• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.27-34
• /
• 2019

In this paper, a new type of lip feature is proposed as distance metric in CIELUV color system. The performance of the proposed feature was tested on face image database, Helen dataset from University of Illinois. The test processes consists of three steps. The first step is feature extraction and second step is principal component analysis for the optimal projection of a feature vector. The final step is Otsu's threshold for a two-class problem. The performance of the proposed feature was better than conventional features. Performance metrics for the evaluation are OverLap and Segmentation Error. Best performance for the proposed feature was OverLap of 65% and 59 % of segmentation error. Conventional methods shows 80~95% for OverLap and 5~15% of segmentation error usually. In conventional cases, the face database is well calibrated and adjusted with the same background and illumination for the scene. The Helen dataset used in this paper is not calibrated or adjusted at all. These images are gathered from internet and therefore, there are no calibration and adjustment.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• Journal of KIISE:Information Networking
• /
• v.27 no.1
• /
• pp.76-87
• /
• 2000

ATM is a key technology of integration of multimedia service. Recently, Many study have been concentrated on performance testing for evaluation network performance are stronger everyday. The performance testing is on evaluation of maximal throughput of network by measuring and analyzing of various performance parameters. There are two ways to test ATM network performance; one is using QoS in cell level on the point of network's view, and the other is using metric in frame level in the point of user's view. And, the standardization process is also under way. In this paper, we derive a performance requirement of TCP in TCP/IP data transmission over ATM UBR service. By applying the derived requirements to ATM and packet networks, we evaluate the performance of TCP over UBR based on the result of our simulations. Therefore, we evaluate the result of simulation and find degradation of network throughput by interaction between TCP congestion control and ATM cell drop policy. So we suggest the accelerated Vegas that modify traditional TCP Vegas in congestion control mechanism for batter network throughput.

• Journal of Internet Computing and Services
• /
• v.13 no.1
• /
• pp.45-55
• /
• 2012

Electronic data management is getting important to reduce overall cost and run-time of clinical data management with the enhancement of data quality. It also critically needs to meet regulated guidelines for the overall quality and safety of electronic clinical trials. The purpose of this paper is to develop the performance evaluation framework in electronic clinical data management. Four key metrics in the area of infrastructure, intellectual preparation, study implementation and study completion covering major aspects of clinical trial processes are proposed. The performance measures evaluate the extent of regulation compliance, data quality, cost and efficiency of electronic data management process. They also provide measurement indicators for each evaluation items. Based on the key metrics, the performance evaluation framework is developed in three major areas involved in clinical data management - clinical site, monitoring and data coordinating center. As of the initial attempt how to evaluate the extent of electronic data management in clinical trials by Delphi survey, further empirical studies are planned and recommended.

• Journal of information and communication convergence engineering
• /
• v.14 no.1
• /
• pp.14-20
• /
• 2016

The AODV protocol uses many RREQ messages and one RREP message in the path-discovery process. This protocol has only one metric, the number of hops. Although it is simple, this protocol is not efficient. To avoid this problem, we propose a new AODV with two auxiliary metrics (AuM-2-AODV). The AuM-2-AODV protocol tries multiple route replies, which reduces the chance of path failure and helps the network obtain a better data rate. It has two auxiliary metrics, the remaining energy of its nodes and the number of HELLO messages received at the nodes. With these two metrics, the reliable path from the source node to the destination node will be chosen. In this paper, the performance of the AuM-2-AODV is evaluated using the NS-3 simulator. The performance results show that AuM-2-AODV provides greater throughput and packet delivery ratio by 20% and up to 50% and about 100% in some cases, respectively, than previous protocols.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.51-57
• /
• 2021

In this paper, we propose a task distribution scheme in fog computing environment considering opportunistic fog computing nodes. As latency is one of the important performance metric for IoT(Internet of Things) applications, there have been lots of researches on the fog computing system. However, since the load can be concentrated to the specific fog computing nodes due to the spatial and temporal IoT characteristics, the load distribution should be considered to prevent the performance degradation. Therefore, this paper proposes a task distribution scheme which considers the static as well as opportunistic fog computing nodes according to their mobility feature. Especially, based on the task requirements, the proposed scheme supports the delay sensitive task processing at the static fog node and delay in-sensitive tasks by means of the opportunistic fog nodes for the task distribution. Based on the performance evaluation, the proposed scheme shows low service response time compared to the conventional schemes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.271-277
• /
• 2022

PBFT (Practical Byzantine Fault Tolerant) is a consensus algorithm that can achieve consensus by resolving unintentional and intentional faults in a distributed network environment and can guarantee high performance and absolute finality. However, as the size of the network increases, the network load also increases due to message broadcasting that repeatedly occurs during the consensus process. Due to the characteristics of the PBFT algorithm, it is suitable for small/private blockchain, but there is a limit to its application to large/public blockchain. Because PBFT affects the performance of blockchain networks, the industry should test whether PBFT is suitable for products and services, and academia needs a unified evaluation metric and technology for PBFT performance improvement research. In this paper, quantitative evaluation metrics and evaluation frameworks that can evaluate PBFT family consensus algorithms are studied. In addition, the throughput, latency, and fault tolerance of PBFT are evaluated using the proposed PBFT evaluation framework.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.777-779
• /
• 2012

인터넷의 확산으로 인해 전송, 서비스 및 보안과 관련된 많은 장비들이 개발되고 출시되고 있다. 서비스 및 보안과 관련된 장비들은 새로운 개발과 급속한 도입으로 인해 적절한 성능측정방법의 부재로 인해 많은 혼란과 문제들을 가져오기도 했었다. 이에 장비를 도입하는 기관들은 전문 시험기관의 시험과 평가를 거쳐 발행된 성적서나 보고서를 참고하거나 직접 벤치마킹테스트를 거쳐 도입을 결정하고 있다. 본 논문에서는 IP 네트워크 장비들의 성능측정을 위한 방법들을 분석하고 표준으로 제정된 시험 방법론을 분석하여 시스템 성능측정을 위한 메트릭을 제시하고자 한다.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.7 s.100
• /
• pp.821-828
• /
• 2005

In our life, we have used many digital appliances. They help us to improve the quality of life but sometimes give us unsatisfactory result. Because they produce specific noise. Especially vacuum cleaner produce much noise that is very annoying. So we need to study what sound metrics affect human sensibility. In this paper, we develop sound quality index for vacuum cleaner using the sound quality metrics defined in psychoacoustics. First, we carry out the subjective evaluation of vacuum cleaner sound to verify what vacuum sound feels good to human. And then artificial neural network estimated the complexity and the nonlinear characteristics of the relations between subjective evaluation and sound metrics. Finally the ANN is trained repeatedly to have a good performance for sound qualify index of the vacuum cleaner. As a result, the sound quality index of vacuum cleaner has a correlation of $93.5\%$ between the subjective evaluation and ANN. So, there exist three factors that Is loudness, sharpness, roughness which affect the sound quality of vacuum cleaner.

• Journal of Korea Multimedia Society
• /
• v.21 no.5
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.