4 citations · 7 across the 4 of their papers we have counts for
5 papers
Flexible framework for generating synthetic electrocardiograms and photoplethysmograms
Katri Karhinoja, Antti Vasankari, Jukka-Pekka Sirkiä +3
By generating synthetic biosignals, the quantity and variety of health data can be increased. This is especially useful when training machine learning models by enabling data augme…
Playtime Measurement with Survival Analysis
Markus Viljanen, Antti Airola, Jukka Heikkonen +1
Maximizing product use is a central goal of many businesses, which makes retention and monetization two central analytics metrics in games. Player retention may refer to various du…
A two-step learning approach for solving full and almost full cold start problems in dyadic prediction
Tapio Pahikkala, Michiel Stock, Antti Airola +3
Dyadic prediction methods operate on pairs of objects (dyads), aiming to infer labels for out-of-sample dyads. We consider the full and almost full cold start problem in dyadic pre…
Identification of functionally related enzymes by learning-to-rank methods
Michiel Stock, Thomas Fober, Eyke Hüllermeier +6
Enzyme sequences and structures are routinely used in the biological sciences as queries to search for functionally related enzymes in online databases. To this end, one usually de…
Linear Time Feature Selection for Regularized Least-Squares
Tapio Pahikkala, Antti Airola, Tapio Salakoski
We propose a novel algorithm for greedy forward feature selection for regularized least-squares (RLS) regression and classification, also known as the least-squares support vector…