Refine
Document Type
- Master's Thesis (121) (remove)
Year of publication
Language
- English (121) (remove)
Keywords
- Maschinelles Lernen (24)
- Vektorquantisierung (8)
- Blockchain (7)
- Algorithmus (5)
- Bioinformatik (5)
- Neuronales Netz (5)
- Deep learning (4)
- Kryptologie (4)
- Virtuelle Währung (4)
- China (3)
As new sensors are added to VR headsets, more data can be collected. This introduces a new potential threat to user privacy. We focused on the feasibility of extracting personal information from eye-tracking. To achieve this, we designed a preliminary user study focusing on the pupil response to audio stimuli. We used a variation of machine learning models to test the collected data to determine the feasibility of obtaining information such as the age or gender of the participant. Several of the experiments show promise for obtaining this information. We were able to extract with reasonable certainty whether caffeine was consumed and the gender of the participant. This demonstrates the unknown threat that embedded sensors pose to users. A further studies are planned to verify the results.
This thesis investigates the efficacy of four machine learning algorithms, namely linear regression, decision tree, random forest and neural network in the task of lead scoring. Specifically, the study evaluates the performance of these algorithms using datasets without sampling and with random under-sampling and over-sampling using SMOTE. The performance of each algorithm is measure using various performance metrics, including accuracy, AUC-ROC, specificity, sensitivity, precision, recall, F1 score, and G-mean. The results indicate that models trained on the dataset without sampling achieved higher accuracy than those trained on the dataset with either random under-sampling or random over-sampling using SMOTE. However, the neural network demonstrated remarkable results on each dataset compared to the other algorithms. These findings provide valuable insights into the effectiveness of machine learning algorithms for lead scoring tasks, particularly when using different sampling techniques. The findings of this study can aid lead management practices in selecting the most suitable algorithm and sampling technique for their needs. Furthermore, the study contributes to the literature by providing a comprehensive evaluation of the performance of machine learning algorithms for lead scoring tasks. This thesis has practical implications for businesses looking to improve their lead management practices, and future research could extend the analysis to other machine learning algorithms or more extensive datasets.
As the cryptocurrency ecosystem rapidly grows, interoperability has become increasingly crucial, enabling assets and data to interact seamlessly across multiple chains. This work describes the concept and implementation of a trustless connection between the Bitcoin Lightning Network and EVM-compatible blockchains, allowing the transfer of assets between the two ecosystems. Establishing such a connection can significantly contribute to the growth of both ecosystems as they can benefit from each other’s advantages and emerge new pos- sibilities.
To investigate the effects of climate change on interactions within ecosystems, a microcosm experiment was conducted. The effects of temperature increase and predator diversity on Collembola communities and their decomposition rate were investigated. The predators used were mites and Chilopods, whose predation effects on several response variables were analysed. This data included Collembola abundance, biomass and body mass as well as basal respiration and microbial biomass carbon. These response variables were tested against the predictors in several models. Temperature showed high significance in interaction with mite abundance in almost all models. Furthermore, the results of the basal respiration and microbial biomass carbon support the suggestion of a trophic cascade within the animal interaction.
Recently a deep neural network architecture designed to work on graph- structured data have been capturing notice as well as getting implemented in various domains and application. However, learning representation (feature embedding) from graphical data picking pace in research and constructing graph(s) from dataset remains a challenge. The ability to map the data to lower dimensions further makes the task easier while providing comfort in applying many operations. Graph neural network (GNN) is one of the novel neural network models that is catching attention as it is outperforming in various applications like recommender systems, social networks, chemical synthesis, and many more. This thesis discusses a unique approach for a fundamental task on graphs; node classification. The feature embedding for a node is aggregated by applying a Recurrent neural network (RNN), then a GNN model is trained to classify a node with the help of aggregated features and Q learning supports in optimizing the shape of neural networks. This thesis starts with the working principles of the Feedforward neural network, recurrent units like simple RNN, Long short-term memory (LSTM), and Gated recurrent unit (GRU), followed by concepts of Reinforcement learning (RL) and the Q learning algorithm. An overview of the fundamentals of graphs, followed by the GNN architecture and workflow, is discussed subsequently. Some basic GNN models are discussed in brief later before it approaches the technical implementation details, the output of the model, and a comparison with a few other models such as GraphSage and Graph attention network (GAN).
Assessment of COI and 16S for insect species identification ti determine the diet of city bats
(2023)
Despite the numerous benefits of urbanization to human living conditions, urbanization has also negatively affected humans, their environment, and other organisms that share urban habitats with humans. Undoubtedly adverse while some wild animals avoid living in urban areas, others are more tolerant or prefer life in urban habitats. There are more than 1,400 species of bats in the world.
