Professional Documents
Culture Documents
a r t i c l e i n f o a b s t r a c t
Article history: This study proposes a method for the estimation of peripheral vascular occlusion (PVO) in diabetic foot
Received 17 January 2013 using a support vector machine (SVM) classifier with the wolf pack search (WPS) algorithm. The long-
Received in revised form term presence of elevated blood sugar levels commonly results in peripheral neuropathy, peripheral
29 September 2013
vascular disease, nephropathy, and retinopathy in patients with Type 2 diabetes mellitus. Patients with
Accepted 5 October 2013
PVO disease have decreased walking capability and life quality in diabetes mellitus and poor peripheral
Available online 27 October 2013
circulation of PVO causes morbidity like infection and amputation of the legs or feet of diabetics. This
progressively vascular occlusion is often ignored by the patients and primary care physicians in early
Keywords:
Peripheral vascular occlusion (PVO) stage. Therefore, a reliable method of diagnostic assistance is crucial for early diagnosis and monitor-
Support vector machine (SVM) ing of PVO and prevention of amputation. Photoplethysmography (PPG) is a non-invasive technique for
Wolf pack search (WPS) detecting blood volume changes in peripheral vascular bed. Literature indicates that the pulse transit
Photoplethysmography (PPG) time increases and waveform shape changes increase in PPG of the vascular occlusion. PPG pulses of
Synchronizing chaotification feet gradually become asynchronous due to the different speed of deteriorating patency and collateral
circulation in the peripheral arteries. We utilized synchronizing chaotification to compare the bilateral
similarity and asymmetry of PPG signals, and applied SVM to estimate three degrees of PVO. Among 33
subjects tested, this classification technique could recognize various butterfly motion patterns represent-
ing severities successfully including normal condition, lower-degree disease, and higher-degree disease.
The proposed method has potential for providing diagnostic assistance for PVO of diabetics and other
high-risk populations, with efficiency and higher accuracy.
© 2013 Elsevier Ltd. All rights reserved.
1746-8094/$ – see front matter © 2013 Elsevier Ltd. All rights reserved.
http://dx.doi.org/10.1016/j.bspc.2013.10.001
46 C.-M. Li et al. / Biomedical Signal Processing and Control 9 (2014) 45–55
sympathetic nervous system [1]. PPG signals can be recorded from of synchronous detection. Chaos synchronization provides a new
earlobe, index finger, thumb, and big toe, bilaterally or unilater- approach for deeper understanding of non-linear physical systems
ally. Most current PPG applications focus on cardiac and vascular and physical informatics. In general, a chaotic system consists of
diseases [2–4] and supported by recent development in computer- a master system and a slave system, mimicking the behavior of
based digital signal processing and analysis algorithms. another chaotic system; such a design is called chaos synchroniza-
Both the time-domain and the frequency-domain methods have tion (CS). A typical CS system can be described as:
been applied to analyze plethysmograms of PVO disease [5–7].
Master system : Ẋ = A(X)X (1)
In the time-domain, the PPG signals recorded from both body
Slave System : Ẏ = A(Y )Y − U (2)
sites are described according to timing and shape features. It
was found that the differences of transit time between left and where X = [x1 , x2 , x3 ] and Y = [y1 , y2 , y3 ] are state variables, A
right signals increase as the disease severity exacerbates, and the is called coefficient matrix, and U is control input. The family
calibrated amplitudes decrease [5,6]. These findings reflected asyn- of Lorenz chaotic systems contained at least thirty members of
