Refine
Document Type
- Master's Thesis (6)
- Bachelor Thesis (4)
- Contribution to a Periodical (4)
- Article (unreviewed) (3)
- Article (reviewed) (1)
- Doctoral Thesis (1)
- Other (1)
Keywords
- Maschinelles Lernen (20) (remove)
Institute
- Fakultät Wirtschaft (W) (9)
- Fakultät Medien (M) (ab 22.04.2021) (5)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (4)
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (2)
- IfTI - Institute for Trade and Innovation (2)
- IMLA - Institute for Machine Learning and Analytics (1)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (1)
Open Access
- Open Access (10)
- Closed (5)
- Closed Access (5)
- Bronze (2)
The last decades have seen the evolution of industrial production into more sophisticated processes. The development of specialized, high-end machines has increased the importance of predictive maintenance of mechanical systems to produce high-quality goods and avoid machine breakdowns. Predictive maintenance has two main objectives: to classify the current status of a machine component and to predict the maintenance interval by estimating its remaining useful life (RUL). Nowadays, both objectives are covered by machine learning and deep learning approaches and require large training datasets that are often not available. One possible solution may be transfer learning, where the knowledge of a larger dataset is transferred to a smaller one. This thesis is primarily concerned with transfer learning for predictive maintenance for fault classification and RUL estimation. The first part presents the state-of-the-art machine learning techniques with a focus on techniques applicable to predictive maintenance tasks (Chapter 2). This is followed by a presentation of the machine tool background and current research that applies the previously explained machine learning techniques to predictive maintenance tasks (Chapter 3). One novelty of this thesis is that it introduces a new intermediate domain that represents data by focusing on the relevant information to allow the data to be used on different domains without losing relevant information (Chapter 4). The proposed solution is optimized for rotating elements. Therefore, the presented intermediate domain creates different layers by focusing on the fault frequencies of the rotating elements. Another novelty of this thesis is its semi and unsupervised transfer learning-based fault classification approach for different component types under different process conditions (Chapter 5). It is based on the intermediate domain utilized by a convolutional neural network (CNN). In addition, a novel unsupervised transfer learning loss function is presented based on the maximum mean discrepancy (MMD), one of the state-of-the-art algorithms. It extends the MMD by considering the intermediate domain layers; therefore, it is called layered maximum mean discrepancy (LMMD). Another novelty is an RUL estimation transfer learning approach for different component types based on the data of accelerometers with low sampling rates (Chapter 6). It applies the feature extraction concepts of the classification approach: the presented intermediate domain and the convolutional layers. The features are then used as input for a long short-term memory (LSTM) network. The transfer learning is based on fixed feature extraction, where the trained convolutional layers are taken over. Only the LSTM network has to be trained again. The intermediate domain supports this transfer learning type, as it should be similar for different component types. In addition, it enables the practical usage of accelerometers with low sampling rates during transfer learning, which is an absolute novelty. All presented novelties are validated in detailed case studies using the example of bearings (Chapter 7). In doing so, their superiority over state-of-the-art approaches is demonstrated.
In dieser Arbeit wird die Identifikation von Trägheitsparametern von Mehrkörpersystemen, am Beispiel eines ein aus vier Segmenten bestehenden Roboterarms untersucht. Es werden verschiedene neuronale Netzarchitekturen zur Identifikation der Trägheitsparameter des Roboterarms exploriert. Als Referenz für das Abschneiden der Ansätze wird ein vorab implementierter numerischer Optimierungsansatz, welcher mittels der Software „Matalb“ umgesetzt wurde, benutzt. Der Ansatz zum Aufstellen der benötigten Bewegungsgleichungen und die Formulierung des Regressionsproblems unterscheidet sich von den in der Literatur verwendeten Ansätzen, und beruht auf einem neu entwickelten Sensorkonzept der Hochschule Offenburg (des Sweaty Labors).
Der numerische Ansatz, insbesondere nach Linearisierung des Problems, erzielte herausragende Ergebnisse und konnte die idealen Parameterwerte präzise identifizieren. Demgegenüber standen die neuronalen Netzwerke, deren Potenzial trotz umfassender Untersuchung verschiedener Architekturen und Ansätze nicht vollends ausgeschöpft werden konnte. Die Resultate zeigen deutlich die Grenzen und Herausforderungen bei der Anwendung maschineller Lernmethoden in der spezifischen Aufgabenstellung der Trägheitsparameteridentifikation auf.
