My first healthy PIZZA
August 23, 2020
Student Research Assistant
Fraunhofer SCAI, Sankt Augustin, Germany
AIOLOS PROJECT - ALERT model
- Rule-based text mining approach to generate COVID-19/symptom knowledge graph.
- Generation of multidimensional, quantitative, longitudinal datasets from social media platforms (Google Trends and Twitter).
- Implementation of algorithms (SH_ESD test, isolation forest and LSTM autoencoder) to detect anomalies in time series data.
- Time series trend analysis: log-linear regression model.
- Trend forecasting model generation (sliding window Random Forest and LSTM) and predict onset waves of RKI confirmed cases and hospitalization in Germany.
