
Cyber-physical systems (CPSs) are affected by cyberattacks once they are more connected to cyberspace. Advanced CPSs are highly complex and susceptible to attacks such as false data injection attacks (FDIA) targeted to mislead the systems and make them unstable. Leveraging an integration of anomaly detection methods, real-time monitoring, and machine learning (ML) algorithms, research workers are developing robust frameworks to recognize and alleviate the effect of FDIA. These methods often scrutinize deviations from predictable system behavior, using statistical analysis and anomaly detection systems to determine abnormalities that can indicate malicious activities. This manuscript offers the design of an election-based optimization algorithm with a deep learning-enabled false data injection attack detection (EBODL-FDIAD) method in the CPS infrastructure. The purpose of the EBODL-FDIAD technique is to enhance security in the CPS environment via the detection of FDIAs. In the EBODL-FDIAD technique, the linear scaling normalization (LSN) approach can be used to scale the input data into valuable formats. Besides, the EBODL-FDIAD system performs ensemble learning classification comprising three classifiers, namely the kernel extreme learning machine (KELM), long short-term memory (LSTM), and attention-based bidirectional recurrent neural network (ABiRNN) model. For optimal hyperparameter selection of the ensemble classifiers, the EBO algorithm can be applied. To validate the enriched performance of the EBODL-FDIAD technique, wide-ranging simulations were involved. The extensive results highlighted that the EBODL-FDIAD algorithm performed well over other systems concerning numerous measures.
Citation: Hend Khalid Alkahtani, Nuha Alruwais, Asma Alshuhail, Nadhem NEMRI, Achraf Ben Miled, Ahmed Mahmud. Election-based optimization algorithm with deep learning-enabled false data injection attack detection in cyber-physical systems[J]. AIMS Mathematics, 2024, 9(6): 15076-15096. doi: 10.3934/math.2024731
[1] | Aidi Yao . Two-dimensional pseudo-steady supersonic flow around a sharp corner for the generalized Chaplygin gas. AIMS Mathematics, 2022, 7(7): 11732-11758. doi: 10.3934/math.2022654 |
[2] | Jianhong Zhuang, Yaqing Liu, Ping Zhuang . Variety interaction solutions comprising lump solitons for the (2+1)-dimensional Caudrey-Dodd-Gibbon-Kotera-Sawada equation. AIMS Mathematics, 2021, 6(5): 5370-5386. doi: 10.3934/math.2021316 |
[3] | Yonghui Zou, Xin Xu, An Gao . Local well-posedness to the thermal boundary layer equations in Sobolev space. AIMS Mathematics, 2023, 8(4): 9933-9964. doi: 10.3934/math.2023503 |
[4] | Guangyue Huang, Botao Wang . Rigidity results for closed vacuum static spaces. AIMS Mathematics, 2023, 8(12): 28728-28737. doi: 10.3934/math.20231470 |
[5] | Yellamma, N. Manjunatha, Umair Khan, Samia Elattar, Sayed M. Eldin, Jasgurpreet Singh Chohan, R. Sumithra, K. Sarada . Onset of triple-diffusive convective stability in the presence of a heat source and temperature gradients: An exact method. AIMS Mathematics, 2023, 8(6): 13432-13453. doi: 10.3934/math.2023681 |
[6] | Abdelkader Laiadi, Abdelkrim Merzougui . Free surface flows over a successive obstacles with surface tension and gravity effects. AIMS Mathematics, 2019, 4(2): 316-326. doi: 10.3934/math.2019.2.316 |
[7] | Jin Yang, Zhenzhen Wei . The optimal problems for torsional rigidity. AIMS Mathematics, 2021, 6(5): 4597-4613. doi: 10.3934/math.2021271 |
[8] | Yusuke Ishigaki, Yoshihiro Ueda . Stability of stationary solutions to outflow problem for compressible viscoelastic system in one dimensional half space. AIMS Mathematics, 2024, 9(11): 33215-33253. doi: 10.3934/math.20241585 |
[9] | Jin Liu, Botao Wang . A rigidity result for 2-dimensional λ-translators. AIMS Mathematics, 2023, 8(10): 24947-24956. doi: 10.3934/math.20231272 |
[10] | Jae-Myoung Kim . Time decay rates for the coupled modified Navier-Stokes and Maxwell equations on a half space. AIMS Mathematics, 2021, 6(12): 13423-13431. doi: 10.3934/math.2021777 |
