• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.7
• /
• pp.1699-1706
• /
• 1998

This paper presents a threshold decision technique for direct sequence code acquistion employing Pseudo-Noise(PN) matched filter. The probabilities of detection and false alarm are derived as a measure of the system performance in both nonfading and nonselective Rician fading channels. For received PN codes with different SNR, the proposed acquisition scheme is able to detect a desired threshold in the search mode so that this value is utilized as a threshold for the verification mode. Thus, there is no need to determine a threshold by applying the Neyman-Person ciriteron. It is shown that this scheme achieves lower probability of false alarm than the acquisition scheme based on the Neyman-Person criterion, giving comparable performance in terms of the probability of detection.

• Proceedings of the KIEE Conference
• /
• 2001.11b
• /
• pp.403-405
• /
• 2001

This paper presents the detection method of partial discharge in metal clad switchgear(MCS) using electromagnetic technique. Two antennas are located in the inside and outside of the MCS, and electromagnetic waves detected by these antennas are analyzed and compared by FFT method in order to identify an insulation abnormality. As a result of the experiment by the proposed method, we show the detection possibility for partial discharge in the MCS. The proposed method is expected to apply to insulation condition observation and an accident prevention in the MCS effectively.

• Journal of the Korea Furniture Society
• /
• v.12 no.1
• /
• pp.27-37
• /
• 2001

Automation of wood processing is strongly required to improve the productivity and quality of wood products in wood industry which is one of the most labor-intensive industries. Classification of surface defects on wood boards such as knots is one of the important steps towards a completely automated wood processing system. In this study the possibility of detection of knots by image processing technique was investigated. Algorithm for the automatic determination of threshold value was developed to enhance the flexibility of image processing system. Two different approaches, grid method and tile method, were developed to enhance the speed in extracting features from images. Grid method showed slightly higher processing speed and tile method proved much more stable in determining threshold values. Tile size of $5{\times}5$ pixels or $6{\times}6$ pixels was found to be proper to get stable results with resonable processing time.

• Smart Structures and Systems
• /
• v.2 no.3
• /
• pp.275-293
• /
• 2006

For health monitoring purpose usually the structure is instrumented with a large scale and multichannel measurement system. In case of highway bridges, operating vehicle could be utilized to reduce the number of measuring devices. First this paper presents a static damage detection algorithm of using operating vehicle load. The technique has been validated by finite element simulation and simple laboratory test. Next the paper presents an approach of using this technique to field application. Here operating vehicle load data has been used by instrumenting the bridge at single location. This approach gives an upper hand to other sophisticated global damage detection methods since it has the potential of reducing the measuring points and devices. It also avoids the application of artificial loading and interruption of any traffic flow.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.606-608
• /
• 1998

Digital watermarking is the technique which embeds the invisible signal into multimedia data such as audio, video, images, for copyright protection, including owner identification and copy control information. In this paper, a new watermark detection algorithm by local masking cross covariance between watermarked signal and pseudo noise signal is proposed. The proposed algorithm enhances the detection probability for embedding information. Since reducing detection errors for the weak embedding signals, the algorithm improves the image quality and robusts against illegal attack to delete the embedding information and data compression applications such as JPEG and MPEGs.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• pp.300-310
• /
• 2022

A vast amount of labeled data is required for deep neural network training. A typical strategy to improve the performance of a neural network given a training data set is to use data augmentation technique. The goal of this work is to offer a novel image augmentation method for improving object detection accuracy. An object in an image is removed, and a similar object from the training data set is placed in its area. An in-painting algorithm fills the space that is eliminated but not filled by a similar object. Our technique shows at most 2.32 percent improvements on mAP in our testing on a military vehicle dataset using the YOLOv4 object detector.

• Journal of Korean Society of Water and Wastewater
• /
• v.38 no.2
• /
• pp.83-93
• /
• 2024

In this study, we present a sewer pipe inspection technique through a combination of active sonar technology and deep learning algorithms. It is difficult to inspect pipes containing water using conventional CCTV inspection methods, and there are various limitations, so a new approach is needed. In this paper, we introduce a inspection method using active sonar, and apply an auto encoder deep learning model to process sonar data to distinguish between normal and abnormal pipelines. This model underwent training on sonar data from a controlled environment under the assumption of normal pipeline conditions and utilized anomaly detection techniques to identify deviations from established standards. This approach presents a new perspective in pipeline inspection, promising to reduce the time and resources required for sewer system management and to enhance the reliability of pipeline inspections.

• Journal of Korea Multimedia Society
• /
• v.23 no.9
• /
• pp.1181-1190
• /
• 2020

Detection of an anomaly pattern deviating normal data distribution in streaming data is an important technique in many application areas. In this paper, a method for detection of an newly emerging pattern in text streaming data which is an ordered sequence of texts is proposed based on text embedding and anomaly pattern detection. Using text embedding methods such as BOW(Bag Of Words), Word2Vec, and BERT, the detection performance of the proposed method is compared. Experimental results show that anomaly pattern detection using BERT embedding gave an average F1 value of 0.85 and the F1 value of 1 in three cases among five test cases.

• ETRI Journal
• /
• v.41 no.4
• /
• pp.437-451
• /
• 2019

Outlier detection techniques play an important role in enhancing the reliability of data communication in wireless sensor networks (WSNs). Considering the importance of outlier detection in WSNs, many outlier detection techniques have been proposed. Unfortunately, most of these techniques still have some potential limitations, that is, (a) high rate of false positives, (b) high time complexity, and (c) failure to detect outliers online. Moreover, these approaches mainly focus on either temporal outliers or spatial outliers. Therefore, this paper aims to introduce novel algorithms that successfully detect both temporal outliers and spatial outliers. Our contributions are twofold: (i) modifying the Hampel Identifier (HI) algorithm to achieve high accuracy identification rate in temporal outlier detection, (ii) combining the Gaussian process (GP) model and graph-based outlier detection technique to improve the performance of the algorithm in spatial outlier detection. The results demonstrate that our techniques outperform the state-of-the-art methods in terms of accuracy and work well with various data types.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.1
• /
• pp.161-174
• /
• 1996

Addressed in this paper is performance analysis of the maximum-likelihood code acquisition technique for slotted-mode preamble search in the CDMA reverse link. The probabilities of detection, miss, and false alarm are derived analytically for a multiple $H_{1}$ cell case in a frequency-selective Rayleigh fading channel, based on the statics of the CDMA noncoherent demodulator output. the probability density function of the decision variable consisting of successive demodulator outputs is also derived by considering the fading characteristics of the received signal for both single and dual antenna cases. The performance of the code acquisition technique is evaluated numerically with an emphasis on investigating the effects of post-detection integration, fading rate, and antenna diversity on the detection performance.