Professional Documents
Culture Documents
Paper 9
Paper 9
fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
(a)
(b) (c)
Fig. 1. (a) The system diagram with its specification. (b) The developed EEG bio-potentials conditioning circuit and the open-source hardware platform. (c)
Prototype of the proposed wearable DDD system.
In order to detect driver drowsiness as early as possible, was developed and combined with a commercial smartwatch to
several decision-making models have been proposed to classify extract FFT features and implement the probabilistic model.
driver drowsiness into several levels. For example, M. Compared with previous studies, this system has several
Murugappan et al. classified drowsiness into 4 levels with 84.4% advantages. First, this system uses probabilistic model which
accuracy by using subtractive fuzzy classifier [12]. Khushaba. can estimate the probability of drowsy driving with a value
R. N. et al. classified drowsiness to 5 levels with about 95% range from 0 to 1 and thus can effectively increase the detection
accuracy by using kernel spectral regression based linear resolution. Second, an early-warning threshold probability was
discrimination analysis and the ground truth of Wierwille scale developed to detect drowsiness at its early stage. Third, the
[13]. However, most of this kind of studies used conventional ground truth of percentage of eyelid closure over pupil over
wet Ag/AgCI electrodes. In addition, their methods were not time (PERCLOS) was used in all the experiments. Unlike other
evaluated in real-time way. In a more recent work [9], C. T. Lin ground truth mentioned above, PERCLOS techniques has been
et al. developed a dry electrode based driver vigilance commercialized and intensively tested for more than ten years
monitoring system for real-time monitoring driver drowsiness. by U. S. NHTSA for field application (actual truck drivers
Based on the ground truth of subjects’ response time to lane driving commercial trucks) [14-16]. Therefore, it can ensure
departure event, this system could classify drowsiness to more convincing experimental results. Fourth, the proposed
maximum 8 levels by using the combined approach of model was implemented on wearable smartwatch which could
threshold-based method and a support vector regression model. effectively prevent the distracted driving caused by the usage of
In this paper, we propose to apply Support Vector Machine smartphones or tablets in cars [6, 9, 17-19].
(SVM)-based posterior probabilistic model (SVMPPM) for The rest of the paper is organized as follows. Section II
automated drowsiness detection and estimation of the severity presents the whole system architecture includes hardware parts
of drowsy driving based on dry EEG sensor signals obtained and proposed SVMPPM. Section III presents the experiment
from simulated driving experiment. To evaluate the real-time design for simulated driving. Section IV presents the validation
performance of the proposed model, a wireless EEG headband
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
of the system with further discussion. Section V concludes the order to acquire the most useful EEG bands for DDD
paper with future work. application (θ (4-7 Hz), α (8-12 Hz) and β (13-30 Hz)), the
output signal of IA is transferred to High Pass Filter (HPF) and
II. SYSTEM ARCHITECTURE then filtered by the Low Pass Filter (LPF). Finally, the signal is
A. System Overview amplified by amplifier to meet the ADC’s input requirement
(0~3.3V).
As shown in Fig. 1, the wearable EEG system is powered by
a 3.6 V 100-mAh lithium-ion rechargeable battery and consists C. SPU
of a wireless EEG acquisition device and a commercial The SPU consists of an inexpensive open-source hardware
smartwatch. The wireless EEG acquisition device consists of an (OSHW) platform [25] and a BLE transmitter. The OSHW
EEG sensory input unit (SIU) as well as a sensory processing platform was chosen because it is inexpensive, lightweight, and
unit (SPU). The analog EEG data (i.e., voltage output) from the
specifically designed for wearable devices with sewing holes. It
SIU are converted to digital data and wirelessly transmitted to
includes a low-power 8-bit MCU with a clock speed of 8 MHz.
the smartwatch via a Bluetooth Low-Energy (BLE) or so-called
It has 6 ADC input pins. The present application uses a single
Bluetooth Smart module by SPU [20]. The smartwatch further
extracts EEG features and estimates the probability of drowsy ADC pin. The digitalized EEG data is saved to SRAM and then
driving by a well-trained SVMPPM. If the estimated directly transmitted to the smartwatch via BLE interface. BLE
probability exceeds a particular threshold, a drowsy warning is used because the smartwatch has embedded BLE
can be activated. For real-life application, the wireless EEG microprocessors with capabilities for connecting wirelessly to
acquisition device is sewed to an elastic headband. The EEG external biomedical sensors by lower power consumption.