Cyber-physical systems (CPSs) are affected by cyberattacks once they are more connected to cyberspace. Advanced CPSs are highly complex and susceptible to attacks such as false data injection attacks (FDIA) targeted to mislead the systems and make them unstable. Leveraging an integration of anomaly detection methods, real-time monitoring, and machine learning (ML) algorithms, research workers are developing robust frameworks to recognize and alleviate the effect of FDIA. These methods often scrutinize deviations from predictable system behavior, using statistical analysis and anomaly detection systems to determine abnormalities that can indicate malicious activities. This manuscript offers the design of an election-based optimization algorithm with a deep learning-enabled false data injection attack detection (EBODL-FDIAD) method in the CPS infrastructure. The purpose of the EBODL-FDIAD technique is to enhance security in the CPS environment via the detection of FDIAs. In the EBODL-FDIAD technique, the linear scaling normalization (LSN) approach can be used to scale the input data into valuable formats. Besides, the EBODL-FDIAD system performs ensemble learning classification comprising three classifiers, namely the kernel extreme learning machine (KELM), long short-term memory (LSTM), and attention-based bidirectional recurrent neural network (ABiRNN) model. For optimal hyperparameter selection of the ensemble classifiers, the EBO algorithm can be applied. To validate the enriched performance of the EBODL-FDIAD technique, wide-ranging simulations were involved. The extensive results highlighted that the EBODL-FDIAD algorithm performed well over other systems concerning numerous measures.
The study of the propagation of Rayleigh waves in the layered non-homogeneous earth is central interested in theoretical seismologists. As a result of intensive studies of many authors, a good amount of information about the propagation of Rayleigh waves with different variations in density and rigidity is available. A book of Ewing, Jardetzky and Press (1957) [1], Achenbach (1973) [2], Miklowitz (1978) [3], Pilant (1979) [4] and many other different books contains a vast amount of information on the propagation of Rayleigh waves. After these books were published, many publications on these topics are available in different journals. Wang et al. (2008) [5] studied the propagation and localization of Rayleigh waves in disordered piezoelectric phononic-crystals. Liu and Liu (2004) [6] studied the propagation characteristics of Rayleigh waves in orthotropic fluid-saturated porous media. Abd-All et al. (2011) [7] studied the propagation of Rayleigh waves in generalized magneto-thermo-elastic orthotropic material under initial stress and gravity field. Rayleigh wave propagation in layered heterogeneous media has been studied in detail by Wilson (1942) [8], Biot (1965) [9], Newlands (1950) [10] and Stonely (1934) [11]. Dutta (1963) [12] illustrated Rayleigh wave propagation in a two-layer anisotropic media whereas propagation of Rayleigh wave in an elastic half-space of orthotropic and viscoelastic material has been discussed by Abd-Alla (1999) [13] and Abd-Alla (2015) [14]. Sharma and Mohinder (2004) [15] studied Rayleigh-lamb waves in the magneto-thermo-elastic homogeneous isotropic plate. Mitra (1957) [16] studied Rayleigh waves in multi-layered media. In some of the studies reported their solution is expressed in Whittaker function (1990) [17] and the computation is involved with the asymptotic expansion of the function. The effects of tidal waves are studied by different authors such as Z. Hu et al. (2015, 2015, 2017) [18,19,20], Chen et al. (2018) [21] and Suzuki et al. (2019) [22]. The expansion is valid on larger depth but does not give good result in shallow depth. Newlands (1950) [10] found a new approach to the problem and obtained a solution that may be used in shallow depth. Following Newlands, in this paper attempt has been made to study the effect of rigid boundary on the propagation of Rayleigh wave in an incompressible heterogeneous medium over an incompressible half-space. The non-homogeneity has been taken in variation in the rigidity.
