• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.715-721
• /
• 2012

A threat evaluation is the technique which decides order of priority about tracks engaging with enemy by recognizing battlefield situation and making it efficient decision making. That is, in battle situation of multiple target it makes expeditious decision making and then aims at minimizing asset's damage and maximizing attack to targets. Threat value computation used in threat evaluation is calculated by sensor data which generated in battle space. Because Battle situation is unpredictable and there are various possibilities generating potential events, the damage or loss of data can make confuse decision making. Therefore, in this paper we suggest that substantial threat value calculation using learning bayesian network which makes it adapt to the varying battle situation to gain reliable results under given incomplete data and then verify this system's performance.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.123-123
• /
• 2018

가뭄은 홍수와 달리 진행속도가 비교적 느리기 때문에 초기에 감지한다면 피해를 최소화 할 수 있다. 국내에서는 가뭄전망을 위해 물리적 기반의 기상-수문연계해석 시스템을 구축하여 월 내지 계절전망을 수행하고 있다. 물리적 기반의 가뭄전망은 수치예보모델의 불확실성을 가지고 있으므로 예보 정확도 개선의 측면에서는 통계적 모델을 같이 활용하는 것이 바람직하다. 최근 국외에서는 통계적 방법인 AI (Artificial Intelligence) 기술을 사용하여 가뭄을 전망하는 연구가 활발히 진행 중이나, 아직까지 국내에서는 관련연구가 미흡한 실정이다. 이에 본 연구에서는 ANFIS (Adaptive Neuro-Fuzzy Inference System) 기반의 댐 유입량 예측 모델을 구축하고 SRI (Standardized Runoff Index)를 활용하여 수문학적 가뭄전망을 수행하였다. 대상유역은 국내 주요 다목적댐이 위치한 충주댐 유역과 소양강댐 유역을 선정하였다. 수문 및 기상자료는 국토 교통부 및 기상청의 관측 댐 유입량, 관측 강수량, 관측 기온 및 장기기상예보 자료를 사용하였다. ANFIS 모델 구축을 위한 훈련 및 보정기간과 검정기간은 각각 1987~2010년과 2011~2016년을 선정하였다. 수문학적 가뭄전망은 지속기간 3개월의 1개월 전망 SRI3를 활용하였으며, SRI3는 관측유입량과 예측유입량을 결합하여 산정하였다. 댐 예측유입량 및 수문학적 가뭄전망의 정확도 평가를 위해 상관계수, 평균제곱근오차를 활용하였다. 댐 예측유입량 평가 결과 예측값과 관측값의 상관계수가 높게 나타났으며, 평균제곱근오차는 낮아 예측성이 뛰어났다. SRI3의 경우 관측값과 예측값의 가뭄발생시기가 유사하여 가뭄을 적절하게 반영하는 것으로 나타났다. 본 연구의 결과는 통계적 기반의 수문학적 가뭄전망기법을 개발하였다는 측면에서 의의가 있으며, 향후 물리적 기반의 가뭄전망정보와 결합한다면 보다 실효성이 향상될 것으로 기대된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.553-557
• /
• 2009

USS(Ubiquitous Smart Space) give services, that fit in with customer's goal, by cognizing various situations that happens in a space and cooperating autonomously objects or services in a space. In USS, U-Safety is a system that cognizes more exact situations with multiple sensors in USS, deals with this and take proper actions. When men reason on situations objectively, it is most ideal that image data among collected data with used various sensors in U-Safety. A senter collects a lot of image data from image input devices equipped in various points and work a multiple situation cognition and inference that are based on this. So, senters spend many resources for processing massive data. This paper proposes hierarchical image processing method that does the first situation cognization in image input devices, blocks only points that situation cognization possibility is high among a total image, and transfers to senters. It improves the efficiency of smooth situation cognization by reducing resources that a senter spends on image processing. So, it reduces proportion of image data in U-Safety.

