• Journal of Information Processing Systems
• /
• 제18권6호
• /
• pp.719-728
• /
• 2022

The prediction of short-term traffic flow is the theoretical basis of intelligent transportation as well as the key technology in traffic flow induction systems. The research on short-term traffic flow prediction has showed the considerable social value. At present, the support vector regression (SVR) intelligent prediction model that is suitable for small samples has been applied in this domain. Aiming at parameter selection difficulty and prediction accuracy improvement, the artificial bee colony (ABC) is adopted in optimizing SVR parameters, which is referred to as the ABC-SVR algorithm in the paper. The simulation experiments are carried out by comparing the ABC-SVR algorithm with SVR algorithm, and the feasibility of the proposed ABC-SVR algorithm is verified by result analysis. Continuously, the simulation experiments are carried out by comparing the ABC-SVR algorithm with particle swarm optimization SVR (PSO-SVR) algorithm and genetic optimization SVR (GA-SVR) algorithm, and a better optimization effect has been attained by simulation experiments and verified by statistical test. Simultaneously, the simulation experiments are carried out by comparing the ABC-SVR algorithm and wavelet neural network time series (WNN-TS) algorithm, and the prediction accuracy of the proposed ABC-SVR algorithm is improved and satisfactory prediction effects have been obtained.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2001년도 가을 학술발표회 논문집
• /
• pp.859-864
• /
• 2001

An effective live load model for analyzing probable maximum live load effects such as moment and shear in transverse direction was developed. The main procedure of this live load model is composed of four parts, i.e., firstly, determination of the appropriate influence lines in longitudinal direction, secondly, application of the characteristics of vehicles and traffic patterns in longitudinal direction, thirdly, determination of the appropriate influence lines in transverse direction, and fourthly, application of the characteristics of vehicles and traffic patterns in transverse direction. Through this procedure, the probabilistic distributions of maximum probable load effects are deduced in the form of probability density function (PDF) and/or cumulative density function(CDF). This live load model is able to consider local or global deterioration of bridges in the structural analysis.

• 대한교통학회지
• /
• 제6권2호
• /
• pp.49-56
• /
• 1988

Alternate use of lane at a signalized intersection is a quite different control of the operation of an intersection. This control introduces a new stop line and signal before the original stop line. All of the lanes between the two stop lines are used for left turn traffic or through traffic at a time. The purpose of the control is increasing the capacity of a n intersection without widening the approach width. this paper contains a study on the condition of a application, the proper distances between the two stop lines, the reasonable offsets(rear) to guarantee clearing the vehicles of previous phase, the comparison of approach capacity between the existing control and this control. The study results reveals that the offsets(rear) are rather stable showing the range(maximum value minus minimum value) of it's value does not exceed 3.6 seconds according to the field data. The approach capacity will be increased by 27%, 43%, 59%, 84% when the distances between the stop lines are 30.0m respectively. The control might have theoretical limitation to operate in practice. So an experimental application of the control at some suitable intersections prior to expanding it.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2006년도 하계학술대회
• /
• pp.145-150
• /
• 2006

For most of the measuring methods of traditional control theory, measuring equipments are located at the output of the system to measure quantities transformed from non-electrical form into electrical one. This method helps us to define the value of parameters to be measured, but it has limitation because it can only assess the efficiency of a movement process. That means we can not understand the inner kinetics which is the essence of the system. In the modern control theory, states of system are considered as the feedback to the control process, which helps us to assess the elements in the inside of the system. In this paper, we survey methods for estimating states being not exposed to the correct measurements. Using this method, we also suggest an application for giving an estimate of the traffic on the LSPs to adapt the network configuration for changing traffic conditions.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 1998년도 창립기념 춘계학술대회 논문집
• /
• pp.31-38
• /
• 1998

Guideway Transportation will provide the break-through to solve the traffic problems, which a lot of big cities have over the world. APM (Automated People Mover) system, Guideway Transportation, is classified by PRT, GRT, and MRT according to the capacity of passenger to be carried by its system. In the Application of PRT (Personal Rapid Transit) system, the enact analysis of the traffic problem on the area to be applied should be preceded. PRT system is characterized by Off-Line and Demand Operation. The Network of PRT system depends on the Load Time and Load Pattern. The operation of PRT system will have move efficient way when it is applied to the network with evenly distributed Load Time and Load Pattern.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.641-644
• /
• 2017

LTE(Long Term Evolution) 기술은 스마트폰 중심의 모바일 인터넷으로 상징되는 상용 통신을 넘어 산업 및 긴급 통신 분야로 사용이 확대되고 있다. 본 논문에서는 다양한 분야로 보급되고 있는 LTE 기술의 전송 성능을 응용 트래픽 수준에서 분석해 본다. 성능 분석은 NS-2를 기반으로 한 컴퓨터 시뮬레이션을 사용하여 수행하며, CBR(Constant Bit rate), VBR(Variable Bit Rate) 등의 트래픽을 분석 대상으로 한다. 본 논문의 결과와 방법은 LTE 기반 네트워크의 연구 및 개발에 활용될 수 있을 것으로 생각된다.

