Refine
Has Fulltext
- no (30)
Document Type
- Conference Proceeding (11)
- Part of a Book (8)
- Article (6)
- Other (3)
- Monograph/Edited Volume (1)
- Doctoral Thesis (1)
Is part of the Bibliography
- yes (30)
Keywords
- Industry 4.0 (4)
- knowledge management (4)
- CPS (3)
- knowledge transfer (3)
- Analytics (2)
- CPPS (2)
- Internet of Things (2)
- Internet of things (2)
- Simulation (2)
- artificial intelligence (2)
- evaluation (2)
- knowledge transfers (2)
- product generation engineering (2)
- AI and business informatics (1)
- AI-based decision support system (1)
- Analytic Infrastructures (1)
- Architecture concepts (1)
- Architekturkonzept (1)
- Artificial Neuronal Network (1)
- Augmented reality (1)
- Business Process (1)
- Case Study (1)
- Cloud (1)
- Cyber-Phsysische Systeme (1)
- Cyber-Physical Manufacturing Systems (1)
- Cyber-physical systems (1)
- Decentral Decision Making (1)
- Deep Learning (1)
- Enterprise Architecture (1)
- Enterprise-Resource-Planning (1)
- Erklärbarkeit (1)
- Explainability (1)
- Generalized knowledge constructin axiom (1)
- Geschäftsprozess (1)
- Gradient boosting (1)
- Industrial Analytics (1)
- Industrie 4.0 (1)
- Interpretability (1)
- Interpretierbarkeit (1)
- KI-ERP-Indikator (1)
- Knowledge (1)
- Knowledge Management (1)
- Künstliche Intelligenz (1)
- Künstliche Neuronale Netzwerke (1)
- Learning (1)
- Lernen (1)
- Measuring Efficient Task Processing (1)
- Meta-model (1)
- Modeling (1)
- Modellierung (1)
- NMDL (1)
- Optimierung (1)
- Optimization (1)
- Process (1)
- Process Management (1)
- Process modeling (1)
- Prozess (1)
- Prozessmanagement (1)
- Simulation process building (1)
- Task realization strategies (1)
- Use cases Morphologic box (1)
- Wissen (1)
- Wissensmanagement (1)
- adaptable software systems (1)
- artificial neural networks (1)
- augmented reality (1)
- backpropagation (1)
- business process (1)
- business process improvement (1)
- business process optimization (1)
- business processes (1)
- case-based reasoning (1)
- chronic obstructive pulmonary disease (1)
- claims data (1)
- cognitive levels (1)
- context-aware computing (1)
- conversion (1)
- cooperative AI (human-in-the-loop) (1)
- cyber-physical production systems (1)
- cyber-physical systems (1)
- data mining (1)
- design of knowledge-driven systems (1)
- development of AI-based systems (1)
- disease trajectory (1)
- distributed knowledge base (1)
- domain-specific language (1)
- empirical evaluation (1)
- empirical examination (1)
- empirical studies (1)
- experiment (1)
- explainability (1)
- geographical distribution (1)
- human-machine-interaction (1)
- hybrid simulation (1)
- improvement (1)
- industry 4.0 (1)
- intentional forgetting (1)
- intervention (1)
- interventions (1)
- knowledge crystallization (1)
- knowledge engineering (1)
- learning (1)
- manufacturing systems (1)
- modeling language (1)
- morphologic box (1)
- neural networks (1)
- neuronal systems (1)
- new product development (1)
- process modelling (1)
- process-oriented knowledge acquisition (1)
- product development (1)
- production engineering computing (1)
- production networks (1)
- prototype (1)
- quality (1)
- research challenges (1)
- routines (1)
- second-order conditioning (1)
- simulation (1)
- smart automation (1)
- smart production (1)
- stability selection (1)
- symbiotic system design (1)
- task realization strategies (1)
- unlearning (1)
- various applications (1)
Objective We propose a data-driven method to detect temporal patterns of disease progression in high-dimensional claims data based on gradient boosting with stability selection. Materials and methods We identified patients with chronic obstructive pulmonary disease in a German health insurance claims database with 6.5 million individuals and divided them into a group of patients with the highest disease severity and a group of control patients with lower severity. We then used gradient boosting with stability selection to determine variables correlating with a chronic obstructive pulmonary disease diagnosis of highest severity and subsequently model the temporal progression of the disease using the selected variables. Results We identified a network of 20 diagnoses (e.g. respiratory failure), medications (e.g. anticholinergic drugs) and procedures associated with a subsequent chronic obstructive pulmonary disease diagnosis of highest severity. Furthermore, the network successfully captured temporal patterns, such as disease progressions from lower to higher severity grades. Discussion The temporal trajectories identified by our data-driven approach are compatible with existing knowledge about chronic obstructive pulmonary disease showing that the method can reliably select relevant variables in a high-dimensional context. Conclusion We provide a generalizable approach for the automatic detection of disease trajectories in claims data. This could help to diagnose diseases early, identify unknown risk factors and optimize treatment plans.
