Predicting Sleeping Quality using Convolutional Neural Networks

TL;DR

This paper introduces a CNN-based approach for sleep quality prediction, benchmarking its performance against traditional machine learning methods across multiple datasets to establish a baseline for future research.

Contribution

The paper proposes a novel CNN architecture for sleep stage classification and provides a comprehensive performance comparison with traditional methods on public datasets.

Findings

CNN outperforms traditional methods in accuracy and sensitivity

Benchmark results establish baseline metrics for sleep classification

Analysis across datasets demonstrates CNN's robustness

Abstract

Identifying sleep stages and patterns is an essential part of diagnosing and treating sleep disorders. With the advancement of smart technologies, sensor data related to sleeping patterns can be captured easily. In this paper, we propose a Convolution Neural Network (CNN) architecture that improves the classification performance. In particular, we benchmark the classification performance from different methods, including traditional machine learning methods such as Logistic Regression (LR), Decision Trees (DT), k-Nearest Neighbour (k-NN), Naive Bayes (NB) and Support Vector Machine (SVM), on 3 publicly available sleep datasets. The accuracy, sensitivity, specificity, precision, recall, and F-score are reported and will serve as a baseline to simulate the research in this direction in the future.