• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.6
• /
• pp.106-112
• /
• 2001

Unfortunately, the area without economical efficiency, especially the far distance sea, is much lower than that of a urban area-built-up area. It should be promoted the equivalent level to a urban area in the light of future-oriented universal service. Actually, Because propagation environment of mobile communication in the sea is greatly different from that for inland focused on built-up area, a propagation prediction model in the sea should be distinguished from inland-based one. Accordingly, the purpose of this study is to suggest the propagation prediction model for the sea service as a method to minimize unnecessary facilities investment and maintenance caused by additional or new building of a base station. If mobile phone service for far distance sea is provided by expanding limited communication zone of narrow band CDMA mobile communication whose spread band FA is 1.2288MHz. Suggested propagation prediction model includes five parameters to minimize facilities investment of a base station and maximize channel capacity: equivalent line of sight, chip delay by PN code, antenna altitude, power of base station and gain of antennas. Finally, suggested propagation prediction model is simulated and, the results are examined for its utility by comparing with loss of free space.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.524-524
• /
• 2000

We have been developing a method to build one-step-ahead prediction models for time series using genetic programming (GP). Our model building method consists of two stages. In the first stage, functional forms of the models are inherited from their parent models through crossover operation of GP. In the second stage, the parameters of the newborn model arc optimized based on an iterative method just like the back propagation. The proposed method has been applied to various kinds of time series problems. An application to the seismic ground motion was presented in the KACC'99, and since then the method has been improved in many aspects, for example, additions of new node functions, improvements of the node functions, and new exploitations of many kinds of mutation operators. The new ideas and trials enhance the ability to generate effective and complicated models and reduce CPU time. Today, we will present a couple of financial applications, espc:cially focusing on gold price prediction in Tokyo market.

• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.235-245
• /
• 2011

Early criticality prediction models that determine whether a design entity is fault-prone or not are becoming more and more important as software development projects are getting larger. Effective predictions can reduce the system development cost and improve software quality by identifying trouble-spots at early phases and proper allocation of effort and resources. Many prediction models have been proposed using statistical and machine learning methods. This paper builds a prediction model using Support Vector Machine(SVM) which is one of the most popular modern classification methods and compares its prediction performance with a well-known prediction model, BackPropagation neural network Model(BPM). SVM is known to generalize well even in high dimensional spaces under small training data conditions. In prediction performance evaluation experiments, dimensionality reduction techniques for data set are not used because the dimension of input data is too small. Experimental results show that the prediction performance of SVM model is slightly better than that of BPM and polynomial kernel function achieves better performance than other SVM kernel functions.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.35T no.1
• /
• pp.111-119
• /
• 1998

To predict propagation environments of antenna radiation pattern, it is very important for deceision of service area, selection of the best station location and design of cell etc. By analyzing the propagation prediction model that is varied acceding to the kind of antenna, beam angle, terrain and obstacles, we expect that the economic operating of communication networks, calling quality and service of subscriber will be enhanced. It was measured the fields strength to propose the optimal propargation predicted model of the zone of Seji base station in Naju-city. The simulations of field test are 4 types Hata model, the Egri model, the Carey model and the proposed model. Finally the proposed model are more close agreement with experimental test than other models.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.1
• /
• pp.52-59
• /
• 2015

In the conventional model for the prediction of the railway environmental noise, one used an empirical formula of the total noise level at specific distances. Only a function of the distance to the source was also used to calculate the noise level near the railway bridges. However, the noise varies depending on the position of the receiver as well as the distance from the source especially at concrete bridges. In this paper, a noise propagation model in the railway concrete bridge was derived by considering the diffraction at the bridge deck and the ground effect and applying the ISO 9613-2 noise propagation model. We compared the predicted and measured values of environmental noise at a high-speed railway bridge, and it was confirmed that this prediction model gives relatively small errors.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.12 s.115
• /
• pp.1212-1223
• /
• 2006

Microwave(M/W) bands, though having great demand in wireless services, have been used mostly for long distance communications. As a result, the studies on their mobile radio models have been made less than on VHF/UHF. However, as the mobile communication services with M/W bands have been increasing, the development of a more accurate prediction model of the mobile radio environments has been demanded. The development of a reliable radio prediction model in the mobile radio environments requires the measurement and analysis of the characteristics of the radio waves according to reflection, diffraction and scattering of radio signals in various mobile radio environments. The proposed 8 GHz band radio prediction models have 2 different categories: (1) LOS model and (2) non-LOS model. The LOS model predicts signal strength using the analytic result with measured pathless exponents for the waves direct and reflected by ground and buildings, and the non-LOS model suggests a prediction model of received power by calculating the signal variations after diffraction.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.10
• /
• pp.113-119
• /
• 1998

Ship structures and aircraft structures are consisted of thin sheet alloy, so it is very important to understand the characteristics of fatigue crack propagation of that material and to establish the data base. The data for fatigue crack propagation behavior scatter very much even under identical experimental conditions with constant loading. The behavior of fatigue crack propagation under regular and irregular cyclic loadings is known to be highly affected by complicated factors such as plastic zone developed at the vicinity of crack tip and reduction of cross sectional area. In this paper, the controlled stress amplitude and overload fatigue crack propagation tests have been conducted to investigate the effect of varying factors such as plastic zone size near the crack tip and area reduction factor (AF) on the fatigue crack propagation behavior A better simulation of fatigue crack propagation behavior is found to be obtainable by using Wheeler and Willenborg models with AF effect.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.10 no.3
• /
• pp.419-429
• /
• 1999

Identifying the boundary of the effective receiving power of waves is one of the most important factors for cell optimization. In this paper, we introduce a propagation loss prediction model which yields highly accurate prediction in very complex areas as Seoul where a mixture of many large buildings, small buildings, broad streets, narrow alleys, rivers and forests co-exist in an irregular arrangement. This prediction model is based on neural networks trained on field measurement data collected in the past. Using these data along with 3-D digital elevation maps and vector data for building structures, we extract the parameter values which mainly affect the amount of propagation loss. These parameter values are then used as the inputs to the neural network. Trained neural network becomes the approximated function of the propagation loss model which generalizes very well and can predict accurately in the regions not included in training the neural network. The experimental results show a superior performance over the other models in the cells operating in the city of Seoul.

• Journal of KSNVE
• /
• v.8 no.2
• /
• pp.289-296
• /
• 1998

To predict the noise propagation from an elevated railway, sound radiation characteristics of elevated structure are measured by using the sound intensity method. In the base of the results, we propose the source model of elevated structure noise and the calculation model for elevated railway noise. Acoustic model of the former is modeled a row of single sources with directivity cos .theta. positioned in the center of a bogie and arranged in the lower side of slabs. Also prediction model is presented with rolling noise and elevated structure noise calculated by considering the power level of a source for one-third octave band, ground absorption and barrier deflection. Noise level unit patterns of a passing train is calculated based on this model and the results are compared with available field data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.146.4-146
• /
• 2001

Various methods have been proposed for the time series prediction. Most of the conventional methods only optimize parameters of mathematical models, but to construct an appropriate functional form of the model is more difficult in the first place. We employ the Genetic Programming (GP) to construct the functional form of prediction models. Our method is distinguished because the model parameters are optimized by using Back-Propagation (BP)-like method and the prediction model includes discontinuous functions, such as if and max, as node functions for describing complicated phenomena. The above-mentioned functions are non-differentiable, but the BP method requires derivative. To solve this problem, we develop ...