chronous occlusion and collateral circulation of peripheral arteries three-dimensional autonomous system widely applied to control-
in both lower limbs. It also indicates that PPG signals have compo- ling mechanical, electrical and biological systems like arrhythmias
nents of both low frequency and high frequency that were related and epileptics [11–16]. One of them called the Chen–Lee sys-
to synchronous cardiac changes in vascular blood volume with tem, with known and unknown, can generate two-scroll attractors
each heartbeat [8]. On the other hand, frequency domain analy- and showed good symmetrical behavior, with wide applications
sis showed the bilateral similarity with characteristics of higher [20,21]. This chaotic system provided a simplified mathematical
frequency in healthy subjects, and verifies the bilateral asymmetry model for generation of attractors, as described in the following
with characteristics of lower frequency in diabetic patients [9,10]. non-linear differential Eq. [19]:
⎡ ⎡
⎤ ⎤
In recent years, synchronizing chaotification has been exten- ⎤ ⎡ x1 ⎤
ẋ1 −x2 x3 ⎡
sively applied to adaptive control systems, biomedical signal a 0 0
⎢ ⎥ ⎢ ⎥ ⎢ ⎥
processing, secure communication, and information processing Master System (MS) : ⎣ ẋ2 ⎦ = ⎣0 b 0 ⎦ ⎣ x2 ⎦ + ⎢ x1 x3 ⎥
[11–16]. In this study we proposed to extract a broad range of PPG ⎣ ⎦
0 0 c 1
signals in time domain, and utilized a chaotic non-linear dynamical ẋ3 x3 x1 x2
3
system to construct a mathematical model of PPG that character- (3)
ized by random signals. This system would have broad spectrums of ⎡ ⎤
⎤ ⎡ y1 ⎤ ⎡
Fourier transform, and fractal properties of motion in phase space. ẏ1 a 0 0
⎢ ⎥ ⎢ ⎥
During the development of synchronizing chaotification, a Slave System (SS) : ⎣ ẏ2 ⎦ = ⎣ 0 b 0 ⎦ ⎣ y2 ⎦
Chen–Lee system was designed as a discrete-time chaotic system,
ẏ3
0 0 c y3
which would extract the features from PPG signals. The architec-
ture consisting of a master system and a slave system enabled the ⎡ ⎤ ⎡ ⎤
−y2 y3 u1
response of the slave system to automatically track the response
⎢y y ⎥ ⎢ ⎥
of the master system [17–19]. The dynamic error equation was ⎢ ⎥
+
⎦ + ⎣ u2 ⎦
1 3 (4)
defined as the difference between the slave system and the mas- ⎣
1
ter system, which was used to construct various butterfly patterns y1 y2 u3
for estimation of PVO severity. With a swarm-intelligence algo- 3
rithm for searching optimal solution in high-dimensional problem where a, b, and c are system parameters, and U = [u1 , u2 , u3 ] is
space [20,21], a SVM was constructed to judge the three degrees non-linear controller for tracking the differences of right-to-left
or categories of PVO: normal (Nor) condition, lower-degree (LG) sided PPG signals. For the asymptotically stable, x1 ≈ y1 , x2 ≈ y2 ,
disease, and higher-degree (HG) disease. Eventually, a wolf pack and x3 ≈ y3 , we hypothesized x1 x2 − y1 y2 ≈ (x1 − y1 )(x2 − y2 ),
search (WPS) algorithm was implemented to automatically esti- x1 x3 − y1 y3 ≈ (x1 − y1 )(x3 − y3 ), and x2 x3 − y2 y3 ≈ (x2 − y2 )(x3 − y3 ),
mate the best network parameter and adjust the desired targets and defined the error states e = [e1 , e2 , e3 ]T as Eq. (5).
with training patterns. This proposed classifier was then tested in e1 = x1 − y1 , e2 = x2 − y2 , e3 = x3 − y3 (5)
a dynamical modeling environment to improve classification accu-
Then, subtract Eq. (4) derived from Eq. (3), and define
racy. This paper is organized as follows: Section 2 addresses the
the terms, (x1 − y1 )(x2 − y2 ) = e1 e2 , (x1 − y1 )(x3 − y3 ) = e1 e3 , and
problem formulation, Section 3 describes how the pattern classifier
(x2 − y2 )(x3 − y3 ) = e2 e3 , the dynamics of the error system become
was designed, and Sections 4–6 explains the classifier training, test-
as Eq. (6).
ing results, and the final section provides a conclusion to summarize ⎡ ⎤
the efficiency of the proposed model.
