# A Deep Learning Based Ternary Task Classification System Using Gramian Angular Summation Field in fNIRS Neuroimaging Data

arXiv: https://arxiv.org/abs/2101.05891 · HTML: https://mlsanity.com/paper/2101.05891/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 12 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 3 of 3)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Imaging Time-Series to Improve Classification and Imputation](https://mlsanity.com/paper/1506.00327/) (2015)
- [Mental State Recognition via Wearable EEG](https://mlsanity.com/paper/1602.00985/) (2016)

## Built on by (most cited first, 3 of 3)

- [Gramian Angular Fields for leveraging pretrained computer vision models with anomalous diffusion trajectories](https://mlsanity.com/paper/2310.01416/) (2023)
- [Enhancing Cognitive Workload Classification Using Integrated LSTM Layers and CNNs for fNIRS Data Analysis](https://mlsanity.com/paper/2407.15901/) (2024)
- [Hybrid Deep Learning Model to Estimate Cognitive Effort from fNIRS Signals](https://mlsanity.com/paper/2504.13883/) (2025)

## Abstract (arXiv)

Functional near-infrared spectroscopy (fNIRS) is a non-invasive, economical method used to study its blood flow pattern. These patterns can be used to classify tasks a subject is performing. Currently, most of the classification systems use simple machine learning solutions for the classification of tasks. These conventional machine learning methods, which are easier to implement and interpret, usually suffer from low accuracy and undergo a complex preprocessing phase before network training. The proposed method converts the raw fNIRS time series data into an image using Gramian Angular Summation Field. A Deep Convolutional Neural Network (CNN) based architecture is then used for task classification, including mental arithmetic, motor imagery, and idle state. Further, this method can eliminate the feature selection stage, which affects the traditional classifiers' performance. This system obtained 87.14% average classification accuracy higher than any other method for the dataset.