• Proceedings of the KIEE Conference
• /
• 2006.07e
• /
• pp.57-58
• /
• 2006

과거 2003년 북미 대 정전 이후 전력기기의 사고 발생 후 얼마나 빨리 사고를 제거하고 피해가 적도록 신속하게 복구하는 개념에서 사고이전에 사고를 미연에 방지하는 예방개념으로 관심이 높아지고 있다. 전력기기를 사고로부터 보호하는 보호기기도 중요하지만 사고이전의 상태를 감시하여 미연에 사고를 방지할 수 있도록 하는 예방진단시스템의 중요성도 높아지고 있다. 이렇듯 관심이 높아짐에 따라 각종 진단알고리즘의 개발이 신속히 이루어지고 있다. 보호기기처럼 어떤 설정된 정정 값 이상의 값이 입력되면 보호동작을 수행하는 단순 동작과는 달리 예방진단 시스템은 입력되는 신호의 패턴을 인식하여 열화/노화 등의 진행상황 및 정비조치에 대한 정보를 만들므로 인공지능적인 요소가 많이 적용되고 있다. 따라서 각종 Fuzzy, Neural Network, Expert 등 각종 판단 알고리즘과 패턴을 인식하는 확률통계, 프랙탈 기하학 등이 적용되고 있다. 모두가 틀리다는 것은 아니지만 보다 정확한 예방진단을 위해 각종 알고리즘이 추가 및 수정이 자주이루어지고 있는 실정이다. 그러나 새로운 알고리즘을 적용하기 위해서 기 개발되어 운영 중이거나 설치된 예방진단시스템을 멈추고 전반적으로 수정을 수행하는 것은 감시진단시스템의 본래 모습을 무시하는 행동이라고 할 수 있다. 본 연구에서는 이런 문제를 해결하기 위하여 온라인 상태에서 장비를 감시하는 예방진단 시스템의 알고리즘 변형 시 시스템의 운영이 문제되지 않도록하는 다이나믹 인터페이스를 개발하였다.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.132-140
• /
• 2023

In this paper, we propose a method for performance enhancement of speech declipping using clipping detector. Clipping occurs when the input speech level exceeds the dynamic range of microphone, and it significantly degrades the speech quality. Recently, many methods for high-performance speech declipping based on machine learning have been developed. However, they often deteriorate the speech signal because of degradation in signal reconstruction process when the degree of clipping is not high. To solve this problem, we propose a new approach that combines the declipping network and clipping detector, which enables a selective declipping operation depending on the clipping level and provides high-quality speech in all clipping levels. We measured the declipping performance using various metrics and confirmed that the proposed method improves the average performance over all clipping levels, compared with the conventional methods, and greatly improves the performance when the clipping distortion is small.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.619-624
• /
• 2016

Social-aware video displays not only the relationships between characters but also diverse information on topics such as economics, politics and culture as a story unfolds. Particularly, the speaking habits and behavioral patterns of people in different situations are very important for the analysis of social relationships. However, when dealing with this dynamic multi-modal data, it is difficult for a computer to analyze the drama data effectively. To solve this problem, previous studies employed the deep concept hierarchy (DCH) model to automatically construct and analyze social networks in a TV drama. Nevertheless, since location knowledge was not included, they can only analyze the social network as a whole in stories. In this research, we include location knowledge and analyze the social relations in different locations. We adopt data from approximately 4400 minutes of a TV drama Friends as our dataset. We process face recognition on the characters by using a convolutional- recursive neural networks model and utilize a bag of features model to classify scenes. Then, in different scenes, we establish the social network between the characters by using a deep concept hierarchy model and analyze the change in the social network while the stories unfold.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.18-31
• /
• 2002

In this study, we introduce a concept of advanced neurofuzzy polynomial networks(ANFPN), a hybrid modeling architecture combining neurofuzzy networks(NFN) and polynomial neural networks(PNN). These networks are highly nonlinear rule-based models. The development of the ANFPN dwells on the technologies of Computational Intelligence(Cl), namely fuzzy sets, neural networks and genetic algorithms. NFN contributes to the formation of the premise part of the rule-based structure of the ANFPN. The consequence part of the ANFPN is designed using PNN. At the premise part of the ANFPN, NFN uses both the simplified fuzzy inference and error back-propagation learning rule. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. As the consequence structure of ANFPN, PNN is a flexible network architecture whose structure(topology) is developed through learning. In particular, the number of layers and nodes of the PNN are not fixed in advance but is generated in a dynamic way. In this study, we introduce two kinds of ANFPN architectures, namely the basic and the modified one. Here the basic and the modified architecture depend on the number of input variables and the order of polynomial in each layer of PNN structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the ANFPN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed ANFPN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.21-31
• /
• 2018