headband and the smartwatch can continuously work 5.2 and D. EEG Signal Analysis and Feature Extraction
4.5 hours respectively. The following sections introduce in
detail the major components of this system. A digital band-pass filter (4-30Hz) is implemented in
smartwatch to further filter EEG signals, particularly the power
B. SIU line noise (60Hz). In order to reduce individual differences and
SIU consists of three EEG dry electrodes and an EEG enhance the generalization of the SVM model, relative EEG
bio-potentials conditioning circuit. Among the three dry power ratio (power percentages) are used instead of the
electrodes, one ear-clip dry electrode, from Laxtha Co., Ltd absolute EEG power values as input features for building the
[21], serves as a ground electrode and the remaining two dry SVM model. EEG power is calculated as the sum of the squared
electrodes, adapted from [22], are used as EEG signal FFT magnitude of the EEG signal using 2 s Hamming windows;
electrodes. The main difference between the current system and the algorithm is implemented in real-time way on the
smartwatch. Then, the power percentage (Per) is calculated by
that presented in [22] is that we sewed conductive fabric on the
dividing the FFT power of one EEG band by the sum of the
surface of the copper fill plate instead of using copper fill
FFT power of all three EEG bands, as shown in Equation 1,
directly to sense EEG bio-potentials . This alteration effectively
where, zi={ θ, α, β }.
reduces motion artifacts as well as the skin-electrode interface
impedance, as illustrated by Chin in [23]. Its comparison with
Power ( z i )
conventional wet Ag/AgCl electrodes can be found in Section Per ( z i ) = 3
´ 100% (1)
IV. According to the International 10–20 system, they are å Power ( z i )
placed at occipital regions O1 and O2, where is highly i =1
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
Therefore, a set of three features (Per (θ), Per (α) and Per (β)) (e.g., radial basis function (RBF), polynomial kernel function
were extracted from each 2-s EEG epoch. In order to (Poly)), sigmoid kernel function (Sig) and regulation parameter
synchronize the extracted EEG features with the 1-min ground C, SVM is able to do this mapping work and accomplish
truth measurements (PERCLOS), every 30 sets of feature were classification without the need to know explicitly what the
successively averaged before applying SVM operation. The mapping function is.
feature extraction procedure for one participant is demonstrated
in Fig. 2. 2) SVMPPM
E. Drowsiness Detection Model In addition to classifying the labels into the categories of
“drowsy” or “alert,” the posterior class probabilities, i.e.,
We propose to apply SVMPPM for automated drowsiness r
detection and estimation of the severity of drowsy driving P(class=+1| x ) can be calculated based on the outputs of binary
based on EEG signals. As shown in Fig. 3, applying this model SVM classification model using the method initially described
includes three stages - Stage I: Data collection, Stage II: Model by Platt [26]. Briefly, its main idea is given by Equation 2,
r r r
building and Stage III: Model testing. The Stage I and Stage III where, w × F ( x ) + b is just the SVM output for input dataset x .
involve one-hour simulated driving experiment (see Section A and B are parameters that are determined by an improved
III), during which both EEG signals and features were Platt algorithm [27].
recorded. The Stage II was implemented on MATLAB in PC in
off-line way, which aims to build an optimized model and r 1
P (class = +1 | x ) = r r (2)
develop the threshold probabilities for recognizing early 1 + exp( A( w × F ( x ) + b) + B )
drowsy warning group and full drowsy warning group. The
well-trained model was then transferred to smartwatch for Therefore, compared to previous multi-class classification
real-time final testing. The following subsections introduce in based models, the SVMPPM can further increase the resolution
detail the major components of proposed approach. of detected drowsiness level (any value from 0 to 1). For
example, the probability “0” indicates a full alert state, whereas
a value close to “1” indicates a severely drowsy driving state. In
addition, through the combination of true labels and estimated
posterior probabilities, a threshold probability could be found
to provide early warning before drivers actually become
severely drowsy.