In this paper, the author dealt with the effect of the rigid boundary of propagation on Rayleigh waves in an incompressible heterogeneous layer over an initially stressed incompressible half-space. The heterogeneity has been taken in rigidity as and density as and in the upper layer. The equation of the upper layer has been solved by the Newlands method (1950).
Suppose an incompressible medium of thickness H under rigid layer with shear modulus rigidity μ=μ0(1+bz)m and density ρ=ρ0 lying over another incompressible half-space with constant shear modulus μ2 and density ρ2, being taken as the vertical distance from the origin at the interface of an incompressible medium and incompressible half-space whereas the rigid surface exits at z=−H. The downward direction of z has been taken as positive in Figure 1.
Consider the wave propagating along x-axis with wave velocity C and wave-length 2πk. Let u and w are the displacement component in the x- and z- direction respectively at the point (x, y, z) at any time. Suppose that apart from a factor eik(x−Ct) and u, w are functions of z only.
The equation of motion in two diminutions for an elastic solid are
∂∂x{λΔ+2μ∂u∂x}+∂∂z{μ(∂u∂z+∂w∂x)}=ρ∂2u∂t2∂∂z{λΔ+2μ∂w∂z}+∂∂x{μ(∂u∂z+∂w∂x)}=ρ∂2w∂t2 | (1) |
where, since the medium is incompressible,
△=(∂u∂x+∂w∂z)=0▽2φ=0 | (2) |
Substituting,
u=∂ϕ∂x+∂ψ∂zw=∂ϕ∂z−∂ψ∂x | (3) |
where ϕ and ψ being scalar and vector potentials, by μ=μ0(1+bz)m, incompressibility condition Δ=0, together with limλ→∞,Δ→0λΔ→P1, whereP1 the hydrostatic stress, Eq (1) takes the form as Again, substituting,
∂∂x[−P1+2μ0bm(1+bz)m−1w+ρk2C2ϕ]+∂∂z[μ∇2ψ+ρk2C2ψ]=0∂∂z[−P1+2μ0bm(1+bz)m−1w+ρk2C2ϕ]−∂∂x[μ∇2ψ+ρk2C2ψ]=0 | (4) |
which are satisfied by
P1=2μ0bm(1+bz)m−1w+ρk2C2ϕμ∇2ψ=ρk2C2ψ | (5) |
From Eq (5)
∂2ψ∂z2+k2[ρc2μ0(1+bz)m−1]ψ(z)=0∂2ϕ∂z2−k2Φ=0 | (6) |
Taking Z=(1+bz) in Eq (6), we have
d2ψdZ2−(kb)2(1−ρC2μ0Zm)ψ=0 | (7) |
In power of (kb)2, the series solution of Eq (7), may be written as
ψ(Z)=ψ0(Z)+(kb)2ψ1(Z)+......+(kb)2nψn(Z)+... | (8) |
