Extending CNN Classification Capabilities Using a Novel Feature to Image Transformation (FIT) Algorithm

Ammar S. Salman, Odai S. Salman, Garrett E. Katz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

In this work, we developed a novel approach with two main components to process raw time-series and other data forms as images. This includes a feature extraction component that returns 18 Frequency and Amplitude based Series Timed (FAST18) features for each raw input signal. The second component is the Feature to Image Transformation (FIT) algorithm which generates uniquely coded image representations of any numerical feature sets to be fed to Convolutional Neural Networks (CNNs). The study used two datasets: 1) behavioral biometrics dataset in the form of time-series signals and 2) EEG eye-tracker dataset in the form of numerical features. In earlier work, we used FAST18 to extract features from the first dataset. Different classifiers were used and Deep Neural Network (DNN) was the best. In this work, we used FIT on the same features and invoked CNN which scored 96% accuracy surpassing the best DNN results. For the second dataset, the FIT with CNN significantly outperformed DNN scoring ~90% compared to ~60%. An ablation study was performed to test noise effects on classification and the results show high tolerance to large noise. Possible extensions include time-series classification, medical signals, and physics experiments where classification is complex and critical.

Original languageEnglish (US)
Title of host publicationIntelligent Computing - Proceedings of the 2020 Computing Conference
EditorsKohei Arai, Supriya Kapoor, Rahul Bhatia
PublisherSpringer
Pages198-213
Number of pages16
ISBN (Print)9783030522452
DOIs
StatePublished - 2020
EventScience and Information Conference, SAI 2020 - London, United Kingdom
Duration: Jul 16 2020Jul 17 2020

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1229 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceScience and Information Conference, SAI 2020
CountryUnited Kingdom
CityLondon
Period7/16/207/17/20

Keywords

  • Ablation
  • Anti-spoofing protection
  • Biometrics
  • CFS
  • CNN stochastic gradient descend optimizer
  • Feature to Image Transformation FIT
  • Fingerprint
  • Frequency and Amplitude based Series Timed (FAST18)
  • Spoofing

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Extending CNN Classification Capabilities Using a Novel Feature to Image Transformation (FIT) Algorithm'. Together they form a unique fingerprint.

  • Cite this

    Salman, A. S., Salman, O. S., & Katz, G. E. (2020). Extending CNN Classification Capabilities Using a Novel Feature to Image Transformation (FIT) Algorithm. In K. Arai, S. Kapoor, & R. Bhatia (Eds.), Intelligent Computing - Proceedings of the 2020 Computing Conference (pp. 198-213). (Advances in Intelligent Systems and Computing; Vol. 1229 AISC). Springer. https://doi.org/10.1007/978-3-030-52246-9_14