• Journal of Information Processing Systems
• /
• 제18권6호
• /
• pp.719-728
• /
• 2022

The prediction of short-term traffic flow is the theoretical basis of intelligent transportation as well as the key technology in traffic flow induction systems. The research on short-term traffic flow prediction has showed the considerable social value. At present, the support vector regression (SVR) intelligent prediction model that is suitable for small samples has been applied in this domain. Aiming at parameter selection difficulty and prediction accuracy improvement, the artificial bee colony (ABC) is adopted in optimizing SVR parameters, which is referred to as the ABC-SVR algorithm in the paper. The simulation experiments are carried out by comparing the ABC-SVR algorithm with SVR algorithm, and the feasibility of the proposed ABC-SVR algorithm is verified by result analysis. Continuously, the simulation experiments are carried out by comparing the ABC-SVR algorithm with particle swarm optimization SVR (PSO-SVR) algorithm and genetic optimization SVR (GA-SVR) algorithm, and a better optimization effect has been attained by simulation experiments and verified by statistical test. Simultaneously, the simulation experiments are carried out by comparing the ABC-SVR algorithm and wavelet neural network time series (WNN-TS) algorithm, and the prediction accuracy of the proposed ABC-SVR algorithm is improved and satisfactory prediction effects have been obtained.

• 전기학회논문지
• /
• 제65권9호
• /
• pp.1531-1540
• /
• 2016

In this paper, we propose vehicle license plate recognition system based on Radial Basis Function Neural Networks (RBFNNs) with the use of local binarization functions and canny edge algorithm. In order to detect the area of license plate and also recognize license plate numbers, binary images are generated by using local binarization methods, which consider local brightness, and canny edge detection. The generated binary images provide information related to the size and the position of license plate. Additionally, image warping is used to compensate the distortion of images obtained from the side. After extracting license plate numbers, the dimensionality of number images is reduced through Principal Component Analysis (PCA) and is used as input variables to RBFNNs. Particle Swarm Optimization (PSO) algorithm is used to optimize a number of essential parameters needed to improve the accuracy of RBFNNs. Those optimized parameters include the number of clusters and the fuzzification coefficient used in the FCM algorithm, and the orders of polynomial of networks. Image data sets are obtained by changing the distance between stationary vehicle and camera and then used to evaluate the performance of the proposed system.

• 한국광학회지
• /
• 제21권1호
• /
• pp.1-5
• /
• 2010

본 논문에서는 실리콘 태양전지의 흡수효율 증가를 위해 도파모드 공진 특성을 이용한 격자 구조를 제안하였다. 도파모드 공진을 이용함으로써 두께를 ~200 nm 수준으로 줄이면서도 높은 흡수율을 기대할 수 있는 태양전지 설계가 가능함을 확인하였다. 제안된 구조는 은으로 된 반사경 위에 격자구조를 갖는 Poly-Si 유전체 층이 존재하는 1-D 구조로서 각 구조변수들 즉 격자의 주기, 유전체 두께, 격자 간격 및 깊이 등이 흡수 효율에 어떤 영향을 미치는지 알아보고, 변수들의 조절을 통해 최적의 구조를 찾고자 시도하였다. PSO알고리즘을 사용하여 제안된 구조의 적절성을 확인 하였으며, 이로부터 65.8%의 유효 흡수율을 얻을 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.352-361
• /
• 2018

This paper proposes a sensing system of the Halbach array permanent magnet spherical motor(PMSM). The rotor position can be obtained by solving three rotation angles, which revolves around 3 reference axes of the stator. With the development of 3-D hall sensor, the position identification problem of the Halbach array PMSM based on rotor magnetic field is studied in this paper. A nonlinear and serious coupling relationship between the rotation angles and the measured magnetic flux density is established on the basis of the rotation transformation theory and the magnetic field model. In order to get rid of the influence on position detection caused by the harmonics of rotor magnetic field and the stator coil magnetic field, a sensor location combination scheme is proposed. In order to solve the nonlinear equation fast and accurately, a new position solution algorithm which combines the merits of gradient projection and particle swarm optimization(PSO) is presented. Then the rotation angles are obtained and the rotor position is identified. The validity of the sensing system is verified through the simulation.

