• 제목/요약/키워드: traffic classification

검색결과 433건 처리시간 0.029초

Random Forest Classifier-based Ship Type Prediction with Limited Ship Information of AIS and V-Pass

  • Jeon, Ho-Kun;Han, Jae Rim
    • 대한원격탐사학회지
    • /
    • 제38권4호
    • /
    • pp.435-446
    • /
    • 2022
  • Identifying ship types is an important process to prevent illegal activities on territorial waters and assess marine traffic of Vessel Traffic Services Officer (VTSO). However, the Terrestrial Automatic Identification System (T-AIS) collected at the ground station has over 50% of vessels that do not contain the ship type information. Therefore, this study proposes a method of identifying ship types through the Random Forest Classifier (RFC) from dynamic and static data of AIS and V-Pass for one year and the Ulsan waters. With the hypothesis that six features, the speed, course, length, breadth, time, and location, enable to estimate of the ship type, four classification models were generated depending on length or breadth information since 81.9% of ships fully contain the two information. The accuracy were average 96.4% and 77.4% in the presence and absence of size information. The result shows that the proposed method is adaptable to identifying ship types.

페이로드 시그니쳐 품질 평가를 통한 고효율 응용 시그니쳐 탐색 (High Performance Signature Generation by Quality Evaluation of Payload Signature)

  • 이성호;김종현;구영훈;;김명섭
    • 한국통신학회논문지
    • /
    • 제41권10호
    • /
    • pp.1301-1308
    • /
    • 2016
  • 인터넷 속도의 증가와 다양한 응용의 개발로 인해 인터넷 사용자와 이들이 발생시키는 인터넷 트래픽의 양이 급격히 증가하고 있다. 트래픽 분석에 있어서 트래픽 응용 식별 방법은 페이로드 시그니쳐에 의존적이기 때문에 시그니쳐의 구성이나 개수에 따라 높은 부하와 처리 속도가 느린 단점을 갖는다. 따라서 본 논문에서는 응용 식별을 위한 페이로드 시그니쳐의 중요도를 평가하는 방법과 이를 바탕으로 높은 효율의 시그니쳐를 탐색하는 방법을 제안한다. 각 시그니쳐 별로 3가지 기준을 바탕으로 가중치를 계산하고 계산된 가중치와 시그니쳐 맵을 통해 고효율의 시그니쳐 세트를 탐색한다. 제안하는 방법을 실제 트래픽에 적용했을 때 기존 대비 약 4배의 응용 식별 능력을 가진 높은 효율의 시그니쳐들을 정의할 수 있었다.

토양측정망 운영목적에 따른 토양측정망 지점 선정 방안 연구 (Development of Monitoring Site Selection Criteria of the Korean Soil Quality Monitoring Network to Meet its Purposes)

  • 정승우
    • 한국지하수토양환경학회지:지하수토양환경
    • /
    • 제18권2호
    • /
    • pp.19-26
    • /
    • 2013
  • This study developed the classification of National Soil Quality Monitoring Network (NSQM) and its site selection criteria to meet the recently established purposes of the NSQM. The NSQM were suggested by this study to classify into the six-purposes site groups from the current classification of land uses. The six purposes site groups were 1) intensive observation sites, 2) contaminant loading sites, 3) human activity sites, 4) background sites, 5) river soil sites, and 6) sites near the groundwater quality monitoring wells. Furthermore, this study developed the site selection criteria of NSQM utilizing the accumulated NSQM data, road traffic data, chemical emission data, census, soil information, and the literature related to soil quality variation due to contaminant loads. For selecting suitable sites for NSQM, this study used road traffic, chemical emission, the distance from the contaminant sources, and population information as specific criteria. The suggested site classification and criteria were appled for the current 100 NSQM sites for evaluation. Forty sites were met to the criteria suggested by this study, but sixty sites were not met to the criteria. However, some of the sixty sites also included the obscure sites that their addresses were not apparent to find them.

