A5100331950- Design Education and Practice
- Business Process Modeling and Analysis
- Product Development and Customization
- Cognitive Computing and Networks
- Information Systems Theories and Implementation
- Digital Transformation in Industry
- Semantic Web and Ontologies
- Service and Product Innovation
- Flexible and Reconfigurable Manufacturing Systems
- Sustainable Supply Chain Management
- Arctic and Russian Policy Studies
- Systems Engineering Methodologies and Applications
- Quality Function Deployment in Product Design
- Public Procurement and Policy
- Machine Learning in Healthcare
- Petri Nets in System Modeling
- Innovative Educational Techniques
- Service-Oriented Architecture and Web Services
- Simulation and Modeling Applications
- Ideological and Political Education
- Corporate Social Responsibility and Sustainability
- Innovation, Technology, and Society
- Research Data Management Practices
- Machine Learning in Materials Science
- Digital Media Forensic Detection
University of Skövde
2024
North Dakota State University
2024
Guangzhou Medical University Cancer Hospital
2024
Guangzhou Medical University
2023-2024
Anqing Normal University
2024
Beijing Jiaotong University
2024
Inner Mongolia Electric Power (China)
2023
Technische Universität Berlin
2015-2022
Jiangsu University of Science and Technology
2013
Chinese People's Armed Police Force
2013
In the pharmaceutical industry it is common to generate many QSAR models from training sets containing a large number of molecules and descriptors. The best methods are those that can most accurate predictions but not overly expensive computationally. this paper we compare eXtreme Gradient Boosting (XGBoost) random forest single-task deep neural nets on 30 in-house data sets. While XGBoost has adjustable parameters, define set standard parameters at which makes predictions, average, better...
The increasing usage of interconnected devices within the Internet Things (IoT) and Industrial IoT (IIoT) has significantly enhanced efficiency utility in both personal industrial settings but also heightened cybersecurity vulnerabilities, particularly through malware. This paper explores use one-class classification, a method unsupervised learning, which is especially suitable for unlabeled data, dynamic environments, malware detection, form anomaly detection. We introduce TF-IDF...
In response to increasing environmental concerns, many governments have implemented carbon tax policies incentivize green technology investments. However, the impact of such on supply chain coordination, particularly when retailers are risk-averse, remains underexplored. This study investigates a two-tier where manufacturers invest in and engage marketing activities within framework policy. Motivated by need understand how taxes affect strategic decisions profitability, we analyze...
Emission trading is an efficient measure to combat climate change, which one of the biggest threats international community and human health. The shipping industry has previously been considered energy-saving but growth rate its emissions far exceeds that other industries. On 10 May 2023, EU enacted Regulation (EU) 2023/957, officially included in EU-ETS. Therefore, this may lead investor-state disputes regarding emission marine due conflicts between obligation change protect investments...
Modern value creation is characterized by collaboration of large networks specialized companies. Due to market requirements and increasing competition, concurrent or simultaneous engineering has become the standard procedure in product development. Still, development processes often follow traditionally linear sequential patterns, allowing for only a narrow scope iterations. Milestone-driven models are widely used control steer such processes. In this article, authors argue that proper...
As research topics become increasingly complex, large scale interdisciplinary projects are commonly established to foster cross-disciplinary cooperation and utilize potential synergies. In the case of Collaborative Research Center (CRC) 1026, 19 individual from different disciplines brought together investigate perspectives solutions for sustainable manufacturing. Beside overheads regarding coordination activities communication, such also facing challengs data management. For exchange...
Abstract Designing Product-Service Systems (PSS) is associated with multiple problems and challenges, usually derived from its multidisciplinarity partially intangible nature. One particular issue the high likelihood of ignoring creation relevant information regarding one or more PSS elements during early design phases. Proceeding to later stages (e.g., detailed design) without generating required all their relationships may lead rework lack integration. Dealing this problem requires...
In the context of real-time fault-tolerant scheduling in Distributed Control systems, Primary-backup scheme plays an important role. A backup copy is always preferred to be executed as passive backup-copy whenever possible because it can take advantages de-allocation technique and overloading improve schedulabilty. this paper, we propose a novel Fault-tolerant Rate-Monotonic Best-fit algorithm (NRMBF) based on systems enhance schedulability. Unlike existing algorithms (FTRMBF or FTRMFF) that...
Sustainability is characterized by complex interplay between economic, environmental and social aspects a temporal dimension. The public perception often mistakenly limited to single due deliberated influence marketing or misuse. Reliable scientific articles usually address expert audience only. To create broad understanding knowledge has be available comprehensible. In the World Wide Web various concepts are applied represent each utilizing different sets of media without interactive...
In this paper, we introduced an intelligent Customer Service Representative (CSR) Operating System. The system contains three modules: Knowledge Management (KM) module, Natural Language Process (NLP) module and CSR (CSRO) module. KM manages knowledge. When get query through phone, Internet, Fetion, QQ, etc. from customer, the NLP understands gives recommended reply. If confirms that reply is right, replies automatically. CSRO right or retrieves quickly knowledge base, can increase...
Based on the ant colony algorithm, this paper explores its application in optimizing shirt pocket manufacturing process parameters. As one of critical processes garment manufacturing, layout and stitching pockets has an essential impact appearance quality pr
Highly realistic AI generated face forgeries known as deepfakes have raised serious social concerns. Although DNN-based forgery detection models achieved good performance, they are vulnerable to latest generative methods that less traces and adversarial attacks. This limitation of generalization robustness hinders the credibility results requires more explanations. In this work, we provide counterfactual explanations for from an artifact removal perspective. Specifically, first invert images...
Histopathological image classification based on in-depth study is one of the significant methods for diagnosing diseases. Pathology information complex, diverse, and has a large number features, which leads to difficult low diagnostic accuracy. Building computer-aided tools using processing artificial intelligence techniques can dramatically improve pathologists’ productivity reduce error rates. The histopathological images mainly included traditional machine learning manual feature...
Intense collaboration within networks of stakeholders characterizes current engineering design processes. In these, engineers use IT systems to create artifacts, which manifest their knowledge allowing its circulation. Still, a research gap exists regarding the understanding kinds, relations and interdependencies between systems, artifacts types. This article addresses this by presenting results systematic literature review. The contribute close mentioned gap, give insight on focusses...
Introduction: Respiratory diseases pose a global health burden, and early diagnosis is crucial for effective treatment. Developing natural language processing (NLP) diagnostic system based on electronic records (EHRs) essential but challenging due to the complexity of EHR data.Methods: A retrospective study was conducted using EHRs respiratory disease patients from multiple hospitals in China. An NLP algorithm developed extract clinical features phenotypic attributes EHRs. The extracted were...
Abstract Knowledge is a crucial factor in state-of-the-art product development. It often provided by stakeholders from divers disciplinary and individual backgrounds has to be integrated create competitive products. Still, it not fully understood, how knowledge generated, transformed, transferred complex development processes. To investigate the dynamic interrelations between involved stakeholders, applied types related artefacts, researchers at TU Berlin conducted evaluated student...