• Computers and Concrete
• /
• 제21권1호
• /
• pp.47-54
• /
• 2018

Artificial neural network models can be successfully used to simulate the complex behavior of many problems in civil engineering. As compared to conventional computational methods, this popular modeling technique is powerful when the relationship between system parameters is intrinsically nonlinear, or cannot be explicitly identified, as in the case of concrete behavior. In this investigation, an artificial neural network model was developed to assess the residual compressive strength of self-compacted concrete at elevated temperatures ($20-900^{\circ}C$) and various relative humidity conditions (28-99%). A total of 332 experimental datasets, collected from available literature, were used for model calibration and verification. Data used in model development incorporated concrete ingredients, filler and fiber types, and environmental conditions. Based on the feed-forward back propagation algorithm, systematic analyses were performed to improve the accuracy of prediction and determine the most appropriate network topology. Training, testing, and validation results indicated that residual compressive strength of self-compacted concrete, exposed to high temperatures and relative humidity levels, could be estimated precisely with the suggested model. As illustrated by statistical indices, the reliability between experimental and predicted results was excellent. With new ingredients and different environmental conditions, the proposed model is an efficient approach to estimate the residual compressive strength of self-compacted concrete as a substitute for sophisticated laboratory procedures.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.30-33
• /
• 2001

The number of hidden neurons of the feed-forward neural networks is generally decided on the basis of experience. The method usually results in the lack or redundancy of hidden neurons, and causes the shortage of capacity for storing information of learning overmuch. This research proposes a new method for optimizing the number of hidden neurons bases on information entropy, Firstly, an initial neural network with enough hidden neurons should be trained by a set of training samples. Second, the activation values of hidden neurons should be calculated by inputting the training samples that can be identified correctly by the trained neural network. Third, all kinds of partitions should be tried and its information gain should be calculated, and then a decision-tree correctly dividing the whole sample space can be constructed. Finally, the important and related hidden neurons that are included in the tree can be found by searching the whole tree, and other redundant hidden neurons can be deleted. Thus, the number of hidden neurons can be decided. In the case of building a neural network with the best number of hidden units for tea quality evaluation, the proposed method is applied. And the result shows that the method is effective

• International Journal of Knowledge Content Development & Technology
• /
• 제10권4호
• /
• pp.29-46
• /
• 2020

The paper describes the quantitative and qualitative dimensions of artificial neural networks (ANN) in India in the global context. The study is based on research publications data (8260) as covered in the Scopus database during 1999-2018. ANN research in India registered 24.52% growth, averaged 11.95 citations per paper, and contributed 9.77% share to the global ANN research. ANN research is skewed as the top 10 countries account for 75.15% of global output. India ranks as the third most productive country in the world. The distribution of research by type of ANN networks reveals that Feed Forward Neural Network type accounted for the highest share (10.18% share), followed by Adaptive Weight Neural Network (5.38% share), Feed Backward Neural Network (2.54% share), etc. ANN research applications across subjects were the largest in medical science and environmental science (11.82% and 10.84% share respectively), followed by materials science, energy, chemical engineering and water resources (from 6.36% to 9.12%), etc. The Indian Institute of Technology, Kharagpur and the Indian Institute of Technology, Roorkee lead the country as the most productive organizations (with 289 and 264 papers). Besides, the Indian Institute of Technology, Kanpur (33.04 and 2.76) and Indian Institute of Technology, Madras (24.26 and 2.03) lead the country as the most impactful organizations in terms of citation per paper and relative citation index. P. Samui and T.N. Singh have been the most productive authors and G.P.S.Raghava (86.21 and 7.21) and K.P. Sudheer (84.88 and 7.1) have been the most impactful authors. Neurocomputing, International Journal of Applied Engineering Research and Applied Soft Computing topped the list of most productive journals.

• 설비공학논문집
• /
• 제12권7호
• /
• pp.688-696
• /
• 2000

A scheme for fault detection on the subsystem level is presented. The method uses analytical redundancy and consists in generating residuals by comparing each measurement with an estimate computed from the reference models. In this study regression neural network models are used as reference models. The regression neural network is memory-based feed forward network that provides estimates of continuous variables. The simulation result demonstrated that the proposed method can effectively detect faults in an air handling unit(AHU). The results show that the regression models are accurate and reliable estimators of the highly nonlinear and complex AHU.

