• Journal of Information Processing Systems
• /
• 제15권2호
• /
• pp.305-319
• /
• 2019

The prediction of the sum of container is very important in the field of container transport. Many influencing factors can affect the prediction results. These factors are usually composed of many variables, whose composition is often very complex. In this paper, we use gray relational analysis to set up a proper forecast index system for the prediction of the sum of containers in foreign trade. To address the issue of the low accuracy of the traditional prediction models and the problem of the difficulty of fully considering all the factors and other issues, this paper puts forward a prediction model which is combined with a back-propagation (BP) neural networks and the support vector machine (SVM). First, it gives the prediction with the data normalized by the BP neural network and generates a preliminary forecast data. Second, it employs SVM for the residual correction calculation for the results based on the preliminary data. The results of practical examples show that the overall relative error of the combined prediction model is no more than 1.5%, which is less than the relative error of the single prediction models. It is hoped that the research can provide a useful reference for the prediction of the sum of container and related studies.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2000년도 제 25회 정기총회 및 추계학술발표회
• /
• pp.23-28
• /
• 2000

The DGPS is used to improve the accuracy of the GPS by determining the positioning error data known locatio and subsequently transmitting the determined error, or corrective factors, to users of the GPS operating in the same geographical area. The accuracy of the DGPS available to real0time users is published in the Federal Radio-Navigation Plan to be better than 10 meters, although users often experience accuracies of better than 3 meters. USA recently decided to expand the marine DGPS service for land applications and initiated the Nationwide DGPS chain. Korea is processing for improving the marine DGPS. We have not achieved Full Operational Capability. But after announcing FOC, we have to begin expansion of DGPS into land. This paper investigate the availability of marine DGPS in land. The results will provide a basic guide for estimation of a propagation loss of the marine DGPS frequency in land.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 하계종합학술대회 논문집(1)
• /
• pp.55-58
• /
• 2004

This this paper, we propose vertical Bell laboratories layered space time (V-BLAST) system based on variable rate Low-Density Parity Check (LDPC) codes to improve performance of receiver when QR decomposition interference suppression combined with interference cancellation is used over independent Rayleigh fading channel. The different rate LDPC codes can be made by puncturing some rows of a given parity check matrix. This allows to implement a single encoder and decoder for different rate LDPC codes. The performance can be improved by assigning stronger LDPC codes in lower layer than upper layer because the poor SNR of first detected data streams makes error propagation. Keeping the same overall code rates, the V-BLAST system with different rate LDPC codes has the better performance (in terms of Bit Error Rate) than with constant rate LDPC code in fast fading channel.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4584-4599
• /
• 2021

In IEEE 802.11p-based wireless access in vehicular environments (WAVE) communication systems, channel estimation (CE) is one of the important issues to provide stable communication service. It is hard to apply conventional CE schemes based on data pilot to real systems, because error propagation occurs in high mobility and modulation order environments, resulting in degrading the CE performance. In this paper, we propose one data pilot using multiple receive antennas (ODPM) CE scheme based on the weighted sum using update matrix (WSUM) with time-domain averaging (TDA) to overcome this problem. Within the process of WSUM-TDA in the proposed scheme, the maximum ratio combining (MRC) technique is applied so as to create more accurate one data pilot. Moreover, a new reliability test criterion is proposed as the fashion of utilizing MRC, which makes it possible to apply selective TDA that guarantees performance improvement. In simulation results, the packet error rate (PER) performance of the proposed ODPM is compared with that of conventional CE methods and its superiority is demonstrated.

• 전자공학회논문지C
• /
• 제34C권6호
• /
• pp.71-78
• /
• 1997

In this paper, a new neural network training algorithm will be devised for function approximator with good generalization characteristics and tested with the time series prediction problem using santaFe competition data sets. To enhance the generalization ability a constraint term of hidden neuraon activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. A hybrid learning algorithm of the error-back propagation and Hebbian learning algorithm with weight decay constraint will be naturally developed by the steepest decent algorithm minimizing the proposed cost function without much increase of computational requriements.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2005년도 학술발표회 논문집
• /
• pp.18-25
• /
• 2005

Stochastic ground-motion method is adopted to simulate horizontal PGA values for the offshore Uljin earthquake recorded at nationwide seismic stations. For this purpose, the Fourier spectra are calculated at every stations based on comprehensive results of wave propagation and site effect which were previously revealed through inversion process applied to large accumulated spectral D/B. In addition, the apparent source spectrum of the offshore Uljin earthquake is estimated by removing the path and site response from the observed spectra. The distance dependent time-duration model is revised by iteratively fitting the PGA values generated by using the raw spectra data to the observed PGA data. The stochastic ground-motion method predicts the observed PGA values within a error of ${\sigma}_{log10}=0.1$. Transfer functions of a site relative to another site are estimated based on the error residual of the inversion results and used to convert PGA values at multiple stations to expected PGA values at a reference station of TJN. The converted PGA values can be used as basic data to evaluate the ground-motion attenuation relations developed for seismic hazard analysis that concerns the large damaging earthquakes.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.420-423
• /
• 2001

In this paper, the Multi-FNNs(Fuzzy-Neural Networks) architecture is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNNs architecture uses simplified inference and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNNs according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNNs model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model we use the time series data for gas furnace and the NOx emission process data of gas turbine power plant.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.383-386
• /
• 1997

In this paper, We proposed a parallel structure of the Neural Network model to nonlinear complex system. Neural Network was used as basic model which has learning ability and high tolerence level. This paper, we used Neural Network which has BP(Error Back Propagation Algorithm) model. But it sometimes has difficulty to append characteristic of input data to nonlinear system. So that, I used HCM(hard c-Means) method of clustering technique to append property of input data. Clustering Algorithms are used extensively not only to organized categorize data, but are also useful for data compression and model construction. Gas furance, a sewage treatment process are used to evaluate the performance of the proposed model and then obtained higher accuracy than other previous medels.

• 한국통신학회논문지
• /
• 제15권9호
• /
• pp.738-744
• /
• 1990

본 논문은 음성신호의 실시간 저장법과 기존 표본 데이터에서 개선된 표본 데이터 방법을 제안하여, 신경회로망의 역전파 학습 알고리즘을 이용한 고립 단어 음성인식 시스템에 대하여 연구하였다. 각 층의 노드 수 변화에 의한 기존 표본 데이터방식과 새로운 표본 데이터 방식에서의 인식률과 에러율 변화를 비교하였다. 본 연구 결과, 인식률은 95.1%를 얻었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1989년도 추계학술대회 논문집 학회본부
• /
• pp.186-190
• /
• 1989

A Study for Bad Data Processing in state estimation by a Neural Network is presented. State estimation is the process of assigning a value to an unknown system state variable based on measurement from that system according to some criteria. In this case, the ability to detect and identify bad measurements is extremely valuable, and much time in oder to achieve the state estimation is needed. This paper proposed new bad data processing using Neural Network in order to settle it. The concept of neural net is a parallel distributed processing. In this paper, EBP (Error Back Propagation) algorithm based on three layered feed forward network is used.