Hence,
[ψ′′0(Z)+(kb)2ψ′′1(Z)+......]−(kb)2[1−ρC2μ0Zm][ψ0(Z)+(kb)2ψ1(Z)+.....]=0 | (9) |
Thus, if
ψ′′0(Z)=0ψ′′1(Z)=[1−ρC2μ0Zm]ψ0..ψ′′n+1(Z)=[1−ρC2μ0Zm]ψn(Z) | (10) |
Since the series [Eq (9)] converges and involves with two constants, then it is a valid solution. We have,
ψ′n(1)=ψn(1)=0 | (11) |
ψ′n(Z)=A2b,ψ0(Z)=A1+A2b(Z−1)=A1+A2z | (12) |
Due to linearity of Eq (7), we have
ψ=A1[ψ(1)0(Z)+(kb)2ψ(1)1(Z)+...]+A2[ψ(2)0(Z)+(kb)2ψ(2)1(Z)+...]=A1ψ1+A2ψ2 | (13) |
Where,
ψ(1)0=1ψ(2)0=Z−1b=z | (14) |
Now,
ψ1=∫Z1dξ∫ξ1(1−ρC2μ0tm)ψ0(t)dt=∫Z1dξ∫ξ1(1−ρC2μ0tm)[A1+A2b(t−1)]dt=A1{(Z−1)22−ρC2μ0[ZlogZ−(Z−1)]}+A2{(Z−1)32−ρC2μ0[Z22−Z+12−(ZlogZ−(Z−1))]} | (15) |
And the solution of ψ(1) and ψ(2) are readily obtained as follows:
Case Ⅰ : When m = 1
ψ1=A1{(Z−1)22−ρC2μ0[ZlogZ−(Z−1)]}+A2b{(Z−1)32−ρC2μ0[12−Z22+ZlogZ]} | (16) |
The solutions are
ψ(1)Z=1+(kb)2[(Z−1)22−ρC2μ0{ZlogZ−(Z−1)}]ψ2Z=(Z−1)+(kb)2[(Z−1)36−ρC2μ0{12−Z22+ZlogZ}] | (17) |
Case Ⅱ: when m = 2
ψ1=A1[(Z−1)22−ρC2μ0{logZ−(Z−1)}]+A2b[(Z−1)36−ρC2μ0{(Z+1)logZ+2(1−Z)}] | (18) |
The solution are
ψ(1)Z=1+(kb)2[(Z−1)22−ρC2μ0{logZ−(Z−1)}]ψ(2)Z=(Z−1)+(kb)2[(Z−1)36−ρC2μ0{(Z+1)logZ+2(1−Z)}] | (19) |
Case Ⅲ: when m = 3
ψ1=A1[(Z−1)22+ρC2μ0{1−Z2−12Z}]+A2b[(Z−1)36+ρC2μ0{logZ+12Z−Z2}] | (20) |
The solution are
ψ(1)Z=1+(kb)2[(Z−1)22+ρC2μ0{1−Z2−12Z}]ψ(2)Z=(Z−1)+(kb)2[(Z−1)36+ρC2μ0{logZ+12Z−Z2}] | (21) |
Case Ⅳ: when any value of m except 1, 2 and 3
ψ1=A1[(Z−1)22+ρC2μ01(1−m){(Z−1)+1(2−m)(1−1Zm−2)}]+A2b[(Z−1)36+ρC2μ01(2−m){(Z−1)+1(3−m)(1−1Zm−3)}+ρC2μ01(1−m){(1−Z)+1(2−m)(1Zm−2−1)}] | (22) |
The solutions are
ψ(1)Z=1+(kb)2[(Z−1)22+ρC2μ01(1−m){(Z−1)+1(2−m)(1−1Zm−2)}] | (23) |
ψ(2)Z=(Z−1)+(kb)2[(Z−1)36+ρC2μ01(2−m){(Z−1)+1(3−m)(1−1Z(m−3))}+ρC2μ01(1−m){(1−Z)+1(2−m)(1Z(m−2)−1)}] | (24) |
Hence the final solutions are
ϕ=[Q1cosh(kz)+Q2sinh(kz)]cosk(x−Ct)ψ=[A1ψ(1)(z)+A2ψ(2)(z)]sink(x−Ct) | (25) |
Hence the displacement and stress component along x- and z- direction in the incompressible layer sandwiched between the rigid surface and a half-space are given by