F. Wearable Application
Wrist-worn smart devices, particularly
Android-Wear-OS-based smartwatches, have emerged as
miniature but powerful devices for data acquisition and
processing. In this study, a commercial smartwatch is
combined with external EEG sensors, in order to design a fully
wearable DDD system. For real-life application, a simple user
interface was designed (as shown in Fig.4), where the traffic
light principle was used to indicate driving status. The green
light and yellow light indicate safe driving and early warning
respectively. For the full warning, the red light is ON, and
additionally a long-lasting vibration, which is produced by the
built-in vibration sensor of the smartwatch, is activated
simultaneously. Also, a pie chart is used to imitate a sort of
watch face and display the extracted EEG features in real-time
way. The complete working flowchart of this wearable
Fig. 3. Flowchart of estimation of driver drowsiness using SVM-based application is described in Fig. 5. It is very important to note
posterior probabilistic model. that besides the usage of BLE, two Services that incorporate
with two Activities are carefully designed for this smartwatch
1) Binary SVM Classification application aiming to meet the low power requirement. In
A conventional binary SVM classifier outputs a class label Android OS, each Activity corresponds to each user interface.
(e.g., +1: drowsy driving or -1: alert driving) for each input Each user interface has a short life time due to the power save
r
dataset x comprising several features (e.g., Per (θ), Per (α) and mode of smartwatch screen. So, the simplest and Activity-based
Per (β) in this study), according to the sign function way to collect data continuously is to keep the screen always
r r r r
f ( x ) = sign( w × F ( x ) + b), where the w is a vector perpendicular ON by using the WindowManager component; while Service is
to the decision surface and b is a scalar (decision surface bias). independent of Activity and specifically designed to run the
r
F (x ) is the mapping function which is used to map each input repeating task in background. So, two Services are employed to
r
dataset x from the linearly non-separable input space  n to collect data continuously in background instead of keeping
linearly separable feature space H. By using kernel functions screen ON. In this case, much power can be saved.
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
Fig. 4. Smartwatch screen showing the designed user interface for this
wearable application (termed “Brainwatch”). The three circles on the top side
display the driving status. Green circle (left side) indicates safe driving.
Yellow circle (middle) indicates early warning. Red circle (right side)
indicates full warning. The pie chart shows the EEG features.
The true alert and drowsy data are labeled based on the
combination of percentage of eyelid closure over pupil over
time (PERCLOS) and the number of adjustment (NOA) on
steering wheel. PERCLOS is a video based real-time driver
drowsiness monitoring technology. It assesses drowsiness by
measuring slow eyelid closure and estimating the proportion of
time for which the eyes are closed over 1-min interval (high
sensitivity) or 3-min interval (medium sensitivity) or 5-min
interval (low sensitivity) [16]. The approach of NOA on
steering wheel is developed by our group by using the built-in
accelerometer and gyroscope of smartwatch [30]. The basic
assumption of this approach is that alert drivers who are driving
on a highway (not city driving or countryside driving) would
Fig. 5. The working flowchart of the proposed wearable application. have more NOA on steering wheel if compared to drowsy
drivers. We found that some drivers’ faces are occasionally
outside of the camera field of view while their NOA data can
III. EXPERIMENT DESIGN AND MATERIALS remain stable. Thus, in order to provide a robust ground truth,
According to our previous experiences [28, 29], one-hour we combined the two methods together in this study. According
monotonous driving after lunch (typically around 1:00-2:30 pm) to [16] and [30], PERCLOS ≥ 12% and NOA ≤ 9 was chosen as
results in drowsiness in a majority of subjects. Therefore, the threshold to identify the presence of true drowsy driving
twenty subjects (twelve males and eight females, aged and PERCLOS < 8% and NOA > 26 for true alert driving.
