• Journal of Korean Society of Transportation
• /
• v.32 no.6
• /
• pp.589-599
• /
• 2014

This paper analyzes the forecasting errors of traffic volumes by comparing forecasted volumes for the opening year with the observed ones in the years after the urban railway construction in the metropolitan areas. The result shows that the average inaccuracy of traffic volumes for each station was estimated at around 7.27. Based on the confirmed factors of demand estimation errors, this study seeks for an alternative method to reduce estimation errors in feasibility studies. It is noted that there is a tendency that the inaccuracy varies by regions and the longer construction period or the shorter station spacing is, the overestimation increases. If urban railway projects are proceeded as planed, therefore, the level of the inaccuracy for traffic volume forecast will be decreased. In addition, thanks to the theoretical progress, recent estimation results show higher accuracy than before. In that sense, when we introduce the new railway line, it is necessary to make an accurate and realistic demand forecast based on actual outcomes and tendency of the previous estimation. The limitation of our study is that we only cover the errors of the initial period, the opening year and deal with the exogenous variables. Further research including other variables which might be considered to cause overestimation or errors would be needed for increasing the estimation accuracy of traffic volumes.

• International Journal of Highway Engineering
• /
• v.9 no.1 s.31
• /
• pp.17-27
• /
• 2007

Since early 1990s, several developed countries have applied the Electronic Toll Collection System (ETCS) to toll roads in order to solve traffic congestion and delay problems at toll plazas. For the successful operation of the ETCS, it is important to correctly forecast the ETCS using rate. In this study, it was conceived to develop a sophisticated demand forecasting model of the ETCS for toll roads in Changwon City The Binary Logit and neural network models were tested for the model considering 11 explaining variables. The best results in prediction accuracy and goodness-of-fit were obtained on the neural network model. However, because of the difficulty in predicting the 11 variables and its fitness in wide range, the Binary Logit model which considers three policy variables only is recommended as the model to forecast the ETCS using rate.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.1-25
• /
• 2022

After the first Covid-19 confirmed case occurred in Korea in January 2020, interest in personal transportation such as public bicycles not public transportation such as buses and subways, increased. The demand for 'Ddareungi', a public bicycle operated by the Seoul Metropolitan Government, has also increased. In this study, a demand prediction model of a GRU(Gated Recurrent Unit) was presented based on the rental history of public bicycles by time zone(2019~2021) in Seoul. The usefulness of the GRU method presented in this study was verified based on the rental history of Around Exit 1 of Yeouido, Yeongdengpo-gu, Seoul. In particular, it was compared and analyzed with multiple linear regression models and recurrent neural network models under the same conditions. In addition, when developing the model, in addition to weather factors, the Seoul living population was used as a variable and verified. MAE and RMSE were used as performance indicators for the model, and through this, the usefulness of the GRU model proposed in this study was presented. As a result of this study, the proposed GRU model showed higher prediction accuracy than the traditional multi-linear regression model and the LSTM model and Conv-LSTM model, which have recently been in the spotlight. Also the GRU model was faster than the LSTM model and the Conv-LSTM model. Through this study, it will be possible to help solve the problem of relocation in the future by predicting the demand for public bicycles in Seoul more quickly and accurately.

• International Journal of Railway
• /
• v.5 no.4
• /
• pp.139-143
• /
• 2012

In Korea, almost 700 industrial parks are under operation. Generally, industrial parks consist of national industrial parks and local industrial parks which are managed by a central government and by local governments respectively. The developing countries such as Korea, China and Vietnam etc. have constructed many industrial parks, which result in the change of land use pattern and also affect future trip demands. Therefore, in estimating traffic demands, it is very important to consider the industrial park development. This study aims to improve the methodology in estimating a freight trip generation rate with the data based on a nationwide commodity freight survey. The result showed that it is desirable to apply freight trip generation rate by the industry sector in estimating freight trip generations and using the production area of firm as an indicator. Specially, the reliability of the rates through a survey could be made sure because a sample rate based on firms in industrial parks was over 25% and the response rate was over 67%. The sample rate and response rate are very superior as compared to surveys conducted in many other countries. Because industrial parks have significant effects on forecasting transportation demand in pre-feasibility studies of transport and logistics projects, it is expected that the accuracy of freight trip demands would be improved through the results of this study.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.29-32
• /
• 1993

A technique computing short-term load foadcasting is essential for monitoring and controlling power system operation. This paper shows the use of general exponential smoothing to develop an adaptive forecasting system based on observed value of hourly demand. Forecasts of hourly load with lead times of one to twenty-four hours are computed at hourly intervals throughout the week. Standard error for lead times of one to twenty-four hour range from three to four percent average load. Studies are planned to investigate the use of weather influence to increase forecast accuracy.

