• The KIPS Transactions:PartC
• /
• v.9C no.4
• /
• pp.489-496
• /
• 2002

This study proposes a new polling algorithm allowing dynamic change in polling period based on line utilization prediction. Polling is the most important function in network monitoring, but excessive polling data causes rather serious congestion conditions of network when network is In congestion. Therefore, existing multiple polling algorithms decided network congestion or load of agent with previously performed polling Round Trip Time or line utilization, chanced polling period, and controlled polling traffic. But, this algorithm is to change the polling period based on the previous polling and does not reflect network conditions in the current time to be polled. A algorithm proposed in this study is to predict whether polling traffic exceeds threshold of line utilization on polling path based on the past data and to change the polling period with the prediction. In this study, utilization of each line configuring network was predicted with AR model and violation of threshold was presented in probability. In addition, suitability was evaluated by applying the proposed dynamic polling algorithm based on line utilization prediction to the actual network, reasonable level of threshold for line utilization and the violation probability of threshold were decided by experiment. Performance of this algorithm was maximized with these processes.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.11
• /
• pp.15-22
• /
• 2008

The cdma2000 1xEV-DO system controls the data rates of mobile terminals based on a binary overload indicator from the base station and a simple probabilistic model. However, this control scheme has difficulty in predicting the future behavior of mobile terminals due to a probabilistic uncertainty and has no reliable means of suppressing the traffic overload, which may result in performance degradation of CDMA systems that have interference-limited capacity. This Paper proposes a new traffic control scheme that controls the data rates of mobile terminals effectively by predicting the future traffic load and adjusting the forward-link control channel. The proposed scheme is analyzed by modeling it as a multi-dimensional Markov process and compared with conventional schemes. The numerical results show that the maximum cell throughput of the proposed scheme is much higher than those of the conventional schemes.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.70-85
• /
• 2021

Deep learning methodology, which has been actively studied in recent years, has improved the performance of artificial intelligence. Accordingly, systems utilizing deep learning have been proposed in various industries. In traffic systems, spatio-temporal graph modeling using GNN was found to be effective in predicting traffic speed. Still, it has a disadvantage that the model is trained inefficiently due to the memory bottleneck. Therefore, in this study, the road network is clustered through the graph clustering algorithm to reduce memory bottlenecks and simultaneously achieve superior performance. In order to verify the proposed method, the similarity of road speed distribution was measured using Jensen-Shannon divergence based on the analysis result of Incheon UTIC data. Then, the road network was clustered by spectrum clustering based on the measured similarity. As a result of the experiments, it was found that when the road network was divided into seven networks, the memory bottleneck was alleviated while recording the best performance compared to the baselines with MAE of 5.52km/h.

• Structural Engineering and Mechanics
• /
• v.74 no.1
• /
• pp.55-67
• /
• 2020

The common practice to predict the characteristic structural load effects (LEs) in long reference periods is to employ the extreme value theory (EVT) for building limit distributions. However, most applications ignore that LEs are driven by multiple loading events and thus do not have the identical distribution, a prerequisite for EVT. In this study, we propose the composite extreme value modeling approach using clustering to (a) cluster initial blended samples into finite identical distributed subsamples using the finite mixture model, expectation-maximization algorithm, and the Akaike information criterion; (b) combine limit distributions of subsamples into a composite prediction equation using the generalized Pareto distribution based on a joint threshold. The proposed approach was validated both through numerical examples with known solutions and engineering applications of bridge traffic LEs on a long-span bridge. The results indicate that a joint threshold largely benefits the composite extreme value modeling, many appropriate tail approaching models can be used, and the equation form is simply the sum of the weighted models. In numerical examples, the proposed approach using clustering generated accurate extrema prediction of any reference period compared with the known solutions, whereas the common practice of employing EVT without clustering on the mixture data showed large deviations. Real-world bridge traffic LEs are driven by multi-events and present multipeak distributions, and the proposed approach is more capable of capturing the tendency of tailed LEs than the conventional approach. The proposed approach is expected to have wide applications to general problems such as samples that are driven by multiple events and that do not have the identical distribution.