Künstliche Intelligenz ist in aller Munde. Immer mehr Anwendungsbereiche werden durch die Auswertung von vorliegenden Daten mit Algorithmen und Frameworks z.B. des Maschinellen Lernens erschlossen. Dieses Buch hat das Ziel, einen Überblick über gegenwärtig vorhandene Lösungen zu geben und darüber hinaus konkrete Hilfestellung bei der Auswahl von Algorithmen oder Tools bei spezifischen Problemstellungen zu bieten. Um diesem Anspruch gerecht zu werden, wurden 90 Lösungen mittels einer systematischen Literaturrecherche und Praxissuche identifiziert sowie anschließend klassifiziert. Mit Hilfe dieses Buches gelingt es, schnell die notwendigen Grundlagen zu verstehen, gängige Anwendungsgebiete zu identifizieren und den Prozess zur Auswahl eines passenden ML-Tools für das eigene Projekt systematisch zu meistern.
The paper deals with the increasing growth of embedded systems and their role within structures similar to the Internet (Internet of Things) as those that provide calculating power and are more or less appropriate for analytical tasks. Faced with the example of a cyber-physical manufacturing system, a common objective function is developed with the intention to measure efficient task processing within analytical infrastructures. A first validation is realized on base of an expert panel.
Faced with the triad of time-cost-quality, the realization of knowledge-intensive tasks at economic conditions is not trivial. Since the number of knowledge-intensive processes is increasing more and more nowadays, the efficient design of knowledge transfers at business processes as well as the target-oriented improvement of them is essential, so that process outcomes satisfy high quality criteria and economic requirements. This particularly challenges knowledge management, aiming for the assignment of ideal manifestations of influence factors on knowledge transfers to a certain task. Faced with first attempts of knowledge transfer-based process improvements [1], this paper continues research about the quantitative examination of knowledge transfers and presents a ready-to-go experiment design that is able to examine quality of knowledge transfers empirically and is suitable to examine knowledge transfers on a quantitative level. Its use is proven by the example of four influence factors, which namely are stickiness, complexity, competence and time pressure.
The collaboration during the modeling process is uncomfortable and characterized by various limitations. Faced with the successful transfer of first process modeling languages to the augmented world, non-transparent processes can be visualized in a more comprehensive way. With the aim to rise comfortability, speed, accuracy and manifoldness of real world process augmentations, a framework for the bidirectional interplay of the common process modeling world and the augmented world has been designed as morphologic box. Its demonstration proves the working of drawn AR integrations. Identified dimensions were derived from (1) a designed knowledge construction axiom, (2) a designed meta-model, (3) designed use cases and (4) designed directional interplay modes. Through a workshop-based survey, the so far best AR modeling configuration is identified, which can serve for benchmarks and implementations.
Business processes are regularly modified either to capture requirements from the organization’s environment or due to internal optimization and restructuring. Implementing the changes into the individual work routines is aided by change management tools. These tools aim at the acceptance of the process by and empowerment of the process executor. They cover a wide range of general factors and seldom accurately address the changes in task execution and sequence. Furthermore, change is only framed as a learning activity, while most obstacles to change arise from the inability to unlearn or forget behavioural patterns one is acquainted with. Therefore, this paper aims to develop and demonstrate a notation to capture changes in business processes and identify elements that are likely to present obstacles during change. It connects existing research from changes in work routines and psychological insights from unlearning and intentional forgetting to the BPM domain. The results contribute to more transparency in business process models regarding knowledge changes. They provide better means to understand the dynamics and barriers of change processes.
Manufacturing Analytics
(2018)
Since more and more business tasks are enabled by Artificial Intelligence (AI)-based techniques, the number of knowledge-intensive tasks increase as trivial tasks can be automated and non-trivial tasks demand human-machine interactions. With this, challenges regarding the management of knowledge workers and machines rise [9]. Furthermore, knowledge workers experience time pressure, which can lead to a decrease in output quality. Artificial Intelligence-based systems (AIS) have the potential to assist human workers in knowledge-intensive work. By providing a domain-specific language, contextual and situational awareness as well as their process embedding can be specified, which enables the management of human and AIS to ease knowledge transfer in a way that process time, cost and quality are improved significantly. This contribution outlines a framework to designing these systems and accounts for their implementation.
As part of the digitization, the role of artificial systems as new actors in knowledge-intensive processes requires to recognize them as a new form of knowledge bearers side by side with traditional knowledge bearers, such as individuals, groups, organizations. By now, artificial intelligence (AI) methods were used in knowledge management (KM) for knowledge discovery, for the reinterpreting of information, and recent works focus on the studying of different AI technologies implementation for knowledge management, like big data, ontology-based methods and intelligent agents [1]. However, a lack of holistic management approach is present, that considers artificial systems as knowledge bearers. The paper therefore designs a new kind of KM approach, that integrates the technical level of knowledge and manifests as Neuronal KM (NKM). Superimposing traditional KM approaches with the NKM, the Symbiotic Knowledge Management (SKM) is conceptualized furthermore, so that human as well as artificial kinds of knowledge bearers can be managed as symbiosis. First use cases demonstrate the new KM, NKM and SKM approaches in a proof-of-concept and exemplify their differences.