Feature extraction and dynamic identification of drivers’ emotions

Wang, Xiaoyuan; Liu, Yaqi; Wang, Fang; Wang, Jianqiang; Liu, Liping; Wang, Jingheng

doi:10.1016/j.trf.2019.01.002

Cited by 43 publications

(25 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The

formed the initial observed variables. We applied the factor analysis method to reduce the dimension of the original observation variables in SPSS 24 [ 28 ]. Table 3 shows the common factor variance of the initial observed variables.…”

Section: Study 1-a: Driving Intention Prediction Model Based On Hmmentioning

confidence: 99%

Differences in Driving Intention Transitions Caused by Driver’s Emotion Evolutions

Liu

Wang

2020

IJERPH

Self Cite

View full text Add to dashboard Cite

Joining worldwide efforts to understand the relationship between driving emotion and behavior, the current study aimed at examining the influence of emotions on driving intention transition. In Study 1, taking a car-following scene as an example, we designed the driving experiments to obtain the driving data in drivers’ natural states, and a driving intention prediction model was constructed based on the HMM. Then, we analyzed the probability distribution and transition probability of driving intentions. In Study 2, we designed a series of emotion-induction experiments for eight typical driving emotions, and the drivers with induced emotion participated in the driving experiments similar to Study 1. Then, we obtained the driving data of the drivers in eight typical emotional states, and the driving intention prediction models adapted to the driver’s different emotional states were constructed based on the HMM severally. Finally, we analyzed the probabilistic differences of driving intention in divers’ natural states and different emotional states, and the findings showed the changing law of driving intention probability distribution and transfer probability caused by emotion evolution. The findings of this study can promote the development of driving behavior prediction technology and an active safety early warning system.

show abstract

“…The

Section: Study 1-a: Driving Intention Prediction Model Based On Hmmentioning

confidence: 99%

Differences in Driving Intention Transitions Caused by Driver’s Emotion Evolutions

Liu

Wang

2020

IJERPH

Self Cite

View full text Add to dashboard Cite

show abstract

“… Spectral Subtraction Method: Spectral subtraction is a technique used to recover signal energy or amplitude in additional noise by extracting an approximation of the normal noise range from the noisy signal spectrum [33][34][35][36][37], [65].  Wiener Filtering for enhancement: It is a filter that uses noise range, stationary signal, known and additive noise to approximate a desired or target the random process and observed noise stream by filtering a linear time-invariant (LTI) [38][39][40], [66].…”

Section: Filtering Techniquesmentioning

confidence: 99%

An Appraisal on Speech and Emotion Recognition Technologies based on Machine Learning

Kumar¹,

Jason²

2020

IJRTE

View full text Add to dashboard Cite

In earlier days, people used speech as a means of communication or the way a listener is conveyed by voice or expression. But the idea of machine learning and various methods are necessary for the recognition of speech in the matter of interaction with machines. With a voice as a bio-metric through use and significance, speech has become an important part of speech development. In this article, we attempted to explain a variety of speech and emotion recognition techniques and comparisons between several methods based on existing algorithms and mostly speech-based methods. We have listed and distinguished speaking technologies that are focused on specifications, databases, classification, feature extraction, enhancement, segmentation and process of Speech Emotion recognition in this paper

show abstract

“…The liquid inlet velocity is set to zero for all cases because of there being no water supply into the reactors. The inlet conditions for the turbulent energy and the dissipation rate are estimated according to Wang and Wang:

k_{in} = 0.004 u_{g,in}^{2}

ϵ_{in} = C_{μ}^{3 / 4} k_{in}^{3 / 2} / (0.07 D)

At the top of the column, the liquid axial velocity is zero, while all other variables at the outlet are set as

\partial φ / \partial z = 0

. The fixedFluxPressure boundary condition is applied to the pressure field at the walls, which adjusts the pressure gradient so that the boundary flux matches the velocity boundary.…”

Section: Numerical Detailsmentioning

confidence: 99%

“…It is derived by the ensemble average of the fluctuating component of the drag forces between bubbles and the liquid phase. The model of Lopez de Bertodano was used by many authors, however, the coefficient was taken at different values between 0.09 and 1.0 . Burns et al derived a formulation based on the Favre averaging of the drag term, and obtained acceptable results.…”

Section: Introductionmentioning

confidence: 99%

CFD‐PBE‐PBE simulation of an airlift loop crystallizer

Cheng

Yang

et al. 2018

Can J Chem Eng

View full text Add to dashboard Cite

A complete solver (CFD‐PBE‐PBE) for crystallization processes in an airlift loop crystallizer is developed in OpenFOAM (open‐source field operation and manipulation) in this work. It combines computational fluid dynamics (CFD) with population balance equations (PBE) for both gas bubbles and crystals. Models for gas‐liquid mass transfer and chemical reaction are included as well in the solver. PBE describing bubble coalescence and breakage is solved by the cell average method. Primary nucleation, secondary nucleation, and particle growth are considered in the PBE describing the crystallization process. The solver is validated with the formation of calcium carbonate via the reaction of CO2 with Ca(OH)2 solution in an airlift reactor. Effects of the chemical enhancement factor and crystallization kinetics on predictions are systematically investigated. Variation of predicted pH value, concentration of Ca2+, mean particle size, and crystal size distribution (CSD) with time is in qualitative and semi‐quantitative agreement with the published experimental data, when the appropriate crystallization kinetics are used. Effects of operation parameters such as initial concentration and superficial gas velocity are further numerically examined. The increase in superficial gas velocity results in the increasing consumption rates of OH‐ and Ca2+, while the particle diameter seems unchanged in the present simulation. A higher initial concentration of reactants will lead to a smaller particle diameter and a narrower CSD. The predicted results indicate that the developed solver is feasible, and can be used for the design and scale‐up of airlift loop crystallizers.

show abstract

Feature extraction and dynamic identification of drivers’ emotions

Cited by 43 publications

References 22 publications

Differences in Driving Intention Transitions Caused by Driver’s Emotion Evolutions

Differences in Driving Intention Transitions Caused by Driver’s Emotion Evolutions

An Appraisal on Speech and Emotion Recognition Technologies based on Machine Learning

CFD‐PBE‐PBE simulation of an airlift loop crystallizer

Contact Info

Product

Resources

About