• The Journal of the Acoustical Society of Korea
• /
• v.24 no.5
• /
• pp.294-300
• /
• 2005

Generally, traditional approaches to track the target position are to estimate ranges and bearings by 2-D MUSIC (MUltiple 519na1 Classification) method. and to associate estimates of 2-D MUSIC made at different time points with the right targets by JPDA (Joint Probabilistic Data Association) filter in the near field. However, the disadvantages of these approaches are that these have the data association Problem in tracking multiple targets. and that these require the heavy computational load in estimating a 2-D range/bearing spectrum. In case multiple targets are adjacent. the tracking performance degrades seriously because the estimate of each target's Position has a large error. In this paper, we proposed a new tracking algorithm using Position innovations extracted from the senor output covariance matrix in the near field. The proposed algorithm is demonstrated by the computer simulations dealing with the tracking of multiple closing and crossing targets.

• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.318-326
• /
• 2005

This paper presents the image feature extraction method and the image classification technique to select the harmful image flowed from the Internet by grade of image contents such as harmlessness, sex-appealing, harmfulness (nude), serious harmfulness (adult) by the characteristic of the image. In this paper, we suggest skin area detection technique to recognize whether an input image is harmful or not. We also propose the ROI detection algorithm that establishes region of interest to reduce some noise and extracts harmful degree effectively and defines the characteristics in the ROI area inside. And this paper suggests the multiple-SVM training method that creates the image classification model to select as 4 types of class defined above. This paper presents the multiple-SVM classification algorithm that categorizes harmful grade of input data with suggested classification model. We suggest the skin likelihood image made of the shape information of the skin area image and the color information of the skin ratio image specially. And we propose the image feature vector to use in the characteristic category at a course of traininB resizing the skin likelihood image. Finally, this paper presents the performance evaluation of experiment result, and proves the suitability of grading image using image feature classification algorithm.

• Journal of the Korean Society for information Management
• /
• v.35 no.4
• /
• pp.141-164
• /
• 2018

Recently, as the amount of academic literature has increased rapidly and complex researches have been actively conducted, researchers have difficulty in analyzing trends in previous research. In order to solve this problem, it is necessary to classify information in units of academic papers. However, in Korea, there is no academic database in which such information is provided. In this paper, we propose an automatic classification system that can classify domestic academic literature into multiple classes. To this end, first, academic documents in the technical science field described in Korean were collected and mapped according to class 600 of the DDC by using K-Means clustering technique to construct a learning set capable of multiple classification. As a result of the construction of the training set, 63,915 documents in the Korean technical science field were established except for the values in which metadata does not exist. Using this training set, we implemented and learned the automatic classification engine of academic documents based on deep learning. Experimental results obtained by hand-built experimental set-up showed 78.32% accuracy and 72.45% F1 performance for multiple classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.2
• /
• pp.389-396
• /
• 1999

In this paper, we propose a multiple underwater object classification and tracking algorithm using the narrowband tonal and frequency line features extracted from the frequency spectrum of the acoustic signal. The general algorithm using the wideband and narrowband energy has a high tracking error when objects are close and cross each other. But the proposed algorithm shows a good tracking performance for the simulation scenarios generated by the real acoustic data.

• Journal of Industrial Technology
• /
• v.29 no.B
• /
• pp.9-15
• /
• 2009

In the case of traditional binary encoding technique, it takes long time to converge the optimal solutions and brings about complexity of the systems due to encoding and decoding procedures. However, the ROGAs (real-coded genetic algorithms) do not require these procedures, and the k-means clustering algorithm can avoid global searching space. Thus, this paper proposes a new approach by using their advantages. The proposed method constructs the multiple predictors using the optimal differences that can reveal the patterns better and properties concealed in non-stationary time series where the k-means clustering algorithm is used for data classification to each predictor, then selects the best predictor. After selecting the best predictor, the cluster centers of the predictor are tuned finely via RCGKA in secondary tuning procedure. Therefore, performance of the predictor can be more enhanced. Finally, we verifies the prediction performance of the proposed system via simulating typical time series examples.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.9-11
• /
• 1998

