Online Mental Fatigue Monitoring via Indirect Brain Dynamics Evaluation

2021 ◽  
pp. 1-40
Author(s):  
Yuangang Pan ◽  
Ivor W. Tsang ◽  
Yueming Lyu ◽  
Avinash K Singh ◽  
Chin-Teng Lin
Keyword(s):  
Steady State ◽  
Traffic Accidents ◽  
Low Cost ◽  
Mental Fatigue ◽  
Data Driven ◽  
Behavioral Measure ◽  
Eeg Signals ◽  
Regression Methods ◽  
Fatigue Monitoring ◽  
Fatigue Estimation

Driver mental fatigue leads to thousands of traffic accidents. The increasing quality and availability of low-cost electroencephalogram (EEG) systems offer possibilities for practical fatigue monitoring. However, non-data-driven methods, designed for practical, complex situations, usually rely on handcrafted data statistics of EEG signals. To reduce human involvement, we introduce a data-driven methodology for online mental fatigue detection: self-weight ordinal regression (SWORE). Reaction time (RT), referring to the length of time people take to react to an emergency, is widely considered an objective behavioral measure for mental fatigue state. Since regression methods are sensitive to extreme RTs, we propose an indirect RT estimation based on preferences to explore the relationship between EEG and RT, which generalizes to any scenario when an objective fatigue indicator is available. In particular, SWORE evaluates the noisy EEG signals from multiple channels in terms of two states: shaking state and steady state. Modeling the shaking state can discriminate the reliable channels from the uninformative ones, while modeling the steady state can suppress the task-nonrelevant fluctuation within each channel. In addition, an online generalized Bayesian moment matching (online GBMM) algorithm is proposed to online-calibrate SWORE efficiently per participant. Experimental results with 40 participants show that SWORE can maximally achieve consistent with RT, demonstrating the feasibility and adaptability of our proposed framework in practical mental fatigue estimation.

scholarly journals Detecting driver mental fatigue based on Electroencephalogram (EEG) signals during simulated driving

2021 ◽  
Vol 1070 (1) ◽  
pp. 012096
Author(s):  
S Pradeep Kumar ◽  
Suganiya Murugan ◽  
Jerritta Selvaraj ◽  
Arun Sahayadhas
Keyword(s):  
Mental Fatigue ◽  
Eeg Signals ◽  
Simulated Driving ◽  
Electroencephalogram Eeg

scholarly journals Design, manufacture and testing of a prototype obstacle-detection device at blind corners: an automated highway system technology

2020 ◽  
Author(s):  
Charles Atombo ◽  
Emmanuel Gbey ◽  
Apevienyeku Kwami Holali
Keyword(s):  
Traffic Accidents ◽  
Low Cost ◽  
Effective Area ◽  
Obstacle Detection ◽  
The Road ◽  
Vibration Sensors ◽  
Road Signs ◽  
Sensor Module ◽  
Vehicle Path ◽  
Automated Highway

Abstract Traffic accidents on highways are attributed mostly to the "invisibility" of oncoming traffic and road signs. "Speeding" also causes drivers to reduce the effective radius of the vehicle path in the curve, thus trespassing into the lane of the oncoming traffic. The main aim of this paper was to develop a multisensory obstacle-detection device that is affordable, easy to implement and easy to maintain to reduce the risk of road accidents at blind corners. An ultrasonic sensor module with a maximum measuring angle of 15° was used to ensure that a significant portion of the lane was detected at the blind corner. The sensor covered a minimum effective area of 0.5 m2 of the road for obstacle detection. Yellow light was employed to signify caution while negotiating the blind corner. Two photoresistors (PRs) were used as sensors because of the limited number of pins on the microcontroller (Arduino Uno). However, the device developed for this project achieved obstacle detection at blind corners at relatively low cost and can be accessed by all road users. In real-world applications, the use of piezoelectric accelerometers (vibration sensors) instead of PR sensors would be more desirable in order to detect not only cars but also two-wheelers.

scholarly journals Data-Driven Reduced-Order Modeling of Convective Heat Transfer in Porous Media

Fluids ◽  
2021 ◽  
Vol 6 (8) ◽  
pp. 266
Author(s):  
Péter German ◽  
Mauricio E. Tano ◽  
Carlo Fiorina ◽  
Jean C. Ragusa
Keyword(s):  
Heat Transfer ◽  
Porous Medium ◽  
Porous Media ◽  
Steady State ◽  
Convective Heat Transfer ◽  
Convective Heat ◽  
Data Driven ◽  
Reduced Order ◽  
Medium Formulation ◽  
Flow Resistances

