• Corpus ID: 235828933

Stress Classification and Personalization: Getting the most out of the least

@article{Sah2021StressCA,
  title={Stress Classification and Personalization: Getting the most out of the least},
  author={Ramesh Kumar Sah and Hassan Ghasemzadeh},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.05666}
}
Stress detection and monitoring is an active area of research with important implications for the personal, professional, and social health of an individual. Current approaches for affective state classification use traditional machine learning algorithms with features computed from multiple sensor modalities. These methods are data-intensive and rely on handcrafted features which impede the practical applicability of these sensor systems in daily lives. To overcome these shortcomings, we… 

Figures and Tables from this paper

Designing Deep Neural Networks Robust to Sensor Failure in Mobile Health Environments

This work shows that the naive known methods of dealing with missing input data such as zero-filling or mean-Filling are not suitable for senors-based prediction and proposes an algorithm that can reconstruct theMissing input data for unavailable sensors and can outperform the baselines by large accuracy margins.

References

SHOWING 1-10 OF 14 REFERENCES

Feature Selection Framework for XGBoost Based on Electrodermal Activity in Stress Detection

This paper proposes several enhancements to get higher f1-scores, including less overlapped signal segmentation, more signal processing features, and extreme gradient boosting classification algorithm (XGBoost), and selects dominant features according to their importance in classifier and correlation among other features while keeping high performance.

Stress Detection with Machine Learning and Deep Learning using Multimodal Physiological Data

  • Pramod BobadeV. M
  • Computer Science
    2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA)
  • 2020
This paper proposes different machine learning and deep learning techniques for stress detection on individuals using multimodal dataset recorded from wearable physiological and motion sensors, which can prevent a person from various stress-related health problems.

Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection

This work introduces WESAD, a new publicly available dataset for wearable stress and affect detection that bridges the gap between previous lab studies on stress and emotions, by containing three different affective states (neutral, stress, amusement).

Continuous stress detection using a wrist device: in laboratory and real life

A method for continuous detection of stressful events using data provided from a commercial wrist device that consists of three machine-learning components: a laboratory stress detector that detects short-term stress every 2 minutes; an activity recognizer that continuously recognizes user's activity and thus provides context information; and a context-based stress detectors that exploits the output of the laboratorystress detector and the user's context in order to provide the final decision on 20 minutes interval.

GSR Analysis for Stress: Development and Validation of an Open Source Tool for Noisy Naturalistic GSR Data

This paper proposes an open-source tool, which uses deep learning algorithms alongside statistical algorithms to extract GSR features for stress detection and shows that it is capable of detecting stress with the accuracy of 92 percent using 10-fold cross-validation and using the features extracted from the tool.

Development and Evaluation of an Ambulatory Stress Monitor Based on Wearable Sensors

A new spectral feature is proposed that estimates the balance of the autonomic nervous system by combining information from the power spectral density of respiration and heart rate variability and is validated on a binary discrimination problem when subjects are placed under two psychophysiological conditions: mental stress and relaxation.

Automatic Stress Detection in Working Environments From Smartphones’ Accelerometer Data: A First Step

Data from the smartphone's built-in accelerometer is used to detect behavior that correlates with subjects stress levels, and a maximum overall accuracy of 71% for user-specific models and an accuracy of 60% for the use of similar-users models are achieved, relying solely on data from a single accelerometer.

What is the best multi-stage architecture for object recognition?

It is shown that using non-linearities that include rectification and local contrast normalization is the single most important ingredient for good accuracy on object recognition benchmarks and that two stages of feature extraction yield better accuracy than one.

Stress and health.

Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct

Welcome to the Proceedings of the 2016 ACM Joint International Conference on Pervasive and Ubiquitous Computing (UbiComp 2016), held in Heidelberg, Germany from Sep. 12-16, co-located with the