Sökning: "Time Series Feature Extraction"
Visar resultat 1 - 5 av 25 uppsatser innehållade orden Time Series Feature Extraction.
1. Unsupervised Online Anomaly Detection in Multivariate Time-Series
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/DatorteknikSammanfattning : This research aims to identify a method for unsupervised online anomaly detection in multivariate time series in dynamic systems in general and on the case study of Devwards IoT-system in particular. A requirement of the solution is its explainability, online learning and low computational expense. LÄS MER
2. A Deep Learning Approach To Vehicle Fault Detection Based On Vehicle Behavior
Master-uppsats, Malmö universitet/Institutionen för datavetenskap och medieteknik (DVMT)Sammanfattning : Vehicles and machinery play a crucial role in our daily lives, contributing to our transportationneeds and supporting various industries. As society strives for sustainability, the advancementof technology and efficient resource allocation become paramount. LÄS MER
3. Extraction of Global Features for enhancing Machine Learning Performance
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Data Science plays an essential role in many organizations and industries to become data-driven in their decision-making and workflow, as models can provide relevant input in areas such as social media, the stock market, and manufacturing industries. To train models of quality, data preparation methods such as feature extraction are used to extract relevant features. LÄS MER
4. Time Series Anomaly Detection in Radio Test
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Production tests evaluate products with automated systems enabling swift data collection, while anomaly detection in the gathered data is widely employed in industries for damage prediction and issue prevention. Ericsson, a leader in the telecommunications industry, has a Temperature Quality Test (TQT) platform which involves precise performance measurements on radios, gathering abundant data in both single value and time series formats to evaluate and improve tested products. LÄS MER
5. Forecasting Efficiency in Cryptocurrency Markets : A machine learning case study
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Financial time-series are not uncommon to research in an academic context. This is possibly not only due to its challenging nature with high levels of noise and non-stationary data, but because of the endless possibilities of features and problem formulations it creates. LÄS MER