Therefore, they have the potential to contribute significantly to the mammalian biodiversity in urban areas. Insectivorous bats species play a key role in agriculture by improving yields and reducing chemical pesticide costs. Using metabarcoding, it is possible to determine the prey consumed by these noctule mammals based on the DNA fragments in their fecal pellets. This study
aimed to evaluate COI and 16S metabarcodes for insect species identification to determine the diet of metropolitan bats. For this purpose, COI and 16S metabarcodes were extracted, amplified, and sequenced from 65 bat feces collected in the Berlin metropolitan areas. Following a taxonomic annotation, I found that 73% of all identified insects could only be detected using the COI method, while 15% could be recovered using the 16S approach. Just 12% of all detected insects were identified simultaneously by both markers. According to this result, COI is more suitable for the taxonomic identification of insects from bat feces. However, given the bias of COI primers, it is recommended to use both markers for a more precise estimation of species diversity. Additionally,based on the insect species identified, I noticed that urban bats fed mainly on Diptera, Coleoptera,and Lepidoptera. The bat species Nyctalus noctula was most abundant in the samples. His diet analysis revealed that 91% of the samples contained the insect species Chironomus plumosus. 14 pest insect species were also found in his diet.
Analysis of the Forensic Preparation of Biometric Facial Features for Digital User Authentication
(2023)
Biometrics has become a popular method of securing access to data as it eliminates the need for users to remember a password. Although exploiting the vulnerabilities of biometric systems increased with their usage, these could also be helpful during criminal casework.
This thesis aims to evaluate approaches to bypass electronic devices with forged faces to access data for law enforcement. Here, obtaining the necessary data in a timely manner is critical. However, unlocking the devices with a password can take several years with a brute force attack. Consequently, biometrics could be a quicker alternative for unlocking.
Various approaches were examined to bypass current face recognition technologies. The first approaches included printing the user's face on regular paper and aimed to unlock devices performing face recognition in the visible spectrum. Further approaches consisted of printing the user's infrared image and creating three-dimensional masks to bypass devices performing face recognition in the near-infrared. Additionally, the underlying software responsible for face recognition was reverse-engineered to get information about its operation mode.
The experiments demonstrate that forged faces can partly bypass face recognition and obtain secured data. Devices performing face recognition in the visible spectrum can be unlocked with a printed image of the user's face. Regarding devices with advanced near-infrared face recognition, only one could be bypassed with a three-dimensional face mask. In addition, its underlying software provided evidence about the demands of face recognition. Other devices under attack remained locked, and their software provided no clues.
Machine learning models for timeseries have always been a special topic of interest due to their unique data structure. Recently, the introduction of attention improved the capabilities of recurrent neural networks and transformers with respect to their learning tasks such as machine translation. However, these models are usually subsymbolic architectures, making their inner working hard to interpret without comprehensive tools. In contrast, interpretable models such learning vector quantization are more transparent in the ability to interpret their decision process. This thesis tries to merge attention as a machine learning function with learning vector quantization to better handle timeseries data. A design on such a model is proposed and tested with a dataset used in connection with the attention based transformers. Although the proposed model did not yield the expected results, this work outlines improvements for further research on this approach.
Analysis of Continuous Learning Strategies at the Example of Replay-Based Text Classification
(2023)
Continuous learning is a research field that has significantly boosted in recent years due to highly complex machine and deep learning models. Whereas static models need to be retrained entirely from scratch when new data get available, continuous models progressively adapt to new data saving computational resources. In this context, this work analyzes parameters impacting replay-based continuous learning approaches at the example of a data-incremental text classification task using an MLP and LSTM. Generally, it was found that replay improves the results compared to naive approaches but achieves not the performance of a static model. Mainly, the performances increased with more replayed examples, and the number of training iterations has a significant influence as it can partly control the stability-plasticity-trade-off. In contrast, the impact of balancing the buffer and the strategy to select examples to store in the replay buffer were found to have a minor impact on the results in the present case.
Traditional user management on the Internet has historically required individuals to give up control over their identities. In contrast, decentralized solutions promise to empower users and foster decentralized interactions. Over the last few years, the development of decentralized accounts and tokens has significantly increased, aiming at broader user adoption and shared social economies.
This thesis delves into smart contract standards and social infrastructure for Ethereum-based blockchains to enable identity-based data exchange between abstracted blockchain accounts. In this regard, the standardization landscapes of account and social token developments were analyzed in-depth to form guidelines that allow users to retain complete control over their data and grant access selectively.
Based on the evaluations, a pioneering Solidity standard is presented, natively integrating consensual restrictive on-chain assets for abstracted blockchain accounts. Further, the architecture of a decentralized messaging service has been defined to outline how new token and account concepts can be intertwined with efficient and minimal data-sharing principles to ensure security and privacy, while merging traditional server environments with global ledgers.