30.8±9.37 years), possessing valid driver’s licenses, PERCLOS measures between 8% and 12% and NOA measures
participated in the one-hour monotonous driving experiment. between 9 and 26 can be used as the early-warning reference. In
Experimental data from fifteen subjects (subjects No.1-15) was our previous study [31, 32], we already developed a
used for building drowsiness detection model. Final testing smartphone application to measure PERCLOS. Thus, in this
phase was performed for the remaining subjects (subjects study, the measures of PERCLOS were automatically
No.16-20). implemented on the smartphone which was placed in front of
The driving simulation environment consisted of a the steering wheel.
commercial truck driving simulator (Euro Truck Simulator 2), a
Logitech® steering wheel, and acceleration and brake pedals
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
Fig 7. EEG signals (line chart) and EEG band power (pie chart) comparison between wet electrodes (the top) and dry electrodes (the bottom). For the line chart,
X-axis indicates the time. The unit is second. Y-axis indicates the amplitude of the digitalized EEG samples which are already filtered by the digital band-pass filter
(4-30Hz) in smartwatch. For the pie chart, the X-axis indicates the frequency ranged from 0 to 64Hz (the half of the sampling rate 128Hz). Y-axis indicates the
magnitude of FFT power.
Fig 8. EEG signals comparison of alert driving status (the top) and drowsy driving status (the middle). The driving status was confirmed by PERCLOS
measurement as shown on the left side of the EEG signals. The EEG signal on the bottom is the zoomed in signal that is marked by red circle aiming to clearly show
the abundant alpha wave occurred in drowsy driving status.
IV. EXPERIMENTAL RESULTS AND DISCUSSION was embedded into the smartwatch. Finally, smartwatch can
The LibSVM® (ver 3.17) [33] implementation for SVM was call library functions such as svm.svm_load_model and
used in this study. In model building stage, an optimized svm.svm_predict_probability to run SVM in real time way.
SVMPPM were trained on a PC using leave-one-subject-out A. Data Collection Stage
(LOSO) cross-validation tests with different kernel functions, Firstly, the dry electrodes were compared with conventional
such as linear kernel, RBF and Poly, and different regulation
wet Ag/AgCl electrodes. We recorded EEG signals using the
parameters “C”. LOSO approach is a cross-validation approach,
two types of electrodes in the same positions (O1 & O2) but in
where each subject serves as a test set. The specific steps are as
separate sessions (dry electrodes were tested first) when one
follows: (1) Omit one subject from the training set; (2) Train the
subject was instructed to close his eyes for 5 seconds. What we
binary classification model using the remaining subjects; (3) expected to be common between these two sessions was the
Test the omitted subject using the trained model in step (2) and appearance of obvious rhythmicity of α rhythm in time domain
calculate the binary classification accuracy and posterior
and the largest power percentage for α band in frequency
probabilities; (4) Repeat the steps that are listed above until
domain. What exactly we observed is shown in Fig. 7, which is
each subject has been omitted and tested once; (5) Calculate the
just consistent with our expectation. Similarly, every time
overall binary classification accuracy and set the threshold before formal experiment we instructed each subject to close
probabilities for final test. In model testing stage, the eyes in order to check the contact quality of dry electrodes.
parameters of the well-trained SVM model were hardcoded in
Totally 210 labeled alert datasets and 227 labeled drowsy
text-file format and stored on the Secure Digital (SD) card
datasets were collected from 15 subjects. Each dataset consists
memory of the smartwatch. Meanwhile, the LibSVM library
of three EEG features: Per(θ), Per(α) and Per(β). Fig. 8 shows
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
the examples of the recorded EEG signals that paired with one
alert dataset and one drowsy dataset. With the obvious
rhythmicity of α rhythm shown in the time-domain signals,
Per(α) is increased from 38.8% in the alert dataset to 47.4% in
the drowsy dataset. The Box-Whiskers plots (Fig. 9) show that
the median values for all 15 subjects are 16.07%, 29.37% and
54.56% for Per(θ), Per(α) and Per(β) for alert driving group,
and 12.51%, 41.72% and 45.76% for drowsy driving group.
Fig. 10 ROC curve showing sensitivity (possibility of true drowsy event) and
1-specificity (possibility of false drowsy event) for extracted EEG features.
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
Fig. 11. The histogram of estimated posterior probability for each subject (#1~#15) in training phase for alert group (left side) and drowsy group (right side). The
X-axis indicates the drowsiness level (0~1). The Y-axis indicates the number of dataset that falls into the corresponding bins of estimated drowsiness levels.
Fig. 13. The threshold probabilities for each subject in training phase for (panel A) alert group with X-axis 1~15 and (panel B) drowsy group with X-axis 16~30.
The threshold probabilities for each subject refer to the maximum probability in alert group and minimum probability in drowsy group.
