• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.

• Journal of the Korean Society for Railway
• /
• v.13 no.1
• /
• pp.71-77
• /
• 2010

It is increasing annually that the cost for bridge Maintenance Repair & Rehabilitation (MR&R) in developed countries. Based on Intelligent Technology, Bridge Management System (BMS) is developed for optimization of Life Cycle Cost (LCC) and reliability to predict long-term bridge deteriorations. However, such data are very limited amongst all the known bridge agencies, making it difficult to reliably predict future structural performances. To alleviate this problem, an Artificial Neural Network (ANN) based Backward Prediction Model (BPM) for generating missing historical condition ratings has been developed. Its reliability has been verified using existing condition ratings from the Maryland Department of Transportation, USA. The function of the BPM is to establish the correlations between the known condition ratings and such non-bridge factors as climate and traffic volumes, which can then be used to obtain the bridge condition ratings of the missing years. Since the non-bridge factors used in the BPM can influence the variation of the bridge condition ratings, well-selected non-bridge factors are critical for the BPM to function effectively based on the minimized discrepancy rate between the BPM prediction result and existing data (deck; 6.68%, superstructure; 6.61%, substructure; 7.52%). This research is on the generation of usable historical data using Artificial Intelligence techniques to reliably predict future bridge deterioration. The outcomes (Long-term Bridge deterioration Prediction) will help bridge authorities to effectively plan maintenance strategies for obtaining the maximum benefit with limited funds.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1D
• /
• pp.43-50
• /
• 2011

The monitoring system for link travel speed using taxi probe is one of key sub-systems of ITS. Link travel speed collected by taxi probe has been widely employed for both monitoring the traffic states of urban road network and providing real-time travel time information. When sample size of taxi probe is small and link travel time is longer than a length of time interval to collect travel speed data, and in turn the missing state is inevitable. Under this missing state, link travel speed data is real-timely not collected. This missing state changes from single to multiple time intervals. Existing single interval prediction techniques can not generate multiple future states. For this reason, it is necessary to replace multiple missing states with the estimations generated by multi-interval prediction method. In this study, a multi-interval prediction method to generate the speed estimations of single and multiple future time step is introduced overcoming the shortcomings of short-term techniques. The model is developed based on Non-Parametric Regression (NPR), and outperformed single-interval prediction methods in terms of prediction accuracy in spite of multi-interval prediction scheme.

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.29-40
• /
• 2008

Although a good understanding of the relationship between highway traffic accidents and highway geometric features is fundamental in highway design and safety, the relationship is not well understood quantitatively. The overall goal of this paper is to formulate a reliable statistical model fitting to historical highway accident data. The model can be used to estimate the effect of road design elements on safety for the practical purposes of highway design applications. En route to achieving this goal, a number of specific research objectives were accomplished: investigate the major design elements affecting highway safety; review the existing modeling approaches in order to assess the relationship between safety and highway design features; and formulate a statistical model fitting to the accident data in order to estimate the interchange ramp junction accident frequency of rural highways.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.40 no.3
• /
• pp.46-56
• /
• 2022

This study aimed to analyze the locational characteristics of heritage sites in Seoul in order to identify flood susceptibility by type. As for the location factors related to flood susceptibility, elevation, slope, distance to streams, and topographic location were analyzed. Literature review was supplemented for the historical and humanistic environments of heritage sites. The results of the study are as follows. First, heritage sites in Seoul are distributed throughout the city, and are especially highly dense in the Hanyangdoseong fortress. It was also confirmed that heritage sites were concentrated around Jung-gu, Jongno-gu, Jingwan-dong, and Ui-dong in the quantitative spatial analyses. Second, types of heritage sites at the circumstance susceptible to flood damage were related to commerce and distribution, traffic, modern traffic and communication, geological monument, residence, government office, and palace. Third, heritage types with locational characteristics that showed low flood susceptibility were found to be natural scenic spots, telecommunication, ceramics, Buddhism, tombs, and tomb sculptural heritage assets. In a time when risk factors that can damage the value of heritage are gradually increasing due to anthropogenic influences along with changes in the natural environment, this study provides basic data for vulnerability analysis that reflects the unique characteristics of heritage assets. The results can contribute to more comprehensive and comprehensive insights for the management and protection of heritage by including the humanities and social science data together with natural factors in the analysis.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.10a
• /
• pp.297-302
• /
• 2003