• Wind and Structures
• /
• 제38권1호
• /
• pp.75-91
• /
• 2024

Reliable wind signal reconstruction can be beneficial to the operational safety of long-span bridges. Non-Gaussian characteristics of wind signals make the reconstruction process challenging. In this paper, non-Gaussian wind signals are converted into a combined prediction of two kinds of features, actual wind speeds and wind angles of attack. First, two decomposition techniques, empirical mode decomposition (EMD) and variational mode decomposition (VMD), are introduced to decompose wind signals into intrinsic mode functions (IMFs) to reduce the randomness of wind signals. Their principles and applicability are also discussed. Then, four artificial intelligence (AI) algorithms are utilized for wind signal reconstruction by combining the particle swarm optimization (PSO) algorithm with back propagation neural network (BPNN), support vector regression (SVR), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), respectively. Measured wind signals from a bridge site in a deep-cutting gorge are taken as experimental subjects. The results showed that the reconstruction error of high-frequency components of EMD is too large. On the contrary, VMD fully extracts the multiscale rules of the signal, reduces the component complexity. The combination of VMD-PSO-Bi-LSTM is demonstrated to be the most effective among all hybrid models.

• 한국항공우주학회지
• /
• 제41권7호
• /
• pp.524-531
• /
• 2013

본 연구에서는 헬리콥터 로터 블레이드의 제작 과정 및 여러 가지 요인으로 인해 발생하는 불균형성을 해소하기 위한 RTB(Rotor Track and Balance) 알고리즘을 개발하였다. 비행 시험 결과로부터 RTB 조절 값과 트랙 및 기체 진동 사이의 상호관계를 선형모델을 이용한 회귀분석을 통하여 RTB 모델을 구축하였다. 개발된 RTB 알고리즘을 실기 시험 결과에 적용하여 RTB 모델을 검증하였고 선형화 모델만으로도 비교적 정확한 모델링이 가능함을 확인하였다. RTB 조절값 설정을 위해 최적화 문제를 정식화하고 유전자 알고리즘에 입자 군집 최적화(PSO) 알고리즘을 결합하여 빠른 수렴성을 갖는 최신의 최적화 기법을 적용하였다. 또한 최적화 해석을 통하여 얻은 RTB 조절값을 이용하여 트랙 편차와 기체 진동을 허용 기준치 아래로 감소시키고, 다양한 비행 조건에 대하여 효율적인 RTB를 수행할 수 있음을 보였다.

• Journal of Electrical Engineering and Technology
• /
• 제12권6호
• /
• pp.2388-2398
• /
• 2017

In this study, we propose a robust face recognition system to pose variations based on automatic pose estimation. Radial basis function neural network is applied as one of the functional components of the overall face recognition system. The proposed system consists of preprocessing and recognition modules to provide a solution to pose variation and high-dimensional pattern recognition problems. In the preprocessing part, principal component analysis (PCA) and 2-dimensional 2-directional PCA ($(2D)^2$ PCA) are applied. These functional modules are useful in reducing dimensionality of the feature space. The proposed RBFNNs architecture consists of three functional modules such as condition, conclusion and inference phase realized in terms of fuzzy "if-then" rules. In the condition phase of fuzzy rules, the input space is partitioned with the use of fuzzy clustering realized by the Fuzzy C-Means (FCM) algorithm. In conclusion phase of rules, the connections (weights) are realized through four types of polynomials such as constant, linear, quadratic and modified quadratic. The coefficients of the RBFNNs model are obtained by fuzzy inference method constituting the inference phase of fuzzy rules. The essential design parameters (such as the number of nodes, and fuzzification coefficient) of the networks are optimized with the aid of Particle Swarm Optimization (PSO). Experimental results completed on standard face database -Honda/UCSD, Cambridge Head pose, and IC&CI databases demonstrate the effectiveness and efficiency of face recognition system compared with other studies.

