• Journal of Internet Computing and Services
• /
• v.20 no.5
• /
• pp.95-104
• /
• 2019

Various kinds of devices are used for the Internet of Things (IoT) service, and IoT devices mainly use communication technology that uses the frequency of the unlicensed band. There are several types of communication technology in the unlicensed band, but WiFi is most commonly used. Devices used for IoT services vary in computing resources from devices with limited capabilities to smartphones and provide services over wireless networks such as WiFi. Most IoT devices can't perform complex operations for network control, thus they choose a WiFi access point (AP) based on signal strength. This causes a decrease in IoT service efficiency. In this paper, an intelligent AP system that can efficiently control the WiFi connection of the IoT devices is implemented. Based on the network information measured by the IoT device, the access point learns using a feed forward neural network algorithm, and predicts a network connection state to control the WiFi connection. By controlling the WiFi connection at the AP, the service efficiency of the IoT device can be improved.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.2089-2090
• /
• 2006

본 논문은 기호 코딩 및 정보입자를 이용한 유전자 알고리즘의 전방향 퍼지 집합 기반 뉴럴네트워크 (Information Granules and Symbolic Encoding-based Fuzzy Set Polynomial Neural Networks ; IG and SE based FSPNN)의 모델 설계를 제안한다. 기존 퍼지 집합기반 다항식 뉴럴네트워크(FSPNN)의 구조 최적화를 위해 이진코딩을 사용하였다. 그러나 이진코딩에서 스트링의 길이가 길면 길수록 인접한 두 수 사이에 발생하는 급격한 비트 차이라는 해밍절벽이 발생하였다. 이에 제안된 모델에서는 해밍절벽의 문제를 해결하기 위해 기호코딩을 사용하였다. 제안된 모델은 각 입력에 대해 MFs의 개수 만큼 규칙을 생성하는 Fuzzy 집합기반 다항식 뉴럴네트워크(FSPNN)를 그대로 사용한다. 그리고 IG based gFSPNN의 평가을 위해 실험적 예제를 통하여 제안된 모델의 성능 및 근사화 능력의 우수함을 보인다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.11
• /
• 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.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.13 no.12
• /
• pp.1288-1296
• /
• 2001

A scheme for on-line fault detection and diagnosis of an air-handling unit is presented. The fault detection scheme uses residuals which are generated by comparing each measurement with analytical redundancies computed from the reference models. In this paper, artificial neural networks (ANNs) are used to estimate analytical redundancy and to classify faults. The Lebenburg-Marquardt algorithm is used to train feed forward ANNs that provide estimates of continuous states and diagnosis results. The simulation result demonstrated that the ANNs can effectively detect and diagnose faults in the highly non-linear and complex HVAC systems.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• 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

• Computers and Concrete
• /
• v.11 no.3
• /
• pp.237-252
• /
• 2013

This paper presents the application of artificial neural network (ANN) to predict deep beam deflection using experimental data from eight high-strength-self-compacting-concrete (HSSCC) deep beams. The optimized network architecture was ten input parameters, two hidden layers, and one output. The feed forward back propagation neural network of ten and four neurons in first and second hidden layers using TRAINLM training function predicted highly accurate and more precise load-deflection diagrams compared to classical linear regression (LR). The ANN's MSE values are 40 times smaller than the LR's. The test data R value from ANN is 0.9931; thus indicating a high confidence level.

• Advances in Computational Design
• /
• v.3 no.3
• /
• pp.289-302
• /
• 2018

The use of optimum content of supplementary cementing materials (SCMs) such as limestone filler (LF) to blend with Portland cement has been resulted in many environmental and technical advantages, such as increase in physical properties, enhancement of sustainability in concrete industry and reducing $CO_2$ emission are well known. Artificial neural networks (ANNs) have been already applied in civil engineering to solve a wide variety of problems such as the prediction of concrete compressive strength. The feed forward back propagation (FFBP) algorithm and Tan-sigmoid transfer function were used for the ANNs training in this study. The training, testing and validation of data during the backpropagation training process yielded good correlations exceeding 97%. A parametric study was conducted to study the sensitivity of the developed model to certain essential parameters affecting the compressive strength of concrete. The effects and benefits of limestone filler on hardened properties of the concrete such as compressive strength were well established endorsing previous results in the literature. The results of this study revealed that the proposed ANNs model showed a high performance as a feasible and highly efficient tool for simulating the LF concrete compressive strength prediction.

• Journal of Information Technology Applications and Management
• /
• v.19 no.1
• /
• pp.1-12
• /
• 2012

Data mining is the process of searching and analyzing large quantities of data for finding out meaningful patterns and rules. Artificial Neural Network (ANN) is one of the tools of data mining which is becoming very popular in forecasting the future values. Some of the areas where it is used are banking, medicine, retailing and fraud detection. In finance, artificial neural network is used in various disciplines including stock market forecasting. In the stock market time series, due to high volatility, it is very important to choose a model which reads volatility and forecasts the future values considering volatility as one of the major attributes for forecasting. In this paper, an attempt is made to develop two models - one using feed forward back propagation Artificial Neural Network and the other using Autoregressive Conditional Heteroskedasticity (ARCH) technique for forecasting stock market returns. Various parameters which are considered for the design of optimal ANN model development are input and output data normalization, transfer function and neuron/s at input, hidden and output layers, number of hidden layers, values with respect to momentum, learning rate and error tolerance. Simulations have been done using prices of daily close of Sensex. Stock market returns are chosen as input data and output is the forecasted return. Simulations of the Model have been done using MATLAB$^{(R)}$ 6.1.0.450 and EViews 4.1. Convergence and performance of models have been evaluated on the basis of the simulation results. Performance evaluation is done on the basis of the errors calculated between the actual and predicted values.

• Journal of Intelligence and Information Systems
• /
• v.14 no.3
• /
• pp.25-39
• /
• 2008

The objective of this study is to forecast the operational continuous ability using Artificial Neural Networks in battalion defensive operation for the commander decision making support. The forecasting of the combat result is one of the most complex issue in military science. However, it is difficult to formulate a mathematical model to evaluate the combat power of a battalion in defensive operation since there are so many parameters and high temporal and spatial variability among variables. So in this study, we used company combat power level data in Battalion Command in Battle Training as input data and used Feed-Forward Multilayer Perceptrons(MLP) and General Regression Neural Network (GRNN) to evaluate operational continuous ability. The results show 82.62%, 85.48% of forecasting ability in spite of non-linear interactions among variables. We think that GRNN is a suitable technique for real-time commander's decision making and evaluation of the commitment priority of troops in reserve.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.3
• /
• pp.1-12
• /
• 2001

In this paper, we investigate and analyze weight distribution of feed forward two-layer neural networks with a hidden layer in order to understand and improve time-consuming training process of neural networks. Generally, when a new problem is presented, neural networks have to be trained again without any benefit from the previous training process. In order to address this problem, training process is viewed as finding a solution point in the weight space and the distribution of solution points is analyzed. Then we propose to initialize neural networks using the information of the distribution of the solution points. Experimental results show that the proposed initialization using the weight distribution provides a better performance than the conventional one.