• 한국환경과학회지
• /
• 제27권7호
• /
• pp.531-541
• /
• 2018

Road freezing caused by snowfall during wintertime causes traffic congestion and many accidents. To prevent such problems, we developed, in this study, a system to predict road freezing based on weather forecast data and the freezing generation modules. The weather forecast data were obtained from a high-resolution model with 1 km resolution for Jeju Island from 00:00 KST on December 1, 2017, to 23:00 KST on February 28, 2018. The results of the weather forecast data show that index of agreement (IOA) temperature was higher than 0.85 at all points, and that for wind speed was higher than 0.7 except in Seogwipo city. In order to evaluate the results of the freezing predictions, we used model evaluation metrics obtained from a confusion matrix. These metrics revealed that, the Imacho module showed good performance in precision and accuracy and that the Karlsson module showed good performance in specificity and FP rate. In particular, Cohen's kappa value was shown to be excellent for both modules, demonstrating that the algorithm is reliable. The superiority of both the modules shows that the new system can prevent traffic problems related to road freezing in the Jeju area during wintertime.

• 한국정보과학회논문지:정보통신
• /
• 제30권1호
• /
• pp.1-8
• /
• 2003

본 논문에서는 광 인터넷의 가상 토폴로지 재구성을 효과적으로 관리하는 정책을 제시한다. 기존의 휴리스틱 기법의 근사 문제를 해결하기 위해 트래픽 예측 기반 다단계 재구성 알고리즘을 바탕으로 트래픽 패턴과 망 혼잡 정도의 변화에 따라 적응적인 토폴로지 재구성 기법을 제시한다. 이 알고리즘은 네트워크의 상태를 고려하여 적정 재구성 시기를 결정함으로써 가상망의 관리를 단순화한다. 시뮬레이션 결과, 제안된 가상망 관리 정책이 물리적인 자원 사용이 제한될 때 기존의 방법에 비해 좋은 성능을 보인다.

• 디지털산업정보학회논문지
• /
• 제9권4호
• /
• pp.127-134
• /
• 2013

While there are many services that can check current traffic condition and application program such as bus arrival alarm are developed, since it only provide simple alarm and check level of information, it is still insufficient in many senses. Therefore, the program that try to develop in this study is the system that predict arrival time to destination and inform the bus passengers by applying real time traffic information. The system developed related to this study is still very inadequate. In the system developed in this thesis, when the user input the current bus number and destination using smart-phone, relevant server acquire the bus route information from bus information DB, and analyze real time traffic information based on the information from traffic information DB, and inform customer of expected arrival time to destination. In this thesis, traffic congestion can be eased off and regular operation of public transportation can be improved with reliable destination arrival alarm. Also, it is considered that pattern of bus users can be analyzed by using these information, and analyzing average transport speed and time of public transportation, travel time depending on various situation can give a boost to study related to transportation information and its development.

• 응용통계연구
• /
• 제34권5호
• /
• pp.773-794
• /
• 2021

교통량 예측은 지방 행정의 의사결정에 매우 중요한 정보를 제공한다. 교통량 예측을 통해 교통혼잡비용을 줄이고 지역경제를 활성화 함으로써 사회적, 경제적 이익을 창출할 수 있다. 교통량은 미지의 확률적 규칙하에서 시간의 흐름에 따라 궤적을 가지며 변화하는 함수데이터의 일종이다. 본 논문에서는 세 가지 함수회귀모형을 이용하여 과거에 관측된 교통량 궤적을 기반으로 미래의 관측되지 않은 교통량 궤적을 예측하는 방법을 제시한다. 본 논문에서 소개하는 세가지 방법은 전국 고속도로 영업소 중 서울, 춘천, 강릉 세 개 영업소에서 수집된 고속도로 영업소 데이터에 적용한다. 각 영업소 별로 세가지 방법의 예측오차를 비교함으로써 영업소별 최적 교통량 예측모형을 찾는다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3416-3435
• /
• 2023

Task offloading in vehicular networks is hot topic in the development of autonomous driving. In these scenarios, due to the role of vehicles and pedestrians, task characteristics are changing constantly. The classical deep learning algorithm always uses a pre-trained neural network to optimize task offloading, which leads to system performance degradation. Therefore, this paper proposes a neural network fine-tuning task offloading algorithm, combining with location prediction for pedestrians and vehicles by the Payne model of fluid dynamics and the car-following model, respectively. After the locations are predicted, characteristics of tasks can be obtained and the neural network will be fine-tuned. Finally, the proposed algorithm continuously predicts task characteristics and fine-tunes a neural network to maintain high system performance and meet low delay requirements. From the simulation results, compared with other algorithms, the proposed algorithm still guarantees a lower task offloading delay, especially when congestion occurs.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (3)
• /
• pp.301-303
• /
• 2003