⎡ ⎤ ⎡ ⎤ ⎡ x1 − y1 ⎤ −x2 x3 + y2 y3
ė1
a 0 0
⎢ ⎥ ⎣ ⎢ ⎥ ⎢ ⎥
2. Problem formulation ⎣ ė2 ⎦ = 0 b 0 ⎦ ⎣ x2 − y2 ⎦ + ⎢
⎣
x1 x3 − y1 y3 ⎥
⎦
ė3 0 0 c x3 − y3
1
(x1 x2 − y1 y2 )
2.1. The model design of chaos synchronization (CS) 3
⎡ ⎤⎡
⎡ ⎤ ⎡ e1 ⎤ 0 −e3 0 e1
⎤
The present diagnosis of lower-limb PVO relies on the ankle a 0 0
⎢ ⎥ ⎢ ⎥
0⎥⎢e ⎥
brachial pressure index as a gold standard that is insensitive ≈ ⎣ 0 b 0 ⎦ ⎣ e2 ⎦ + ⎢ e3 0
for hardened arteries. Vascular occlusion can also be diagnosed ⎣ ⎦⎣ 2 ⎦
0 0 c 1
with angiography that is invasive. Modern medicine is still lack- e3 e2 0 0 e3
3
ing a proper tool of diagnostic aid for PVO. As the occlusion of
⎡ ⎤⎡ ⎡ ⎤
peripheral arteries exacerbates, the differences of PPG transit time a −e3 0 ⎤ ⎡ ⎤ a −e3 0
e1 e1
between right and left side would increase significantly, so did ⎢ ⎥ ⎢ ⎥
= ⎢ e3 b 0⎥⎢e ⎥ = ⎢ (e3 )2 ⎥⎢ ⎥
the differences of bilateral amplitudes, referring to bilateral asyn- ⎣ ⎦⎣ 2 ⎦ ⎢⎣
0 b+
a
0 ⎥ ⎣ e2 ⎦
⎦
chronous. By contrast, both discrepancies of bilateral signals were 1
e2 0 c e3 e3
insignificant in healthy subjects, referring to bilateral approximate 3 0 0 c
synchronization. These phenomena can be described as a problem (6)
C.-M. Li et al. / Biomedical Signal Processing and Control 9 (2014) 45–55 47
Normal subjects (11) Diabetic patients (12) 4. Pattern classification using wolf pack search algorithm
PTTf (ms)
Mean 2.58 9.2 29.2 4.1. Support vector machine (SVM)
Max–min 0.3–7.4 5.1–23.7 23.6–34.8
K
fj (˚) = ˛jk wjk R(˚k , ) + biasj (10)
k=1
⎡
2 ⎤
1 − k
R(˚k , ) = exp ⎣− ⎦ (11)
2
m K
p
MSEF = (erjk )2 pmax − p wolfbest − wolfg
= wolfg + ⎝ ⎠
p+1 p
K (12) wolfg )(
j=1 k=1 pmax 2 p 2
Subject to 0 < aj ≤ 1, j = 1, 2, 3, . . ., m (wolfbest ) + (wolfg )
p p
where ˛j , , and biasj are regularization parameters, controlling a = wolfg + pwolfg (14)
compromise between maximizing the margin and minimizing the
where wolfbest is the best search route, wolfg p the search route, g
MSEF. With the non-linear SVM mechanism, a non-linear decision
the population size, p the number of running steps, pmax the max-
function is used for extending the non-linear boundary to separate
imum running step, and wolfg p the change of search route. With
the high dimensional and the training data that are non-linearly
time-varying running steps (TVRS), wolves are allowed to move
separable. Given the final outputs of node fj (), j = 1, 2, 3, . . ., m,
large distance p around the search space at the beginning stage.
fj () ∈ {0,1}, the decision function is defined as Eq. (13).
K
Each subgroup will communicate the other wolf groups and jointly
1, ≥
fj () = sign ˛jk wjk R(k , ) + biasj = sign() =
k=1 0, <
(13)
Eq. (13) is a label that determines the class of input vector . Once
a binary classifier is trained with the known training patterns and
the corresponding target associations, the targets fjk , k = 1, 2, 3, . . .,
K, are encoded as binary values with signal “1” denoting the three
disease severity, and the rest of the weights are zero. In our design,
three SVM classifiers are built for estimation of the three degrees
of PVO disease. Fig. 3 illustrates these output nodes (m = 3).
Table 2
Quantitative results of the WPS algorithm.
Task Method
Training data 23 23
Population size G = 20–40 G = 20–40
Convergent condition Maximum number of iterations pmax = 25–50 Maximum number of iterations pmax = 25–50
Parameter assignment ˛j (0 ≤ ˛j ≤ 1), , and biasj = 0 ˛j (0 ≤ ˛j ≤ 1), , biasj = 0, and p = 0–1
Note:(1) TVRS: time-varying running step; (2) CRS: constant running step.
attack the targeted quarry. By reducing the walk p, a small step errors 1 , 2 , and 3 reflect the characteristic chaotic behaviors
change allows the wolves to chase down the quarry (optimal solu- for the three disease degrees, with butterfly patterns lying in the
tion) at the end of the continuous search. Based on this metaphoric first and third quadrant. As a chaotic system displays, the choice
behavior, the WPS is summarized as follows: of parameters a, b, and c controls governs the chaotic motion,
and its trajectory diverges exponentially as these parameters
Step 1: Randomly generate a pack of wolves G, g = 1, 2, 3, . . ., G, increase.