Diese Arbeit leistet einen Beitrag zum Verständnis der Möglichkeiten und Grenzen bei der Anwendung neuer Messtechnologien und Berechnungsverfahren in der Robotik. Die überlegene Leistung des numerischen Solvers gegenüber den neuronalen Netzansätzen unterstreicht die Bedeutung weiterer Forschungen in diesem Bereich.
Diese Bachelorthesis behandelt die Entwicklung eines Prototyps zur Identifizierung und Verhinderung von Angriffen mithilfe von KI- und ML-Modellen. Untersucht werden die Leistungsfähigkeit verschiedener theoretischer Modelle im Kontext der Intrusion Detection, wobei Machine-Learning-Modelle wie Entscheidungsbäume, Random Forests und Naive Bayes analysiert werden. Die Arbeit betont die Relevanz der Datensatzauswahl, die Vorbereitung der Daten und bietet einen Ausblick auf zukünftige Entwicklungen in der Angriffserkennung.
Much of the research in the field of audio-based machine learning has focused on recreating human speech via feature extraction and imitation, known as deepfakes. The current state of affairs has prompted a look into other areas, such as the recognition of recording devices, and potentially speakers, by only analysing sound files. Segregation and feature extraction are at the core of this approach.
This research focuses on determining whether a recorded sound can reveal the recording device with which it was captured. Each specific microphone manufacturer and model, among other characteristics and imperfections, can have subtle but compounding effects on the results, whether it be differences in noise, or the recording tempo and sensitivity of the microphone while recording. By studying these slight perturbations, it was found to be possible to distinguish between microphones based on the sounds they recorded.
After the recording, pre-processing, and feature extraction phases we completed, the prepared data was fed into several different machine learning algorithms, with results ranging from 70% to 100% accuracy, showing Multi-Layer Perceptron and Logistic Regression to be the most effective for this type of task.
This was further extended to be able to tell the difference between two microphones of the same make and model. Achieving the identification of identical models of a microphone suggests that the small deviations in their manufacturing process are enough of a factor to uniquely distinguish them and potentially target individuals using them. This however does not take into account any form of compression applied to the sound files, as that may alter or degrade some or most of the distinguishing features that are necessary for this experiment.
Building on top of prior research in the area, such as by Das et al. in in which different acoustic features were explored and assessed on their ability to be used to uniquely fingerprint smartphones, more concrete results along with the methodology by which they were achieved are published in this project’s publicly accessible code repository.
As e-commerce platforms have grown in popularity, new difficulties have emerged, such as the growing use of bots—automated programs—to engage with e-commerce websites. Even though some algorithms are helpful, others are malicious and can seriously hurt e-commerce platforms by making fictitious purchases, posting fictitious evaluations, and gaining control of user accounts. Therefore, the development of more effective and precise bot identification systems is urgently needed to stop such actions. This thesis proposes a methodology for detecting bots in E-commerce using machine learning algorithms such as K-nearest neighbors, Decision Tree, Random Forest, Support Vector Machine, and Neural Network. The purpose of the research is to assess and contrast the output of these machine learning methods. The suggested approach will be based on data that is readily accessible to the public, and the study’s focus will be on the research of bots in e-commerce.
The purpose of the study is to provide an overview of bots in e-commerce, as well as information on the different kinds and traits of bots, as well as current research on bots in e-commerce and associated work on bot detection in e-commerce. The research also seeks to create a more precise and effective bot detection system as well as find critical factors in detecting bots in e-commerce.
This research is significant because it sheds light on the increasing issue of bots in e-commerce and the requirement for more effective bot detection systems. The suggested approach for using machine learning algorithms to identify bots in ecommerce can give e-commerce platforms a more precise and effective bot detection system to stop malicious bot activities. The study’s results can also be used to create a more effective bot detection system and pinpoint key elements in detecting bots in e-commerce.
