• Korean Journal of Artificial Intelligence
• /
• v.11 no.2
• /
• pp.19-27
• /
• 2023

In recent times, an exponential increase in Internet traffic has been observed as a result of advancing development of the Internet of Things, mobile networks with sensors, and communication functions within various devices. Further, the COVID-19 pandemic has inevitably led to an explosion of social network traffic. Within this context, considerable attention has been drawn to research on network traffic analysis based on machine learning. In this paper, we design and develop a new machine learning framework for network traffic analysis whereby normal and abnormal traffic is distinguished from one another. To achieve this, we combine together well-known machine learning algorithms and network traffic analysis techniques. Using one of the most widely used datasets KDD CUP'99 in the Weka and Apache Spark environments, we compare and investigate results obtained from time series type analysis of various aspects including malicious codes, feature extraction, data formalization, network traffic measurement tool implementation. Experimental analysis showed that while both the logistic regression and the support vector machine algorithm were excellent for performance evaluation, among these, the logistic regression algorithm performs better. The quantitative analysis results of our proposed machine learning framework show that this approach is reliable and practical, and the performance of the proposed system and another paper is compared and analyzed. In addition, we determined that the framework developed in the Apache Spark environment exhibits a much faster processing speed in the Spark environment than in Weka as there are more datasets used to create and classify machine learning models.

• Journal of the Korean Society for Railway
• /
• v.12 no.6
• /
• pp.902-908
• /
• 2009

TETRA is the standard of Digital Trunked Radio System developed by the ETSI (European Telecommunications Standards Institute). It is currently adopted as Electric Power IT Wireless Backbone Network in Korea, and a national enterprise is going on for versatile utilization of TETRA. To use TETRA wireless network, TETRA modem is very necessary such that performance measurements are very crucial for each TETRA modem by various manufacturers. In this paper, PED (Protocol Evaluation Data) is suggested for PD performance measurement in D-TRS wireless network environment. The performance measurements for different data lengths and transmission intervals are done using TG (Traffic Generator) on Test Bed. The data size is increased by 10 bytes from 10-byte to 400-byte, and it is measured 1,000 times for each transmission interval of 0.5, 1.0, and 1.5 seconds. Based on the transmission time measured, average transmission speed and MER (Message Error Rate) are derived for TETRA Modem performance measurement. Two TMR880i's of EADS are used for TETRA modem, and SwMI (Switching and Management Infrastructure) of EADS is used for switching system in this paper.

• Journal of KIISE:Information Networking
• /
• v.36 no.5
• /
• pp.369-375
• /
• 2009

Residential broadband networks (RBN) are quickly evolving from xDSL/Cable networks to FTTH services with lOOMbps bandwidth. With the high-speed Internet services, subscribers tend to use web, multimedia, game or file sharing applications. Therefore, performance of RBN is important to the quality of services for users. Typically, Internet service providers (ISPs) are providing their RBN performance results that are measured by subscribers with the dedicated measurement tools. However, they do not make their results public to people. In order to obtain the performance results measured by users, we have to induce a lot of subscribers, which will take a lot of cost and time. Monarch, that is used in this paper, could provide the 3rd party measurement method without the help of ISPs and subscribers. With the extensive experiments through Monarch, we have shown that 3rd party measurement results are not much different from those of user-initiated measurement. In addition, we have observed that bandwidth is around $80{\sim}90Mbps$ and RTT is less than 30ms in FTTH services provided by three major Korean ISPs.

• Current Optics and Photonics
• /
• v.8 no.2
• /
• pp.127-137
• /
• 2024

The distribution of tags is an important factor that affects the performance of radio-frequency identification (RFID). To study RFID performance, it is necessary to obtain RFID tags' coordinates. However, the positioning method of RFID technology has large errors, and is easily affected by the environment. Therefore, a new method using optical measurement is proposed to achieve RFID performance analysis. First, due to the possibility of blurring during image acquisition, the paper derives a new image prior to removing blurring. A nonlocal means-based method for image deconvolution is proposed. Experimental results show that the PSNR and SSIM indicators of our algorithm are better than those of a learning deep convolutional neural network and fast total variation. Second, an RFID dynamic testing system based on photoelectric sensing technology is designed. The reading distance of RFID and the three-dimensional coordinates of the tags are obtained. Finally, deep learning is used to model the RFID reading distance and tag distribution. The error is 3.02%, which is better than other algorithms such as a particle-swarm optimization back-propagation neural network, an extreme learning machine, and a deep neural network. The paper proposes the use of optical methods to measure and collect RFID data, and to analyze and predict RFID performance. This provides a new method for testing RFID performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4B
• /
• pp.387-393
• /
• 2009

In this paper, we have considered the network performance of the VoIP service with the measurement by an emulator, and analyzed the major factors to affect its performance. Also, we have used the measured values to investigate the traffic variations, where their values were observed in the commercial operated network after the delay, jitter and packet loss, and loss compensation methods were applied as the dominant elements. It is expected that our presented results will be a good data to provide the high-quality of voice service in the Internet.

