• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.10-16
• /
• 2000

A new algorithm for estimating bladder volume for portable bladder volume measurement system is proposed. Given the actual image of a bladder, edges between bladder wall and urine are extracted first. Axes are calculated from these data and actual cross section shape is obtained by filtering. Since ordinary shape of a bladder is irregular, two cross-sections(transverse and longitudinal) are considered. With the area of a longitudinal cross-section projected along the axes of transverse cross-section, or vice versa, two estimated volume are obtained. Averaging these two value yields the volume of the bladder. Applied to actual experiments, the proposed algorithm showed explicitly good results in comparison with the conventional techniques.

• Journal of Soil and Groundwater Environment
• /
• v.27 no.3
• /
• pp.1-10
• /
• 2022

Most wells developed in Jeju island before the enactment of the Groundwater Management Ordinance in 2002 are vulnerable to aquifer contamination due to inflow of upper groundwater having the high concentration of nitrate nitrogen, likely due to incomplete grouting in upper section of the wells. Although these wells require entire reinstallation, it is often necessary to rehabilitate the existing wells due to various constraints. Therefore, to identified the inflow section of contaminants, the thermal level sensor (TLS) technique was firstly applied for three wells, which enables to monitor temperature variations in every 50 cm depth. Then, the grouting material was injected to the upper section to prevent the inflow of upper contaminated groundwater into the entire aquifer. By applying TLS technique, it was found that the temperature deviations in the upper groundwater inflow section decreased sharply. Moreover, both the change in the concentration of nitrate nitrogen in the rainy/dry seasons and the average concentrations were found to decrease rapidly after grouting material injection. Consequently, the application of TLS proposed in the study turned out to be appropriate to prevent aquifer contamination.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.446-448
• /
• 2023

최근 문화유산 해설 분야에도 AI를 도입하기 위해 여러 노력을 기울이고 있으나, 관람객의 특성이나 관심사를 고려하지 않고 사전에 수동으로 입력한 동일한 문화해설 콘텐츠를 다수의 관람객에게 반복 전달하는 형태로만 제공되는데 그치고 있다. 본 논문에서는 관람객이 관람 중인 문화유산을 관람객의 다양한 관심사에 맞추어 문화유산을 다양하게 해설해주기 위한 기초 연구로 영상을 통해 입력된 한국 전통회화에서 도상을 검출하는 연구를 진행하였다. 아직 가능성 타진 연구로 진행되어 현재 제시된 실험 결과에서는 우수한 도상 검출 성능을 내지 못하였지만, 다양한 증강기법과 퓨샷 러닝기법을 통하여 성능 향상을 도모할 경우 충분히 관람객 맞춤형 문화유산 해설 분야에 활용 가능할 것으로 기대된다.

• ETRI Journal
• /
• v.16 no.2
• /
• pp.15-25
• /
• 1994

In this paper we present a new formula which can predict the exact detection probability of a generalized order statistics (GOS) constant false alarm rate (DFAR) detector for a partially correlated Rayleigh target model (0 < $ \rho$< 1) in a closed form, where $\rho$ is the correlation coefficient between returned pulses. By simply substituting a set of specific coefficient into the derived formula, one can obtain the detection probability of any kind of CFAR detector. Detectors may include the order statistics CFAR detector, the censored mean level detector, and the trimmed mean CFAR detector, but are not necessarily restricted to them. The numerical result for the first order Markov correlation model as applied to some of the detectors shows that as $\rho$ increases from zero to one, higher signal-to-noise ratio is required to achieve the same detection probability.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.4 no.3
• /
• pp.85-90
• /
• 2008

Recently, with the sensor technology, research about the electronic nose system which imitated the olfactory organ are being pushed actively. But, in case of general electronic nose system, an aroma is measured at the laboratory space where blocked external environment and is analyzed a part of measured data. In this paper, we propose the system which can measure and recognize an aroma in natural environment. We propose the Entropy algorithm which can detect the sensor reaction section among the continuous detection processing about an aroma. And we implement the aroma recognition system using the PCA(Principal Components Analysis) and K-NN(K-Nearest Neighbor) about the detected aroma. In order to evaluate the performance, we measured the aroma pattern, about 9 aroma oil, 50 times respectively. And we experimented the aroma detection and recognition using this. There was an error of 0.2s in the aroma detection and we get 84.3% recognition rate of the aroma recognition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.3063-3068
• /
• 2014

