• Steel and Composite Structures
• /
• v.17 no.3
• /
• pp.215-236
• /
• 2014

The flexural behaviour of steel beams significantly affects the structural performance of the steel frame structures. In particular, the flexural overstrength (namely the ratio between the maximum bending moment and the plastic bending strength) that steel beams may experience is the key parameter affecting the seismic design of non-dissipative members in moment resisting frames. The aim of this study is to present a new formulation of flexural overstrength factor for steel beams by means of artificial neural network (NN). To achieve this purpose, a total of 141 experimental data samples from available literature have been collected in order to cover different cross-sectional typologies, namely I-H sections, rectangular and square hollow sections (RHS-SHS). Thus, two different data sets for I-H and RHS-SHS steel beams were formed. Nine critical prediction parameters were selected for the former while eight parameters were considered for the latter. These input variables used for the development of the prediction models are representative of the geometric properties of the sections, the mechanical properties of the material and the shear length of the steel beams. The prediction performance of the proposed NN model was also compared with the results obtained using an existing formulation derived from the gene expression modeling. The analysis of the results indicated that the proposed formulation provided a more reliable and accurate prediction capability of beam overstrength.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.735-742
• /
• 2004

We present a new use of common graphics hardware to perform a faster artificial neural network. And we examine the use of GPU enhances the time performance of the image processing system using neural network, In the case of parallel computation of multiple input sets, the vector-matrix products become matrix-matrix multiplications. As a result, we can fully utilize the parallelism of GPU. Sigmoid operation and bias term addition are also implemented using pixel shader on GPU. Our preliminary result shows a performance enhancement of about thirty times faster using ATI RADEON 9800 XT board.

• Journal of the Korea Convergence Society
• /
• v.9 no.4
• /
• pp.47-55
• /
• 2018

In this paper, we propose a novel face recognition(FR) method that takes advantage of combining weighted deep local features extracted from multiple Deep Convolutional Neural Networks(DCNNs) learned with a set of facial local regions. In the proposed method, the so-called weighed deep local features are generated from multiple DCNNs each trained with a particular face local region and the corresponding weight represents the importance of local region in terms of improving FR performance. Our weighted deep local features are applied to Joint Bayesian metric learning in conjunction with Nearest Neighbor(NN) Classifier for the purpose of FR. Systematic and comparative experiments show that our proposed method is robust to variations in pose, illumination, and expression. Also, experimental results demonstrate that our method is feasible for improving face recognition performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.2
• /
• pp.436-444
• /
• 2010

In this study, we introduce and discuss a concept of a granular-oriented radial basis function neural networks (GRBF NNs). In contrast to the typical architectures encountered in radial basis function neural networks(RBF NNs), our main objective is to develop a design strategy of GRBF NNs as follows : (a) The architecture of the network is fully reflective of the structure encountered in the training data which are granulated with the aid of clustering techniques. More specifically, the output space is granulated with use of K-Means clustering while the information granules in the multidimensional input space are formed by using a so-called context-based Fuzzy C-Means which takes into account the structure being already formed in the output space, (b) The innovative development facet of the network involves a dynamic reduction of dimensionality of the input space in which the information granules are formed in the subspace of the overall input space which is formed by selecting a suitable subset of input variables so that the this subspace retains the structure of the entire space. As this search is of combinatorial character, we use the technique of genetic optimization to determine the optimal input subspaces. A series of numeric studies exploiting some nonlinear process data and a dataset coming from the machine learning repository provide a detailed insight into the nature of the algorithm and its parameters as well as offer some comparative analysis.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2217-2220
• /
• 2003

It is known that an EEG is characterized by the unique and personal characteristics of an individual. Little research has been done to take into account these personal characteristics when analyzing EEG signals. Often the EEG has frequency components which can describe most of the significant characteristics. These combinations are often unique like individual human beings and yet they have an underlying basic characteristics as well. We think that these combinations are the personal characteristics frequency components of the EEG. In this seminar, the EEG analysis method by using the Genetic Algorithms (GA), Factor Analysis (FA), and the Neural Networks (NN) is proposed. The GA is used for selecting the personal characteristic frequency components. The FA is used for extracting the characteristics data of the EEG. The NN is used for estimating the characteristics data of the EEG. Finally, in order to show the effectiveness of the proposed method, classifying the EEG pattern is carried out via computer simulations. The EEG pattern is evaluated under 4 conditions: listening to Rock music, Schmaltzy Japanese ballad music, Healing music, and Classical music. The results, when personal characteristics frequency components are NOT used, gave over 80 % accuracy versus a 95 % accuracy when personal characteristics frequency components are used. This result of our experiment shows the effectiveness of the proposed method.

