• Journal of the Korean Institute of Educational Facilities
• /
• v.25 no.6
• /
• pp.35-44
• /
• 2018

The purpose of this study is to predict more accurate construction costs and to support efficient decision making in the planning and design stages of smart education facilities. The higher the error in the projected cost, the more risk a project manager takes. If the manager can predict a more accurate construction cost in the early stages of a project, he/she can secure a decision period and support a more rational decision. During the planning and design stages, there is a limited amount of variables that can be selected for the estimating model. Moreover, since the number of completed smart schools is limited, there is little data. In this study, various artificial intelligence models were used to accurately predict the construction cost in the planning and design phase with limited variables and lack of performance data. A theoretical study on an artificial neural network and deep learning was carried out. As the artificial neural network has frequent problems of overfitting, it is found that there is a problem in practical application. In order to overcome the problem, this study suggests that the improved models of Deep Neural Network and Deep Belief Network are more effective in making accurate predictions. Deep Neural Network (DNN) and Deep Belief Network (DBN) models were constructed for the prediction of construction cost. Average Error Rate and Root Mean Square Error (RMSE) were calculated to compare the error and accuracy of those models. This study proposes a cost prediction model that can be used practically in the planning and design stages.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

• Structural Engineering and Mechanics
• /
• v.39 no.2
• /
• pp.267-285
• /
• 2011

There can be a significant amount of moment redistribution in composite frames consisting of steel columns and composite beams, due to cracking, creep and shrinkage of concrete. Considerable amount of computational effort is required for taking into account these effects for large composite frames. A methodology has been presented in this paper for taking into account these effects. In the methodology that has been demonstrated for moderately high frames, neural network models are developed for rapid prediction of the inelastic moments (typically for 20 years, considering instantaneous cracking, and time effects, i.e., creep and shrinkage, in concrete) at a joint in a frame from the elastic moments (neglecting instantaneous cracking and time effects). The proposed models predict the inelastic moment ratios (ratio of elastic moment to inelastic moment) using eleven input parameters for interior joints and seven input parameters for exterior joints. The training and testing data sets are generated using a hybrid procedure developed by the authors. The neural network models have been validated for frames of different number of spans and storeys. The models drastically reduce the computational effort and predict the inelastic moments, with reasonable accuracy for practical purposes, from the elastic moments, that can be obtained from any of the readily available software.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.179-184
• /
• 2021

In this paper, we propose the deep learning-based neural network model to predict bunker price. In the shipping industry, since fuel oil accounts for the largest portion of ship operation costs and its price is highly volatile, so companies can secure market competitiveness by making fuel oil purchasing decisions based on rational and scientific method. In this paper, short-term predictive analysis of HSFO 380CST in Singapore is conducted by using three recurrent neural network models like RNN, LSTM, and GRU. As a result, first, the forecasting performance of RNN models is better than LSTM and GRUs using long-term memory, and thus the predictive contribution of long-term information is low. Second, since the predictive performance of recurrent neural network models is superior to the previous studies using econometric models, it is confirmed that the recurrent neural network models should consider nonlinear properties of bunker price. The result of this paper will be helpful to improve the decision quality of bunker purchasing.

• Journal of Korean Society of Water and Wastewater
• /
• v.21 no.5
• /
• pp.601-607
• /
• 2007

In order to maintain constant residual chlorine in sedimentation basin, It is necessary to develop real time prediction model of residual chlorine considering water treatment plant data such as water qualities, weather, and plant operation conditions. Based on the operation data acquired from K water treatment plant, prediction models of residual chlorine in sediment basin were accomplished. The input parameters applied in the models were water temperature, turbidity, pH, conductivity, flow rate, alkalinity and pre-chlorination dosage. The multiple regression models were established with linear and non-linear model with 5,448 data set. The corelation coefficient (R) for the linear and non-linear model were 0.39 and 0.374, respectively. It shows low correlation coefficient, that is, these multiple regression models can not represent the residual chlorine with the input parameters which varies independently with time changes related to weather condition. Artificial neural network models are applied with three different conditions. Input parameters are consisted of water quality data observed in water treatment process based on the structure of auto-regressive model type, considering a time lag. The artificial neural network models have better ability to predict residual chlorine at sediment basin than conventional linear and nonlinear multi-regression models. The determination coefficients of each model in verification process were shown as 0.742, 0.754, and 0.869, respectively. Consequently, comparing the results of each model, neural network can simulate the residual chlorine in sedimentation basin better than mathematical regression models in terms of prediction performance. This results are expected to contribute into automation control of water treatment processes.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1716-1722
• /
• 2005

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision in complex systems. The fuzzy-neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes bacteria foraging algorithm based optimal learning fuzzy-neural network (BA-FNN). The proposed learning scheme is the fuzzy-neural network structure which can handle linguistic knowledge as tuning membership function of fuzzy logic by bacteria foraging algorithm. The learning algorithm of the BA-FNN is composed of two phases. The first phase is to find the initial membership functions of the fuzzy neural network model. In the second phase, bacteria foraging algorithm is used for tuning of membership functions of the proposed model.

• Advances in Computational Design
• /
• v.5 no.3
• /
• pp.291-304
• /
• 2020

In this paper, we develop models to design the airfoil using Multilayer Feed-forward Artificial Neural Network (MFANN) and Support Vector Regression model (SVR). The aerodynamic coefficients corresponding to series of airfoil are stored in a database along with the airfoil coordinates. A neural network is created with aerodynamic coefficient as input to produce the airfoil coordinates as output. The performance of the models have been evaluated. The results show that the SVR model yields the lowest prediction error.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.2
• /
• pp.149-158
• /
• 1996

In this paper we describe designing and implementing a digital neural chip and a parallel neural machine for simulating large scale neural netsorks. The chip is a single-chip multiprocessor which has four digiral neural processors (DNP-II) of the same architecture. Each DNP-II has program memory and data memory, and the chip operates in MIMD (multi-instruction, multi-data) parallel processor. The DNP-II has the instruction set tailored to neural computation. Which can be sed to effectively simulate various neural network models including on-chip learning. The DNP-II facilitates four-way data-driven communication supporting the extensibility of parallel systems. The parallel neural machine consists of a host computer, processor boards, a buffer board and an interface board. Each processor board consists of 8*8 array of DNP-II(equivalently 2*2 neural chips). Each processor board acn be built including linear array, 2-D mesh and 2-D torus. This flexibility supports efficiency of mapping from neural network models into parallel strucgure. The neural system accomplishes the performance of maximum 40 GCPS(giga connection per second) with 16 processor boards.

• MALSORI
• /
• no.62
• /
• pp.113-131
• /
• 2007

It is reported that the segmental feature based recognition system shows better results than conventional feature based system in the previous studies. On the other hand, the various studies of combining neural network and hidden Markov models within a single system are done with expectations that it may potentially combine the advantages of both systems. With the influence of these studies, tandem approach was presented to use neural network as the classifier and hidden Markov models as the decoder. In this paper, we applied the trend information of segmental features to tandem architecture and used posterior probabilities, which are the output of neural network, as inputs of recognition system. The experiments are performed on Auroral database to examine the potentiality of the trend feature based tandem architecture. From the results, the proposed system outperforms on very low SNR environments. Consequently, we argue that the trend information on tandem architecture can be additionally used for traditional MFCC features.