• East Asian mathematical journal
• /
• v.40 no.1
• /
• pp.119-125
• /
• 2024

Predicting the number of ICU patients holds significant importance, serving as a critical aspect in efficiently allocating resources, ensuring high-quality care for critically ill individuals, and implementing effective public health strategies to mitigate the impact of diseases. This research focuses on estimating ICU patient numbers through the development of a simple mathematical model. Utilizing data on confirmed COVID-19 cases and deaths, this model becomes a valuable tool for predicting and managing ICU resource requirements during the ongoing pandemic. By incorporating historical data on infected individuals and fatalities from previous weeks, we establish a straightforward equation. We found the substantial impact of the delay in infected individuals, particularly those occurring more than five weeks earlier, on the accuracy of ICU predictions. Proactively preparing for potential surges in severe cases becomes feasible by forecasting the demand for intensive care beds, ultimately improving patient outcomes and preventing excessive strain on medical facilities.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2701-2717
• /
• 2023

In this paper, a hybrid fuzzy-based method is suggested for determining India's best system for power generation. This suggested approach was created using a fuzzy-based combination of the Giza Pyramids Construction (GPC) and Recalling-Enhanced Recurrent Neural Network (RERNN). GPC is a meta-heuristic algorithm that deals with solutions for many groups of problems, whereas RERNN has selective memory properties. The evaluation of the current load requirements and production profile information system is the main objective of the suggested method. The Central Electricity Authority database, the Indian National Load Dispatch Centre, regional load dispatching centers, and annual reports of India were some of the sources used to compile the data regarding profiles of electricity loads, capacity factors, power plant generation, and transmission limits. The RERNN approach makes advantage of the ability to analyze the ideal power generation from energy data, however the optimization of RERNN factor necessitates the employment of a GPC technique. The proposed method was tested using MATLAB, and the findings indicate that it is effective in terms of accuracy, feasibility, and computing efficiency. The suggested hybrid system outperformed conventional models, achieving the top result of 93% accuracy with a shorter computation time of 6814 seconds.

• Journal of Korean Society of Transportation
• /
• v.22 no.4 s.75
• /
• pp.117-134
• /
• 2004

Truck traffic accounts for a substantial fraction of the traffic stream in many regions and is often the source of localized traffic congestion, potential parking and safety problems. Truck trips tend to be ignored or treated superficially in travel demand models. It reduces the effectiveness and accuracy of travel demand forecasting and may result in misguided transportation policy and project decisions. This paper presents the development of speed-flow relationships with truck impacts based on CORSIM simulation results in order to enhance travel demand model by incorporating truck trips. The traditional BPR(Bureau of Public Road) function representing the speed-flow relationships for roadway facilities is modified to specifically include the impacts of truck traffics. A number of new speed-flow functions have been developed based on CORSIM simulation results for freeways and urban arterials.

• Environmental and Resource Economics Review
• /
• v.26 no.4
• /
• pp.519-547
• /
• 2017

This paper explores whether it is better to forecast city gas demand in Korea using national level data directly or, alternatively, construct forecasts from regional demand models and then aggregate these regional forecasts. In the regional model, we consider gas demand for Seoul metropolitan and the other local areas. Our forecast evaluation exercise for 2013-2016 shows the regional forecast model generally outperforms the national forecasting model. This result comes from the fact that the dynamic properties of each region's gas demands can be better taken into account in the regional demand model. More specifically, the share of residential gas demand in the Seoul metropolitan area is above 50%, and subsequently this demand is heavily influenced by temperature fluctuations. Conversely, the dominant portion of regional gas demand is due to industrial gas consumption. Moreover, electricity is regarded as a substitute for city gas in the residential sector, and industrial gas competes with certain oil products. Our empirical results show that a regional demand forecast model can be an effective alternative to the demand model based on nation-wide gas consumption and that regional information about gas demand is also useful for analyzing sectoral gas consumption.

• International Journal of Highway Engineering
• /
• v.12 no.4
• /
• pp.61-70
• /
• 2010

The purpose of this study is to analyze the accuracy of traffic volume forecast by comparing an estimated to real traffic volume. For this study, total 10 sections of national highways, which are planned in 1980s and 1990s, were selected and traffic analysis data for highway construction were collected. In addition, targeted 10 sections were categorized into network-related and -unrelated sections. In the analysis of inaccuracy between the estimated and real traffic, for network-related sections, appeared to have lower inaccuracy. As time goes on after traffic open, inaccuracy between the estimated and real traffic appeared to be lower. In various section lengths, the longer the section length, the higher the inaccuracy is. Using 3 years passed data after traffic open, national highway have lower inaccuracy than expressway. However, the traffic analysis according to traffic open time resulted in little change of the inaccuracy.