• Annual Conference of KIPS
• /
• 2003.11b
• /
• pp.1077-1080
• /
• 2003

본 연구는 룰들의 각 필드들을 index하여 곱한 cross-product 테이블을 이용한 packet classification 알고리즘에 대해 연구하고 그 것의 성능을 평가하고 분석한다. 현재 Packet Classification은 Packet Filtering, Policy Routing, Accounting & Billing, Traffic Rate Limiting, Traffic Shaping, 등등의 서비스를 위한 가장 핵심적인 작업이다. 그러나 이들을 빠르게 서비스하는 알고리즘은 아직 존재하지 않는다. 단지 하드웨어 TCAM 을 이용해서 작은 룰들에 대한 처리만이 어느 정도 가능한 실정이다. 이에 본 연구는 소프트웨어를 이용한 cross-product 알고리즘의 효용성을 가늠하고자 연구하고 이를 실제 구현해 평가하고자 한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.115.3-115
• /
• 2001

In this paper, discrete-time cellular neural networks are designed in order to function as associative memories by using Hebbian learning rule and non-cloning template. The proposed method has a very simple structure to design and to learn. Weights are updated by the connection between the neuron and its neighborhood. In the simulation, the proposed method is applied to the classification of a traffic sign pattern.

• International Journal of Highway Engineering
• /
• v.17 no.6
• /
• pp.11-18
• /
• 2015

PURPOSES : The purpose of this thesis is to evaluate the effectiveness of an active noise cancellation (ANC) system in reducing the traffic noise level against frequencies from the predictive model developed by previous research. The predictive model is based on ISO 9613-2 standards using the Noble close proximity (NCPX) method and the pass-by method. This means that the use of these standards is a powerful tool for analyzing the traffic noise level because of the strengths of these methods. Traffic noise analysis was performed based on digital signal processing (DSP) for detecting traffic noise with the pass-by method at the test site. METHODS : There are several analysis methods, which are generally divided into three different types, available to evaluate traffic noise predictive models. The first method uses the classification standard of 12 vehicle types. The second method is based on a standard of four vehicle types. The third method is founded on 5 types of vehicles, which are different from the types used by the second method. This means that the second method not only consolidates 12 vehicle types into only four types, but also that the results of the noise analysis of the total traffic volume are reflected in a comparison analysis of the three types of methods. The constant percent bandwidth (CPB) analysis was used to identify the properties of different frequencies in the frequency analysis. A-weighting was applied to the DSP and to the transformation process from analog to digital signal. The root mean squared error (RMSE) was applied to compare and evaluate the predictive model results of the three analysis methods. RESULTS : The result derived from the third method, based on the classification standard of 5 vehicle types, shows the smallest values of RMSE and max and min error. However, it does not have the reduction properties of a predictive model. To evaluate the predictive model of an ANC system, a reduction analysis of the total sound pressure level (TSPL), dB(A), was conducted. As a result, the analysis based on the third method has the smallest value of RMSE and max error. The effect of traffic noise reduction was the greatest value of the types of analysis in this research. CONCLUSIONS : From the results of the error analysis, the application method for categorizing vehicle types related to the 12-vehicle classification based on previous research is appropriate to the ANC system. However, the performance of a predictive model on an ANC system is up to a value of traffic noise reduction. By the same token, the most appropriate method that influences the maximum reduction effect is found in the third method of traffic analysis. This method has a value of traffic noise reduction of 31.28 dB(A). In conclusion, research for detecting the friction noise between a tire and the road surface for the 12 vehicle types needs to be conducted to authentically demonstrate an ANC system in the Republic of Korea.

• Journal of Korean Society for Geospatial Information Science
• /
• v.5 no.2 s.10
• /
• pp.131-144
• /
• 1997

Traffic jam densified day by day is phenomenon to occur lack of the road capacity in comparison with traffic density, but lack of the road cannot be concluded by main cause of traffic ism. Because the central function of a city would be concentrated upon the downtown and traffic demand would not be evenly distributed by the classification of an hour. Therefore, this study based on the fact that each driver will select the route generating traffic delay very low when path choice from origin to destination in travel plan estimating the quality of passage could be maintained the speed he want will approach to a characteristic grasp of a road, traffic, driver changing every moment by traffic-demand of road increased as a geometrical series with analysis a classification of a street, a intersection along the path on traffic density and highway capacity analysis the path using GIS techniques about complex street network, also will get the path of actual optimum for traffic delay trend creating under various condition the classification per a hour, a day of week and an incident through network such as analysis for traffic generation zone adjacent about street, intersection, afterward will expect the result increasing efficiency of the road-use through a good distribution of traffic by optimum-path choice, accordingly will prepare the scientific, objective, appropriate basis to decide the reasonable time of a road-widen and expansion through section analysis along a rate of traffic volume vs. road capacity.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.6
• /
• pp.1059-1068
• /
• 2016