and set the maximum number of running steps pmax . Parts of these butterfly patterns were used to train SVM classi-
Step 2: Find the best route, wolfbest , defined as optimal solution fier. We have 23 input–output pairs of training data (K = 23), each
and calculate the object function MSEF. number of averaged patterns from the same category are 11-, 6-,
Step 3: Update the running route wolfg p of all the wolves using Eq. and 6-set data, respectively. These datasets are computed from a
(14). total of 20 good-quality PPG signals from consecutive recording. We
Step 4: Circulate and update the running routes. If the maximum proposed an SVM classifier with 798 input nodes, 3 decision nodes,
number of running step is achieved or the MSEF is less than the and 3 output nodes (m = 3). The desired target vectors were encoded
pre-specified value, then stop the procedure, or else, go back to as binary values, following the pattern [w1k , w2k , w3k ] = [Nor, LG,
Step 2. HG] = [1/0, 1/0, 1/0], k = 1, 2, 3, . . ., 23, for 3 degrees, and the vectors
were encoded as Nor: [1 0 0], LG: [0 1 0], and HG: [0 0 1]. A thresh-
In the WPS algorithm, when a new solution is more optimal than old value = 0.5 was set to confirm the decision boundary using Eq.
the best solution so far, it can be saved as the best one. Therefore, (13), which can be defined as
the solution sequence is monotone decreasing. In this study, sup-
pose constant biasj = 0, adjusting parameters ˛ (˛=˛1 = ˛2 = · · · = ˛m ) 1, ≥
fj () = sign() = , j = 1, 2, 3 (17)
and would refine the discrimination accuracy in a dynamic envi- 0, <
ronment. The optimum parameters are intended to minimize the
MSEF, which are given by where the index fj () is binary value “1” referring to a possible
⎛ ⎞ degree.
˛best − ˛jg p The quantitative results of the WPS algorithm are shown in
˛jg p+1 = ˛jg p + p ⎝ ⎠ (15) Table 2. In optimization research, WPS can find a good solution
(˛best )2 + (˛jg p )2 using three control factors, such as population size, number of run-
ning step, and moving step. A WPS with constant running step is
a simplified concept to easily control parameters and implement
best − g p in engineering problems. In this study the WPS with an invari-
g p+1 p
= g + p
(best )2 + (g p )2 (16) able velocity was given by population size G = 20, 30, and 40, walk
p = 0.2, 0.5, and 0.7 for each step, with maximum allowable run-
Subject to 0 < aj ≤ 1, j = 1, 2, 3, . . ., m
ning step pmax = 25, and pre-specified value ε ≤ 0.05. The walk p
There are two convergent conditions to terminate the WPS algo- was determined following a trial-and-error selection; as a result,
rithm: (a) the objective function MSEF is less than the pre-specified the fittest parameters were obtained from the training dataset and
value ε; (b) the number of running steps achieves the maximum shown in Table 3. One of its advantages is high search speed for
allowable number pmax . Thus, the optimum parameters can be a good solution, requiring less than 5 running steps, as shown in
obtained by minimizing the MSEF. Fig. 6(a). However, when confronting with inequality constraint
0 < ˛ ≤ 1, special attention must be paid to avoid being trapped
4.3. SVM classifier training results on local minima and resulting premature convergence. Therefore,
global searching of the WPS was improved with varying running
PPG pulses were simultaneously measured from both toes of step given by the population size G = 20–40 for each running step,
the tested subjects. Then each PF–PF interval of the signals were and maximum allowable running step pmax = 25 and 50. For exper-
located, and 800 sampling data were acquired within an sampling imental analysis, only slight improvement of optimal parameters
window, as shown in Fig. 5(a), where the horizontal axis is the was obtained by increasing population size and running step. In
sampling number, and the vertical axis is the normalized ampli- addition, the whole process had a large evolutionary computation,
tude. In this figure, the rising edge left to the vertical dashed line and average CPU time also increased from 5.131 to 10.194 s. It could
exhibits a systolic phase of cardiac cycle, and the dicrotic notch edge converge within less than 10 running steps to classify the 23-pairs
on the other side can be seen during diastole in healthy compliant of training data. As a result, the fittest parameters best = 0.0879
arteries. In case that resistance or obstruction of peripheral vessels and ˛best = 0.8917 can minimize the MSEF with G = 30, pmax = 25,
increases, bilateral PPG pulses become asynchronous, resulting to and the pre-specified value ε ≤ 0.03. Fig. 6(b) illustrates the solution
proportional increase of transit time delay. According to Eq. (8), the list that is monotone decreasing. Thus, WPS with time-varying run-
dynamic errors 2i , i = 1, 2, 3, . . ., n − 2 (n = 800), were calculated ning step provides a stable mode for SVM learning and construction
and shown in Fig. 5(b). Let a = 2, b = −4, and c = −3, the dynamic procedure.
