• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1069-1079
• /
• 2019

In this study, we developed a $PM_{10}$ forecasting model using DNN and Membership Function, and improved the forecasting performance. The model predicts the $PM_{10}$ concentrations of the next 3 days in the Seoul area by using the weather and air quality observation data and forecast data. The best model(RM14)'s accuracy (82%, 76%, 69%) and false alarm rate(FAR:14%,33%,44%) are good. Probability of detection (POD: 79%, 50%, 53%), however, are not good performance. These are due to the lack of training data for high concentration $PM_{10}$ compared to low concentration. In addition, the model dose not reflect seasonal factors closely related to the generation of high concentration $PM_{10}$. To improve this, we propose Julian date membership function as inputs of the $PM_{10}$ forecasting model. The function express a given date in 12 factors to reflect seasonal characteristics closely related to high concentration $PM_{10}$. As a result, the accuracy (79%, 70%, 66%) and FAR (24%, 48%, 46%) are slightly reduced in performance, but the POD (79%, 75%, 71%) are up to 25% improved compared with those of the RM14 model. Hence, this shows that the proposed Julian forecast model is effective for high concentration $PM_{10}$ forecasts.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.6
• /
• pp.85-94
• /
• 2019

Warhead and debris show the different micro-Doppler frequency shape in the spectrogram because of the different micro motion. So we can classify them using the micro-Doppler features. In this paper, we classified warhead and debris in the separation phase using CNN(Convolutional Neural Networks). For the input image of CNN, we used micro-Doppler spectrogram. In addition, to improve classification performance of warhead and debris, we applied the preprocessing using CA-CFAR to the micro-Doppler spectrogram. As a result, when the preprocessing of micro-Doppler spectrogram was used, classification performance is improved in all signal-to-noise ratio(SNR).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.134-134
• /
• 2021

Precipitation is a crucial component of water cycle and play a key role in hydrological processes. Traditionally, gauge-based precipitation is the main method to achieve high accuracy of rainfall estimation, but its distribution is sparsely in mountainous areas. Recently, satellite-based precipitation products (SPPs) provide grid-based precipitation with spatio-temporal variability, but SPPs contain a lot of uncertainty in estimated precipitation, and the spatial resolution quite coarse. To overcome these limitations, this study aims to generate new grid-based daily precipitation using Automatic weather system (AWS) in Korea and multiple SPPs(i.e. CHIRPSv2, CMORPH, GSMaP, TRMMv7) during the period of 2003-2017. And this study used a machine learning based Random Forest (RF) model for generating new merging precipitation. In addition, several statistical linear merging methods are used to compare with the results of the RF model. In order to investigate the efficiency of RF, observed data from 64 observed Automated Synoptic Observation System (ASOS) were collected to evaluate the accuracy of the products through Kling-Gupta efficiency (KGE), probability of detection (POD), false alarm rate (FAR), and critical success index (CSI). As a result, the new precipitation generated through the random forest model showed higher accuracy than each satellite rainfall product and spatio-temporal variability was better reflected than other statistical merging methods. Therefore, a random forest-based ensemble satellite precipitation product can be efficiently used for hydrological simulations in ungauged basins such as the Mekong River.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.143-143
• /
• 2022

Precipitation plays an essential role in water resources management and disaster prevention. Therefore, the understanding related to spatiotemporal characteristics of rainfall is necessary. Nowadays, highly accurate precipitation is mainly obtained from gauge observation systems. However, the density of gauge stations is a sparse and uneven distribution in mountainous areas. With the proliferation of technology, satellite-based precipitation sources are becoming increasingly common and can provide rainfall information in regions with complex topography. Nevertheless, satellite-based data is that it still remains uncertain. To overcome the above limitation, this study aims to take the strengthens of machine learning to generate a new reanalysis of precipitation data by fusion of multiple satellite precipitation products (SPPs) with gauge observation data. Several machine learning algorithms (i.e., Random Forest, Support Vector Regression, and Artificial Neural Network) have been adopted. To investigate the robustness of the new reanalysis product, observed data were collected to evaluate the accuracy of the products through Kling-Gupta efficiency (KGE), probability of detection (POD), false alarm rate (FAR), and critical success index (CSI). As a result, the new precipitation generated through the machine learning model showed higher accuracy than original satellite rainfall products, and its spatiotemporal variability was better reflected than others. Thus, reanalysis of satellite precipitation product based on machine learning can be useful source input data for hydrological simulations in ungauged river basins.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.796-799
• /
• 2008

최근 유비쿼터스 컴퓨팅과 유비쿼터스 네트워크를 활용하여 새로운 서비스들을 개발하려는 노력이 진행 중이며, 이와 관련된 기술의 중요성도 급증하고 있다. 특히 감시정찰 센서네트워크의 핵심 구성요소인 저가의 경량 센서노드에서 측정한 미가공 데이터(raw data)를 사용하여 침입 물체의 실시간 탐지, 식별, 추적 및 예측하기 위한 디지털 신호처리 기술은 주요 기술 중 하나이다. 본 논문에서는 감시정찰 센서네트워크의 핵심 구성요소인 소리센서 노드에서 측정한 소리 미가공 데이터를 사용하여 차량을 탐지할 수 있는 소리센서 디지털 신호처리 알고리즘을 설계 및 구현 한다. 알고리즘의 주 목표는 감시정찰용 센서노드의 탐지 신뢰성을 높이기 위한 높은 침입물체 탐지 성공률(success rate)과 낮은 허위신고(false alarm) 횟수를 가지는 것이다. 성능평가 결과에 의하면 제안한 AMIDA 알고리즘은 90% 이상의 탐지 성공률과 2 회 이하의 허위신고 횟수를 가지는 것을 확인할 수 있었다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.5D
• /
• pp.623-631
• /
• 2011