u=[−k(Q1cosh(kz)+Q2sinh(kz))+(A1∂∂zψ(1)(Z)+A2∂∂zψ(2)(Z))]sink(x−Ct)w=[k(Q1sinh(kz)+Q2cosh(kz))+k(A1ψ(1)(Z)+A2ψ(2)(Z))]cosk(x−Ct)σxz=2k[−μ∂ϕ∂z+k(μ−εμ02)ψ]σzz=2[k2ϕ(μ−εμ02)ψ−μ0bm(1+bz)m−1∂ϕ∂z+μ0bm(1+bz)m−1kψ−μk∂ψ∂z] | (26) |
where, ε=C2ρμ0
The values of ϕ and ψ as
ϕ=Re−kzcosk(x−Ct)ψ=Se−knzsink(x−Ct) | (27) |
Where, n=(1−ρ2C2μ2)
Hence the displacement and stress component along x- and z- direction in the incompressible layer sandwiched between the rigid surface and a half space are given by
u=[−kRe−kz−Skne−knz]sink(x−Ct)w=[−kRe−kz−Ske−knz]cosk(x−Ct)σxz=2k[−μ∂ϕ∂z+k(μ−εδμ02)ψ]σzz=2[k2ϕ(μ−εδμ02)ψ−μk∂ψ∂z] | (28) |
where, δ=ρ2ρ0
From the Figure 1 we can use the following boundary conditions:
(ⅰ) At z=0, the displacements are continuous
u1=u2
w1=w2
(ⅱ) At the interface z = 0, the continuity of the stress requires that
(σxz)1=(σxz)2
(σzz)1=(σzz)2
(ⅲ) At z = -H, the displacement vanishes
u1=0
w1=0
By using the boundary condition (ⅰ) and (ⅱ), we have
−kQ1+A2b=−kR−knSQ2−A1=−R−S−Q2+(1−ε2)A1=μ2Rμ0+(μ2μ0−εδ2)SkQ1(1−ε2)−bmQ2+bmA1−bA2=kR(μ2μ0−εδ2)+μ2μ0knS | (29) |
By using the boundary condition (ⅲ), we have
(Q1cosh(kz)+Q2sinh(kz))−1k(A1∂∂zψ(1)(Z)+A2∂∂zψ(2)(Z))=0k(Q1sinh(kz)+Q2cosh(kz))+k(A1ψ(1)(Z)+A2ψ(2)(Z))=0 | (30) |
From the Eqs (29) and (30), we have the relation between Q1,Q2,A1 and A2
12εQ1=D1R+E1S12εQ2=D2R+E2S12εA1=D3R+E3S12εA2=D4R+E4S | (31) |
where
D1=1k[k−bmD2ε/2+bmD3ε/2−k(μ2μ0−εδ2)]D2=D3−ε2D3=1−μ2μ0D4=1b(kD1−εk2) | (32) |
E1=1k[kn−bmD2ε/2+bmD3ε/2−μ2μ0kn]E2=E3−ε2E3=1−μ2μ0+εδ2E4=1b(kE1−εkn2) | (33) |
M1=(coshkz)z=−HM2=(sinhkz)z=−HM3=−1k[∂∂zψ(1)(Z)]z=−HM4=−1k[∂∂zψ(2)(Z)]z=−H | (34) |
N1=(sinhkz)z=−HN2=(coshkz)z=−HN3=(ψ(1)(Z))z=−HN4=(ψ(2)(Z))z=−H | (35) |
The consistency of Eq (30) for non-trivial solution of R and S implies that,
Σ4i=1DiMiΣ4j=1EjNj=Σ4k=1DkNkΣ4l=1ElMl | (36) |
Equation (36) is the required equation for the dispersion of Rayleigh surface wave in an incompressible heterogeneous layer lying over an incompressible homogeneous elastic half-space under rigid layer.