C.-M. Li et al. / Biomedical Signal Processing and Control 9 (2014) 45–55 51
Fig. 5. (a) PPG pulses at the right and left big toes from normal subject and diabetic patients with PVO disease. (b) The dynamic errors 2 for normal subject and diabetic
patients with PVO disease.
Table 3
Results of the parameter estimation.
Fig. 6. (a) Mean squared errors versus the number of running steps for WPS with
conducted by John Allen et al. [5]. Two subjects were randomly
CRS. (b) Mean squared errors versus the number of running steps for WPS with TVRS.
chosen to validate the diagnostic value of this method. Initially,
each peak-foot interval was identified with digital signal processing
5. Experimental results and discussion algorism, followed by the computation of dynamic errors. When
the trajectories approached a stable point, the origin point was
The proposed method was developed on a PC Pentium-IV seen as asymptotically stable for normal condition, as shown in
3.0 GHz with 480 MB RAM and MATLAB software (Mathwork, Nat- Fig. 8. For the bilateral synchronous signals (normal subject), the
ick, MA). Portable optical measurement was employed to acquire trajectories of the butterfly patterns were bounded in red dash-line
the biomedical signals of the tested persons. The experiment was portion (1: ±0.10 and 2: ±0.10). By contrast, at the phase plane
proceeded as the follows: (1) record PPG signals; (2) track the differ- of 1 versus 2 , their trajectories diverged in higher degree of PVO
ence of the timing parameters using the dynamic error equation; disease; accordingly, the resultant tracking dynamic errors can be
and (3) estimate PVO degree with the SVM classifier. To demon- utilized to estimate the degree of the PVO disease, as illustrated in
strate the effectiveness of the proposed method, ten subjects were Fig. 8. With the 100 consecutive PPG signals, the diagnostic results
tested as shown in Table 4. With the reference to ABPI and clinical of the ten subjects in Table 4 demonstrate that the outputs of the
presentations like findings of angiography, there are five records SVM classifier could be computed using Eq. (17), with correct esti-
of the normal subjects (#1–5), three of cases of low-degree (LG) mation in the respective output space of the Nor, LG, and HG. The
disease (#6–8), and two of high-degree (HG) (#9–10). Numerical maximum one is greater than the threshold = 0.5, and sign() = 1,
experiments are presented as detailed below to verify the proposed ≥ , indicating the possible degree. This result confirms the major
method. degrees are “LG disease” and “HG disease”, as shown in Table 4.
These test results imply that the proposed method has the poten-
5.1. PVO disease estimation tial to be a diagnostic tool for estimating the degree of PVO disease
and monitoring the progression of this vascular disorder.
Before PPG measurement, subjects were asked to relax and
lie supine on a couch for 10 min. The laboratory tempera- 5.2. Classifier performance comparison
ture was 25 ± 1 ◦ C, while the hospital room temperature was
set at 23 ± 1 ◦ C. The examination lasted for 10 min, with two In literature many classification algorithms, including artificial
PPG probes mounted on both big toes of subjects as Fig. 7 neural network [28,29], the Fuzzy method, and adaptive network-
illustrated. In Fig. 8, a representative result is displayed, con- based fuzzy inference system (ANFIS) [30], have been proposed for
taining 10 time-domain signals, dynamic errors, and butterfly PVO disease estimation. By comparison, Fuzzy method has three
motions for LG disease (#6) and HG disease (#9). Our test input variables for PTTf , PTTp , and RT, each has three mem-
results showed that the normal range of timing parameters bership functions for various ranges of bilateral timing differences;
PTTf , PTTp , and RT were: 0.3 ms–7.4 ms, 0.4 ms–22.3 ms, and further, each output variable needs three membership functions for
1.3 ms–15.6 ms, respectively, as listed in Table 1. According to individual group of Nor, LG, and HG, as shown in Table 1. The seven
the bilateral-timing differences and the ABPI, except two sub- linguistic Fuzzy rules for the three degrees are based on the ankle
jects (#6: PTTf = 15.321, PTTp = 17.286, RT = 1.964, and #9: brachial index [14].
