Lie detection based on heart rate variability
View Patent ↗The present disclosure provides computer readable storage media useful in lie detection based on heart rate variability (HRV) analysis and HRV analysis using strange entropy. The computer readable storage medium may have a computer program encoded thereon, the computer program, when executed by a computer, instructs the computer to execute a method of lie detection that includes receiving an input associated with HRV and performing a nonlinear HRV analysis based on the input associated with HRV to obtain a lie detection result, the nonlinear HRV analysis.
1. A non-transitory computer-readable storage medium having a computer program encoded thereon, the computer program when executed by a computer instructs the computer to execute a method of lie detection, comprising:
receiving an input associated with heart rate variability; and
performing a heart rate variability analysis based on the input associated with heart rate variability to obtain a lie detection result, wherein the heart rate variability analysis includes at least one of nonlinear heart rate variability analysis and neural network-based linear heart rate variability analysis, and wherein the nonlinear heart rate variability analysis is performed by using at least one of strange entropy, Chaos, correlation dimension, fractal theory, strange attractors, mode entropy, multifractal, multiscale multifractal, Lyapunov index, base-scale entropy, and approximate entropy.
2. The non-transitory computer-readable storage medium of claim 1 , wherein the input associated with heart rate variability comprises a time series of electrocardiograph recordings.
3. The non-transitory computer-readable storage medium of claim 1 , wherein the heart rate variability analysis includes nonlinear heart rate variability analysis.
4. The non-transitory computer-readable storage medium of claim 1 , wherein the nonlinear heart rate variability analysis is performed using strange entropy.
5. The non-transitory computer-readable storage medium of claim 1 , wherein the nonlinear heart rate variability analysis comprises:
taking a time series with N elements, u:{u(i):1≦i≦N},wherein u(i) represents signals carried in the input associated with heart rate variability, and for each u(i) , there is a corresponding vector with m elements:
X ( i )=[ u ( i ), u ( i+ 1), . . . , i− 1)];
calculating a base scale BS(i) for each vector X(i);
transforming every X(i) to an m-dimensional symbol series S i ={s(i), . . . −1)}, s∈A(A=0,1,2,3) based on a scale of a×BS(i);
calculating the probability of S i , wherein the probability of each different combination among the entire N−m+1m-dimensional vectors is:
p
(
π
)
=
#
{
t
(
u
i
,
…
,
u
t
+
m
-
1
)
has
type
π
}
N
-
m
+
1
,
wherein 1≦t≦N−m+1; # is the number of states, and each possible combination π for S i represents a vibration mode for S i ;
obtaining nonlinear heart rate variability parameters or m-word distribution graph according to the probability of S i ; and
obtaining a nonlinear heart rate variability parameter PSS, which is defined as sum probabilities of all strange states calculated according to the following equation:
PSS
=
∑
P
s
∑
i
=
0
255
P
i
;
wherein P i is probability of combination i, P s is probability of strange state, andΣP s is probability sum of all strange states.
6. The non-transitory computer-readable storage medium of claim 1 , wherein the lie detection result is obtained by real-time monitoring using a sliding window in a range from about 300 data points to about 500 data points, each of the data points representing a heartbeat.
7. The non-transitory computer-readable storage medium of claim 1 , wherein the neural network-based linear heart rate variability analysis comprises at least one of total power, low frequency power, high frequency power, LFnorm, HFnorm, low frequency power / high frequency power, heart rate, and standard deviation of adjacent R-R interval.
8. A non-transitory computer-readable storage medium having a computer program encoded thereon, the computer program when executed by a computer instructs the computer to execute a method of lie detection, comprising:
receiving an input associated with heart rate variability; and
performing a heart rate variability analysis based on the input associated with heart rate variability to obtain a lie detection result, wherein the heart rate variability analysis is performed using strange entropy.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the input associated with heart rate variability includes a time series of electrocardiograph recordings.
