• Journal of the Korea Society of Computer and Information
• /
• v.21 no.1
• /
• pp.1-8
• /
• 2016

Convolutional neural network (CNN) consists of a few pairs of both convolution layer and subsampling layer. Thus it has more hidden layers than multi-layer perceptron. With the increased layers, the size of convolution mask ultimately determines the total number of weights in CNN because the mask is shared among input images. It also is an important learning factor which makes or breaks CNN's learning. Therefore, this paper proposes the best method to choose the convolution size and the number of layers for learning CNN successfully. Through our face recognition with vast learning examples, we found that the best size of convolution mask is 5 by 5 and 7 by 7, regardless of the number of layers. In addition, the CNN with two pairs of both convolution and subsampling layer is found to make the best performance as if the multi-layer perceptron having two hidden layers does.

• Journal of Environmental Science International
• /
• v.11 no.3
• /
• pp.201-207
• /
• 2002

This study was carried out to evaluate the artificial neural network algorithm for water quality forecasting in Chungju lake, north Chungcheong province. Multi-layer perceptron(MLP) was used to train artificial neural networks. MLP was composed of one input layer, two hidden layers and one output layer. Transfer functions of the hidden layer were sigmoid and linear function. The number of node in the hidden layer was decided by trial and error method. It showed that appropriate node number in the hidden layer is 10 for pH training, 15 for DO and BOD, respectively. Reliability index was used to verify for the forecasting power. Considering some outlying data, artificial neural network fitted well between actual water quality data and computed data by artificial neural networks.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.84-87
• /
• 2003

This paper proposes the enhanced REF network, which arbitrates learning rate and momentum dynamically by using the fuzzy system, to arbitrate the connected weight effectively between the middle layer of REF network and the output layer of REF network. ART2 is applied to as the learning structure between the input layer and the middle layer and the proposed auto-turning method of arbitrating the learning rate as the method of arbitrating the connected weight between the middle layer and the output layer. The enhancement of proposed method in terms of learning speed and convergence is verified as a result of comparing it with the conventional delta-bar-delta algorithm and the REF network on the basis of the ART2 to evaluate the efficiency of learning of the proposed method.

• Korean Journal of Remote Sensing
• /
• v.15 no.2
• /
• pp.91-105
• /
• 1999

Spatial data integration using multiple geo-based data sets has been regarded as one of the primary GIS application issues. As for this issue, several integration schemes have been developed as the perspectives of mathematical geology or geo-mathematics. However, research-based approaches for statistical/quantitative assessments between integrated layer and input layers are not fully considered yet. Related to this niche point, in this study, spatial data integration using multiple geoscientific data sets by known integration algorithms was primarily performed. For spatial integration by using raster-based GIS functionality, geological, geochemical, geophysical data sets, DEM-driven data sets and remotely sensed imagery data sets from the Ogdong area were utilized for geological thematic mapping related by mineral potential mapping. In addition, statistical/quantitative information extraction with respective to relationships among used data sets and/or between each data set and integrated layer was carried out, with the scope of multiple data fusion and schematic statistical assessment methodology. As for the spatial integration scheme, certainty factor (CF) estimation and principal component analysis (PCA) were applied. However, this study was not aimed at direct comparison of both methodologies; whereas, for the statistical/quantitative assessment between integrated layer and input layers, some statistical methodologies based on contingency table were focused. Especially, for the bias reduction, jackknife technique was also applied in PCA-based spatial integration. Through the statistic analyses with respect to the integration information in this case study, new information for relationships of integrated layer and input layers was extracted. In addition, influence effects of input data sets with respect to integrated layer were assessed. This kind of approach provides a decision-making information in the viewpoint of GIS and is also exploratory data analysis in conjunction with GIS and geoscientific application, especially handing spatial integration or data fusion with complex variable data sets.

• Journal of Korea Water Resources Association
• /
• v.56 no.11
• /
• pp.801-813
• /
• 2023

Recently, as studies about Artificial Neural Network (ANN) are actively progressing, studies for predicting water quality of rivers using ANN are being conducted. However, it is difficult to analyze the operation process inside ANN, because ANN is form of Black-box. Although eXplainable Artificial Intelligence (XAI) is used to analyze the computational process of ANN, research using XAI technology in the field of water resources is insufficient. This study analyzed Multi Layer Perceptron (MLP) to predict Water Temperature (WT), Dissolved Oxygen (DO), hydrogen ion concentration (pH) and Chlorophyll-a (Chl-a) at the Dasan water quality observatory in the Nakdong river using Layer-wise Relevance Propagation (LRP) among XAI technologies. The MLP that learned water quality was analyzed using LRP to select the optimal input data to predict water quality, and the prediction results of the MLP learned using the optimal input data were analyzed. As a result of selecting the optimal input data using LRP, the prediction accuracy of MLP, which learned the input data except daily precipitation in the surrounding area, was the highest. Looking at the analysis of MLP's DO prediction results, it was analyzed that the pH and DO a had large influence at the highest point, and the effect of WT was large at the lowest point.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.91-102
• /
• 2022