Since the RCS(Radar Cross Section) of target is important factor to determine radar performance, it is important to locate radar where large RCS is observed. However, the distance between the target and the radar is an important factor of the received power, as well as RCS. In this paper, it is calculated that received power from ballistic missile to radar based on different observed position and it is studied that to place radar for high detection efficiency.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.2
• /
• pp.183-189
• /
• 1987

The performance of frame synchronization can be represented by the values of three characteristic variables-average misframe interval, average syncloss detection time, average reframe time. In this paper, we have analyzed the performance of frame synchronization of the standardized 90Mb/s optical transmission system by Markov chain method, with the suggestion of an extended algorithm for performance improvement. Maximum average reframe time of 1.18 ms can be obtained by the suggested algorithm, which is compared with that of 2.28 ms for the existing algorithm.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.96-105
• /
• 2024

We propose a method to automatically predict Alzheimer's disease from speech data using the ChatGPT large language model. Alzheimer's disease patients often exhibit distinctive characteristics when describing images, such as difficulties in recalling words, grammar errors, repetitive language, and incoherent narratives. For prediction, we initially employ a speech recognition system to transcribe participants' speech into text. We then gather opinions by inputting the transcribed text into ChatGPT as well as a prompt designed to solicit fluency evaluations. Subsequently, we extract embeddings from the speech, text, and opinions by the pretrained models. Finally, we use a classifier consisting of transformer blocks and linear layers to identify participants with this type of dementia. Experiments are conducted using the extensively used ADReSSo dataset. The results yield a maximum accuracy of 87.3% when speech, text, and opinions are used in conjunction. This finding suggests the potential of leveraging evaluation feedback from language models to address challenges in Alzheimer's disease recognition.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.12
• /
• pp.471-480
• /
• 2016

Recently, the damage of cyber attack toward infra-system, national defence and security system is gradually increasing. In this situation, military recognizes the importance of cyber warfare, and they establish a cyber system in preparation, regardless of the existence of threaten. Thus, the study of Intrusion Detection System(IDS) that plays an important role in network defence system is required. IDS is divided into misuse and anomaly detection methods. Recent studies attempt to combine those two methods to maximize advantagesand to minimize disadvantages both of misuse and anomaly. The combination is called Hybrid IDS. Previous studies would not be inappropriate for near real-time network environments because they have computational complexity problems. It leads to the need of the study considering the structure of IDS that have high detection rate and low computational cost. In this paper, we proposed a Hybrid IDS which combines C4.5 decision tree(misuse detection method) and Weighted K-means algorithm (anomaly detection method) hierarchically. It can detect malicious network packets effectively with low complexity by applying mutual information and genetic algorithm based efficient feature selection technique. Also we construct upgraded the the hierarchical structure of IDS reusing feature weights in anomaly detection section. It is validated that proposed Hybrid IDS ensures high detection accuracy (98.68%) and performance at experiment section.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.449-455
• /
• 2021

This paper proposes an encryption web transaction attack detection system based on the existing web application monitoring system. Although there was difficulty in detecting attacks on the encrypted web traffic because the existing web traffic security systems detect and defend attacks based on encrypted packets in the network area of the encryption section between the client and server, by utilizing the technology of the web application monitoring system, it is possible to detect various intelligent cyber-attacks based on information that is already decrypted in the memory of the web application server. In addition, since user identification is possible through the application session ID, statistical detection of attacks such as IP tampering attacks, mass web transaction call users, and DDoS attacks are also possible. Thus, it can be considered that it is possible to respond to various intelligent cyber attacks hidden in the encrypted traffic by collecting and detecting information in the non-encrypted section of the encrypted web traffic.