no code implementations • 20 Jan 2023 • Pekka Siirtola, Juha Röning
As a main result of this article, it is shown that feature relevance analysis cannot only be used to detect the concept drift but also to explain the reason for the drift when a limited number of typical reasons for the concept drift are predefined.
no code implementations • 16 Mar 2022 • Bike Chen, Wei Peng, Xiaofeng Cao, Juha Röning
Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes.
no code implementations • 24 Feb 2020 • Tuomo Alasalmi, Jaakko Suutala, Heli Koskimäki, Juha Röning
When the amount of data for training is limited, the traditional approach to improve calibration starts to crumble.
no code implementations • 30 Jan 2020 • Tuomo Alasalmi, Jaakko Suutala, Heli Koskimäki, Juha Röning
Many classification applications require accurate probability estimates in addition to good class separation but often classifiers are designed focusing only on the latter.
no code implementations • 29 May 2019 • Pekka Siirtola, Heli Koskimäki, Juha Röning
In this study, a novel method to obtain user-dependent human activity recognition models unobtrusively by exploiting the sensors of a smartphone is presented.
no code implementations • 29 May 2019 • Pekka Siirtola, Heli Koskimäki, Juha Röning
At first, the recognition is based on user-independent model.
no code implementations • 28 May 2019 • Pekka Siirtola, Heli Koskimäki, Juha Röning
Inertial sensor data from three body positions are used, and the classification is based on Learn++ ensemble method.