• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10c
• /
• pp.409-411
• /
• 2001

기존의 인터넷 라우터는 Drop tail 방식으로 패킷을 관리한다. 따라서 네트워크 트래픽의 지수적인 증가로 인한 혼잡 상황으로 발생하는 패킷 손실을 해결 한 수 없다. 이 문제를 해결하기 위해 IETF (Internet Engineering Task Force)에서는 REU(Random Early Detection) 알고리즘과 같은 능동적인 큐 관리 알고리즘을 제시하였다. 하지만 RED 알고리즘은 네트워터 환경에 따른 매개 변수의 설정의 어려움을 가지고 치어 잘못 된 매개변수 설정으로 인하여 네트워크 성능이 저하되는 문제점을 가지고 있다. 본 논문에서는 기존의 RED를 개선한 ARED를 제안했다. ARED는 RED 알고리즘의 문제점을 개선하여 네트워크 특성에 맞추어 동적으로 매개변수글 조절하는 알고리즘이다. ns를 이용한 실험을 통하여 ARED의 성능을 검증하였다.

• IE interfaces
• /
• v.23 no.4
• /
• pp.365-371
• /
• 2010

In this study, we propose a novel remote health monitoring system to accurately predict Parkinson's disease severity using a signomial regression method. In order to characterize the Parkinson's disease severity, sixteen biomedical voice measurements associated with symptoms of the Parkinson's disease, are used to develop the telemonitoring model for early detection of the Parkinson's disease. The proposed approach could be utilized for not only prediction purposes, but also interpretation purposes in practice, providing an explicit description of the resulting function in the original input space. Compared to the accuracy performance with the existing methods, the proposed algorithm produces less error rate for predicting Parkinson's disease severity.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.2
• /
• pp.285-291
• /
• 2008

Active Queue Management(AQM) has been widely used for congestion avoidance in Transmission Control Protocol(TCP) networks. Although numerous AQM schemes have been proposed to regulate a queue size close to a reference level, most of them are incapable of adequately adapting to TCP network dynamics due to TCP's non-linearity and time-varying stochastic properties. To alleviate these problems, we introduce an AQM technique based on a dynamic neural network using the Back-Propagation(BP) algorithm. The dynamic neural network is designed to perform as a robust adaptive feedback controller for TCP dynamics after an adequate training period. We evaluate the performances of the proposed neural network AQM approach using simulation experiments. The proposed approach yields superior performance with faster transient time, larger throughput, and higher link utilization compared to two existing schemes: Random Early Detection(RED) and Proportional-Integral(PI)-based AQM. The neural AQM outperformed PI control and RED, especially in transient state and TCP dynamics variation.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.331-337
• /
• 2013

Acoustic Emission technique is widely applied to develop the early fault detection system, and the problem about a signal processing method for AE signal is mainly focused on. In the signal processing method, envelope analysis is a useful method to evaluate the bearing problems and Wavelet transform is a powerful method to detect faults occurred on rotating machinery. However, exact method for AE signal is not developed yet. Therefore, in this paper two methods which are Hilbert transform and DET for feature extraction. In addition, we evaluate the classification performance with varying the parameter from 2 to 15 for feature selection DET, 0.01 to 1.0 for the RBF kernel function of SVR, and the proposed algorithm achieved 94% classification accuracy with the parameter of the RBF 0.08, 12 feature selection.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7A
• /
• pp.586-599
• /
• 2012

This paper proposes a fast face detection and tracking method which uses depth images as well as RGB images. It consists of the face detection procedure and the face tracking procedure. The face detection method basically uses an existing method, Adaboost, but it reduces the size of the search area by using the depth image. The proposed face tracking method uses a template matching technique and incorporates an early-termination scheme to reduce the execution time further. The results from implementing and experimenting the proposed methods showed that the proposed face detection method takes only about 39% of the execution time of the existing method. The proposed tracking method takes only 2.48ms per frame with $640{\times}480$ resolution. For the exactness, the proposed detection method showed a little lower in detection ratio but in the error ratio, which is for the cases when a detected one as a face is not really a face, the proposed method showed only about 38% of that of the previous method. The proposed face tracking method turned out to have a trade-off relationship between the execution time and the exactness. In all the cases except a special one, the tracking error ratio is as low as about 1%. Therefore, we expect the proposed face detection and tracking methods can be used individually or in combined for many applications that need fast execution and exact detection or tracking.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.91-98
• /
• 2021