• International Journal of Highway Engineering
• /
• v.14 no.6
• /
• pp.131-138
• /
• 2012

PURPOSES : Two-lane highways have one lane in each direction, and lane changing and passing maneuvers take place in the opposing lane depending on the availability of passing sight distance. 2001 Korea Highway Capacity Manual (KHCM) is classified into two classes of two-lane highways (Type I, II), and average travel speed and time-delayed rate are used as measures of effectiveness (MOEs). However, since existing two-lane highways have both uninterrupted and interrupted traffic flow-system elements, a variety of free-flow speeds exhibits in two-lane highways. In addition, it is necessary to check if the linear-relationship between volumes and time-delayed rate is appropriate. Then, this study is to reestablish the relationship between average travel speed, time-delayed rate, and flow. METHODS : TWOPAS model was selected to conduct this study, and the free-flow speeds of passenger cars and the percentage of following vehicles observed in two-lane highways were applied to the model as the input. The revised relationships were developed from the computer simulation. RESULTS : In the revised average travel speed vs. flow relationship, the free-flow speed of 90km/h and 70km/h were added. It shows that the relationship between time delayed-rate and flow appeared to be appropriate with the log-function form and that there was no difference in time-delayed rate between the free flow speeds. In addition to revise the relationships, the speed prediction model and the time-delayed rate prediction model were also developed. CONCLUSIONS : The revised relationships between average travel speed, time-delayed rate, and flow would be useful in estimating the Level of Service(LOS) of a two-lane highway.

• Journal of the Society of Disaster Information
• /
• v.16 no.4
• /
• pp.682-690
• /
• 2020

Purpose: This study builds a database by collecting and refining disaster occurrence data and real-time weather and atmospheric data. In conjunction with the public data provided by the API, we propose a service model for the Big Data-based Urban Safety Index. Method: The plan is to provide a way to collect various information related to disaster occurrence by utilizing public data and SNS, and to identify and cope with disaster situations in areas of interest by real-time dashboards. Result: Compared with the prediction model by extracting the characteristics of the local safety index and weather and air relationship by area, the regional safety index in the area of traffic accidents confirmed that there is a significant correlation with weather and atmospheric data. Conclusion: It proposed a system that generates a prediction model for safety index based on machine learning algorithm and displays safety index by sector on a map in areas of interest to users.

• 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.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2016.05a
• /
• pp.285-286
• /
• 2016

We aim to propose the prediction modeling method of ship's position with extracting ship's trajectory model through pattern recognition based on the data that are being collected in VTS centers at real time. Support Vector Machine algorithm was used for data modeling. The optimal parameters are calculated with k-fold cross validation and grid search. We expect that the proposed modeling method could support VTS operators' decision making in case of complex encountering traffic situations.

• Wind and Structures
• /
• v.32 no.5
• /
• pp.453-469
• /
• 2021

Snow accumulation on the road frequently induces a big traffic problem in the cold snowy region. Accurate prediction on snow distribution is fundamental for solving drifting snow disasters on roads. The present study adopts the transient method to simulate the wind-induced snow distribution on embankment based on the mixture multiphase model and dynamic mesh technique. The simulation and field measurement are compared to confirm the applicability of the simulation. Furthermore, the process of snow accumulation is revealed. The effects of friction velocity and snow concentration on snow accumulation are analyzed to clarify its mechanism. The results show that the simulation agrees well with the field measurement in trends. Moreover, the snow accumulation on the embankment can be approximately divided into three stages with time, the snow firstly deposited on the windward side, then, accumulation occurs on the leeward side which induced by the wake vortex, finally, the snow distribution reaches an equilibrium state with the slope of approximately 7°. The friction velocity and duration have a significant influence on the snow accumulation, and the vortex scale directly affected the snow deposition range on the embankment leeward side.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.77-93
• /
• 2022

In this study, we present an algorithm that analyzes the risk by reflecting regional characteristics for factors affected by direct and indirect damage from heavy-snow. Factors affected by heavy-snow damage by 29 regions are selected as influencing variables, and the concept of sensitivity is derived through the relationship with the amount of damage. A snow damage risk prediction model was developed using a machine learning (XGBoost) algorithm by setting weather conditions (snow cover, humidity, temperature) and sensitivity as independent variables, and setting the risk derived according to changes in the independent variables as dependent variables.