This study was carried out to check the contingency planning methods under the analysis of oil spill potential and make a guide line to apply the results to the port of Busan. The expected spilled oil drift patterns are considered with the most probable scenarios under the base of the oil spill potential. The results obtained from this study are as follows: (1) Analysis method of oil spill potent was proposed and the applicability was proved by the application example to the port of Busan to make the contingency plan. (2) Responsible oil spill contingency planning methods / flow are suggested considered environmental factors and the oil spill potential. (3) The coastal waters of Busan was consist of rocky flat, man-made solid shore and beach shore. Marine traffic have high density of oil tanker and cargo ship. Also, oil tanker ship are examined in the small ships to be less than 3000t to supply oil to the ship moored / anchored as well as the large amount of oil tank / basin are located along the coast of Busan port. These systems are introduced to make in put data to the analysis of oil spill potential. (4) According to the analysis of historical records of oil spill accident in Busan, the frequency of accidents by cargo ship rank highest and 45% of accidents is caused by carelessness. about 65% of total accidents shows a small spill accident of less than $10k{\ell}$.

• Journal of the Korean association of regional geographers
• /
• v.12 no.5
• /
• pp.583-594
• /
• 2006

Relics are life traces of ancestors, and they are good data for giving an idea about space locations of that period. This study classifies relics according to their type, and for each classified group metrical analysis is carried out using GIS and triangle diagram. The criteria used for analysis of relics' locations are elevation, road accessibility and water accessibility. The analysis results show that every relic has its own distribution characteristics according to the time and the type. This means high possibility of approaching a geographical focus on relics distribution and location. While historical period was taking over prehistorical, relics locations moved from the points of great usage water supply possibility to the points of great traffic accessibility. Also, relics of the ruling class for each time period generally have good locations.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.21 no.2
• /
• pp.154-163
• /
• 2015

This study is based on deductions from analysis of historical changes in hydrographic surveys, the problems with the existing system in Korea and analysis of the literature, including foreign cases. Using these criteria, we created and administered a survey of marine professionals of Korea, and based on the results, established an order of priority for hydrographic surveys, as follows: changes in the seabed, quantities of marine traffic, existing performance data from hydrographic survey, consumer's demand, marine accidents, conservation of oceanic environment, and natural resources. The study also deduced, based on a survey of experts, the relative importance ranking of the major ports in South Korea and suggests policy implications and a priority decision model to conduct future hydrographic surveys in a more scientific and systematic way.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.23 no.7
• /
• pp.775-782
• /
• 2017

The position of existing patrol ships has been decided according to subjective judgments, not purely by any reasonable or scientific criteria, because of a lack of access to marine accident positions. In this study, the optimal location of patrol ships is quantitatively determined based on historical marine accident data. The study area used included the coastal sea of Pohang in South Korea. In this study, a k-means clustering algorithm was used to derive the location of patrol ships, and then a Voronoi diagram was used to divide the region around each patrol ship. As a result, the average navigation distance for patrol ships was improved by 4.4 nautical miles, and the average arrival time was improved by 13.2 minutes per marine accident. Moreover, if the locations of patrol ships need to be changed flexibly, it will be possible to optimally arrange limited resources using the technique developed in this study to ensure a fast rescue.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.3
• /
• pp.51-61
• /
• 2023

Travel demand estimation of E-Scooter is the start point of solving the regional demand-supply imbalance problem and plays pivotal role in a linked transportation system such as Mobility-as-a-Service (a.k.a. MaaS). Most focuses on developing trip generation model of shared E-Scooter but it is no study on selection of an appropriate zone scale when it comes to estimating travel demand of E-Scooter. This paper aimed for selecting an optimal TAZ scale for developing trip distribution model for shared E-Scooter. The TAZ scale candidates were selected in 250m, 500m, 750m, 1,000m square grid. The shared E-Scooter usage historical data were utilized for calculating trip distance and time, and then applying to developing gravity model. Mean Squared Error (MSE) is applied for the verification step to select the best suitable gravity model by TAZ scale. As a result, 250m of TAZ scale is the best for describing practical trip distribution of shared E-Scooter among the candidates.