Today's information and communication technology is rapidly developing, the security of IT infrastructure is becoming more important, and at the same time, cyber attacks of various forms are becoming more advanced and sophisticated like intelligent persistent attacks (Advanced Persistent Threat). Early defense or prediction of increasingly sophisticated cyber attacks is extremely important, and in many cases, the analysis of network-based intrusion detection systems (NIDS) related data alone cannot prevent rapidly changing cyber attacks. Therefore, we are currently using data generated by intrusion detection systems to protect against cyber attacks described above through Host-based Intrusion Detection System (HIDS) data analysis. In this paper, we conducted a comparative study on machine learning algorithms using LID-DS (Leipzig Intrusion Detection-Data Set) host-based intrusion detection data including thread information, metadata, and buffer data missing from previously used data sets. The algorithms used were Decision Tree, Naive Bayes, MLP (Multi-Layer Perceptron), Logistic Regression, LSTM (Long Short-Term Memory model), and RNN (Recurrent Neural Network). Accuracy, accuracy, recall, F1-Score indicators and error rates were measured for evaluation. As a result, the LSTM algorithm had the highest accuracy.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.2
• /
• pp.71-75
• /
• 2013

Recently proliferating heterogeneous multimedia service environments should be able to deal with many different transmission speeds, image sizes, or qualities of video. However, not many existing video compression standards satisfy those necessities. To satisfy the functional requirements, the standardization of the H.264/AVC Scalable Extension (SE) technique has been recently completed. It is an extension of the H.264/AVC which can encode several image sizes and qualities at the same time as a single bitstream. To perform optimum mode decision, motion estimation is performed for all MB modes, and the RD costs are compared to identify an MB mode with the smallest RD cost. This increases computational complexity of H.264/AVC SE encoding. In this paper, we propose an early skip mode detection scheme to reduce candidate modes and suggest an algorithm of fast mode decision utilizing reference modes according to the mode history.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.96-101
• /
• 2014

Wind power is the fastest growing renewable energy source in the world and it is expected to remain so for some times. Recently, there is a constant need for the reduction of Operational and Maintenance(O&M) costs of Wind Energy Conversion Systems(WECS). The most efficient way of reducing O&M cost would be to utilize CMS(Condition Monitoring System) of WECS. CMS allows for early detection of the deterioration of the wind generator's health, facilitating a proactive action, minimizing downtime, and finally maximizing productivity. There are two types of faults such as mass unbalance and aerodynamic asymmetry which are related to wind turbine's rotor faults. Generally, these faults tend to generate various vibrations. Therefore, in this work a simple fault detection algorithm based on spectrums of vibration signals and simple max-min decision logic is proposed. Furthermore, in order to verify its feasibility, several simulation studies are carried out by using GH-bladed software.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1231-1240
• /
• 2020

Water pipes are laid on the ground, making it impossible to visually detect leaks due to aging of pipes, and technology to detect leaks in pipes is mainly used to detect leaks in pipes by detecting leaks. In this paper, two accelerometers were attached to both ends of the constant water piping to calculate the time difference between the acquired data to detect leakage points. The leak test of piping was performed by installing valves at 4.3m, 8.6m, and 12.9m points on piping 17.2m, and changing the development rate of valves to 30% and 70%. Leakage can be detected for pressure drop in piping, which is 30% and 70% open valve. It is very important to detect leakage in the early stage, and it is judged that detection of the initial leak point from the algorithm applied in this paper will be possible.

• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.73-84
• /
• 2020

As the Internet began to become popular, there have been hacking and attacks on networks including systems, and as the techniques evolved day by day, it put risks and burdens on companies and society. In order to alleviate that risk and burden, it is necessary to detect hacking and attacks early and respond appropriately. Prior to that, it is necessary to increase the reliability in detecting network intrusion. This study was conducted on applying weight initialization and weight optimization to the KDD'99 dataset to improve the accuracy of detecting network intrusion. As for the weight initialization, it was found through experiments that the initialization method related to the weight learning structure, like Xavier and He method, affects the accuracy. In addition, the weight optimization was confirmed through the experiment of the network intrusion detection dataset that the Adam algorithm, which combines the advantages of the Momentum reflecting the previous change and RMSProp, which allows the current weight to be reflected in the learning rate, stands out in terms of accuracy.