• Convergence Security Journal
• /
• v.11 no.1
• /
• pp.39-48
• /
• 2011

QoS(Quality of Service) is defined "The collective effect of service performance which determines the degree of satisfaction of a user of the service" by ITU-T Rec. E.800. The final goal of information system is to secure the performance efficiency within the required time. The security QoS framework is the modeling of the QoS measurement metrics, the measurement time schedule, instrument, method of measurement and the series of methodology about analysis of the result of measurement. This paper relates to implementing issue and performance measuring about blended mechanism between networking technology and security technology. We got more effectiveness in overall network security, when applying and composing amalgamated security mechanism between network technology and security technology. In this paper, we suggest techniques being used on infrastructure system and also offers a security QoS methodology as a model of more effective way. Methodology proposed in this research has proven that it is possible to measure response time through the scheduled method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.2
• /
• pp.313-329
• /
• 2011

To provide a seamless network to customers, Internet service providers must promptly detect and control abnormal traffic. One approach is to shorten the traffic information measurement cycle. However, performance degradation is inevitable if traffic measurement servers merely shorten the cycle and measure all traffic. This paper presents a software architecture that can measure traffic more frequently without degrading performance by estimating the level of abnormal traffic. The algorithm in the architecture estimates the values of the interface group objects in MIB by using the IP group objects thereby reducing the number of measurements and the size of measured data. We evaluated this architecture on part of Internet service provider's IP network. When the traffic was measured 5 times more than before, the CPU usage and TPS of the proposed scheme was 7% and 41% less than that of the original scheme while the false positive rate and false negative rate were 3.2% and 2.7% respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.6
• /
• pp.888-894
• /
• 2018

In this paper, we proposed a mixed-mode s-parameter measurement system for measuring the performance of twisted pairs. A twisted pair is a balanced type component, its characteristics can not be directly measured using network analyzer, which is generally implemented as a unbalanced type. It is possible to convert between balanced signal and unbalanced signal by using a balun but it restricts the frequency range of the measurement system. The proposed system measures the performance of twisted pairs by measuring mixed-mode s-parameters using a 4-port vector network analyzer and a designed fixture, without using a balun. We measured the performance of a commercial Ethernet cable and compared with the results which measured by using baluns. The results showed that the proposed system is capable of measuring the performance of twisted pairs.

• Journal of Distribution Research
• /
• v.4 no.2
• /
• pp.21-39
• /
• 1999

This study investigates the general applicability of the measurement scale for assessing channel-member performance for the supplier's view that was proposed by Kumar, and Achrol (1992). First, we attempted to examine whether the measurement-scale could be used without any change; the results from the initial data-analysis proposed that the scale needed a certain amount of a revision for further utilization. It seemed that the scale needed some adjustment for being applied to this study; their scale was developed with the data collected from the network of independent dealers handling multiple product items or multiple brands in the U.S. and Canada, while the data of this study were provided by a Korean car manufacturer having a dealer network selling and servicing only its own brand without ownership. Accordingly, we determined that it was necessary to develop a newly finalized performance-measurement scale revising Kumar et al.'s. During the data-analysis of the data resulted in a scale of fifteen items measuring three facets-financial performance, behavioral performance, and competence, each of which consisted of five items respectively. This empirically developed scale looked more valid for the situation of this study than the Kumar, Stern, and Achrol's which was composed of twenty-one items measuring seven facets--three items each.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.11
• /
• pp.1676-1681
• /
• 2012

In network-based control system, measurement and control information is delivered by the network messages. Therefore, the performance of control system is directly affected by the performance of network system. System engineers need to evaluate the performance of network system to maintain the entire system in stable condition. BACnet is an international standard data communication protocol especially designed for building automation and control systems. In this study, experimental performance evaluation methodologies of BACnet MS/TP protocol and their practical evaluation results are presented.