PTTf = 33.072, PTTp = 48.500, RT = 15.428) were rightly clas- The Fuzzy decision representing the output is defuzzified using
sified to the output space of PVO diseases. the center-of-area method, which converts linguistic information
These timing differences of bilateral plethysmograms are highly to numerical center values. For the 10 subjects tested, the Fuzzy
correlated with different severity of PVO in a retrospective study method had 80% accuracy with two failures, as depicted in Table 4.
C.-M. Li et al. / Biomedical Signal Processing and Control 9 (2014) 45–55 53
Fig. 8. (a) PPG signals in the time-domain, dynamic error 2 , and butterfly motions for normal subject, (b) PPG signals in the time-domain, dynamic error 2 , and butterfly
motions for diabetic patient with LG disease and (c) PPG signals in the time-domain, dynamic error 2 , and butterfly motions for diabetic patient with HG disease.
Measurement of parameters PTTf , PTTp , and RT might be affected by training data [30]. The back-propagation algorithm is used to find
cardiac cycle, asynchronous measurement during extraction of sig- the optimum parameters under mean square error criterion, with
nals, and quantification error, leading to incorrect the PVO disease an enhanceable accuracy of estimation.
estimation. ANFIS describes the linguistic variables and memorizes A neural network classifier is an adaptive mechanism that has
some assigned weighted values, 1, 2, and 3, for the three degrees been widely applied in continuous modeling system (network
of the vascular disease. It is a feed-forward multi-layer network, topology 799 × 23 × 4 × 3), which is suitable for tasks such as tuning
integrating the basic principle of fuzzy system into a connectionist network parameters and automatic target adjustment. By contrast,
structure. Table 5 summarizes the quantitative results of compar- particle swarm optimization algorithm is an optimization tech-
isons among these methods. The results show that ANFIS can be nique that avoids the drawbacks of back-propagation algorithm,
trained by numerical data and linguistic information expressed regardless of gradient or steepest descent method. Briefly, these
by if-then rules, and can automatically construct itself from algorithms have difficulty in obtaining the first and second partial
Table 4
The results of PVO disease estimation in ten subjects.
Subject no. Mean values of bilateral differences Professional Proposed ANN decision Fuzzy decision ANFIS
physicians method (average (center value) decision
decision decision output) (center value)
(sign() = 1,
PTTf (ms) PTTp (ms) RT (ms) ≥ 0.5)
Note: (1) ANFIS method: 3 singleton membership functions, and the center values of the functions are 1, 2, and 3 for Nor, LG, and HG, (2) Fuzzy method: 1 output variable
with 3 triangular membership functions, and the center values of the functions are 0.0, 0.4, and 0.8 for Nor, LG, and HG.
54 C.-M. Li et al. / Biomedical Signal Processing and Control 9 (2014) 45–55
Table 5
Related data of the proposed method and other methods.
derivatives of non-linear mean square error function. Furthermore, experimental tests, a Chen–Lee based chaos synchronization detec-
learning performance is heavily relied on the choices of the initial tor was able to track synchronous and asynchronous indices from
condition, learning rate, and convergent condition. Under high- the bilateral PPG signals. Eventually, the dynamic errors and chao-
dimensional pattern space, the training process and classification tification patterns were successfully applied to estimate the degree
efficiency become a main problem when handling huge train- of PVO disease.
ing data. Training neural network is time-consuming, without a
guaranteed global minimum. However, the swarm intelligence can
guide searches using high-dimensional search space or multiple 6. Conclusion
particles rather than individuals. Individuals in a swarm approach
the optimum through the present solution, previous experience, In this study synchronizing chaotification for feature extrac-
and other individuals’ experiences, and can avoid of trapping at tion was designed using Chen–Lee chaotic system to estimate
a local minimum. A good solution is sensitive in consideration of disease severity of peripheral vascular occlusion. This technique
certain control factors, such as the number of iterations and pop- was developed to track dynamic errors and construct butterfly
ulation sizes, time-varying acceleration coefficients, and inertia motion patterns from the difference of the timing parameters
weight coefficient as a whole. Suitable control of those param- between bilateral PPG signals. Due to the increases of differences,
eters is important to find the optimum solution accurately and the results show that dynamic errors increase as asynchronous
efficiently. Our comparison also indicates that neural network using phenomena gradually become serious, and motion trajectories are
particle swarm optimization algorithm also has high accuracy for also increasingly revealed in the diabetic group. And then the
PVO estimation. classifier of support vector machine was applied to estimate the dis-
Another finding of the present study is the proposed SVM- ease severity. In addition, numerical experiments are presented to
based classifier could be built with a small network architecture demonstrate and verify the performance of the proposed method.
