• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.253-263
• /
• 2021

Machine learning is the process of constructing a cost function using learning data used for learning and an artificial neural network to predict the data, and finding parameters that minimize the cost function. Parameters are changed by using the gradient-based method of the cost function. The more complex the digital signal and the more complex the problem to be learned, the more complex and deeper the structure of the artificial neural network. Such a complex and deep neural network structure can cause over-fitting problems. In order to avoid over-fitting, a weight decay regularization method of parameters is used. We additionally use the value of the cost function in this method. In this way, the accuracy of machine learning is improved, and the superiority is confirmed through numerical experiments. These results derive accurate values for a wide range of artificial intelligence data through machine learning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.50-56
• /
• 2020

With the rapid development of deep neural network theory and application research, the effect of face detection has been improved. However, due to the complexity of deep neural network calculation and the high complexity of the detection environment, how to detect face quickly and accurately becomes the main problem. This paper is based on the relatively simple model of the MTCNN model, using FDDB (Face Detection Dataset and Benchmark Homepage), LFW (Field Label Face) and FaceScrub public datasets as training samples. At the same time of sorting out and introducing MTCNN(Multi-Task Cascaded Convolutional Neural Network) model, it explores how to improve training speed and Increase performance at the same time. In this paper, the dynamic image pyramid technology is used to replace the traditional image pyramid technology to segment samples, and OHEM (the online hard example mine) function in MTCNN model is deleted in training, so as to improve the training speed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.987-994
• /
• 2020

In this paper, we studied the effect of kernel size of CNN layer on performance in acoustic noise attenuators. This system uses a deep learning algorithm using a neural network adaptive prediction filter instead of using the existing adaptive filter. Speech is estimated from a single input speech signal containing noise using a 100-neuron, 16-filter CNN filter and an error back propagation algorithm. This is to use the quasi-periodic property in the voiced sound section of the voice signal. In this study, a simulation program using Tensorflow and Keras libraries was written and a simulation was performed to verify the performance of the noise attenuator for the kernel size. As a result of the simulation, when the kernel size is about 16, the MSE and MAE values are the smallest, and when the size is smaller or larger than 16, the MSE and MAE values increase. It can be seen that in the case of an speech signal, the features can be best captured when the kernel size is about 16.

• Structural Engineering and Mechanics
• /
• v.81 no.3
• /
• pp.293-303
• /
• 2022

As infrastructure ages and traffic load increases, serious public concerns have arisen for the well-being of bridges. The current health monitoring practice focuses on large-scale bridges rather than short span bridges. However, it is critical that more attention should be given to these behind-the-scene bridges. The relevant information about the construction methods and as-built properties are most likely missing. Additionally, since the condition of a bridge has unavoidably changed during service, due to weathering and deterioration, the material properties and boundary conditions would also have changed since its construction. Therefore, it is not appropriate to continue using the design values of the bridge parameters when undertaking any analysis to evaluate bridge performance. It is imperative to update the model, using finite element (FE) analysis to reflect the current structural condition. In this study, a FE model is established to simulate a concrete culvert bridge in New South Wales, Australia. That model, however, contains a number of parameter uncertainties that would compromise the accuracy of analytical results. The model is therefore updated with a neural network (NN) optimisation algorithm incorporating Monte Carlo (MC) simulation to minimise the uncertainties in parameters. The modal frequency and strain responses produced by the updated FE model are compared with the frequency and strain values on-site measured by sensors. The outcome indicates that the NN model updating incorporating MC simulation is a feasible and robust optimisation method for updating numerical models so as to minimise the difference between numerical models and their real-world counterparts.

• Steel and Composite Structures
• /
• v.44 no.2
• /
• pp.241-254
• /
• 2022

The cables in a cable-stayed bridge are critical load-carrying parts. The potential damage to cables should be identified early to prevent disasters. In this study, an efficient deep learning model is proposed for the damage identification of cables using both a multi-layer perceptron (MLP) and a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), which is a robust program for modeling and analyzing bridge structures with low computational costs. The model based on the MLP and GNN can capture complex nonlinear correlations between the vibration characteristics in the input data and the cable system damage in the output data. Multiple hidden layers with an activation function are used in the MLP to expand the original input vector of the limited measurement data to obtain a complete output data vector that preserves sufficient information for constructing the graph in the GNN. Using the gated recurrent unit and set2set model, the GNN maps the formed graph feature to the output cable damage through several updating times and provides the damage results to both the classification and regression outputs. The model is fine-tuned with the original input data using Adam optimization for the final objective function. A case study of an actual cable-stayed bridge was considered to evaluate the model performance. The results demonstrate that the proposed model provides high accuracy (over 90%) in classification and satisfactory correlation coefficients (over 0.98) in regression and is a robust approach to obtain effective identification results with a limited quantity of input data.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.641-649
• /
• 2021

