Sökning: "Tolkbarhet"
Visar resultat 6 - 10 av 17 uppsatser innehållade ordet Tolkbarhet.
6. Hybrid Ensemble Methods: Interpretible Machine Learning for High Risk Aeras
Master-uppsats, KTH/Matematisk statistikSammanfattning : Despite the access to enormous amounts of data, there is a holdback in the usage of machine learning in the Cyber Security field due to the lack of interpretability of ”Blackbox” models and due to heterogenerous data. This project presents a method that provide insights in the decision making process in Cyber Security classification. LÄS MER
7. Improving Occupant’s sleep quality with the help of OURA ring and data from Smart Buildings
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Well-being is associated with comfort and health, and it represents wellness and quality of life. Sleep quality is an important index when evaluating a person’s well-being. LÄS MER
8. On the impact of geospatial features in real estate appraisal with interpretable algorithms
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Real estate appraisal is the means of defining the market value of land and property affixed to it. Many different features determine the market value of a property. For example, the distance to the nearest park or the travel time to the central business district may be significant when determining its market value. LÄS MER
9. Adding external factors in Time Series Forecasting : Case study: Ethereum price forecasting
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The main thrust of time-series forecasting models in recent years has gone in the direction of pattern-based learning, in which the input variable for the models is a vector of past observations of the variable itself to predict. The most used models based on this traditional pattern-based approach are the autoregressive integrated moving average model (ARIMA) and long short-term memory neural networks (LSTM). LÄS MER
10. Interpreting Multivariate Time Series for an Organization Health Platform
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Machine learning-based systems are rapidly becoming popular because it has been realized that machines are more efficient and effective than humans at performing certain tasks. Although machine learning algorithms are extremely popular, they are also very literal and undeviating. LÄS MER