This work presents a data-driven Reduced-Order Model (ROM) for parametric convective heat transfer problems in porous media. The intrusive Proper Orthogonal Decomposition aided Reduced-Basis (POD-RB) technique is employed to reduce the porous medium formulation of the incompressible Reynolds-Averaged Navier–Stokes (RANS) equations coupled with heat transfer. Instead of resolving the exact flow configuration with high fidelity, the porous medium formulation solves a homogenized flow in which the fluid-structure interactions are captured via volumetric flow resistances with nonlinear, semi-empirical friction correlations. A supremizer approach is implemented for the stabilization of the reduced fluid dynamics equations. The reduced nonlinear flow resistances are treated using the Discrete Empirical Interpolation Method (DEIM), while the turbulent eddy viscosity and diffusivity are approximated by adopting a Radial Basis Function (RBF) interpolation-based approach. The proposed method is tested using a 2D numerical model of the Molten Salt Fast Reactor (MSFR), which involves the simulation of both clean and porous medium regions in the same domain. For the steady-state example, five model parameters are considered to be uncertain: the magnitude of the pumping force, the external coolant temperature, the heat transfer coefficient, the thermal expansion coefficient, and the Prandtl number. For transient scenarios, on the other hand, the coastdown-time of the pump is the only uncertain parameter. The results indicate that the POD-RB-ROMs are suitable for the reduction of similar problems. The relative L2 errors are below 3.34% for every field of interest for all cases analyzed, while the speedup factors vary between 54 (transient) and 40,000 (steady-state).

Data-driven parameter estimation of steady-state load models

2016 ◽  
Author(s):  
Tushar ◽  
Shikhar Pandey ◽  
Anurag K. Srivastava ◽  
Penn Markham ◽  
Navin Bhatt ◽  
...  
Keyword(s):  
Parameter Estimation ◽  
Steady State ◽  
Data Driven ◽  
Load Models

Multipoint kinetic methods evaluated for quantitation of theophylline with prosthetic group label immunoassay.

1982 ◽  
Vol 28 (10) ◽  
pp. 2081-2087 ◽  
Author(s):  
J D Lin ◽  
H L Pardue
Keyword(s):  
Steady State ◽  
Single Point ◽  
Reaction System ◽  
Fixed Time ◽  
Total System ◽  
Prosthetic Group ◽  
Order Zero ◽  
Regression Methods ◽  
Fitting Method ◽  
Processing Steps

Abstract We describe the development and evaluation of a multipoint kinetic approach to the measurement and data-processing steps in immunoassays. Nonlinear regression methods are used to fit data obtained during the kinetic phase of the immunochemical reaction to a model that represents the kinetic behavior of the total system. This approach is evaluated for quantitation of theophylline with a new reaction system in which FAD is the label in a homogeneous reaction system. Competition for antibody binding sites between drug and labeled drug is monitored by the activity of glucose oxidase (EC 1.1.3.4) generated by the reaction of unbound label with apoglucose oxidase. The process is fit well by a parallel first-order/zero-order model and regression methods are used to predict steady-state velocities from non-steady-state portions of the response. One fitting method yields results in about 3 min after mixing, as compared with longer than 8 min for single-point fixed-time methods. Steady-state velocities vary linearly with theophylline concentration.

scholarly journals A Portable Fuzzy Driver Drowsiness Estimation System

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4093
Author(s):  
Alimed Celecia ◽  
Karla Figueiredo ◽  
Marley Vellasco ◽  
René González
Keyword(s):  
Real Time ◽  
Traffic Accidents ◽  
Fuzzy Inference ◽  
Low Cost ◽  
Raspberry Pi ◽  
Inference System ◽  
Visual Occlusion ◽  
Computational Performance ◽  
Estimation System ◽  
Definition Of