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
measures for drowsy driving is from 0.12 to 0.20. Few of them which are expected as subjects started to appear some irregular
can reach to 0.30 and very few of them can reach to 0.90. In
contrast, the measures representing alert driving (cluster_1)
show better agreement because there is no big difference (near
the bias of zero). Specifically, most of SVM-based probabilities
for alert dataset are around 0.05. This corresponds to the range
of PERCLOS measures for alert dataset (min=0 and
max=0.07).
Besides the Bland-Altman plot, the threshold probabilities
for each subject were summarized in Fig. 13 and two overall
threshold probabilities which indicate early warning threshold
(TH_1:P=0.424) and fully warning threshold (TH_2: P=0.545)
were developed to validate the calculated probabilities in
real-life application. The rules for this validation are
summarized in Table II.
TABLE II
RULES (THRESHOLDS FOR DDD)
Rules Ground truth Decision
8% ≤ PERCLOS < 12% (a)
0.424 ≤ P < 0.545 Early warning
9 < NOA ≤ 26
PERCLOS ≥ 12%
P ≥ 0.545 Full drowsy warning
NOA ≤ 9
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
10
TABLE IV
COMPARISON OF EEG AND PROBABILISTIC MODEL BASED DDD STUDIES
Evaluation
Reference No. Time window Model Dry Terminal Accuracy
Signal Source Ground Truth
electrodes Device (%)
[38] 6 min DBN Two-Channel EEG × - - -
TABLE V
COMPARISON OF POWER CONSUMPTION OF BLUETOOTH-ENABLED AND EEG-BASED DDD SYSTEMS
EEG acquisition part Power Consumption /
Reference No. Terminal device
Signal Source ADC Sampling rate (Hz) Wireless module Battery life
movements is inevitable [36] and some methods directly use used) [38]. However, the primary advantage of SVM is its
these movements to identify the early drowsy phenomenon ability to minimize both structural and empirical risk [42]. In
instead of avoiding them, such as the ground truth Wierwille this study, we apply SVM-based probabilistic model to detect
scale [37]. driver drowsiness. There are presently no ‘gold-standard’
To compare the prediction model in current work with prior methods for assessing the estimated probabilities thus direct
studies, three DDD-related studies that also involve EEG validation of the calculated posterior probability values to
signals and probabilistic models are carefully found from the another technique is not currently possible. However, based on
existing literatures (as shown in Table IV). For example, in PERCLOS measurements, the Bland-Altman plot and a
2010, G. S. Yang et al. [38] proposed a Dynamic Bayesian smartwatch-based wearable EEG system were used to validate
Network (DBN) based posterior probabilistic model to detect the estimated probability values in off-line way and real-time
driver drowsiness. They employed Independent Component way respectively.
Analysis (ICA) to preprocess EEG signals and FFT to extract To compare the practical utility, such as power consumption,
EEG features. Then, thirty sleep-deprived subjects who three EEG-based DDD studies that also involve Bluetooth
participated in a simulated driving experiment were used to communication are carefully found from the existing
validate the proposed model. However, the EEG channel literatures. For previous studies, Table V shows that the
location and the ground truth used in this study are not clear and maximum power consumption of 356mA was obtained by a
the detection accuracy using EEG alone was not reported. In Bluetooth and RF dual-mode system [3] against 31mA and
addition, the length of the time window was 6 minutes, which 33mA by Bluetooth v2.0+EDR based systems [4, 9]. By using
might be a major drawback for practical application. The other BLE module, the present work obtained the minimum power
possible practical hurdles include: 1) The usage of ICA. The consumption of 19mA. In addition, a major limitation behind
ICA is a complex algorithm that is not suitable for real-time these previous studies is that they only reported the power
application [39]. 2) The usage of wet electrodes. In 2011 and consumption of EEG acquisition device and did not include the
2014, A. Murata. et al [40, 41] proposed a Basic Bayesian terminal device which is the other indispensable device that
Estimation (BBE) based posterior probabilistic model. They constitutes the whole DDD system. Considering the practical
used shorter time window, 1 minute, to extract FFT-based EEG utility (e.g., the requirement of low-cost and easy-to-use), we
features and also conducted a simulated driving experiment to combined the DDD application-specific EEG acquisition
validate the proposed model. However, the ground truth used device and a commercial smartwatch together and 4.5-hour
was subjective (subject self-assessment-based) and wet battery life was obtained by its built-in 300 mAh battery. The
electrodes were also used. Also, the detection accuracy using battery capacity of 300mAh is quite less than that used in
EEG alone was not reported. Besides the practical hurdles and previous studies, such as 750mAh [9], 1100mAh [4] and
technical drawbacks mentioned above, building 16000mAh [3].