On the above study the authors are used to parametric relation are taken as bH=0.5,ρ2ρ0=1.2,μ2μ0=1.8., respectively as given in Table 1. For equation, the dispersion curve of Rayleigh waves has been calculated in Eq (35) for different values of m starting from 0 to 5 and the authors observed that the nature of phase velocity for different values of 2πkH in an incompressible heterogeneous under rigid layer. The results are presented in Figures 2 and 3. In Figure 2 for different values of m = 1, 2 and 3 respectively being shows that in the assumed medium under a rigid layer, Rayleigh wave velocity decreases with increases of 2πkH.We also observed that in case of linear, quadratic and cubic variation of rigidity in an incompressible heterogeneous under rigid layer as the phase velocity of Rayleigh waves increases as rigidity increases. On the other hand in case in case of the phase velocity of Rayleigh waves increases as 2πkH increases under rigid layer. In case the homogeneous incompressible elastic medium under rigid layer the phase velocity of Rayleigh waves more compares to m = 0, 0.5, 4 and 5.
From the above study, the authors reveals that some of the important facts regarding the propagation of Rayleigh waves in assumed medium and half-space under rigid layer as
(ⅰ)The phase velocity of Rayleigh waves in an assumed medium under rigid layer decreases in the linear, quadratic and cubic variation of rigidity only.
(ⅱ)The phase velocity of Rayleigh waves increases for different values of m = 0, 0.5, 4 and 5.
(ⅲ)The phase velocity of Rayleigh waves in an assumed medium under a rigid layer decreases only m = 1, 2 and 3 otherwise increases.
The authors are sincerely thankful to the Asansol Engineering College, IIT(ISM), Dhanbad and Brainware Group of Institutions for their all kind of support. The authors are also thankful to the reviewer for their guidance to improve the work.
The authors declare no conflict of interest in this paper.
[1] |
K. D. Lu, Z. G. Wu, Multi-objective false data injection attacks of cyber-physical power systems, IEEE T. Circuits Syst. Ⅱ, 69 (2022), 3924–3928. https://doi.org/10.1109/TCSⅡ.2022.3181827 doi: 10.1109/TCSⅡ.2022.3181827
![]() |
[2] |
P. L. Bhattar, N. M. Pindoriya, A. Sharma, A combined survey on distribution system state estimation and false data injection in cyber-physical power distribution networks, IET Cyber Phys. Syst. Theory Appl., 6 (2021), 41–62. https://doi.org/10.1049/cps2.12000 doi: 10.1049/cps2.12000
![]() |
[3] |
Y. Li, Y. Wang, Developing graphical detection techniques for maintaining state estimation integrity against false data injection attack in integrated electric cyber-physical system, J. Syst. Architect., 105 (2020), 101705. https://doi.org/10.1016/j.sysarc.2019.101705 doi: 10.1016/j.sysarc.2019.101705
![]() |
[4] |
Q. Wang, W. Tai, Y. Tang, M. Ni, Review of the false data injection attack against the cyber-physical power system, IET Cyber Phys. Syst. Theory Appl., 4 (2019), 101–107. https://doi.org/10.1049/iet-cps.2018.5022 doi: 10.1049/iet-cps.2018.5022
![]() |
[5] |
S. Padhan, A. K. Turuk, Design of false data injection attacks in cyber-physical systems, Inform. Sci., 608 (2022), 825–843. https://doi.org/10.1016/j.ins.2022.06.082 doi: 10.1016/j.ins.2022.06.082
![]() |
[6] |
