Bio-signals Collecting System for Fatigue Level Classification.

Fatigue is a risk factor that reduces quality of life and work efficiency, and threatens safety in a high-risk environment. However, fatigue is not yet precisely defined and is not a quantified concept as it relies on subjective evaluation. The purpose of this study is to manage risks, improve mission efficiency, and prevent accidents through the development of machine learning and deep learning based fatigue level classifier. Acquiring true fatigue levels to train machine learning and deep learning fatigue classifier may play a fundamental role. Aims of this study are to develop a bio-signal collecting device and to establish a protocol for capturing and purifying data for extracting the true fatigue levels accurately. The bio-signal collection system gathered visual, thermal, and vocal signals at the same time for one minute. The true fatigue level of the subjects is classified through the Daily Multidimensional Fatigue Inventory and physiological indicators related to fatigue for screening the subjective factors out. The generated dataset is constructed as a DB along with the true fatigue levels and is provided to the research institutions. In conclusion, this study proposes a research method that collects bio-signals and extracts the true fatigue levels for training machine learning and deep learning based fatigue level classifier to evaluate the fatigue of healthy subjects in multi-levels.

The Psychomotor Cognition Test for Measurement of Sleepiness/Fatigue on a Touch Screen.

The Psychomotor Vigilance Test (PVT) is a simple and reliable performance test that measures sustained attention, alertness level, and fatigue level. The PVT is a convenient tool that can be used in real time in situ through a mobile device without the assistance of experts and therefore can be used to improve safety and prevent accidents. However, the original PVT is vulnerable to the subject's intentional concentration on the test, and the variance range among tests is narrow; these factors limit its usefulness in classifying the level of fatigue. This study overcome these limitations and develop the Psychomotor Cognition Test (PCT) by transforming the PVT into a tool that stably classifies fatigue levels, still requiring a short period of time. In the PCT, compared to the PVT, reaction time is significantly longer, and success rate is significantly lower (both p<0.0001). Whereas reaction time and success rate of the PVT do not show a significant correlation with fatigue level, those of the PCT show significant correlations with fatigue level, respectively (p<0.001). This study suggests that the PCT can be used in real time in situ as a risk management tool for workers performing dangerous tasks and can become an even more powerful tool when combined with other physiological indicators.

G-LOC Warning Algorithms Based on EMG Features of the Gastrocnemius Muscle.

BACKGROUND: G-induced loss of consciousness (G-LOC) is mainly caused by failure to sustain an oxygenated blood supply to the pilot's brain because of the sudden acceleration in the direction of the +Gz axis, and is considered a critical safety issue. The purpose of this study was to develop G-LOC warning algorithms based on monitoring electromyograms (EMG) of the gastrocnemius muscle on the calf. METHODS: EMG data was retrieved from a total of 67 pilots and pilot trainees of the Korean Air Force during high-G training on a human centrifugal simulator. Seven EMG features were obtained from root mean square (RMS), integrated absolute value (IAV), and mean absolute value (MAV) for muscle contraction, slope sign changes (SSC), waveform length (WL), zero crossing (ZC), and median frequency (MF) for muscle contraction and fatigue. RESULTS: Out of seven EMG features, IAV and WL showed a rapid decay before G-LOC. Based on these findings, this study developed two algorithms which can detect G-LOC during flight and provide warning signals to the pilots. The probability of G-LOC occurrence was detected through monitoring the decay trend for representing muscle endurance and climb rate of the IAV and WL value during sudden acceleration above 6 G, representing muscle power. The sensitivity of the algorithms using IAV and WL features was 100% and the specificity was 66.7%. DISCUSSION: This study suggests that a G-LOC detecting and warning system may be a customized, real-time countermeasure by improving the accuracy of detecting G-LOC.Kim S, Cho T, Lee Y, Koo H, Choi B, Kim D. G-LOC warning algorithms based on EMG features of the gastrocnemius muscle. Aerosp Med Hum Perform. 2017; 88(8):737-742.

Application of flat panel OLED display technology for the point-of-care detection of circulating cancer biomarkers.

Point-of-care molecular diagnostics can provide efficient and cost-effective medical care, and they have the potential to fundamentally change our approach to global health. However, most existing approaches are not scalable to include multiple biomarkers. As a solution, we have combined commercial flat panel OLED display technology with protein microarray technology to enable high-density fluorescent, programmable, multiplexed biorecognition in a compact and disposable configuration with clinical-level sensitivity. Our approach leverages advances in commercial display technology to reduce pre-functionalized biosensor substrate costs to pennies per cm(2). Here, we demonstrate quantitative detection of IgG antibodies to multiple viral antigens in patient serum samples with detection limits for human IgG in the 10 pg/mL range. We also demonstrate multiplexed detection of antibodies to the HPV16 proteins E2, E6, and E7, which are circulating biomarkers for cervical as well as head and neck cancers.