• 전자공학회논문지B
• /
• 제30B권11호
• /
• pp.56-65
• /
• 1993

This paper presents the design consideration of the MFNNs(Multilayer Feed forward Neural Networks) based on the distribution of the given teching patterns. By extracting the feature points from the given teaching patterns, the structure of a network including the netowrk size and interconnection weights of a network is initialized. This network is trained based on the modified version of the EBP(Error Back Propagation) algorithm. As a result, the proposed method has the advantage of learning speed compared to the conventional learning of the MFNNs with randomly chosen initial weights. To show the effectiveness of the suggested approach, the simulation result on the approximation of a two demensional continuous function is shown.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권5호
• /
• pp.353-360
• /
• 2004

This paper considers reinforcement learning control with the self-organizing map. Reinforcement learning uses the observable states of objective system and signals from interaction of the system and environment as input data. For fast learning in neural network training, it is necessary to reduce learning data. In this paper, we use the self-organizing map to partition the observable states. Partitioning states reduces the number of learning data which is used for training neural networks. And neural dynamic programming design method is used for the controller. For evaluating the designed reinforcement learning controller, an inverted pendulum on the cart system is simulated. The designed controller is composed of serial connection of self-organizing map and two Multi-layer Feed-Forward Neural Networks.

• Computers and Concrete
• /
• 제12권6호
• /
• pp.785-802
• /
• 2013

Ready-mixed soil material, known as a kind of controlled low-strength material, is a new way of soil cement combination. It can be used as backfill materials. In this paper, artificial neural network and nonlinear regression approach were applied to predict the compressive strength of ready-mixed soil material containing Portland cement, slag, sand, and soil in mixture. The data used for analyzing were obtained from our testing program. In the experiment, we carried out a mix design with three proportions of sand to soil (e.g., 6:4, 5:5, and 4:6). In addition, blast furnace slag partially replaced cement to improve workability, whereas the water-to-binder ratio was fixed. Testing was conducted on samples to estimate its engineering properties as per ASTM such as flowability, strength, and pulse velocity. Based on testing data, the empirical pulse velocity-strength correlation was established by regression method. Next, three topologies of neural network were developed to predict the strength, namely ANN-I, ANN-II, and ANN-III. The first two models are back-propagation feed-forward networks, and the other one is radial basis neural network. The results show that the compressive strength of ready-mixed soil material can be well-predicted from neural networks. Among all currently proposed neural network models, the ANN-I gives the best prediction because it is closest to the actual strength. Moreover, considering combination of pulse velocity and other factors, viz. curing time, and material contents in mixture, the proposed neural networks offer better evaluation than interpolated from pulse velocity only.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.664-667
• /
• 1997

For higher component density per chip, it is necessary to identify and control the semiconductor manufacturing process more stringently. Recently, neural networks have been identified as one of the most promising techniques for modeling and control of complicated processes such as plasma etching process. Since wafer states after each run using identical recipe may differ from each other, conventional neural network models utilizing input factors only cannot represent the actual state of process and equipment. In this paper, in addition to the input factors of the recipe, real-time tool data are utilized for modeling of 64M DRAM s-poly plasma etching process to reflect the actual state of process and equipment. For real-time tool data, we collect optical emission spectroscopy (OES) data. Through principal component analysis (PCA), we extract principal components from entire OES data. And then these principal components are included to input parameters of neural network model. Finally neural network model is trained using feed forward error back propagation (FFEBP) algorithm. As a results, simulation results exhibit good wafer state prediction capability after plasma etching process.

• 한국물환경학회지
• /
• 제24권1호
• /
• pp.91-98
• /
• 2008

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.49.1-49
• /
• 2001

The skin color model is a very important concept in face detection, face recognition and face tracking. Usually, this model is obtained by estimating a probability density function of skin color distribution. In many cases, it is assumed that the underlying density function follows a Gaussian distribution. In this paper, a new method for non-parametric estimation of the probability density function, by using feed-forward neural network, is used to estimate the underlying skin color model. By using this method, the resulting skin color model is better than the Gaussian estimation and substantially approaches the real distribution. Applications to face detection and face ...