T. Zhou, K. Xiahou, L. L. Zhang, Q. H. Wu, Real-time detection of cyber-physical false data injection attacks on power systems, IEEE T. Ind. Inform., 17 (2021), 6810–6819. https://doi.org/10.1109/TⅡ.2020.3048386 doi: 10.1109/TⅡ.2020.3048386
![]() |
[7] |
Z. Qu, Y. Dong, N. Qu, H. Li, M. Cui, X. Bo, et al., False data injection attack detection in power systems based on cyber-physical attack genes, Front. Energy Res., 9 (2021), 644489. https://doi.org/10.3389/fenrg.2021.644489 doi: 10.3389/fenrg.2021.644489
![]() |
[8] |
G. Cao, W. Gu, G. Lou, W. Sheng, K. Liu, Distributed synchronous detection for false data injection attack in cyber-physical microgrids, Int. J. Elec. Power Energy Syst., 137 (2022), 107788. https://doi.org/10.1016/j.ijepes.2021.107788 doi: 10.1016/j.ijepes.2021.107788
![]() |
[9] |
J. Li, C. Sun, Q. Su, Analysis of cascading failures of power cyberphysical systems considering false data injection attacks, Global Energy Interconnect., 4 (2021), 204–213. https://doi.org/10.1016/j.gloei.2021.05.002 doi: 10.1016/j.gloei.2021.05.002
![]() |
[10] |
T. Zou, A. S. Bretas, C. Ruben, S. C. Dhulipala, N. Bretas, Smart grids cyber-physical security: Parameter correction model against unbalanced false data injection attacks, Electr. Pow. Syst. Res., 187 (2020), 106490. https://doi.org/10.1016/j.epsr.2020.106490 doi: 10.1016/j.epsr.2020.106490
![]() |
[11] |
M. Mazare, Adaptive optimal secure wind power generation control for variable speed wind turbine systems via reinforcement learning, Appl. Energ., 353 (2024), 122034. https://doi.org/10.1016/j.apenergy.2023.122034 doi: 10.1016/j.apenergy.2023.122034
![]() |
[12] |
M. Mazare, M. Taghizadeh, H. Asharioun, Attack‐resilient pitch angle control for variable‐speed wind turbine systems under cyber threats, Int. J. Adapt. Control, 37 (2023), 1423–1439. https://doi.org/10.1002/acs.3580 doi: 10.1002/acs.3580
![]() |
[13] |
M. Mazare, Reinforcement learning-based fixed-time resilient control of nonlinear cyber physical systems under false data injection attacks and mismatch disturbances, J. Franklin I., 360 (2023), 14926–14938. https://doi.org/10.1016/j.jfranklin.2023.10.026 doi: 10.1016/j.jfranklin.2023.10.026
![]() |
[14] |
H. Alamro, K. Mahmood, S. S. Aljameel, A. Yafoz, R. Alsini, A. Mohamed, Modified red fox optimizer with deep learning enabled false data injection attack detection, IEEE Access, 11 (2023), 79256–79264. https://doi.org/10.1109/ACCESS.2023.3298056 doi: 10.1109/ACCESS.2023.3298056
![]() |
[15] |
J. Sakhnini, H. Karimipour, A. Dehghantanha, R. M. Parizi, Physical layer attack identification and localization in cyber–physical grid: An ensemble deep learning based approach, Phys. Commun., 47 (2021), 101394. https://doi.org/10.1016/j.phycom.2021.101394 doi: 10.1016/j.phycom.2021.101394
![]() |
[16] |
K. Liu, H. Zhang, Y. Zhang, C. Sun, False data-injection attack detection in cyber–physical systems with unknown parameters: A deep reinforcement learning approach, IEEE T. Cybernetics, 11 (2023), 7115–7125. https://doi.org/10.1109/TCYB.2022.3225236 doi: 10.1109/TCYB.2022.3225236
![]() |
[17] |
E. Vincent, M. Korki, M. Seyedmahmoudian, A. Stojcevski, S. Mekhilef, Detection of false data injection attacks in cyber–physical systems using graph convolutional network, Electr. Pow. Syst. Res., 217 (2023), 109118. https://doi.org/10.1016/j.epsr.2023.109118 doi: 10.1016/j.epsr.2023.109118
![]() |
