Activities per year
Abstract / Description of output
Functional Data Analysis (FDA) is devoted to the study of data which are functions. Support Vector Machine (SVM) is a benchmark tool for classification, in particular, of functional data. SVM is frequently used with a kernel (e.g.: Gaussian) which involves a scalar bandwidth parameter. In this paper, we propose to use kernels with functional bandwidths. In this way, accuracy may be improved, and the time intervals critical for classification are identified. Tuning the functional parameters of the new kernel is a challenging task expressed as a continuous optimization problem, solved by means of a heuristic. Our experiments with benchmark data sets show the advantages of using functional parameters and the effectiveness of our approach.
Original language | English |
---|---|
Pages (from-to) | 195-207 |
Journal | European Journal of Operational Research |
Volume | 275 |
Issue number | 1 |
Early online date | 24 Nov 2018 |
DOIs | |
Publication status | Published - 16 May 2019 |
Keywords / Materials (for Non-textual outputs)
- data mining
- Functional Data classification
- parameter tuning
- SVM
- functional bandwidth
Fingerprint
Dive into the research topics of 'Functional-bandwidth kernel for Support Vector Machine with Functional Data: An alternating optimization algorithm'. Together they form a unique fingerprint.Activities
- 1 Participation in conference
-
CRC Credit Scoring and Credit Control XVI conference
Belen Martin-Barragan (Presenter)
28 Aug 2019 → 30 Aug 2019Activity: Participating in or organising an event types › Participation in conference
Profiles
-
Belen Martin-Barragan
- Business School - Reader in Management Science
- Management Science and Business Economics
- Edinburgh Strategic Resilience Initiative
- Credit Research Centre
- Management Science
- Edinburgh Centre for Financial Innovations
Person: Academic: Research Active