본 논문에서는 인터넷 혼잡제어를 위한 새로운 방법을 제안한다. 라우터 큐에 예측제어함수를 적용하여 미래의 혼잡상황을 예측하고 소스에게 미리 피드백을 수행하여 혼잡제어를 한다. 예측제어함수는 실제 큐와 예측된 큐의 오차를 계산하여 주기적으로 예측함수를 갱신하는 NLMS 방식의 예측제어함수를 적용한다. 피드백 정보의 전송지연으로 인한 혼잡상황 악화가 발생하기 전에 혼잡상황에 대응할 수 있으므로 라우터 버퍼 사용효율의 최적함을 유지할 수 있으며 버퍼 오퍼플로우로 발생하는 패킷의 손실을 최소화 할 수 있다. 혼잡상황을 야기하도록 과도한 트래픽을 생성하여 라우터에서 예측함수를 적용하는 경우와 단지 혼잡알림제어를 수행하는 경우를 비교하여 시뮬레이션을 수행하였다. 예측함수를 적용하는 경우는 시스템 성능효율을 증가시키며 라우터 버퍼 크기를 최적하게 사용할 뿐만 아니라 오퍼플로우가 발생하지 않았으나 예측함수를 적용하지 않고 혼잡알림제어를 수행하는 경우는 과도한 큐 크기와 오버플로우가 발생하였음을 시뮬레이션을 통해서 보인다.

• Advances in environmental research
• /
• 제4권4호
• /
• pp.211-218
• /
• 2015

Traffic noise estimation models are useful in evaluation of the noise pollution in current circumstances. They are helpful tools for design and planning new roads and highways. Measurement of average traffic noise level is possible when traffic speed and volume are known. The objective of this study was to devise a model for prediction of highway traffic noise levels based on current traffic variables in Iran. The design of this model was to take the impact of traffic congestion into consideration and to be field tested. This study is a library research augmented by field study conducted on Saeedi Highway located south west of Tehran. The period for the field study lasted 5 days from 7-12 February, 2013. This study examined liner and non-liner methods in formulation of its model. Liner method without a fixed coefficient was the best fit for the intended model. The proposed model can serve as a decision making tool to estimate the impact of key influential factors on sound pressure levels in urban areas in Iran.

• International Journal of Advanced Culture Technology
• /
• 제8권3호
• /
• pp.275-279
• /
• 2020

Due to the recent rapid industrialization worldwide, the number of pediatric asthma patients is increasing. And the fine dust containing heavy metals is linked to the characteristics of high toxic lead due to the increase heating in factory operation and automobile driving. It is the reason of arsenic increasing. In the treatment of pediatric asthma patients, drug administration, oral drug entry, and HMPC (Home Management Plan of Care) are used. In this paper, we analyze the relationship between the onset of asthma and the method of prescription for specific childhood asthma in the United States using EM (Expectation Maximization) and MDL (Minimum Description Length) algorithms. And the association is also analyzed by comparing the nature of specific congestion between the past prevalence of digestive asthma and the recent prevalence of environmental pollution.

• ETRI Journal
• /
• 제37권6호
• /
• pp.1096-1107
• /
• 2015

This paper presents a dynamic retry adaptation scheme for H.264 HD video, called DRAS.264, which dynamically adjusts the retry limits of frames at the medium access control (MAC) layer according to the impact those frames have on the streamed H.264 HD video. DRAS.264 is further improved with a bandwidth estimation technique, better prediction of packet delays, and expanded results covering multi-slice video. Our study is performed using the Open Evaluation Framework for Video Over Networks as a simulation environment for various congestion scenarios. Results show improvements in average peak signal-to-noise ratios of up to 4.45 dB for DRAS.264 in comparison to the default MAC layer operation. Furthermore, the ability of DRAS.264 to prioritize data of H.264 bitstreams reduces error propagation during video playback, leading to noticeable visual improvements.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2005년도 추계학술대회 논문집
• /
• pp.1109-1114
• /
• 2005

The rolling contact fatigue of wheels for high speed trains is a matter of increasing importance. The wheel damages from fatigue crack makes noise up and safety down. RCF-casued accidents cause traffic congestion and economical costs as well as personal injuries. In this study, we examine the rolling contact fatigue of wheels for power car running at 300km/h. Using the results of multi-body dynamic analysis and the proposed procedure of Ekberg, we calculate the fatigue index of surface-initiated fatigue, subsurface-initiated fatigue and fatigue initiated at deep material defects. As a result. the fatigue index shows us whether fatigue will appear and in which form. In addition, we present Shakedown map on surface-initiated fatigue.