An Analysis on the Relative Importance of the Risk Factors for the Marine Traffic Environment using Analytic Hierarchy Process

  • Lee, Hong-Hoon;Kim, Chol-Seong
    • 해양환경안전학회지
    • /
    • 제19권3호
    • /
    • pp.257-263
    • /
    • 2013
  • The classification of risk factors and the identification of risk acceptance criteria are core works to assess risk levels with high enough confidential level in the field of marine traffic environment. In the previous study work, the twenty kinds of risk factors and its assessment criteria for the domestic marine traffic environment were proposed. In this paper, with these previous studying results, the relative importance of the risk factors were analyzed by questionnaire survey of marine traffic experts using the analytic hierarchy process. The analysis results showed that the relative importance of the visibility restriction is the highest among the twenty kinds of risk factors, and the relative importance of the traffic condition is the highest among the five kinds of risk categories. As results from analysis, it is expected that the approaching method on the relative importance is to be one of basic techniques for the development of risk assessment models in the domestic marine traffic environment.

ICT기반 폐플라스틱 관리 전주기 기술 동향 (ICT-based Waste Plastic Management Life Cycle Technology)

  • 문영백;정훈;허태욱
    • 전자통신동향분석
    • /
    • 제37권4호
    • /
    • pp.28-35
    • /
    • 2022
  • To solve the challenge of waste plastics, this study investigated the related technologies and company trends along the plastic life cycle, and primarily describes ICT technologies to improve efficiency in the process of sorting and sorting waste plastics. Waste plastic discharge caused by the explosive increase in parcel traffic because of COVID-19 is also growing exponentially. Hence, waste treatment is emerging as a social challenge. Most of the domestic waste classification depends on the manual process according to the waste pollution level. The plastic material classification approach using the spectroscopy approach reveals a high error in the contaminated waste plastic classification, but if the Artificial Intelligence-based image classification technology is employed together, the classification precision can be enhanced because of the type of waste plastic product and the contaminated part can be differentiated.

기계학습 기반 저 복잡도 긴장 상태 분류 모델 (Design of Low Complexity Human Anxiety Classification Model based on Machine Learning)

  • 홍은재;박형곤
    • 전기학회논문지
    • /
    • 제66권9호
    • /
    • pp.1402-1408
    • /
    • 2017
  • Recently, services for personal biometric data analysis based on real-time monitoring systems has been increasing and many of them have focused on recognition of emotions. In this paper, we propose a classification model to classify anxiety emotion using biometric data actually collected from people. We propose to deploy the support vector machine to build a classification model. In order to improve the classification accuracy, we propose two data pre-processing procedures, which are normalization and data deletion. The proposed algorithms are actually implemented based on Real-time Traffic Flow Measurement structure, which consists of data collection module, data preprocessing module, and creating classification model module. Our experiment results show that the proposed classification model can infers anxiety emotions of people with the accuracy of 65.18%. Moreover, the proposed model with the proposed pre-processing techniques shows the improved accuracy, which is 78.77%. Therefore, we can conclude that the proposed classification model based on the pre-processing process can improve the classification accuracy with lower computation complexity.

자료 연계성을 고려한 차종 분류 기준의 제시 (The New Criterion of Classification System for Data Linkage)

  • 김윤섭;오주삼;김현석
    • 한국도로학회논문집
    • /
    • 제7권4호
    • /
    • pp.57-68
    • /
    • 2005
  • 현재 국내의 차종 분류 기준은 그 조사목적과 조사지점에 따라 이원화되어 운영되고 있다. 고속국도와 지방도의 경우는 8종 분류 기준이 그리고 일반국도의 경우는 11종 분류 기준이 활용되고 있는데, 이러한 이원화된 분류 기준은 자료 활용의 효율성을 저하시키고 있는 실정이다. 본 연구는 이러한 이원화된 차종 분류 기준의 문제점을 해결하기 위해 통합된 차종 분류 기준을 제시하고 있다. 분류 기준은 차량 제원에 의한 기계식 조사에 초점을 맞추었으며, 현장 조사의 문제점을 완화하기 위해 인력식 조사에도 적용이 가능하도록 설정되었다. 제안된 차종 분류 기준은 차량의 다양화 및 대형화 추세를 반영하고, 기타 차종 분류 기준과의 호환성을 고려하고 있어 보다 합리적인 차종 분류 기준이라 할 수 있다.

