Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable Sensors
The resilience of machine learning models for anxiety detection through wearable technology was explored. The effectiveness of feature-based and end-to-end machine learning models for anxiety detection was evaluated under varying conditions of Gaussian noise. By adding synthetic Gaussian noise to a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/88 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549449160032256 |
|---|---|
| author | Abdulrahman Alkurdi Jean Clore Richard Sowers Elizabeth T. Hsiao-Wecksler Manuel E. Hernandez |
| author_facet | Abdulrahman Alkurdi Jean Clore Richard Sowers Elizabeth T. Hsiao-Wecksler Manuel E. Hernandez |
| author_sort | Abdulrahman Alkurdi |
| collection | DOAJ |
| description | The resilience of machine learning models for anxiety detection through wearable technology was explored. The effectiveness of feature-based and end-to-end machine learning models for anxiety detection was evaluated under varying conditions of Gaussian noise. By adding synthetic Gaussian noise to a well-known open access affective states dataset collected with commercially available wearable devices (WESAD), a performance baseline was established using the original dataset. This was followed by an examination of the impact of noise on model accuracy to better understand model performance (F<sub>1</sub>-score and Accuracy) changes as a function of noise. The results of the analysis revealed that with the increase in noise, the performance of feature-based models dropped from a high of 90% F1-score and 92% accuracy to 65% and 70%, respectively; while end-to-end models showed a decrease from an 85% F1-score and 87% accuracy to below 60% and 65%, respectively. This indicated a proportional decline in performance across both feature-based and end-to-end models as noise levels increased, challenging initial assumptions about model resilience. This analysis highlights the need for more robust algorithms capable of maintaining accuracy in noisy, real-world environments and emphasizes the importance of considering environmental factors in the development of wearable anxiety detection systems. |
| format | Article |
| id | doaj-art-756902a6f0514ec7a59dcf4b68125b14 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-756902a6f0514ec7a59dcf4b68125b142025-01-10T13:14:24ZengMDPI AGApplied Sciences2076-34172024-12-011518810.3390/app15010088Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable SensorsAbdulrahman Alkurdi0Jean Clore1Richard Sowers2Elizabeth T. Hsiao-Wecksler3Manuel E. Hernandez4Department of Mechanical Science & Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USADepartment of Psychiatry and Behavioral Medicine, University of Illinois College of Medicine at Peoria, Peoria, IL 61605, USADepartment of Industrial & Enterprise Systems Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USADepartment of Mechanical Science & Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USADepartment of Biomedical and Translational Sciences, Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, IL 61801, USAThe resilience of machine learning models for anxiety detection through wearable technology was explored. The effectiveness of feature-based and end-to-end machine learning models for anxiety detection was evaluated under varying conditions of Gaussian noise. By adding synthetic Gaussian noise to a well-known open access affective states dataset collected with commercially available wearable devices (WESAD), a performance baseline was established using the original dataset. This was followed by an examination of the impact of noise on model accuracy to better understand model performance (F<sub>1</sub>-score and Accuracy) changes as a function of noise. The results of the analysis revealed that with the increase in noise, the performance of feature-based models dropped from a high of 90% F1-score and 92% accuracy to 65% and 70%, respectively; while end-to-end models showed a decrease from an 85% F1-score and 87% accuracy to below 60% and 65%, respectively. This indicated a proportional decline in performance across both feature-based and end-to-end models as noise levels increased, challenging initial assumptions about model resilience. This analysis highlights the need for more robust algorithms capable of maintaining accuracy in noisy, real-world environments and emphasizes the importance of considering environmental factors in the development of wearable anxiety detection systems.https://www.mdpi.com/2076-3417/15/1/88anxietymachine learningwearable technologydeep learningmultimodal |
| spellingShingle | Abdulrahman Alkurdi Jean Clore Richard Sowers Elizabeth T. Hsiao-Wecksler Manuel E. Hernandez Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable Sensors Applied Sciences anxiety machine learning wearable technology deep learning multimodal |
| title | Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable Sensors |
| title_full | Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable Sensors |
| title_fullStr | Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable Sensors |
| title_full_unstemmed | Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable Sensors |
| title_short | Resilience of Machine Learning Models in Anxiety Detection: Assessing the Impact of Gaussian Noise on Wearable Sensors |
| title_sort | resilience of machine learning models in anxiety detection assessing the impact of gaussian noise on wearable sensors |
| topic | anxiety machine learning wearable technology deep learning multimodal |
| url | https://www.mdpi.com/2076-3417/15/1/88 |
| work_keys_str_mv | AT abdulrahmanalkurdi resilienceofmachinelearningmodelsinanxietydetectionassessingtheimpactofgaussiannoiseonwearablesensors AT jeanclore resilienceofmachinelearningmodelsinanxietydetectionassessingtheimpactofgaussiannoiseonwearablesensors AT richardsowers resilienceofmachinelearningmodelsinanxietydetectionassessingtheimpactofgaussiannoiseonwearablesensors AT elizabeththsiaowecksler resilienceofmachinelearningmodelsinanxietydetectionassessingtheimpactofgaussiannoiseonwearablesensors AT manuelehernandez resilienceofmachinelearningmodelsinanxietydetectionassessingtheimpactofgaussiannoiseonwearablesensors |