With the evolution of wireless sensor network (WSN) technology, the routing policy has foremost importance in the Internet of Things (IoT). A systematic routing policy is one of the primary mechanics to make certain the precise and robust transmission of wireless sensor networks in an energy-efficient manner. In an IoT environment, WSN is utilized for controlling services concerning data like, data gathering, sensing and transmission. With the advantages of IoT potentialities, the traditional routing in a WSN are augmented with decision-making in an energy efficient manner to concur finer optimization. In this paper, we study how to combine IoT-based deep learning classifier with routing called, Kriging Regressive Deep Belief Neural Learning (KR-DBNL) to propose an efficient data packet routing to cope with scalability issues and therefore ensure robust data packet transmission. The KR-DBNL method includes four layers, namely input layer, two hidden layers and one output layer for performing data transmission between source and destination sensor node. Initially, the KR-DBNL method acquires the patient data from different location. Followed by which, the input layer transmits sensor nodes to first hidden layer where analysis of energy consumption, bandwidth consumption and light intensity are made using kriging regression function to perform classification. According to classified results, sensor nodes are classified into higher performance and lower performance sensor nodes. The higher performance sensor nodes are then transmitted to second hidden layer. Here high performance sensor nodes neighbouring sensor with higher signal strength and frequency are selected and sent to the output layer where the actual data packet transmission is performed. Experimental evaluation is carried out on factors such as energy consumption, packet delivery ratio, packet loss rate and end-to-end delay with respect to number of patient data packets and sensor nodes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.807-812
• /
• 2007

Recently, Extreme learning machine(ELM), a novel learning algorithm which is much faster than conventional gradient-based learning algorithm, was proposed for single-hidden-layer feedforward neural networks. The initial input weights and hidden biases of ELM are usually randomly chosen, and the output weights are analytically determined by using Moore-Penrose(MP) generalized inverse. But it has the difficulties to choose initial input weights and hidden biases. In this paper, an advanced method using the bacterial foraging algorithm to adjust the input weights and hidden biases is proposed. Experiment at results show that this method can achieve better performance for problems having higher dimension than others.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.12-14
• /
• 2005

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks(SOFPNN) by means of genetically optimized fuzzy polynomial neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms(GAs). The conventional SOFPNNs hinges on an extended Group Method of Data Handling(GMDH) and exploits a fixed fuzzy inference type in each FPN of the SOFPNN as well as considers a fixed number of input nodes located in each layer. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, a collection of the specific subset of input variables, and the number of membership function) and addresses specific aspects of parametric optimization. Therefore, the proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series).

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.910-913
• /
• 2001

Rapid Prototyping(RP) techniques have unique characteristics according to their working principle: the stair-stepped surface of a part due to layer-by-layer stacking, low building speed, and additional post-processing to improve surface roughness. A new RP process, Variable Lamination Manufacturing by using expandable polystyrene foam(VLM-S), has been developed to overcome the unfavorable characteristics. The objective of this study is to investigate the thermal characteristics and skeleton size effects as the hotwire cuts EPS foam sheet in order to improve dimensional accuracy of the parts, which is produced by VLM-S. Empirical and analytical approaches are performed to find the relationship between cutting speed and heat input, and the relationship between maximum available cutting speed and heat input. In addition, empirical approaches are carried out to find the relationship between cutting error and skeleton size, and cutting deviation and skeleton size. Based on these results, the optimal hotwire cutting condition and available minimum skeleton size are derived. The outcomes of this study are reflecting in the enhancement of VLM-S input data generation S/W.

• Proceedings of the KIEE Conference
• /
• 1998.07f
• /
• pp.1984-1986
• /
• 1998

This paper presents an optimal efficiency control for the inverter fed induction machine system using neural network. The motor speed and the load torque vary the efficiency characteristics of an induction motor. The optimal slip frequency has nonlinearity varied by the load torque as well as the motor speed. The induction motor is driven using the inverter system and the indirect vector control method which input is slip frequency. The neural network for estimating the optimal slip frequency has two input layer(the motor speed and the load torque) and one output layer(the optimal slip frequency that minimize the input power). Learning algorithm of the neural network is the back-propagation. Using the equivalent circuit including the nonlinearity of the induction motor, the loss reduction is analyzed quantitatively. Experimental results are shown noticeable power savings by proposed scheme in high speed and light load conditions.