(network topology 798 × 3 × 3) for high-dimensional pattern clas- This optical-based technology without extra ECG measurement
sification. A simple WPS algorithm was written to search for a could be a portable diagnostic aid for PVO as it is a noninvasive, low
good solution nonlinearly, with training data and less parame- cost, and simple-to-use method. However, automatic processing of
ter assignment. The WPS with time-varying running step would PPG waveform and timing parameters still deserves further atten-
lower the possibility of premature convergence in the early tion. In order to develop an automatic screening tool for PVO, the
search stage, and improve convergence at the end of optimiza- proposed method can be further integrated in computer-based
tion stage. So this machine learning provides a potential technique digital signal processing and telemedicine for home healthcare
for classifier design with relatively short design cycle. Through the applications.
C.-M. Li et al. / Biomedical Signal Processing and Control 9 (2014) 45–55 55
Acknowledgments [13] J.-S. Lin, J.-J. Yan, T.-L. Liao, Robust control of chaos in lorenz systems subject to
mismatch uncertainties, Chaos, Solitons & Fractals 27 (2) (2006) 501–510.
[14] X. Zhang, A. Khadra, D. Yang, D. Li, Unified impulsive fuzzy-model-based
This work is supported in part by the National Science Council controllers for chaotic systems with parameter uncertainties via LMI, Com-
of Taiwan, under contract number: NSC 101-2221-E-244-001 and munication in Nonlinear Science and Numerical Simulation 15 (1) (2010) 105–
NSC 102-2218-E-218-006, duration August 1, 2012–July 31, 2014. 144.
[15] A. Bogris, D. Kanakidis, A. Argyris, D. Syvridis, Performance characterization
The Institutional Review Board (IRB) of the Division of of a closed-loop chaotic communication system including fiber transmission
Infectious Diseases of Chi Mei Medical Center approved this in dispersion shifted fibers, IEEE Journal of Quantum Electronics 40 (9) (2004)
study. The research study was also approved by the hospital 1326–1336.
[16] Y. Hong, K.A. Shore, Power loss resilience in laser diode-based optical chaos
research ethics committee, correspondence: Dr. Chien-Ming Li,
communications systems, Journal of Light wave Technology 28 (3) (2010)
yrho@mail.ncku.edu.tw. 270–276.
[17] H.K. Chen, C.-I. Lee, Anti-control of chaos in rigid body motion, Chaos, Solitons
& Fractals 21 (4) (2004) 957–965.
References
[18] H.K. Chen, Global chaos synchronization of new chaotic systems via nonlinear
control, Chaos, Solitons & Fractals 23 (4) (2005) 1245–1251.
[1] J. Allenc, Photoplethysmography and its application in clinical physiological [19] H.K. Chen, Synchronization of two different chaotic systems: a new system and
measurement, Physiological Measurement 28 ((3) February) (2007) 1–39. each of the dynamical systems Lorenz, Chaos, Solitons & Fractals 23 (5) (2005)
[2] M. Nitzan, A. Babchenko, B. Khonokh, D. Landau, The variability of the pho- 1245–1251.
toplethysmographic signal—a potential method for the evaluation of the [20] J.H. Chen, Controlling chaos and chaotification in the Chen–Lee system
automatic nervous system, Physiological Measurement 19 (1998) 93–102. by multiple time delays, Chaos, Solitons & Fractals 36 (4) (2008) 843–
[3] M. Nitzan, A. Babchenko, B. Khonokh, Very low frequency variability in arterial 852.
blood pressure and blood volume pulse, Medical & Biological Engineering & [21] L.M. Tama, J.-H. Chen, H.-K. Chen, W.-M. Si Tou, Generation of hyperchaos from
Computing 37 (1) (1999) 54–58. the Chen–Lee system via sinusoidal perturbation, Chaos, Solitons & Fractals 38
[4] D.W. Kim, S.W. Kim, S.C. Kim, K.C. Nam, E.S. Kang, J.J. Im, Detection of dia- (3) (2005) 826–839.
betic neuropathy using blood volume ratio of finger and toe by PPG, in: [22] E. Pranckeviciene, R. Somorjai, R. Baumgartner, M.-G. Jeon, Identification of sig-
Proceedings of the 29th Annual International Conference of the IEEE Engineer- natures in biomedical spectra using domain knowledge, Artificial Intelligence
ing in Medicine and Biology Society, August, Lyon, France, vol. 23–26, 2007, pp. in Medicine 35 ((3) November) (2005) 215–226.