The adequate automatic detection of driver fatigue is a very valuable approach for the prevention of traffic accidents. Devices that can determine drowsiness conditions accurately must inherently be portable, adaptable to different vehicles and drivers, and robust to conditions such as illumination changes or visual occlusion. With the advent of a new generation of computationally powerful embedded systems such as the Raspberry Pi, a new category of real-time and low-cost portable drowsiness detection systems could become standard tools. Usually, the proposed solutions using this platform are limited to the definition of thresholds for some defined drowsiness indicator or the application of computationally expensive classification models that limits their use in real-time. In this research, we propose the development of a new portable, low-cost, accurate, and robust drowsiness recognition device. The proposed device combines complementary drowsiness measures derived from a temporal window of eyes (PERCLOS, ECD) and mouth (AOT) states through a fuzzy inference system deployed in a Raspberry Pi with the capability of real-time response. The system provides three degrees of drowsiness (Low-Normal State, Medium-Drowsy State, and High-Severe Drowsiness State), and was assessed in terms of its computational performance and efficiency, resulting in a significant accuracy of 95.5% in state recognition that demonstrates the feasibility of the approach.

Assessment and Correction of Solar Radiation Measurements with Simple Neural Networks

Atmosphere ◽  
2020 ◽  
Vol 11 (11) ◽  
pp. 1160
Author(s):  
Jason Kelley
Keyword(s):  
Neural Networks ◽  
Solar Radiation ◽  
Low Cost ◽  
Environmental Data ◽  
Data Driven ◽  
Technical Requirements ◽  
Standard Procedures ◽  
Comparable Accuracy ◽  
Radiation Sensors ◽  
Radiation Measurements

Solar radiation received at the Earth’s surface provides the energy driving all micro-meteorological phenomena. Local solar radiation measurements are used to estimate energy mediated processes such as evapotranspiration (ET); this information is important in managing natural resources. However, the technical requirements to reliably measure solar radiation limits more extensive adoption of data-driven management. High-quality radiation sensors are expensive, delicate, and require skill to maintain. In contrast, low-cost sensors are widely available, but may lack long-term reliability and intra-sensor repeatability. As weather stations measure solar radiation and other parameters simultaneously, machine learning can be used to integrate various types of environmental data, identify periods of erroneous measurements, and estimate corrected values. We demonstrate two case studies in which we use neural networks (NN) to augment direct radiation measurements with data from co-located sensors, and generate radiation estimates with comparable accuracy to the data typically available from agro-meteorology networks. NN models that incorporated radiometer data reproduced measured radiation with an R2 of 0.9–0.98, and RMSE less than 100 Wm−2, while models using only weather parameters obtained R2 less than 0.75 and RMSE greater than 140 Wm−2. These cases show that a simple NN implementation can complement standard procedures for estimating solar radiation, create opportunities to measure radiation at low-cost, and foster adoption of data-driven management.

scholarly journals An Instant Donning Multi-Channel EEG Headset (with Comb-Shaped Dry Electrodes) and BCI Applications

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1537 ◽  
Author(s):  
Jeehoon Kim ◽  
Jeongsu Lee ◽  
Chungmin Han ◽  
Kwangsuk Park
Keyword(s):  
Steady State ◽  
Visual Evoked Potential ◽  
Alpha Rhythm ◽  
Eeg Signals ◽  
State Response ◽  
Dry Electrodes ◽  
Auditory Steady State Response ◽  
New Type ◽  
Electroencephalogram Eeg ◽  
Validation Experiments

We developed a new type of electroencephalogram (EEG) headset system with comb-shaped electrodes that enables the wearer to quickly don and utilize it in daily life. Two models that can measure EEG signals using up to eight channels have been implemented. The electrodes implemented in the headsets are similar to a comb and are placed quickly by wiping the hair (as done with a comb) using the headset. To verify this headset system, donning time was measured and three brain computer interface (BCI) application experiments were conducted. Alpha rhythm-based, steady-state visual evoked potential (SSVEP)-based, and auditory steady state response (ASSR)-based BCI systems were adopted for the validation experiments. Four subjects participated and ten trials were repeated in the donning experiment. The results of the validation experiments show that reliable EEG signal measurement is possible immediately after donning the headsets without any preparation. It took approximately 10 s for healthy subjects to don the headsets, including an earclip with reference and ground electrodes. The results of alpha rhythm-based BCI showed 100% accuracy. Furthermore, the results of SSVEP-based and ASSR-based BCI experiments indicate that performance is sufficient for BCI applications; 95.7% and 76.0% accuracies were obtained, respectively. The results of BCI paradigm experiments indicate that the new headset type is feasible for various BCI applications.

Sign in / Sign up

Export Citation Format

Share Document