• Journal of Magnetics
• /
• v.22 no.1
• /
• pp.34-42
• /
• 2017

Material defects in the Steam Generator Tubes (SGT) of sodium cooled fast breeder reactor (PFBR) can lead to leakage of water into sodium. The water and sodium reaction will lead to major accidents. Therefore, the examination of steam generator tubes for the early detection of defects is an important requirement for safety and economic considerations. In this work, the Magnetic Flux Leakage (MFL) based Non Destructive Testing (NDT) technique is used to perform the defect detection process. The rectangular notch defects on the outer surface of steam generator tubes are modeled using COMSOL multiphysics 4.3a software. The obtained MFL images are de-noised to improve the integrity of flaw related information. Grey Level Co-occurrence Matrix (GLCM) features are extracted from MFL images and taken as input parameter to train the neural network. A comparative study on characterization have been carried out using feed-forward back propagation (FFBP) and cascade-forward back propagation (CFBP) algorithms. The results of both algorithms are evaluated with Mean Square Error (MSE) as a prediction performance measure. The average percentage error for length, depth and width are also computed. The result shows that the feed-forward back propagation network model performs better in characterizing the defects.

• Structural Monitoring and Maintenance
• /
• v.5 no.1
• /
• pp.51-65
• /
• 2018

A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.429-438
• /
• 2006

Neural Networks(NNs) are applied for solving a wide variety of nonlinear problems in several areas, such as image processing, pattern recognition etc. Although NN can be simulated by using software, many potential NN applications required real-time processing. Thus they need to be implemented as hardware. The hardware implementation of multi-layer perceptrons(MLPs) in several kind of NNs usually uses a fixed-point arithmetic due to a simple logic operation and a shorter processing time compared to the floating-point arithmetic. However, the fixed-point arithmetic-based MLP has a drawback which is not able to apply the MLP software that use floating-point arithmetic. We propose a design method for MLPs which has the floating-point arithmetic-based fully-pipelining architecture. It has a processing speed that is proportional to the number of the hidden nodes. The number of input and output nodes of MLPs are generally constrained by given problems, but the number of hidden nodes can be optimized by user experiences. Thus our design method is using optimized number of hidden nodes in order to improve the processing speed, especially in field of a repeated processing such as image processing, pattern recognition, etc.

• Advances in concrete construction
• /
• v.10 no.6
• /
• pp.479-488
• /
• 2020

The experimental and numerical works were carried out on high performance fiber reinforced concrete (HPFRC) with w/cm ratios ranging from 0.25 to 0.40, fiber volume fraction (Vf)=0-1.5% and 10% silica fume replacement. Improvements in compressive and flexural strengths obtained for HPFRC are moderate and significant, respectively, Empirical equations developed for the compressive strength and flexural strength of HPFRC as a function of fiber volume fraction. A relation between flexural strength and compressive strength of HPFRC with R=0.78 was developed. Due to the complex mix proportions and non-linear relationship between the mix proportions and properties, models with reliable predictive capabilities are not developed and also research on HPFRC was empirical. In this paper due to the inadequacy of present method, a back propagation-neural network (BP-NN) was employed to estimate the 28-day compressive strength of HPFRC mixes. BP-NN model was built to implement the highly non-linear relationship between the mix proportions and their properties. This paper describes the data sets collected, training of ANNs and comparison of the experimental results obtained for various mixtures. On statistical analyses of collected data, a multiple linear regression (MLR) model with R2=0.78 was developed for the prediction of compressive strength of HPFRC mixes, and average absolute error (AAE) obtained is 6.5%. On validation of the data sets by NNs, the error range was within 2% of the actual values. ANN model has given the significant degree of accuracy and reliability compared to the MLR model. ANN approach can be effectively used to estimate the 28-day compressive strength of fibrous concrete mixes and is practical.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.2
• /
• pp.102-110
• /
• 2015

The main source of noise in computed tomography (CT) images is a quantum noise, which results from statistical fluctuations of X-ray quanta reaching the detector. This paper proposes a neural network (NN) based hybrid filter for removing quantum noise. The proposed filter consists of bilateral filters (BFs), a single or multiple neural edge enhancer(s) (NEE), and a neural filter (NF) to combine them. The BFs take into account the difference in value from the neighbors, to preserve edges while smoothing. The NEE is used to clearly enhance the desired edges from noisy images. The NF acts like a fusion operator, and attempts to construct an enhanced output image. Several measurements are used to evaluate the image quality, like the root mean square error (RMSE), the improvement in signal to noise ratio (ISNR), the standard deviation ratio (MSR), and the contrast to noise ratio (CNR). Also, the modulation transfer function (MTF) is used as a means of determining how well the edge structure is preserved. In terms of all those measurements and means, the proposed filter shows better performance than the guided filter, and the nonlocal means (NLM) filter. In addition, there is no severe restriction to select the number of inputs for the fusion operator differently from the neuro-fuzzy system. Therefore, without concerning too much about the filter selection for fusion, one could apply the proposed hybrid filter to various images with different modalities, once the corresponding noise characteristics are explored.