  • PDF

TMA(Traffic Measurement Agent)를 이용한 인터넷 응용 트래픽 분류1) (Internet Application Traffic Classification using Traffic Measurement Agent)

  • 윤성호;노현구;김명섭
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2008년도 춘계학술발표대회
    • /
    • pp.946-949
    • /
    • 2008
  • 네트워크를 사용하는 응용프로그램의 종류가 다양해지면서 네트워크 트래픽의 응용별 분류는 효율적인 네트워크 관리에 있어 그 중요성이 커지고 있지만, 오늘날 응용프로그램의 특징인 유동적인 포트번호 사용 및 패킷의 암호화 등은 트래픽의 응용별 분류를 더욱 어렵게 하고 있다. Well-known 포트기반의 응용별 분류방법의 단점을 극복하기 위하여 머신러닝 알고리즘과 Signature 기반 분석 방법들이 연구되고는 있지만 주장하는 높은 분석률에 비하여 실제 네트워크 트래픽에 적용하기에는 신뢰성이 부족하다. 본 논문에서는 일부 종단 호스트에 설치된 TMA(Traffic Measurement Agent)로 부터 수집한 응용프로그램의 트래픽 사용 정보를 기초로 하여 전체 네트워크 트래픽의 응용프로그램을 판별하는 응용 트래픽 분류 방법론을 제안한다. 제안된 방법론은 트래픽 플로우들의 상관관계를 이용하여 TMA 호스트 트래픽으로부터 TMA가 설치되지 않은 호스트에서 발생한 트래픽들의 응용을 판단하며, 분류 된 결과에 대하여 높은 신뢰성을 보장한다. 제안된 방법론은 학내 네트워크에 적용하여 그 타당성을 검증하였다.

Development and testing of a composite system for bridge health monitoring utilising computer vision and deep learning

  • Lydon, Darragh;Taylor, S.E.;Lydon, Myra;Martinez del Rincon, Jesus;Hester, David
    • Smart Structures and Systems
    • /
    • 제24권6호
    • /
    • pp.723-732
    • /
    • 2019
  • Globally road transport networks are subjected to continuous levels of stress from increasing loading and environmental effects. As the most popular mean of transport in the UK the condition of this civil infrastructure is a key indicator of economic growth and productivity. Structural Health Monitoring (SHM) systems can provide a valuable insight to the true condition of our aging infrastructure. In particular, monitoring of the displacement of a bridge structure under live loading can provide an accurate descriptor of bridge condition. In the past B-WIM systems have been used to collect traffic data and hence provide an indicator of bridge condition, however the use of such systems can be restricted by bridge type, assess issues and cost limitations. This research provides a non-contact low cost AI based solution for vehicle classification and associated bridge displacement using computer vision methods. Convolutional neural networks (CNNs) have been adapted to develop the QUBYOLO vehicle classification method from recorded traffic images. This vehicle classification was then accurately related to the corresponding bridge response obtained under live loading using non-contact methods. The successful identification of multiple vehicle types during field testing has shown that QUBYOLO is suitable for the fine-grained vehicle classification required to identify applied load to a bridge structure. The process of displacement analysis and vehicle classification for the purposes of load identification which was used in this research adds to the body of knowledge on the monitoring of existing bridge structures, particularly long span bridges, and establishes the significant potential of computer vision and Deep Learning to provide dependable results on the real response of our infrastructure to existing and potential increased loading.

스마트 교통 단속 시스템을 위한 딥러닝 기반 차종 분류 모델 (Vehicle Type Classification Model based on Deep Learning for Smart Traffic Control Systems)

  • 김도영;장성진;장종욱
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국정보통신학회 2022년도 춘계학술대회
    • /
    • pp.469-472
    • /
    • 2022
  • 최근 지능형 교통 시스템의 발전에 따라 딥러닝을 기술을 적용한 다양한 기술들이 활용되고 있다. 도로를 주행하는 불법 차량 및 범죄 차량 단속을 위해서는 차량 종류를 정확히 판별할 수 있는 차종 분류 시스템이 필요하다. 본 연구는 YOLO(You Only Look Once)를 이용하여 이동식 차량 단속 시스템에 최적화된 차종 분류 시스템을 제안한다. 제안 시스템은 차량을 승용차, 경·소·중형 승합차, 대형 승합차, 화물차, 이륜차, 특수차, 건설기계, 7가지 클래스로 구분하여 탐지하기 위해 단일 단계 방식의 객체 탐지 알고리즘 YOLOv5를 사용한다. 인공지능 기술개발을 위하여 한국과학기술연구원에서 구축한 약 5천 장의 국내 차량 이미지 데이터를 학습 데이터로 사용하였다. 한 대의 카메라로 정면과 측면 각도를 모두 인식할 수 있는 차종 분류 알고리즘을 적용한 지정차로제 단속 시스템을 제안하고자 한다.

  • PDF