# Intent Recognition in Smart Living Through Deep Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1702.06830 · HTML: https://mlsanity.com/paper/1702.06830/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2017.

## Built on by (most cited first, 9 of 9)

- [Genetic algorithm for feature selection of EEG heterogeneous data](https://mlsanity.com/paper/2103.07117/) (2021)
- [Color-based classification of EEG Signals for people with the severe locomotive disorder](https://mlsanity.com/paper/2304.11068/) (2023)
- [Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights](https://mlsanity.com/paper/2310.13901/) (2023)
- [General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement Learning](https://mlsanity.com/paper/2505.09737/) (2025)
- [Machine Learning-based EEG Applications and Markets](https://mlsanity.com/paper/2208.05144/) (2022)
- [The evolution of AI approaches for motor imagery EEG-based BCIs](https://mlsanity.com/paper/2210.06290/) (2022)
- [Motor Imagery EEG Signal Classification Using Minimally Random Convolutional Kernel Transform and Hybrid Deep Learning](https://mlsanity.com/paper/2508.16179/) (2025)
- [RatioWaveNet: A Learnable RDWT Front-End for Robust and Interpretable EEG Motor-Imagery Classification](https://mlsanity.com/paper/2510.21841/) (2025)
- [GCMCG: A Clustering-Aware Graph Attention and Expert Fusion Network for Multi-Paradigm, Multi-task, and Cross-Subject EEG Decoding](https://mlsanity.com/paper/2512.00574/) (2025)

## Abstract (arXiv)

Electroencephalography (EEG) signal based intent recognition has recently attracted much attention in both academia and industries, due to helping the elderly or motor-disabled people controlling smart devices to communicate with outer world. However, the utilization of EEG signals is challenged by low accuracy, arduous and time- consuming feature extraction. This paper proposes a 7-layer deep learning model to classify raw EEG signals with the aim of recognizing subjects' intents, to avoid the time consumed in pre-processing and feature extraction. The hyper-parameters are selected by an Orthogonal Array experiment method for efficiency. Our model is applied to an open EEG dataset provided by PhysioNet and achieves the accuracy of 0.9553 on the intent recognition. The applicability of our proposed model is further demonstrated by two use cases of smart living (assisted living with robotics and home automation).