techniques is particularly strong for logs with a high variant-to-instance ratio (i.e., many non-standard cases). Second, DL techniques perform more stably in case of imbalanced target variables, especially for logs with a high event-to-activity ratio (i.e., many loops in the control flow). Third, logs with a high activity-to-instance payload ratio (i.e., input data is predominantly generated at runtime) call for the application of long short term memory networks. Due to the purposive sampling of event logs and techniques, these findings also hold for logs outside this study.
- ZeitschriftenartikelNot All Doom and Gloom:ÿHow Energy-Intensive and Temporally Flexible Data Center Applications May Actually Promote Renewable Energy Sources (**encoding or data invalid**)(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Fridgen, Gilbert; Körner, Marc-Fabian; Walters, Steffen; Weibelzahl, MartinTo achieve a sustainable energy system, a further increase in electricity generation from renewable energy sources (RES) is imperative. However, the development and implementation of RES entail various challenges, e.g., dealing with grid stability issues due to RES? intermittency. Correspondingly, increasingly volatile and even negative electricity prices question the economic viability of RES-plants. To address these challenges, this paper analyzes how the integration of an RES-plant and a computationally intensive, energy-consuming data center (DC) can promote investments in RES-plants. An optimization model is developed that calculates the net present value (NPV) of an integrated energy system (IES) comprising an RES-plant and a DC, where the DC may directly consume electricity from the RES-plant. To gain applicable knowledge, this paper evaluates the developed model by means of two use-cases with real-world data, namely AWS computing instances for training Machine Learning algorithms and Bitcoin mining as relevant DCÿapplications. The results illustrate that for both cases the NPV of the IES compared to a stand-alone RES-plant increases, which may lead to a promotion of RES-plants. The evaluation also finds that the IES may be able to provide significant energy flexibility that can be used to stabilize the electricity grid. Finally, the IES may also help to reduce the carbon-footprint of new energy-intensive DC applications by directly consuming electricity from RES-plants. (**encoding or data invalid**)
- ZeitschriftenartikelInterview with Rainer Hoffmann on ?The Transformation Towards Artificial Intelligence of Electric Utilities??(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Staudt, Philipp
- ZeitschriftenartikelChanging the Climate in Information Systems Research(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Lehnhoff, Sebastian; Staudt, Philipp; Watson, Richard T.
- ZeitschriftenartikelVirtual Sensors(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Martin, Dominik; Kühl, Niklas; Satzger, Gerhard
- ZeitschriftenartikelBenchmarking Energy Quantification Methods to Predict Heating Energy Performance of Residential Buildings in Germany(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Wenninger, Simon; Wiethe, ChristianTo achieve ambitious climate goals, it is necessary to increase the rate of purposeful retrofit measures in the building sector. As a result, Energy Performance Certificates have been designed as important evaluation and rating criterion to increase the retrofit rate in the EU and Germany. Yet, today?s most frequently used and legally required methods to quantify building energy performance show low prediction accuracy, as recent research reveals. To enhance prediction accuracy, the research community introduced data-driven methods which obtained promising results. However, there are no insights in how far Energy Quantification Methods are particularly suited for energy performance prediction. In this research article the data-driven methods Artificial Neural Network, D-vine copula quantile regression, Extreme Gradient Boosting, Random Forest, and Support Vector Regression are compared with and validated by real-world Energy Performance Certificates of German residential buildings issued by qualified auditors using the engineering method required by law. The results, tested for robustness and systematic bias, show that all data-driven methods exceed the engineering method by almost 50% in terms of prediction accuracy. In contrast to existing literature favoring Artificial Neural Networks and Support Vector Regression, all tested methods show similar prediction accuracy with marginal advantages for Extreme Gradient Boosting and Support Vector Regression in terms of prediction accuracy. Given the higher prediction accuracy of data-driven methods, it seems appropriate to revise the current legislation prescribing engineering methods. In addition, data-driven methods could support different organizations, e.g., asset management, in decision-making in order to reduce financial risk and to cut expenses.
- ZeitschriftenartikelRobotic Process Mining: Vision and Challenges(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Leno, Volodymyr; Polyvyanyy, Artem; Dumas, Marlon; La Rosa, Marcello; Maggi, Fabrizio MariaRobotic process automation (RPA) is an emerging technology that allows organizations automating repetitive clerical tasks by executing scripts that encode sequences of fine-grained interactions with Web and desktop applications. Examples of clerical tasks include opening a file, selecting a field in a Web form or a cell in a spreadsheet, and copy-pasting data across fields or cells. Given that RPA canÿautomate a wide range of routines, thisÿraises the question of which routines should be automated in the first place. This paper presents a vision towards a family of techniques, termed robotic process mining (RPM), aimed at filling this gap. The core idea of RPM is that repetitive routines amenable for automation can be discovered from logs of interactions between workers and Web and desktop applications, also known as user interactions (UI) logs. The paper defines a set of basic concepts underpinning RPM and presents a pipeline of processing steps that would allow an RPM tool to generate RPA scripts from UI logs. The paper also discusses research challenges to realize the envisioned pipeline. (**encoding or data invalid**)