Bayesian-based probabilistic model needs many empirical
work including the construction of prior probability, the
conditional probabilities and transitional probability (if DBN is
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
11
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/JSEN.2015.2473679, IEEE Sensors Journal
12
[32] B. G. Lee and W. Y. Chung. (2012, Dec.). A smartphone-based driver Engineering, Pukyong National University, Busan. His current
safety monitoring system using data fusion. Sensors. [Online]. 12(12), pp. research interests include wireless sensor networks, ubiquitous
17536-17552. Available: http://www.mdpi.com/1424-8220/12/12/17536
[33] C. C. Chang and C. J. Lin. (2011, May.). LIBSVM: A library for support healthcare and automobile applications, smart lighting with
vector machines. ACM Trans Intell Syst Technol. [Online]. 2(3), pp. visible light communication, and embedded systems. He is
27:1-27:27. Available: now the leader of team for next generation u-healthcare
http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf technology development, which is supported by the Brain
[34] S. Theodoridis, A. Pikrakis, K. Koutroumbas and D. Cavouras, “The
receiver operating characteristic curve,” in Introduction to pattern Korea 21 (BK21) plus project. He also serves as the associate
recognition: A Matlab approach, Elsevier Press, 2010. editor in IEEE Sensors Journal.
[35] J. M. Bland and D. G. Altman, “Statistical methods for assessing
agreement between two methods of clinical measurement,” Lancet. vol. 1, Boon-Leng Lee received the B.E.
no. 8476, pp. 307–310, Feb. 1986.
[36] Y. M. Chi, T. P. Jung and G. Cauwenberghs, “Dry-contact and degree in Mechanical Engineering from
Noncontact bio-potential electrodes: Methodological review,” IEEE Multimedia University, Melaka,
Reviews in Biomedical Engineering., vol. 3, pp. 106-119, Oct. 2010. Malaysia, in 2013. Since 2014, he is
[37] W. W. Wierwille and L. A. Ellsworth, “Evaluation of driver drowsiness pursuing a Master degree in
by trained raters,” Accident Analysis & Prevention., vol. 26, no. 5, pp.
571–581, Oct.1994 Engineering at Pukyong National
[38] G. S. Yang, Y. Z. Lin and P. Bhattacharya, “A driver fatigue recognition University, Busan, South Korea.
model based on information fusion and dynamic Bayesian network,” His current research interests the
Information Sciences., vol. 180, no. 10, pp.1942-1954, May. 2010. development of wearable healthcare
[39] G. Geetha, “Scrutinizing different techniques for artifact removal from
EEG signals,” International Journal of Engineering Science and sensors, mobile programming, and
Technology., vol. 3, no. 2, pp. 1167-1172, Feb. 2011. driver drowsiness detection.
[40] A. Murata, Y. Matsuda, M. Moriwaka and T. Hayami, “An Attempt to
Predict Drowsiness by Bayesian Estimation,” in Proc. SICE Annual Conf.
Tokyo, Japan, Sep. 13-18, 2011. pp. 58-63.
[41] A. Murata, Y. Urakami and M. Moriwaka, “An attempt to prevent traffic
accidents due to drowsy driving - Prediction of drowsiness by Bayesian
estimation,” in Proc. the SICE Annual Conference. Sapporo, Japan, Sep.
9-12, 2014, pp. 1708-1715.
[42] S. Gunn. (1998, May.). Support vector machines for classification and
regression. Univ. Southampton, Southampton, U. K., ISIS Tech. Rep,
1998. [Online]. pp. 6. Available:
http://www.svms.org/tutorials/Gunn1998.pdf
1530-437X (c) 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See
http://www.ieee.org/publications_standards/publications/rights/index.html for more information.