Augmented multi-head classification network: MHATT

Garrett I. Cayce; Arthur C. Depoian II; Colleen P. Bailey; Parthasarathy Guturu

doi:10.1117/12.2664123

14 June 2023 Augmented multi-head classification network: MHATT

Garrett I. Cayce, Arthur C. Depoian II, Colleen P. Bailey, Parthasarathy Guturu

Proceedings Volume 12547, Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII; 125470Z (2023) https://doi.org/10.1117/12.2664123
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

Classification of one-dimensional (1D) data is important for a variety of complex problems. From the finance industry to audio processing to the medical field, there are many industries that utilize 1D data. Machine learning techniques have excelled at solving these classification problems, but there is still room for improvement because the techniques have not been perfected. This paper proposes a novel architecture called Multi-Head Augmented Temporal Transformer (MHATT) for 1D classification of time-series data. Highly modified vision transformers were used to improve performance while keeping the network exceptionally efficient. To showcase its efficacy, the network is applied to heartbeat classification using the MIT-BIH OSCAR dataset. This dataset was ethically-split to ensure a fair and intensive test for networks. The novel architecture is 94.6% more efficient and had a peak accuracy of 91.79%, which was a 13.6% reduction in error over a recent state-of-the-art network. The impressive performance and efficiency of the MHATT architecture can be exploited by edge devices for unmatched performance and flexibility of deployment.

Conference Presentation

Citation Download Citation

Garrett I. Cayce, Arthur C. Depoian II, Colleen P. Bailey, and Parthasarathy Guturu "Augmented multi-head classification network: MHATT", Proc. SPIE 12547, Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII, 125470Z (14 June 2023); https://doi.org/10.1117/12.2664123

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available