Dissimilarity-based representations for one-class classification on time series

S Mauceri, J Sweeney, J McDermott - Pattern Recognition, 2020 - Elsevier
In several real-world classification problems it can be impractical to collect samples from
classes other than the one of interest, hence the need for classifiers trained on a single …

Continuous authentication through gait analysis on a wrist-worn device

G Cola, A Vecchio, M Avvenuti - Pervasive and Mobile Computing, 2021 - Elsevier
Being distinctive of every individual, gait can be used as a biometric feature to authenticate
the owner of a wearable device. This paper proposes and evaluates an authentication …

Dissimilarity-preserving representation learning for one-class time series classification

S Mauceri, J Sweeney, M Nicolau… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
We propose to embed time series in a latent space where pairwise Euclidean distances
(EDs) between samples are equal to pairwise dissimilarities in the original space, for a given …

Feature extraction by grammatical evolution for one-class time series classification

S Mauceri, J Sweeney, M Nicolau… - Genetic Programming and …, 2021 - Springer
When dealing with a new time series classification problem, modellers do not know in
advance which features could enable the best classification performance. We propose an …

One-class subject authentication using feature extraction by grammatical evolution on accelerometer data

S Mauceri, J Sweeney, J McDermott - Heuristics for Optimization and …, 2021 - Springer
Abstract In this study Grammatical Evolution (GE) is used to extract features from
accelerometer time series in order to increase the performance of a Kernel Density …

ADLs detection with a wrist-worn accelerometer in uncontrolled conditions

S Fioretti, M Olivastrelli, A Poli, S Spinsante… - … on Wearables in …, 2020 - Springer
Abstract In 2017, the European Commission estimated that 29% of European population will
be aged 65 and over, by 2070. The capability of tracking and recognizing people's daily …

Classificação de uma classe para seleção de conjuntos de dados sintéticos em meta-aprendizado

RR PARENTE - 2022 - bdtd.ibict.br
A seleção de algoritmos é uma tarefa crucial e desafiadora no aprendizado de máquina em
diferentes domínios do conhecimento. O meta-aprendizado trata a seleção de algoritmos …

One-Class Subject Authentication Using Feature Extraction by Grammatical

S Mauceri, J Sweeney… - Heuristics for Optimization …, 2020 - books.google.com
Abstract In this study Grammatical Evolution (GE) is used to extract features from
accelerometer time series in order to increase the performance of a Kernel Density …

[PDF][PDF] One-Class Time Series Classification

S Mauceri - 2020 - researchrepository.ucd.ie
This thesis contributes to the state of the art of time series classification and machine
learning by investigating three novel data-driven representations for time series in the …