Refine
Year of publication
Document type
- Conference Proceeding (16)
- Article (peer-reviewed) (13)
- Contribution to a Periodical (3)
- Bachelor Thesis (1)
- Part of a Book (1)
- Master's Thesis (1)
Keywords
- Machine learning (35) (remove)
Course of studies
The importance of machine learning (ML) has been increasing dramatically for years. From assistance systems to production optimisation to healthcare support, almost every area of daily life and industry is coming into contact with machine learning. Besides all the benefits ML brings, the lack of transparency and difficulty in creating traceability pose major risks. While solutions exist to make the training of machine learning models more transparent, traceability is still a major challenge. Ensuring the identity of a model is another challenge, as unnoticed modification of a model is also a danger when using ML. This paper proposes to create an ML Birth Certificate and ML Family Tree secured by blockchain technology. Important information about training and changes to the model through retraining can be stored in a blockchain and accessed by any user to create more security and traceability about an ML model.
Specification of Neck Muscle Dysfunction through Digital Image Analysis Using Machine Learning
(2023)
The usage of machine learning models for prediction is growing rapidly and proof that the intended requirements are met is essential. Audits are a proven method to determine whether requirements or guidelines are met. However, machine learning models have intrinsic characteristics, such as the quality of training data, that make it difficult to demonstrate the required behavior and make audits more challenging. This paper describes an ML audit framework that evaluates and reviews the risks of machine learning applications, the quality of the training data, and the machine learning model. We evaluate and demonstrate the functionality of the proposed framework by auditing an steel plate fault prediction model.
Die Biografie- und Erinnerungspflege stellt eine Behandlungsform für die unheilbare Demenzerkrankung dar. Hierbei wird versucht durch Aktivitäten, welche einen Bezug zu der Vergangenheit des Menschen mit Demenz haben, Erinnerungen auszulösen. Dies hilft der an Demenz erkrankten Person ihr Identitätsgefühl zu festigen.
Im Rahmen dieser Bachelorarbeit wurde eine innovative Anwendung entwickelt, welche interaktive und multimediale Bilder für die Biografie- und Erinnerungspflege bereitstellt. Mit diesen Bildern kann der Mensch mit Demenz interagieren, indem er auf einzelne Objekte drückt und daraufhin ein thematisch passendes Medium präsentiert wird. Die interaktiven Bilder werden automatisch, mittels Machine Learning, erstellt. Des Weiteren wurde ein Recommender System implementiert, welches basierend auf den Präferenzen des Menschen mit Demenz, Inhalte für eine Biografie- und Erinnerungspflegesitzung vorschlägt.
As machine learning becomes increasingly pervasive, its resource demands and financial implications escalate, necessitating energy and cost optimisations to meet stakeholder demands. Quality metrics for predictive machine learning models are abundant, but efficiency metrics remain rare. We propose a framework for efficiency metrics, that enables the comparison of distinct efficiency types. A quality-focused efficiency metric is introduced that considers resource consumption, computational effort, and runtime in addition to prediction quality. The metric has been successfully tested for usability, plausibility, and compensation for dataset size and host performance. This framework enables informed decisions to be made about the use and design of machine learning in an environmentally responsible and cost-effective manner.
BUSINESS PROCESS AUTOMATION: ENHANCING EFFICIENCY AND COMPETITIVENESS IN MODERN ORGANIZATIONS
(2024)
The first section of the thesis provides a historical overview of automation, spanning from the first industrial revolution to the current era of highly advanced AI-driven technologies. It emphasizes how important Business Process Automation (BPA) is in today's hectic corporate climate when productivity and competitiveness are key factors. The main focus is on Robotic Process Automation (RPA), which is especially useful in situations with legacy systems since it effectively automates repetitive processes. This study explores the differences between terms and concepts related to automation, including business process automation (BPA), robotic process automation (RPA), artificial intelligence (AI), machine learning (ML), and business process management (BPM). Companies looking to optimize their processes face a changing landscape due to the involvement of various technologies. Using real-world case studies and industry best practices, the thesis provides a thorough examination of the effects of BPA, emphasizing the primary drivers, challenges, and benefits of BPA adoption. A mixed-methods approach integrating quantitative and qualitative research was used as the methodology. Surveys, case studies, and documentation from different organizations are included in the study, based on those who have implemented RPA at their work. This method enables a thorough analysis of BPA's effects on efficacy, productivity, and affordability. Case studies from prominent firms like Capgemini Consulting, PwC, and Deloitte are reviewed to gain insights regarding their BPA journey. Significant gains in customer satisfaction, cost savings, error avoidance, and operational efficiency are shown by this research. They also draw attention to difficulties like opposition from employees, problems with integration, and the requirement for upskilling. The thesis indicates that although big firms have similar motives for adopting BPA, the process of adopting BPA varies depending on the specific circumstances of each firm. Stakeholder engagement and change management are critical components of successful BPA programs, according to key results. The study highlights a balanced, strategic, and context-sensitive approach, offering a useful insight for companies in establishing their BPA strategy. It provides a comprehensive examination of the role that business process automation plays in modern companies, highlighting the ways in which it can radically alter corporate strategy and operations in the digital age. It gives a thorough examination of the challenges involved in putting BPA into practice and offers tactical advice to businesses hoping to use these tools to boost productivity and competitiveness.
Quality assurance (QA) plays a crucial role in manufacturing to ensure that products meet their specifications. However, manual QA processes are costly and time-consuming, thereby making artificial intelligence (AI) an attractive solution for automation and expert support. In particular, convolutional neural networks (CNNs) have gained a lot of interest in visual inspection. Next to AI methods, the explainable artificial intelligence (XAI) systems, which achieve transparency and interpretability by providing insights into the decision-making process of the AI, are interesting methods for achieveing quality inspections in manufacturing processes. In this study, we conducted a systematic literature review (SLR) to explore AI and XAI approaches for visual QA (VQA) in manufacturing. Our objective was to assess the current state of the art and identify research gaps in this context. Our findings revealed that AI-based systems predominantly focused on visual quality control (VQC) for defect detection. Research addressing VQA practices, like process optimization, predictive maintenance, or root cause analysis, are more rare. Least often cited are papers that utilize XAI methods. In conclusion, this survey emphasizes the importance and potential of AI and XAI in VQA across various industries. By integrating XAI, organizations can enhance model transparency, interpretability, and trust in AI systems. Overall, leveraging AI and XAI improves VQA practices and decision-making in industries.
Despite the unabated growth of algorithmic decision-making in organizations, there is a growing consensus that numerous situations will continue to require humans in the loop. However, the blending of a formal machine and bounded human rationality also amplifies the risk of what is known as local rationality. Therefore, it is crucial, especially in a data-abundant environment that characterizes algorithmic decision-making, to devise means to assess performance holistically. In this paper, we propose a simulation-based model to address the current lack of research on quantifying algorithmic interventions in a broader organizational context. Our approach allows the combining of causal modeling and data science algorithms to represent decision settings involving a mix of machine and human rationality to measure performance. As a testbed, we consider the case of a fictitious company trying to improve its forecasting process with the help of a machine learning approach. The example demonstrates that a myopic assessment obscures problems that only a broader framing reveals. It highlights the value of a systems view since the effects of the interplay between human and algorithmic decisions can be largely unintuitive. Such a simulation-based approach can be an effective tool in efforts to delineate roles for humans and algorithms in hybrid contexts.