• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.6
• /
• pp.453-460
• /
• 2014

We analyze fault detection algorithm of ephemeris included in navigation message, which is one of the GNSS risk factors. This algorithm uses carrier-phase measurement and baseline vector of two reference stations and is alternative method for uncertainty condition of previous ephemeris. Even though same ephemeris fault is occurred, the geometry condition, between baseline vector of reference stations and satellites, effects on performance of algorithm. Also, we introduce the suitable geometry of reference stations, threshold and performance index (MDE : Minimum Detectable Error) in jeju international airport.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.5B
• /
• pp.338-347
• /
• 2012

In this paper, we propose the cooperative transmission scheme (CTS) for system throughput maximization in OFDMA based enterprise femtocell networks. In our scheme, the user equipment (UE) can receive the desired signal from serving femtocell BS (fBS) as well as an adjacent fBS. Thus, UE achieves an improved signal to interference plus and noise ratio (SINR) by the synchronized two signals. The performances of this strategy consider not only the call-level quality of service (QoS) but also the packet-level QoS. We first measure the call blocking probability and utilization for the downlink resources for various offered load in femtocell. Based on that, the outage probability and effective throughput of the system are simulated. Simulation results show that the proposed scheme can reduce the outage probability for enterprise femtocell compared with conventional systems.

• Journal of Korean Society of Transportation
• /
• v.22 no.6
• /
• pp.175-196
• /
• 2004

This study focuses on improving the performance of freeway incident detection by introducing some new measures to reduce false alarms in developing a new incident detection model. The model consists of the 5 major components through which a series of decision makings in determining the given traffic flow condition are made. The decision making process was designed such that the causes of traffic congestions can be accurately classified into several types including incidents and bottlenecks according to their unique characteristics. The model performance was tested and found to be compatible with that of the existing well-recognized models in terms of the detection rate and detection time. It should noted that the model produced much less false alarms than most of the existing models. The study results prove that the initial objective of the study was satisfied as it was an experimental trial to improve the false alarm rate for the incident detection model to be more pactically usable for traffic management purposes.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.79-85
• /
• 2019

In this paper, we propose a short-term power forecasting method by applying Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network to Internet of Things (IoT) power meter. We analyze performance based on real power consumption data of households. Mean absolute error (MAE), mean absolute percentage error (MAPE), mean percentage error (MPE), mean squared error (MSE), and root mean squared error (RMSE) are used as performance evaluation indexes. The experimental results show that the GRU-based model improves the performance by 4.52% in the MAPE and 5.59% in the MPE compared to the LSTM-based model.

• Convergence Security Journal
• /
• v.21 no.3
• /
• pp.57-66
• /
• 2021

As the detection performance using deep learning and machine learning of the intrusion detection field has been verified, the cases of using it are increasing day by day. However, it is difficult to collect the data required for learning, and it is difficult to apply the machine learning performance to reality due to the imbalance of the collected data. Therefore, in this paper, A mixed sampling technique using t-SNE visualization for imbalanced data processing is proposed as a solution to this problem. To do this, separate fields according to characteristics for intrusion detection events, including payload. Extracts TF-IDF-based features for separated fields. After applying the mixed sampling technique based on the extracted features, a data set optimized for intrusion detection with imbalanced data is obtained through data visualization using t-SNE. Nine sampling techniques were applied through the open intrusion detection dataset CSIC2012, and it was verified that the proposed sampling technique improves detection performance through F-score and G-mean evaluation indicators.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.43-54
• /
• 2022

Simultaneous translation is online decoding to translates with only subsentence. The goal of simultaneous translation research is to improve translation performance against delay. For this reason, most studies find trade-off performance between delays. We studied the experiments of the fixed policy-based simultaneous translation in Korean. Our experiments suggest that Korean tokenization causes many fragments, resulting in delay compared to other languages. We suggest follow-up studies such as n-gram tokenization to solve the problems.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.2
• /
• pp.94-101
• /
• 2023