The progress in machine learning has led to advanced deep neural networks. These networks are widely used in computer vision tasks and safety-critical applications. The automotive industry, in particular, has experienced a significant transformation with the integration of deep learning techniques and neural networks. This integration contributes to the realization of autonomous driving systems. Object detection is a crucial element in autonomous driving. It contributes to vehicular safety and operational efficiency. This technology allows vehicles to perceive and identify their surroundings. It detects objects like pedestrians, vehicles, road signs, and obstacles. Object detection has evolved from being a conceptual necessity to an integral part of advanced driver assistance systems (ADAS) and the foundation of autonomous driving technologies. These advancements enable vehicles to make real-time decisions based on their understanding of the environment, improving safety and driving experiences. However, the increasing reliance on deep neural networks for object detection and autonomous driving has brought attention to potential vulnerabilities within these systems. Recent research has highlighted the susceptibility of these systems to adversarial attacks. Adversarial attacks are well-designed inputs that exploit weaknesses in the deep learning models underlying object detection. Successful attacks can cause misclassifications and critical errors, posing a significant threat to the functionality and safety of autonomous vehicles. With the rapid development of object detection systems, the vulnerability to adversarial attacks has become a major concern. These attacks manipulate inputs to deceive the target system, significantly compromising the reliability and safety of autonomous vehicles. In this study, we focus on analyzing adversarial attacks on state-of-the-art object detection models. We create adversarial examples to test the models’ robustness. We also check if the attacks work on a different object detection model meant for similar tasks. Additionally, we extensively evaluate recent defense mechanisms to see how effective they are in protecting deep neural networks (DNNs) from adversarial attacks and provide a comprehensive overview of the most commonly used defense strategies against adversarial attacks, highlighting how they can be implemented practically in real-world situations.
Diese Arbeit befasst sich mit dem Entwurf und der Herstellung einer Roboterhandprothese, die amputierten Menschen eine gewisse Mobilität und eine teilweise Nutzung der Hand ermöglichen soll.
Das Projekt konzentriert sich insbesondere auf die Erkennung der vom Benutzer ausgeführten Bewegung und wird die Schritte der Erfassung, der Bewegung der Übertragung und die Erkennung detailliert darstellen.
Organizations striving to achieve success in the long term must have a positive brand image which will have direct implications on the business. In the face of the rising cyber threats and intense competition, maintaining a threat-free domain is an important aspect of preserving that image in today's internet world. Domain names are often near-synonyms for brand names for numerous companies. There are likely thousands of domains that try to impersonate the big companies in a bid to trap unsuspecting users, usually falling prey to attacks such as phishing or watering hole. Because domain names are important for organizations for running their business online, they are also particularly vulnerable to misuse by malicious actors. So, how can you ensure that your domain name is protected while still protecting your brand identity? Brand Monitoring, for example, may assist. The term "Brand Monitoring" applies only to keep tabs on an organization's brand performance, reception, and overall online presence through various online channels and platforms [1]. There has been a rise in the need of maintaining one's domain clear of any linkages to malicious activities as the threat environment has expanded. Since attackers are targeting domain names of organizations and luring unsuspecting users to visit malicious websites, domain monitoring becomes an important aspect. Another important aspect of brand abuse is how attackers leverage brand logos in creating fake and phishing web pages. In this Master Thesis, we try to solve the problem of classification of impersonated domains using rule-based and machine learning algorithms and automation of domain monitoring. We first use a rule-based classifier and Machine Learning algorithms to classify the domains gathered into two buckets – "Parked" and "Non-Parked". In the project's second phase, we will deploy object detection models (Scale Invariant Feature Transform - SIFT and Multi-Template Matching – MTM) to detect brand logos from the domains of interest.
Maschinelles Lernen verändert zusehends die Arbeitswelt. Auch in der Produktionsplanung und -steuerung finden sich vielversprechende Anwendungsfälle. In diesem Beitrag sollen ausgewählte Anwendungsbereiche und Ansätze vorgestellt werden, die anhand einer umfangreichen Untersuchung wissenschaftlicher Veröffentlichungen identifiziert wurden. Als Strukturierungshilfe dient das Aachener PPS-Modell.
Die Mehrheit der deutschen Unternehmen verspricht sich aus KI-gestützter Datenanalyse einen großen Geschäftsvorteil. Doch gerade das Thema Datenbestand ist eine der größten, immer noch häufig unterschätzten Hürde beim Trainieren und Einführen von KI-Algorithmen. Im Folgenden sind vier konkrete Erfahrungen und Tipps für KI- & Datenanalyseprojekte in Unternehmen aufgeführt.