[18] | Y. Zhang, W. Deng, K. Huang, C. Yang, False data injection attack testbed of industrial cyber-physical systems of the process industry and a detection application. In: 2021 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE), 2021, 1–7. https://doi.org/10.1109/RASSE53195.2021.9686839 |
[19] |
Y. Li, X. Wei, Y. Li, Z. Dong, M. Shahidehpour, Detection of false data injection attacks in smart grid: A secure federated deep learning approach, IEEE T. Smart Grid, 13 (2022), 4862–4872. https://doi.org/10.1109/TSG.2022.3204796 doi: 10.1109/TSG.2022.3204796
![]() |
[20] |
W. Fu, Y. Yan, Y. Chen, Z. Wang, D. Zhu, L. Jin, Temporal false data injection attack and detection on cyber‐physical power system based on deep reinforcement learning, IET Smart Grid, 7 (2024), 78–88. https://doi.org/10.1049/stg2.12141 doi: 10.1049/stg2.12141
![]() |
[21] |
H. Ruan, B. Dorneanu, H. Arellano-Garcia, P. Xiao, L. Zhang, Deep learning-based fault prediction in wireless sensor network embedded cyber-physical systems for industrial processes, IEEE Access, 10(2022), 10867–10879. https://doi.org/10.1109/ACCESS.2022.3144333 doi: 10.1109/ACCESS.2022.3144333
![]() |
[22] |
J. Tian, C. Shen, B. Wang, X. Xia, M. Zhang, C. Lin, Q. Li, LESSON: Multi-label adversarial false data injection attack for deep learning locational detection, IEEE T. Depend. Secure Comput., 2024, 1–15. https://doi.org/10.1109/TDSC.2024.3353302 doi: 10.1109/TDSC.2024.3353302
![]() |
[23] |
J. Tian, B. Wang, R. Guo, Z. Wang, K. Cao, X. Wang, Adversarial attacks and defenses for deep-learning-based unmanned aerial vehicles, IEEE Internet Things J., 9 (2021), 22399–22409. https://doi.org/10.1109/JIOT.2021.3111024 doi: 10.1109/JIOT.2021.3111024
![]() |
[24] |
J. Tian, B. Wang, Z. Wang, K. Cao, J. Li, M. Ozay, Joint adversarial example and false data injection attacks for state estimation in power systems, IEEE T. Cybernetics, 52 (2022), 13699–13713. https://doi.org/10.1109/TCYB.2021.3125345 doi: 10.1109/TCYB.2021.3125345
![]() |
[25] |
S. Sorguli, H. Rjoub, A novel energy accounting model using fuzzy restricted boltzmann machine—Recurrent neural network, Energies, 16 (2023), 2844. https://doi.org/10.3390/en16062844 doi: 10.3390/en16062844
![]() |
[26] |
Q. Hu, H. Zhou, C. Wang, C. Zhu, J. Shen, P. He, Time-frequency fusion features-based GSWOA-KELM model for gear fault diagnosis, Lubricants, 12 (2024), 10. https://doi.org/10.3390/lubricants12010010 doi: 10.3390/lubricants12010010
![]() |
[27] |
M. Xia, X. Zheng, M. Imran, M. Shoaib, Data-driven prognosis method using hybrid deep recurrent neural network, Appl. Soft Comput., 93 (2020), 106351. https://doi.org/10.1016/j.asoc.2020.106351 doi: 10.1016/j.asoc.2020.106351
![]() |
[28] | S. P. Shashikumar, A. J. Shah, G. D. Clifford, S. Nemati, Detection of paroxysmal atrial fibrillation using attention-based bidirectional recurrent neural networks, In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018,715–723. https://doi.org/10.1145/3219819.3219912 |
[29] |
M. Abd Elaziz, M. E. Zayed, H. Abdelfattah, A. Q. Aseeri, E. M. Tag-eldin, M. Fujii, et al., Machine learning-aided modeling for predicting freshwater production of a membrane desalination system: A long-short-term memory coupled with election-based optimizer, Alex. Eng. J., 86 (2024), 690–703. https://doi.org/10.1016/j.aej.2023.12.012 doi: 10.1016/j.aej.2023.12.012
![]() |