Fuel oil consumption (FOC) must be minimized to determine the economic route of a ship; hence, the ship power must be predicted prior to route planning. For this purpose, a numerical method using test results of a model has been widely used. However, predicting ship power using this method is challenging owing to the uncertainty of the model test. An onboard test should be conducted to solve this problem; however, it requires considerable resources and time. Therefore, in this study, a deep feed-forward neural network (DFN) is used to predict ship power using deep learning methods that involve data pattern recognition. To use data in the DFN, the input data and a label (output of prediction) should be configured. In this study, the input data are configured using ocean environmental data (wave height, wave period, wave direction, wind speed, wind direction, and sea surface temperature) and the ship's operational data (draft, speed, and heading). The ship power is selected as the label. In addition, various treatments have been used to improve the prediction accuracy. First, ocean environmental data related to wind and waves are preprocessed using values relative to the ship's velocity. Second, the structure of the DFN is changed based on the characteristics of the input data. Third, the prediction accuracy is analyzed using a combination comprising five hyperparameters (number of hidden layers, number of hidden nodes, learning rate, dropout, and gradient optimizer). Finally, k-means clustering is performed to analyze the effect of the sea state and ship operational status by categorizing it into several models. The performances of various prediction models are compared and analyzed using the DFN in this study.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1887-1888
• /
• 2008

본 논문에서는 퍼지 추론 기반의 다항식 RBF 뉴럴네트워크(Polynomial Radial Basis Function Neural Network; pRBFNN)를 설계하고 PSO(Particle Swarm Optimization) 알고리즘을 이용하여 모델의 파라미터를 동정한다. 제안된 모델은 "IF-THEN" 형식으로 기술되는 퍼지 규칙에 의해 조건부, 결론부, 추론부의 기능적 모듈로 표현된다. 조건부의 입력공간 분할에는 HCM 클러스터링에 기반을 두어 구조가 결정되며, 기존에 주로 사용된 가우시안 함수를 RBF로 이용하고, 원뿔형태의 선형 함수를 제안한다. 또한 입력공간 분할시 데이터 집합의 특성을 반영하기 위해 분포상수를 각 입력마다 고려하여 설계함으로서 공간 분할의 정밀성을 높인다. 결론부에서는 기존 상수항의 연결가중치를 다항식 형태로 표현하는 pRBFNN을 제안한다. 제안한 모델의 성능을 평가하기 위해 Box와 Jenkins가 사용한 가스로 시계열 데이터를 적용하고, 기존 모델과의 근사화와 일반화 능력에 대하여 토의한다.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.654-656
• /
• 1998

This paper presents an optimal identification method of nonlinear and complex system that is based on fuzzy-neural network(FNN). The FNN used simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. And we use a HCM Algorithm to find initial parameters of membership function. And then to obtain optimal parameters, we use the genetic algorithm. Genetic algorithm is a random search algorithm which can find the global optimum without converging to local optimum. The parameters such as membership functions, learning rates and momentum coefficients are easily adjusted using the genetic algorithms. Also, the performance index with weighted value is introduced to achieve a meaningful balance between approximation and generalization abilities of the model. To evaluate the performance of the FNN, we use the time series data for 9as furnace and the sewage treatment process.

• Computers and Concrete
• /
• v.10 no.1
• /
• pp.49-57
• /
• 2012

Nano-particle-reinforced cement mortars have been the basis of research in recent years and a significant growth is expected in the future. Therefore, optimization and quantification of the effect of processing parameters and mixture ingredients on the performance of cement mortars are quite important. In this work, the effects of nano-silica, water/binder ratio, sand/binder ratio and aging (curing) time on the compressive strength of cement mortars were modeled by means of artificial neural network (ANN). The developed model can be conveniently used as a rough estimate at the stage of mix design in order to produce high quality and economical cement mortars.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• 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.