Ripple Down Rules(RDR)이론은 지식베이스시스템을 지식공학구축기술 또는 지식공학자의 도움 없이 특수분야전문가에 의해 효율적으로 유지보수, 구축되어진다. 특히 시스템의 운용 중 지식베이스의 수정을 효율적으로 처리할 수 있다. 본 논문은 단일결론을 생성하는 RDR이론의 확장인 복수(複數)결론(multiple classification)을 유도하는 MCRDR이론에 대하여 설명한다. MCRDR은 복잡한 복수결론을 허락하면서 RDR이론의 최대 장점인 지식베이스의 간편한 유지보수 기증을 유지한다. MCRDR의 KA과정, 기초케이스 문제해결방법, 그리고 복수결론 추론문제에 대하여 논할 것이다. MCRDR시스템의 우수성을 모의전문가를 이용한 시스템 수축과 실험으로 증명해 보일 것이다. 이 실험을 통하여 복수결론을 지원하는 MCRDR이론이 단일결론을 지원하는 RDR이론을 통하여 효율적으로 증명하고, 또한 기존의 기계학습방법과의 차이점도 보여줄 것이다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.790-795
• /
• 1994

This paper describes multiple fault diagnosis method in complex system with hierarchical structure. Complex system is divided into subsystem, item, component. For diagnosing this hierarchical complex system, it is necessary to implement special neural network. We introducd to Hierarchical Artificial Neural Network(HANN) for this purpose. HANN consists of four level neural network, first level for symptom classification, second level for item fault diagnosis, third level for component symptom classification,forth level for component fault diagnosis. Each network is multi layer perceptron with 7 inputs, 30 hidden node and 7 outputs trainined by backpropagation. UNIX IPC(Inter Process Communication) is used for implementing HANN with multitasking and message transfer between processes in SUN workstation. We tested HANN in reactor system.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.4
• /
• pp.367-378
• /
• 2020

This paper introduces the development of the iterative multiple signal classification (MUSIC)-based direction-of-arrival (DOA) estimation system using a rotator that can control the direction of antenna for the global navigation satellite system (GNSS) interference. The system calculates the spatial spectrum according to the noise eigenvector of all dimensions to measure the number of signals (NOS). Also, to detect the false peak, the system adjusts the array antenna's direction and checks the change's peak angles. The phase delay and gain correction values for system calibration are calculated in consideration of the chamber's structure and the characteristics of radio waves. The developed system estimated DOAs of interferences located about 1km away. The field test results show that the developed system can estimate the DOA without NOS information and detect the false peak even though the inter-element spacing is longer than the half-wavelength of the interference.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2154-2168
• /
• 2022

Our work addresses the issues associated with usage of the semantic features by Bag of Words model, which requires construction of the dictionary. Extracting the relevant features and clustering them into code book or dictionary is computationally intensive and requires large storage area. Hence we propose to use a simple distribution of multiple shape based features, which is a mixture of gradients, radius and slope angles requiring very less computational cost and storage requirements but can serve as an equivalent image representative. The experimental work conducted on PASCAL VOC 2007 dataset exhibits marginally closer performance in terms of accuracy with the Bag of Word model using Self Organizing Map for clustering and very significant computational gain.

• Journal of National Security and Military Science
• /
• s.1
• /
• pp.191-229
• /
• 2003

Multi-sensor data fusion techniques combine evidences from multiple sensors in order to get more accurate and efficient meaningful information through several process levels that may not be possible from a single sensor alone. One of the most important parts in the data fusion system is the identification fusion, and it can be categorized into physical models, parametric classification and cognitive-based models, and parametric classification technique is usually used in multi-sensor data fusion system by its characteristic. In this paper, we propose a novel heuristic identification fusion method in which we adopt desirable properties from not only parametric classification technique but also cognitive-based models in order to meet the realtime processing requirements.