• Geomechanics and Engineering
• /
• 제14권2호
• /
• pp.161-174
• /
• 2018

The present study investigates the soil-structure interaction (SSI) effects on the seismic performance of smart base-isolated structures. The adopted control algorithm for tuning the control force plays a key role in successful implementation of such structures; however, in most studied carried out in the literature, these algorithms are designed without considering the SSI effect. Considering the SSI effects, a linear quadratic regulator (LQR) controller is employed to seismic control of a smart base-isolated structure. A particle swarm optimization (PSO) algorithm is used to tune the gain matrix of the controller in both cases without and with SSI effects. In order to conduct a parametric study, three types of soil, three well-known earthquakes and a vast range of period of the superstructure are considered for assessment the SSI effects on seismic control process of the smart-base isolated structure. The adopted controller is able to make a significant reduction in base displacement. However, any attempt to decrease the maximum base displacement results in slight increasing in superstructure accelerations. The maximum and RMS base displacements of the smart base-isolated structures in the case of considering SSI effects are more than the corresponding responses in the case of ignoring SSI effects. Overall, it is also observed that the maximum and RMS base displacements of the structure are increased by increasing the natural period of the superstructure. Furthermore, it can be concluded that the maximum and RMS superstructure accelerations are significant influenced by the frequency content of earthquake excitations and the natural frequency of the superstructure. The results show that the design of the controller is very influenced by the SSI effects. In addition, the simulation results demonstrate that the ignoring the SSI effect provides an unfavorable control system, which may lead to decline in the seismic performance of the smart-base isolated structure including the SSI effects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.520-541
• /
• 2023

In CRNs, SS is of utmost significance. Every CR user generates a sensing report during the training phase beneath various circumstances, and depending on a collective process, either communicates or remains silent. In the training stage, the fusion centre combines the local judgments made by CR users by a majority vote, and then returns a final conclusion to every CR user. Enough data regarding the environment, including the activity of PU and every CR's response to that activity, is acquired and sensing classes are created during the training stage. Every CR user compares their most recent sensing report to the previous sensing classes during the classification stage, and distance vectors are generated. The posterior probability of every sensing class is derived on the basis of quantitative data, and the sensing report is then classified as either signifying the presence or absence of PU. The ISVM technique is utilized to compute the quantitative variables necessary to compute the posterior probability. Here, the iterations of SVM are tuned by novel GO-PSA by combining GOA and PSO. Novel GO-PSA is developed since it overcomes the problem of computational complexity, returns minimum error, and also saves time when compared with various state-of-the-art algorithms. The dependability of every CR user is taken into consideration as these local choices are then integrated at the fusion centre utilizing an innovative decision combination technique. Depending on the collective choice, the CR users will then communicate or remain silent.

• Earthquakes and Structures
• /
• 제25권6호
• /
• pp.417-427
• /
• 2023

If the center of mass and center of stiffness or strength of a structure plan do not coincide, the structure is considered asymmetric. During an earthquake, in addition to lateral vibration, the structure experiences torsional vibration as well. Lateraltorsional coupling in asymmetric structures in the plan will increase lateral displacement at the ends of the structure plan and, as a result, uneven deformation demand in seismically resistant frames. The demand for displacement in resistant frames depends on the magnitude of transitional displacement to rotational displacement in the plan and the correlation between these two. With regard to the inability to eliminate the asymmetrical condition due to various reasons, such as architectural issues, this study has attempted to use supplemental viscous dampers to decrease the correlation between lateral and torsional acceleration or displacement in the plan. This results in an almost even demand for lateral deformation and acceleration of seismic resistant frames. On this basis, using the concept of Torsional Balance, adequate distribution of viscous dampers for the decrease of this correlation was determined by transferring the "Empirical Center of Balance" (ECB) to the geometrical center of the structure plan and thus obtaining an equal mean square value of displacement and acceleration of the plan edges. This study analyzed stiff and flexible torsional structures with one-way and two-way mass asymmetry in the Opensees software. By implementing the Particle Swarm Optimization (PSO) algorithm, the optimum formation of dampers for controlling lateral displacement and acceleration is determined. The results indicate that with the appropriate distribution of viscous dampers, not only does the lateral displacement and acceleration of structure edges decrease but the lateral displacement or acceleration of the structure edges also become equal. It is also observed that the optimized center of viscous dampers for control of displacement and acceleration of structure depends on the amount of mass eccentricity, the ratio of uncoupled torsional-to-lateral frequency, and the amount of supplemental damping ratio. Accordingly, distributions of viscous dampers in the structure plan are presented to control the structure's torsion based on the parameters mentioned.