A deep neural network composed of encoders and decoders, such as U-Net, used for speech enhancement, concatenates the encoder to the decoder through skip-connection. Skip-connection helps reconstruct the enhanced spectrum and complement the lost information. The features of the encoder and the decoder connected by the skip-connection are incompatible with each other. In this paper, for complex-valued spectrum based speech enhancement, Self-Attention (SA) method is applied to skip-connection to transform the feature of encoder to be compatible with the features of decoder. SA is a technique in which when generating an output sequence in a sequence-to-sequence tasks the weighted average of input is used to put attention on subsets of input, showing that noise can be effectively eliminated by being applied in speech enhancement. The three models using encoder and decoder features to apply SA to skip-connection are studied. As experimental results using TIMIT database, the proposed methods show improvements in all evaluation metrics compared to the Deep Complex U-Net (DCUNET) with skip-connection only.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.2
• /
• pp.13-23
• /
• 2016

Many traffic centers are highly hesitant in employing existing Automatic Incident Detection Algorithms due to high false alarm rate, low detection rate, and enormous effort taken in maintaining algorithm parameters, together with complex algorithm structure and filtering/smoothing process. Concerns grow over the situation particularly in Freeway Incident Management Area This study proposes a new algorithm and introduces a novel concept, the Displaced Flow Index (DiFI) which is similar to a product of relative speed and relative occupancy for every execution period. The algorithm structure is very simple, also easy to understand with minimum parameters, and could use raw data without any additional pre-processing. To evaluate the performance of the DiFI algorithm, validation test on the algorithm has been conducted using detector data taken from Naebu Expressway in Seoul and following transferability tests with Gyeongbu Expressway detector data. Performance test has utilized many indices such as DR, FAR, MTTD (Mean Time To Detect), CR (Classification Rate), CI (Composite Index) and PI (Performance Index). It was found that the DR is up to 100%, the MTTD is a little over 1.0 minutes, and the FAR is as low as 2.99%. This newly designed algorithm seems promising and outperformed SAO and most popular AIDAs such as APID and DELOS, and showed the best performance in every category.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.25 no.2
• /
• pp.126-133
• /
• 2015

연구목적: 이 연구는 노동부의 보건진단 명령에 의해 유리섬유 강화플라스틱(FRP)을 이용한 이중벽 탱크 제조 사업장의 적층 공정 근로자들을 대상으로 스티렌 노출 특성을 평가하기 위해 수행되었다. 연구방법: 스티렌의 주요발생원 파악을 위해 불포화 폴리에스테르 수지(UPR), 경화제, 조색제, 세척액 등의 원료 내 스티렌 함유량을 가스크로마토그래피 질량분석기(GC-MS)를 이용하여 분석하였다. FRP 적층 공정에 근무하는 작업자들을 대상으로 NIOSH 1501 공정시험법에 의해 공기 중 스티렌 노출 농도에 대한 개인노출 평가를 실시하였고, 생물학적 노출 지표로 뇨 중 만델릭산을 채취한 후 고성능액체크로마토그래피(HPLC)로 분석하였다. 또한 각 직무 특성과 단위작업 중심으로 스티렌에 대한 단시간 노출평가를 수행하였다. 연구결과: 스티렌의 함유량이 가장 많은 주요 원료는 중량비율로37%의 스티렌이 함유된 UPR이었다. 적층 공정의 FRP분무 작업자와 보조 작업자들 모두 스티렌의 8시간 가중평균 노출기준(20 ppm)을 초과하였다. 단시간 노출평가 결과 FRP분무 작업자의 경우 45.9 ppm에서 86.1 ppm 수준으로 FRP를 사용하지 않는 작업보다 통계적으로 유의하게 높은 수준이었다(P<0.01). 가장 높은 수준의 스티렌에 노출되는 단위작업은 FRP를 이용하여 1차 코팅 하는 작업으로 특별한 관리가 필요하였다. 결론: 보건진단을 위해 실시한 이중벽 탱크 제조 사업장의FRP 적층 공정 작업자의 스티렌 노출수준은 노출기준을 초과할 정도로 높은 수준이었다. 그러나 탱크를 천장에 매달고 돌리면서 적층작업을 수행하기 때문에 적절한 국소환기 시스템을 구축하는데 어려움이 있다. 따라서 적절한 방독마스크 착용으로 스티렌 노출 예방이 필요하였다.