Cyber penetration attacks can not only damage cyber space but can attack entire infrastructure such as electricity, gas, water, and nuclear power, which can cause enormous damage to the lives of the people. Also, cyber space has already been defined as the fifth battlefield, and strategic responses are very important. Most of recent cyber attacks are caused by malicious code, and since the number is more than 1.6 million per day, automated analysis technology to cope with a large amount of malicious code is very important. However, it is difficult to deal with malicious code encryption, obfuscation and packing, and the dynamic analysis technique is not limited to the performance requirements of dynamic analysis but also to the virtual There is a limit in coping with environment avoiding technology. In this paper, we propose a machine learning based malicious code analysis technique which improve the weakness of the detection performance of existing analysis technology while maintaining the light and high-speed analysis performance applicable to commercial endpoints. The results of this study show that 99.13% accuracy, 99.26% precision and 99.09% recall analysis performance of 71,000 normal file and malicious code in commercial environment and analysis time in PC environment can be analyzed more than 5 per second, and it can be operated independently in the endpoint environment and it is considered that it works in complementary form in operation in conjunction with existing antivirus technology and static and dynamic analysis technology. It is also expected to be used as a core element of EDR technology and malware variant analysis.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.95-111
• /
• 2021

As the population decreases in an aging society, the average age of drivers increases. Accordingly, the elderly at high risk of being in an accident need autonomous-driving vehicles. In order to secure driving safety on the road, several technologies to respond to various obstacles are required in those vehicles. Among them, technology is required to recognize static obstacles, such as poor road conditions, as well as dynamic obstacles, such as vehicles, bicycles, and people, that may be encountered while driving. In this study, we propose a deep neural network algorithm capable of simultaneously detecting these two types of obstacle. For this algorithm, we used 1,418 road images and produced annotation data that marks seven categories of dynamic obstacles and labels images to indicate road damage. As a result of training, dynamic obstacles were detected with an average accuracy of 46.22%, and road surface damage was detected with a mean intersection over union of 74.71%. In addition, the average elapsed time required to process a single image is 89ms, and this algorithm is suitable for personal mobility vehicles that are slower than ordinary vehicles. In the future, it is expected that driving safety with personal mobility vehicles will be improved by utilizing technology that detects road obstacles.

• Journal of Korean Society of Transportation
• /
• v.21 no.1
• /
• pp.91-102
• /
• 2003

There are two goals in this paper. The one is development of existing CA(Cellular Automata) model to explain more realistic deceleration process to stop. The other is the application of the updated CA model to forecasting simulation to predict short term link travel time that takes a key rule in finding the shortest path of route guidance system of ITS. Car following theory of CA models don't makes not response to leading vehicle's velocity but gap or distance between leading vehicles and following vehicles. So a following vehicle running at free flow speed must meet steeply sudden deceleration to avoid back collision within unrealistic braking distance. To tackle above unrealistic deceleration rule, “Slow-to-stop” rule is integrated into NaSch model. For application to interrupted traffic flow, this paper applies “Slow-to-stop” rule to both normal traffic light and random traffic light. And vehicle packet method is used to simulate a large-scale network on the desktop. Generally, time series data analysis methods such as neural network, ARIMA, and Kalman filtering are used for short term link travel time prediction that is crucial to find an optimal dynamic shortest path. But those methods have time-lag problems and are hard to capture traffic flow mechanism such as spill over and spill back etc. To address above problems. the CA model built in this study is used for forecasting simulation to predict short term link travel time in Kangnam district network And it's turned out that short term prediction simulation method generates novel results, taking a crack of time lag problems and considering interrupted traffic flow mechanism.

• Journal of Internet Computing and Services
• /
• v.6 no.1
• /
• pp.105-114
• /
• 2005

This paper describes a new measuring technique by analysing multiple time-series patterns. This paper's goal is that extracts a really measured value having a sample pattern which is the best matched with an inputted time-series, and calculates a difference ratio with the value. Therefore, the proposed technique is not a recognition but a measurement. and not a hardware but a software. The proposed technique is consisted of three stages, initialization, learning and measurement. In the initialization stage, it decides weights of all parameters using importance given by an operator. In the learning stage, it classifies sample patterns using LBG and DTW algorithm, and then creates code sequences for all the patterns. In the measurement stage, it creates a code sequence for an inputted time-series pattern, finds samples having the same code sequence by hashing, and then selects the best matched sample. Finally it outputs the really measured value with the sample and the difference ratio. For the purpose of performance evaluation, we tested on multiple time-series patterns obtained from etching machine which is a semiconductor manufacturing.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1318-1324
• /
• 2003

There are two problems in the conventional ART1 algorithm. One is in similarity testing method of the conventional ART1 between input patterns and stored patterns. The other is that vigilance threshold of conventional ART1 influences the number of clusters and the rate of recognition. In this paper, new similarity testing method and dynamical vigilance threshold method are proposed to solve these problems. The former is similarity test method using the rate of norm of exclusive-NOR between input patterns and stored patterns and the rate of nodes have equivalence value, and the latter method dynamically controls vigilance threshold to similarity using fuzzy operations and the sum operation of Yager. To check the performance of new methods, we used 26 alphabet characters and nosed characters. In experiment results, the proposed methods are better than the conventional methods in ART1, because the proposed methods are less sensitive than the conventional methods for initial vigilance and the recognition rate of the proposed methods is higher than that of the conventional methods.