• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.123-132
• /
• 2021

Malicious activities of Botnets are responsible for huge financial losses to Internet Service Providers, companies, governments and even home users. In this paper, we try to confirm the possibility of detecting botnet traffic by applying the deep learning model Convolutional Neural Network (CNN) using the CTU-13 botnet traffic dataset. In particular, we classify three classes, such as the C&C traffic between bots and C&C servers to detect C&C servers, traffic generated by bots other than C&C communication to detect bots, and normal traffic. Performance metrics were presented by accuracy, precision, recall, and F1 score on classifying both known and unknown botnet traffic. Moreover, we propose a stackable botnet detection system that can load modules for each botnet type considering scalability and operability on the real field.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.250-265
• /
• 2022

Positive effects such as significantly reducing traffic accidents caused by human error can be expected by the introduction of Automated vehicles (AV). However, as new traffic safety issues are expected to occur in the future due to errors in H/W or S/W of autonomous vehicles and lack of its function, it is necessary to establish a scenario to evaluate the driving safety of AV. Therefore, in this study, functional scenario was developed to evaluate the driving safety of AV based on traffic accident data of the National Police Agency. Using the GIS program, QGIS, traffic accident data that occurred in the toll gate and ramp sections of expressway were extracted and accident summary items were checked to classify the types of accident. In addition, based on the results of accident type classification, functional scenario were developed that contains various dangerous situations in the tollgate and ramp sections.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.2
• /
• pp.153-169
• /
• 2022

With the extension of the average life span and the rapid aging of the population, defining elderly population as a single group is difficult as the physical, economic and social conditions of individual have become different. Therefore, policies that take into account the characteristics of each group are required. The purpose of this study is to classify individual travel types and to analyze the characteristics of each travel type, based on individual public transportation trajectory data as known as smart card data. Among the four classified types, the long-distance low-frequency stay type and the short-range medium-frequency mobile type show external activity traffic characteristics for retirement leisure, while the long-distance high-frequency stay type and the long-distance high-frequency mobile group include regular commuting. Traffic variability and residence areas of stay were identified in terms of each classified travel type. The results of this study provide the important suggestions for establishing a transportation policy that takes into account the characteristics of each type of elderly population in Seoul.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6D
• /
• pp.759-766
• /
• 2008

Road classification system is the first step for determining the road function and design standards. Currently, roads are classified by various indices such as road location and function. In this study, we classify road using various traffic indices as well as to identify traffic characteristics for each type of road. To accomplish the objectives, mixture model was applied for classifying road and analyzing traffic characteristics using traffic data that observed at permanent traffic count stations. A total of 8 variables were applied: annual average daily traffic(AADT), $K_{30}$ coefficient, heavy vehicle proportion, day volume proportion, peak hour volume proportion, sunday coefficient, vacation coefficient, and coefficient of variation(COV). A total of 350 permanent traffic count points were categorized into three groups : Group I (Urban road), Group II (Rural road), and Group III (Recreational road). AADT were 30,000 for urban, 16,000 for rural, and 5,000 for recreational road. Group III was typical recreational road showing higher average daily traffic volume during Sunday and vacational periods. Group I showed AM peak and PM peak, while group II and group III did not show AM peak and PM peak.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1123-1130
• /
• 2020

This study aims to classify the severity in car crashes using five classification learning models. The dataset used in this study contains 21,013 vehicle crashes, obtained from Korea Expressway Corporation, between the year of 2015-2017 and the LightGBM(Light Gradient Boosting Model) performed well with the highest accuracy. LightGBM, the number of involved vehicles, type of accident, incident location, incident lane type, types of accidents, types of vehicles involved in accidents were shown as priority factors. Based on the results of this model, the establishment of a management strategy for response of highway traffic accident should be presented through a consistent prediction process of accident severity level. This study identifies applicability of Machine Learning Models for Predicting of the Severity of Car Traffic Accidents on a Highway and suggests that various machine learning techniques based on big data that can be used in the future.

• Journal of Korean Society of Transportation
• /
• v.21 no.4
• /
• pp.47-56
• /
• 2003

There are no specific criteria deciding what type of crosswalk installs although 4 typed crosswalks at signalized intersections classify according to number of stop line, spacing from the border of intersections and existence of traffic islands or not. Accidents involving pedestrians at signalized intersections are classified by type of crosswalks by traffic volume, pedestrian volume at crosswalk, intersection geometry and phase in view of pedestrians' safety at 50 intersections in Gwangju. The Multiple regression models are applied to express the pedestrian accident rate. In addition, process deciding what type of crosswalk installs which includes accident rate involved pedestrian is changed into number of accident is represented to reduce number of accidents. This paper presents what type of crosswalk installs in order to reduce pedestrian involved accidents at new or existing crosswalk.

• Journal of Information Processing Systems
• /
• v.2 no.1
• /
• pp.52-57
• /
• 2006

One of the important functions of an Intelligent Transportation System (ITS) is to classify vehicle types using a vision system. We propose a method using machine-learning algorithms for this classification problem with 3-D object model fitting. It is also necessary to detect road lanes from a fixed traffic surveillance camera in preparation for model fitting. We apply a background mask and line analysis algorithm based on statistical measures to Hough Transform (HT) in order to remove noise and false positive road lanes. The results show that this method is quite efficient in terms of quality.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.17 no.32
• /
• pp.53-62
• /
• 1994

This paper deals with the analysis of the PC communication service system performance which will be installed as a gateway between PSTN and PSDN. Firstly, we classify the data traffic pattern into interactive, conversational, and file transfer type from the actual statistics. Secondly, we model the system structure as a closed queueing network model with multiservers and multiple customer classes and derive the analytic method to be able to measure the system performance using Mean Value Analysis. Finally, the simulation results indicate that the analytic method obtained is a good approximation method to measure the system performance of the PC communication service system as a gateway between PSTN and PSDN.

• Journal of Korean Society of Transportation
• /
• v.28 no.3
• /
• pp.19-28
• /
• 2010

Almost domestic cycleways have been established without characteristic of land uses. These cycleways can always not provide optimal condition for safety and convenience not to speak of efficiency. This research having a purpose to accomplish more safety and convenience has tried to classify cycleways detail and to analyze cycleways types by land uses. It verified the difference among the characteristic of traffic on the land uses using the Chi-square test, and found the land use that had the strongest characteristic. Finally, it has proposed the suitable cycleway types to land uses.

• Journal of KIISE:Information Networking
• /
• v.37 no.5
• /
• pp.317-326
• /
• 2010

Nowadays, transmission bandwidth for network traffic is increasing and the type is varied such as peer-to-peer (PZP), real-time video, and so on, because distributed computing environment is spread and various network-based applications are developed. However, as PZP traffic occupies much volume among Internet backbone traffics, transmission bandwidth and quality of service(QoS) of other network applications such as web, ftp, and real-time video cannot be guaranteed. In previous research, the port-based technique which checks well-known port number and the Deep Packet Inspection(DPI) technique which checks the payload of packets were suggested for solving the problem of the P2P traffics, however there were difficulties to apply those methods to detection of P2P traffics because P2P applications are not used well-known port number and payload of packets may be encrypted. A proposed algorithm for identifying P2P heavy traffics based on flow transport parameters and behavioral characteristics can solve the problem of the port-based technique and the DPI technique. The focus of this paper is to identify P2P heavy traffic flows rather than all P2P traffics. P2P traffics are consist of two steps i)searching the opposite peer which have some contents ii) downloading the contents from one or more peers. We define P2P flow patterns on these P2P applications' features and then implement the system to classify P2P heavy traffics.