2211–2214. [23] J. Kamruzzaman, R.K. Begg, Support vector machines and other pattern recog-
[5] M. Nitzan, B. Khonokh, Y. Slovik, The difference in pulse transit time to the toe nition approaches to the diagnosis of cerebral palsy gait, IEEE Transactions on
and figure measured by photo-plethysmography, Physiological Measurement Biomedical Engineering 53 (12) (2006) 2479–2490.
23 (2002) 85–93. [24] M.E. Mavroforakis, H.V. Georgiou, N. Dimitropoulos, D. avourasionisis, S.
[6] J. Allen, C.P. Oates, T.A. Lees, A. Murray, Photoplethysmography detection of Theodoridis, Mammographic masses characterization based on localized tex-
lower limb peripheral arterial occlusive disease: a comparison of pulse tim- ture and dataset fractal analysis using linear, neural and support vector
ing, amplitude and shape characteristics, Physiological Measurement 26 (2005) machine classifiers, Artificial Intelligence in Medicine 37 ((2) June) (2006)
811–821. 145–162.
[7] H. Hsiu, C.-L. Hsu, T.-L. Wu, A preliminary study on the correlation of frequency [25] Y. Peng, Y. Zhang, L. Wang, Artificial intelligence in biomedical engineering and
components between finger PPG and radial arterial BP waveforms, in: Inter- informatics: an introduction and review, Artificial Intelligence in Medicine 48
national Conference on Biomedical and Pharmaceutical Engineering, 2009, pp. ((2/3) February/March) (2010) 71–73.
1–4. [26] H.S. Chang, Converging marriage in honey-bees optimization and application to
[8] W.B. Murray, P.A. Foster, The peripheral pulse wave: information overlooked, stochastic dynamic programming, Journal of Global Optimization 35 (3) (2006)
Journal of Clinical Monitoring and Computing 12 (5) (1996) 365–377. 423–441.
[9] A. Buchs, Y. Slovik, M. Rapoport, C. Rosenfeld, B. Khanokh, M. Nitzan, Right-left [27] C. Yang, X. Tu, J. Chen, Algorithm of marriage in honey bees optimization based
correlation of the sympathetically induced fluctuations of the photoplethys- on the wolf pack search, in: International Conference on Intelligent Pervasive
mographic signal in diabetic and non-diabetic subjects, Medical & Biological Computing, Jeju Island, Korea, 2007, pp. 462–467.
Engineering & Computing 43 (2) (2005) 252–257. [28] C.-H. Lin, Y.-F. Chen, Y.-C. Du, J.-X. Wu, T. Chen, Chaos synchronization detec-
[10] L. Gbaoui, E. Kaniusas, Decomposition of photoplethysmographical arterial tor combining radial basis network for estimation of lower limb peripheral
pulse waves by independent component analysis: possibilities and limitations, vascular occlusive disease, Lecture Notes in Computer Science 6165 (2010)
Lecture Notes in Electrical Engineering 55 (2010) 1100–1119. 126–136.
[11] C.D. Wagner, R. Mrowka, B. Nafz, P.B. Persson, Complexity and chaos in blood [29] H.-T. Yau, C.-L. Kuo, J.-J. Yan, Fuzzy sliding mode control for a class of chaos
pressure after baroreceptor denervation of conscious dogs, American Physio- synchronization with uncertainties, International Journal of Nonlinear Sciences
logical Society 269 (5) (1996) 1760–1766. and Numerical Simulation 7 (3) (2006) 333–338.
[12] J.S. Lin, J.-J. Yan, T.L. Liao, Chaotic synchronization via adaptive sliding mode [30] Y.-C. Du, C.-H. Lin, Adaptive network-based fuzzy inference system for assess-
observers subject to input nonlinearity, Chaos, Solitons & Fractals 24 (1) (2005) ment of lower limb peripheral vascular occlusive disease, Journal of Medical
371–381. System 36 (2012) 301–310.