In this study, a new method which can detect incidents in interrupted traffic flow was suggested. The applied method of detecting the incident is the Latin Square Analysis Method by using traffic traits. In the Latin Square Analysis, unlike other previously tried methods, the traffic situation was analyzed, this time considering the changes in traffic traits for each lane and for each time period. The data used in this study were the data observed in the actual field with fine weather. The traffic volumes, the vehicle speed and the occupancy rate were collected on the interrupted flow road. The data were collected in normal and incident situations. The incidents occurred on the second lane, the time of persistent incidents was set to 10 minutes. The Latin Square Analyses were performed using the collected data with the traffic volume, with the vehicle speed or with the occupancy rate. As a result in this study, in case of detecting the traffic situations with Latin Square Analysis, it will be more successful to apply traffic volume to detect the traffic situations than to apply other factors.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.4
• /
• pp.347-357
• /
• 2003

This paper describes on the suppression of sea clutter on marine radar display using a cell-averaging CFAR(constant false alarm rate) technique, and on the analysis of radar echo signal data in relation to the estimation of ARPA functions and the detection of the shadow effect in clutter returns. The echo signal was measured using a X -band radar, that is located on the Pukyong National University, with a horizontal beamwidth of $$3.9^{\circ}$$, a vertical beamwidth of $20^{\circ}$, pulsewidth of $0.8 {\mu}s$ and a transmitted peak power of 4 ㎾ The suppression performance of sea clutter was investigated for the probability of false alarm between $l0-^0.25;and; 10^-1.0$. Also the performance of cell averaging CFAR was compared with that of ideal fixed threshold. The motion vectors and trajectory of ships was extracted and the shadow effect in clutter returns was analyzed. The results obtained are summarized as follows；1. The ARPA plotting results and motion vectors for acquired targets extracted by analyzing the echo signal data were displayed on the PC based radar system and the continuous trajectory of ships was tracked in real time. 2. To suppress the sea clutter under noisy environment, a cell averaging CFAR processor having total CFAR window of 47 samples(20+20 reference cells, 3+3 guard cells and the cell under test) was designed. On a particular data set acquired at Suyong Man, Busan, Korea, when the probability of false alarm applied to the designed cell averaging CFAR processor was 10$^{-0}$.75/ the suppression performance of radar clutter was significantly improved. The results obtained suggest that the designed cell averaging CFAR processor was very effective in uniform clutter environments. 3. It is concluded that the cell averaging CF AR may be able to give a considerable improvement in suppression performance of uniform sea clutter compared to the ideal fixed threshold. 4. The effective height of target, that was estimated by analyzing the shadow effect in clutter returns for a number of range bins behind the target as seen from the radar antenna, was approximately 1.2 m and the information for this height can be used to extract the shape parameter of tracked target..

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.3
• /
• pp.428-451
• /
• 2010

Traffic matrix-based anomaly detection and DDoS attacks detection in networks are research focus in the network security and traffic measurement community. In this paper, firstly, a new type of unidirectional flow called IF flow is proposed. Merits and features of IF flows are analyzed in detail and then two efficient methods are introduced in our DDoS attacks detection and evaluation scheme. The first method uses residual variance ratio to detect DDoS attacks after Recursive Least Square (RLS) filter is applied to predict IF flows. The second method uses generalized likelihood ratio (GLR) statistical test to detect DDoS attacks after a Kalman filter is applied to estimate IF flows. Based on the two complementary methods, an evaluation formula is proposed to assess the seriousness of current DDoS attacks on router ports. Furthermore, the sensitivity of three types of traffic (IF flow, input link and output link) to DDoS attacks is analyzed and compared. Experiments show that IF flow has more power to expose anomaly than the other two types of traffic. Finally, two proposed methods are compared in terms of detection rate, processing speed, etc., and also compared in detail with Principal Component Analysis (PCA) and Cumulative Sum (CUSUM) methods. The results demonstrate that adaptive filter methods have higher detection rate, lower false alarm rate and smaller detection lag time.

• Journal of the Korean Society of Safety
• /
• v.32 no.2
• /
• pp.38-45
• /
• 2017

This paper is an experimental study to find an optimal detection method for detecting fire early in a rack-type warehouse stored with goods. In this study, we constructed rack-type structure with the fourth floor of 13.5 m high and conducted fire experiments which were to measure flow of heat/smoke in rack-type structure and response time of fire detectors. The detectors used at experiments were fixed temperature type detectors, rate of rise detectors, photoelectric smoke detectors, air sampling smoke detectors and flame detectors. The used ignition sources are n-heptane fire for response of heat detection and cotton fire for response of smoke detection. The fixed temperature type detectors, rate of rise detectors and photoelectric detectors were installed to every rack level respectively. The results show that the rate of rise detector should be installed every 2 levels and photoelectric smoke detector should be installed every 4 levels for the early stage fire detection. Air sampling smoke detectors can detect fire early in response to control of sensitivity, but there is a problem in false alarm. The fixed temperature detector is not suitable for early stage fire detection in warehouse and flame detector not worked if flame is not visible, so it need to install combination with other detector.