iLid

Rostaminia, Soha; Mayberry, Addison; Ganesan, Deepak; Marlin, Benjamin M.; Gummeson, Jeremy

doi:10.1145/3090088

Cited by 19 publications

(2 citation statements)

References 52 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results showed the mode, Hurst, sample entropy, and mean as the best for all the EOG features. Additionally, the ensemble classifier provided comparatively good performance and accuracy compared to the other classifiers [ 47 ], as it used the bagging strategy. This improvement in accuracy came with a much longer response time and fewer error [ 48 ].…”

Section: Resultsmentioning

confidence: 99%

An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning

Murugan

Sivakumar

Kavitha

et al. 2023

Sensors

View full text Add to dashboard Cite

Driving safely is crucial to avoid death, injuries, or financial losses that can be sustained in an accident. Thus, a driver’s physical state should be monitored to prevent accidents, rather than vehicle-based or behavioral measurements, and provide reliable information in this regard. Electrocardiography (ECG), electroencephalography (EEG), electrooculography (EOG), and surface electromyography (sEMG) signals are used to monitor a driver’s physical state during a drive. The purpose of this study was to detect driver hypovigilance (drowsiness, fatigue, as well as visual and cognitive inattention) using signals collected from 10 drivers while they were driving. EOG signals from the driver were preprocessed to remove noise, and 17 features were extracted. ANOVA (analysis of variance) was used to select statistically significant features that were then loaded into a machine learning algorithm. We then reduced the features by using principal component analysis (PCA) and trained three classifiers: support vector machine (SVM), k-nearest neighbor (KNN), and ensemble. A maximum accuracy of 98.7% was obtained for the classification of normal and cognitive classes under the category of two-class detection. Upon considering hypovigilance states as five-class, a maximum accuracy of 90.9% was achieved. In this case, the number of detection classes increased, resulting in a reduction in the accuracy of detecting more driver states. However, with the possibility of incorrect identification and the presence of issues, the ensemble classifier’s performance produced an enhanced accuracy when compared to others.

show abstract

Section: Resultsmentioning

confidence: 99%

An Electro-Oculogram (EOG) Sensor’s Ability to Detect Driver Hypovigilance Using Machine Learning

Murugan

Sivakumar

Kavitha

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Specifically, our focus is on classifying five different upper facial action units -raising eyebrows (AU01), lowering eyebrows (AU04), raising cheek (AU06), and nose wrinkler (AU09) which are known to be the most important facial actions for pain sensing. In addition to these, we also show that we can detect blinks (AU45) which provides useful information regarding fatigue, attention and even dopaminergic levels [25,46,47,51]. Prior work has focused on detecting these changes using a camera but our goal is to detect these using EOG electrodes on an unobtrusive wearable eyeglass.…”

Section: Challenges In Detecting Upper Facial Actions For Pain Monitomentioning

confidence: 91%

W!nce

Rostaminia

Lamson

Maji

et al. 2019

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

The ability to unobtrusively and continuously monitor one's facial expressions has implications for a variety of application domains ranging from affective computing to health-care and the entertainment industry. The standard Facial Action Coding System (FACS) along with camera based methods have been shown to provide objective indicators of facial expressions; however, these approaches can also be fairly limited for mobile applications due to privacy concerns and awkward positioning of the camera. To bridge this gap, W!NCE re-purposes a commercially available Electrooculography-based eyeglass (J!NS MEME) for continuously and unobtrusively sensing of upper facial action units with high fidelity. W!NCE detects facial gestures using a two-stage processing pipeline involving motion artifact removal and facial action detection. We validate our system's applicability through extensive evaluation on data from 17 users under stationary and ambulatory settings, a pilot study for continuous pain monitoring and several performance benchmarks. Our results are very encouraging, showing that we can detect five distinct facial action units with a mean F1 score of 0.88 in stationary and 0.82 in ambulatory settings, and that we can accurately detect facial gestures that due to pain. CCS Concepts: • Human-centered computing → Mobile devices; User studies; • Computing methodologies → Neural networks; • Applied computing → Consumer health;

show abstract