The current operation method for the AVC (Automatic Vehicle Classification) equipment does not generate vehicle speed, traffic volume and vehicle type information when part of the sensors has failed. Inefficiency of current methods would not use the collected data from the normal sensor. In this study was conducted research on the calculating method at the traffic volume and vehicle speed in the sensor failure AVC equipment. The failure situation of the sensor was classified into 4 types. Calculating the traffic volume and vehicle speed information for each type, and accuracy of these informations were analyzed. Analysis results, traffic volume was possible to calculate a highly accurate value (accuracy: 100%, 98%, 97%). In the case of speed, the accuracy of the calculated speed value reaches a level that can be accepted sufficiently (RMSE value is less than 16.8). So, using the methodology proposed in this study are expected to be able to increase the operational efficiency of the AVC equipment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.65-80
• /
• 2023

In this study, a classification analysis was performed based on the type of traffic situation. The purpose was to derive the major variable factors that could represent the traffic situation. The TTI(Travel Time Index) was used as a criterion for determining traffic conditions, and analysis was performed using data generally detected by the Vehicle Detecting System(VDS). First, the major factors influencing the traffic situation were selected through factor analysis, and traffic conditions were clustered through a cluster analysis of the major factors. After that, variance analysis for each cluster was performed based on the TTI, and similar clusters were merged to categorize the type of traffic situation. The analysis derived, the maximum queue length and occupancy as major factors that could represent the traffic situation. Through this study, it is expected that efficient management of traffic congestion would be possible by just concentrating on the main variable factors that affect the traffic situation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.7-14
• /
• 2010

In this paper, we introduce a hierarchical internet application traffic classification system based on SVM as an alternative overcoming the uppermost limit of the conventional methodology which is using the port number or payload information. After selecting an optimal attribute subset of the bidirectional traffic flow data collected from the campus, the proposed system classifies the internet application traffic hierarchically. The system is composed of three layers: the first layer quickly determines P2P traffic and non-P2P traffic using a SVM, the second layer classifies P2P traffics into file-sharing, messenger, and TV, based on three SVDDs. The third layer makes specific classification of the entire 16 application traffics. By classifying the internet application traffic finely or coarsely, the proposed system can guarantee an efficient system resource management, a stable network environment, a seamless bandwidth, and an appropriate QoS. Also, even a new application traffic is added, it is possible to have a system incremental updating and scalability by training only a new SVDD without retraining the whole system. We validate the performance of our approach with computer experiments.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.99-110
• /
• 2023

This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.

• Journal of KIISE:Information Networking
• /
• v.36 no.3
• /
• pp.153-162
• /
• 2009

It is a challenging work for service operators to accurately classify different services, which runs on various wireless networks based upon numerous platforms. This works focuses on design and implementation of a classifier, which accurately classifies applications, which are captured horn WiBro Network. Notion of session is introduced for the classifier, instead of commonly used Flow to develop a classifier. Based on session information of given traffic, two classification algorithms are presented, Classification and Regression Tree and Support Vector Machine. Both algorithms are capable of classifying accurately and effectively with misclassification rate of 0.85%, and 0.94%, respectively. This work shows that classifier using CART provides ease of interpreting the result and implementation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.11B
• /
• pp.1277-1284
• /
• 2011

Today, many applications use 80 port, which is a basic port number of HTTP protocol, to avoid a blocking of firewall. HTTP protocol is used in not only Web browsing but also many applications such as the search of P2P programs, update of softwares and advertisement transfer of nateon messenger. As HTTP traffics are increasing and various applications transfer data through HTTP protocol, it is essential to identify which applications use HTTP and how they use the HTTP protocol. In order to prevent a specific application in the firewall, not the protocol-level, but the application-level traffic classification is necessary. This paper presents a method to classify HTTP traffics based on applications of the client-side and group the applications based on providing services. We developed an application-level HTTP traffic classification system and verified the method by applying the system to a small part of the campus network.