Search Results for author: Tommi Kärkkäinen

Found 9 papers, 4 papers with code

Toward Scalable and Transparent Multimodal Analytics to Study Standard Medical Procedures: Linking Hand Movement, Proximity, and Gaze Data

no code implementations8 Dec 2023 Ville Heilala, Sami Lehesvuori, Raija Hämäläinen, Tommi Kärkkäinen

This study employed multimodal learning analytics (MMLA) to analyze behavioral dynamics during the ABCDE procedure in nursing education, focusing on gaze entropy, hand movement velocities, and proximity measures.

Minimal Learning Machine for Multi-Label Learning

1 code implementation9 May 2023 Joonas Hämäläinen, Amauri Souza, César L. C. Mattos, João P. P. Gomes, Tommi Kärkkäinen

Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices.

Multi-Label Classification Multi-Label Learning

Knowledge Discovery from Atomic Structures using Feature Importances

no code implementations28 Feb 2023 Joakim Linja, Joonas Hämäläinen, Antti Pihlajamäki, Paavo Nieminen, Sami Malola, Hannu Häkkinen, Tommi Kärkkäinen

Molecular-level understanding of the interactions between the constituents of an atomic structure is essential for designing novel materials in various applications.

Interpretable Machine Learning

An Additive Autoencoder for Dimension Estimation

1 code implementation13 Oct 2022 Tommi Kärkkäinen, Jan Hänninen

An additive autoencoder for dimension reduction, which is composed of a serially performed bias estimation, linear trend estimation, and nonlinear residual estimation, is proposed and analyzed.

Dimensionality Reduction

Scalable Initialization Methods for Large-Scale Clustering

2 code implementations23 Jul 2020 Joonas Hämäläinen, Tommi Kärkkäinen, Tuomo Rossi

In the experiments, comparison of the proposed methods to the K-means++ and K-means|| methods is conducted using an extensive set of reference and synthetic large-scale datasets.


Mislabel Detection of Finnish Publication Ranks

no code implementations19 Dec 2019 Anton Akusok, Mirka Saarela, Tommi Kärkkäinen, Kaj-Mikael Björk, Amaury Lendasse

The paper proposes to analyze a data set of Finnish ranks of academic publication channels with Extreme Learning Machine (ELM).

Minimal Learning Machine: Theoretical Results and Clustering-Based Reference Point Selection

no code implementations22 Sep 2019 Joonas Hämäläinen, Alisson S. C. Alencar, Tommi Kärkkäinen, César L. C. Mattos, Amauri H. Souza Júnior, João P. P. Gomes

Specifically, for a small number of reference points, the clustering-based methods outperformed the standard random selection of the original MLM formulation.


Cannot find the paper you are looking for? You can Submit a new open access paper.