• 통합자연과학논문집
• /
• 제14권2호
• /
• pp.50-56
• /
• 2021

Due to the recent increase in the mobile streaming market, mobile traffic is increasing exponentially. IMT-2020, named as the next generation mobile communication standard by ITU, is called the 5th generation mobile communication (5G), and is a technology that satisfies the data traffic capacity, low latency, high energy efficiency, and economic efficiency compared to the existing LTE (Long Term Evolution) system. 5G implements this technology by utilizing a high frequency band, but there is a problem of path loss due to the use of a high frequency band, which is greatly affected by system performance. In this paper, small cell technology was presented as a solution to the high frequency utilization of 5G mobile communication system, and furthermore, the system performance was improved by applying machine learning technology to macro communication and small cell communication method decision. It was found that the system performance was improved due to the technical application and the application of machine learning techniques.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 추계학술발표대회
• /
• pp.1111-1112
• /
• 2011

본 연구는 최근 널리 보급된 스마트 모바일 단말의 제한된 디스플레이에서 사용자에게 짧은 시간에 효율적으로 핵심 정보를 제공함으로써 사용자 편의성을 향상 시킬 수 있는 사용자 인터페이스(User Interface, UI)를 연구하기 위해 사용자 위치 기반 교통 신호 안내 시스템(Location Based Traffic Signal Guide System, LBTGS) 의 UI 설계에 관한 연구이다. 시각 정보와 음성 정보를 활용하여 짧은 시간에 사용자가 전방 교통 신호 정보를 인지하도록 하여 안전한 도로 운행에 반영할 수 있는 UI 를 효과적으로 설계함으로써 신호 위반으로 인한 교통 사고의 발생을 감소시킬 수 있다. 또한 보다 직관적으로 짧은 시간에 인식할 수 있는 UI 를 설계하여 스마트 모바일 단말의 제한된 디스플레이에서 향상된 사용자 경험을 제공할 수 있을 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권6호
• /
• pp.3230-3253
• /
• 2017

Android malware steals users' private information, and embedded unsafe advertisement (ad) libraries, which execute unsafe code causing damage to users. The majority of such traffic is HTTP and is mixed with other normal traffic, which makes the detection of malware and unsafe ad libraries a challenging problem. To address this problem, this work describes a novel HTTP traffic flow mining approach to detect and categorize Android malware and unsafe ad library. This work designed AndroCollector, which can automatically execute the Android application (app) and collect the network traffic traces. From these traces, this work extracts HTTP traffic features along three important dimensions: quantitative, timing, and semantic and use these features for characterizing malware and unsafe ad libraries. Based on these HTTP traffic features, this work describes a supervised classification scheme for detecting malware and unsafe ad libraries. In addition, to help network operators, this work describes a fine-grained categorization method by generating fingerprints from HTTP request methods for each malware family and unsafe ad libraries. This work evaluated the scheme using HTTP traffic traces collected from 10778 Android apps. The experimental results show that the scheme can detect malware with 97% accuracy and unsafe ad libraries with 95% accuracy when tested on the popular third-party Android markets.

• 한국통신학회논문지
• /
• 제40권11호
• /
• pp.2160-2168
• /
• 2015

네트워크 트래픽이 복잡, 다양해짐에 따라 발생하는 네트워크 보안문제 해결을 위해 다양한 암호화 프로토콜 중 하나인 SSL/TLS가 널리 사용되고 있다. 하지만 현재의 트래픽 분석 시스템은 암호화 트래픽을 프로토콜 레벨에 한정적으로 분석하고 있는 실정이다. 효과적인 네트워크 자원 관리를 위해서는 암호화 트래픽에 대한 서비스 단위 분석이 요구된다. 본 논문에서는 SSL/TLS 암호화 응용 트래픽의 페이로드 시그니쳐를 자동으로 추출하고, 이를 바탕으로 네트워크 트래픽 상에서 SSL/TLS 응용 서비스를 식별하는 방법을 제안한다. 이는 암호화 세션이 맺어질 때 초기에 발생하는 SSL/TLS Handshake 중 인증서 교환 레코드의 인증서 발행 대상정보를 시그니쳐로 이용하여 서비스를 식별을 하는 것이다. 본 논문에서 제안하는 방법은 95%에 가까운 SSL/TLS 트래픽을 분석 하였으며, 이 때 추출한 시그니쳐를 별도의 트래픽 트레이스에 적용시켜 각 서비스 별로 최대 95%의 정확도를 내어 그 성능과 가능성을 증명하였다.