10. The non-transitory computer-readable storage medium of claim 8 , wherein the nonlinear heart rate variability analysis is performed by:
taking a time series signal with N elements, u:{u(i):1≦i≦N}, wherein u(i) represents signals carried in the input associated with heart rate variability, and for each u(i) , there is a corresponding vector with m elements:
X ( i )=[ u ( i ), u ( i+ 1), . . . i− 1)];
calculating a base scale BS(i) for each vector X(i);
transforming every X(i) to an m-dimensional symbol series S i ={s(i),. . . −1)},s∈A(A =0,1,2,3)based on a scale of a×BS(i);
calculating probability of S i such that the probability of each different combination among the entire N−m+1m-dimensional vectors is:
p
(
π
)
=
#
{
t
(
u
i
,
…
,
u
t
+
m
-
1
)
has
type
π
}
N
-
m
+
1
,
wherein 1≦t≦N−m+1,# is the number of states, and each possible combination π for S i represents a vibration mode for S i ; and
obtaining one or more of nonlinear heart rate variability parameters or m-word distribution graph according to the probability of S i .
11. The non-transitory computer-readable storage medium of claim 10 , wherein u(i) represents R-R interval.
12. The non-transitory computer-readable storage medium of claim 10 , wherein BS(i) is defined as square root average of difference between adjacent elements:
B
S
(
i
)
=
∑
j
=
1
m
-
1
(
u
(
i
+
j
)
-
u
(
i
+
j
-
1
)
)
2
m
-
1
.
13. The non-transitory computer-readable storage medium of claim 10 , wherein the every X(i) is transformed to an m-dimensional symbol series S i according to the transformation equation:
S
i
+
k
=
{
0
:
u
_
i
<
u
i
+
k
≤
u
_
i
+
a
×
B
S
(
i
)
1
:
u
i
+
k
>
u
_
i
+
a
×
B
S
(
i
)
2
:
u
_
i
-
a
×
B
S
(
i
)
<
u
i
+
k
≤
u
_
i
3
:
u
i
+
k
≤
u
_
i
-
a
×
B
S
(
i
)
;
wherein i=1, 2, . . . , ;S i+k is the k-th element of S i ; u i+k is the k-th element of X(i); ū i represents the average value of the m-dimensional vector X(i);and 0,1,2, 3 are notations for region partition.
14. The non-transitory computer-readable storage medium of claim 10 , wherein the nonlinear heart rate variability parameters include H(m) which is calculated according to the following equation:
H ( m )=−Σ P (π)log 2 P (π).
15. The non-transitory computer-readable storage medium of claim 10 , wherein the nonlinear heart rate variability parameters include PSS which is defined as sum of probabilities of all strange states calculated according to following equation:
PSS
=
∑
P
s
∑
i
=
0
255
P
i
;
wherein P i is probability of combination i, P s probability of strange state, and ΣP s is probability sum of all strange states.
16. A non-transitory computer-readable storage medium having a computer program encoded thereon, the computer program when executed by a computer instructs the computer to execute a method of lie detection, comprising:
receiving an input associated with heart rate variability; and
performing a nonlinear heart rate variability analysis based on the input associated with heart rate variability to obtain a lie detection result, the nonlinear heart rate variability analysis comprising:
obtaining a nonlinear heart rate variability parameter PSS, which is defined as sum probabilities of all strange states calculated according to the following equation:
PSS
=
∑
P
s
∑
i
=
0
255
P
i
;
wherein P i is probability of combination i, P s is probability of strange state, and ΣP s is probability sum of all strange states.
17. The non-transitory computer-readable storage medium of claim 16 , wherein the nonlinear heart rate variability analysis is performed by using strange entropy method comprising:
taking a time series signal with N elements, u:{u(i):1≦i≦N}, wherein u(i) represents signals carried in the input associated with heart rate variability, and for each u(i) there is a corresponding vector with m elements:
X ( i )=[ u ( i ), u ( i+ 1), . . . , i− 1)];
calculating a base scale BS(i) for each vector X(i);
transforming every X(i) to an m-dimensional symbol series S i ={s(i), . . . −1)},sεA(A =0,1,2,3) based on a scale of a×BS(i);
calculating probability of S i such that the probability of each different combination among the entire N−m+1 m-dimensional vectors is:
p
(
π
)
=
#
{
t
(
u
i
,
…
,
u
t
+
m
-
1
)
has
type
π
}
N
-
m
+
1
,
wherein 1≦t≦N−m+1,# is the number of states, and each possible combination π for S i represents a vibration mode for S i ; and
obtaining one or more of nonlinear heart rate variability parameters or m-word distribution graphs according to the probability of S i .