• Journal of the Korea Society for Simulation
• /
• v.25 no.4
• /
• pp.127-135
• /
• 2016

Even thought modernized marine navigation devices help navigators, marine accidents has been often occurred and ship collision is one of the main types of the accidents. Various studies on the assessment method of collision risk have been reported, and studies using fuzzy theory are remarkable for the reason that reflect linguistic and ambiguous criteria for real situations. In these studies, collision risks were assessed on the assumption that the current state of navigation ship would be maintained. However, navigators ignore or turn off frequent alarms caused by the devices predicting collision risk, because they think that they can avoid the collisions in the most of situations. This paper proposes a model of predicting ship collision risk considering the general patterns of collision avoidance, and the approach is based on fuzzy inference and discrete event system specification (DEVS) formalism.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.8
• /
• pp.943-949
• /
• 2019

As use of digital equipment in various fields is increasing importance of processing video and signals is rising as well. However, in the process of sending and receiving signals, noise occurs due to different reasons and this noise bring about a huge influence on final output of the system. This research suggests algorithm for effectively repairing video in consideration to characteristics of its noise in condition where impulse and AWGN noises are combined. This algorithm tries to preserve video features by considering inference to noise components and resolution of filtering mask. Depending on features of input resolution, standard value is set and similar resolutions is selected for noise removal. This algorithm showing simulation result had outstanding noise removal and is compared and analyzed with existing methods by using different ways such as PSNR.

• Korean Journal of Agricultural Science
• /
• v.46 no.2
• /
• pp.381-393
• /
• 2019

A smart farm is a system that combines information and communication technology (ICT), internet of things (IoT), and agricultural technology that enable a farm to operate with minimal labor and to automatically control of a greenhouse environment. Machine learning based on recently data-driven techniques has emerged with big data technologies and high-performance computing to create opportunities to quantify data intensive processes in agricultural operational environments. This paper presents research on the application of machine learning technology to diagnose the growth status of crops and predicting the harvest time of strawberries in a greenhouse according to image processing techniques. To classify the growth stages of the strawberries, we used object inference and detection with machine learning model based on deep learning neural networks and TensorFlow. The classification accuracy was compared based on the training data volume and training epoch. As a result, it was able to classify with an accuracy of over 90% with 200 training images and 8,000 training steps. The detection and classification of the strawberry maturities could be identified with an accuracy of over 90% at the mature and over mature stages of the strawberries. Concurrently, the experimental results are promising, and they show that this approach can be applied to develop a machine learning model for predicting the strawberry harvesting time and can be used to provide key decision support information to both farmers and policy makers about optimal harvest times and harvest planning.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.26-37
• /
• 2022

In this paper, images are automatically acquired to control the initial disease of strawberries among facility cultivation crops, and disease analysis is performed using the EfficientNet model to inform farmers of disease status, and disease diagnosis service is proposed by experts. It is possible to obtain an image of the strawberry growth stage and quickly receive expert feedback after transmitting the disease diagnosis analysis results to farmers applications using the learned EfficientNet model. As a data set, farmers who are actually operating facility cultivation were recruited and images were acquired using the system, and the problem of lack of data was solved by using the draft image taken with a cell phone. Experimental results show that the accuracy of EfficientNet B0 to B7 is similar, so we adopt B0 with the fastest inference speed. For performance improvement, Fine-tuning was performed using a pre-trained model with ImageNet, and rapid performance improvement was confirmed from 100 Epoch. The proposed service is expected to increase production by quickly detecting initial diseases.

• Computers and Concrete
• /
• v.29 no.3
• /
• pp.187-199
• /
• 2022

The usability of waste materials as raw materials is necessary for sustainable production. This study investigates the effects of different powder materials used to replace cement (0%, 5% and 10%) and standard sand (0%, 20% and 30%) (basalt, limestone, and dolomite) on the compressive strength (f_c), flexural strength (f_r), and ultrasonic pulse velocity (UPV) of mortars exposed to freeze-thaw cycles (56, 86, 126, 186 and 226 cycles). Furthermore, the usability of artificial intelligence models is compared, and the prediction accuracy of the outputs is examined according to the inputs (powder type, replacement ratio, and the number of cycles). The results show that the variability of the outputs was significantly high under the freeze-thaw effect in mortars produced with waste powder instead of those produced with cement and with standard sand. The highest prediction accuracy for all outputs was obtained using the adaptive-network-based fuzzy inference system model. The significantly high prediction accuracy was obtained for the UPV, f_c, and f_r of mortars produced using waste powders instead of standard sand (R² of UPV, f_c and f_f is 0.931, 0.759 and 0.825 respectively), when under the freeze-thaw effect. However, for the mortars produced using waste powders instead of cement, the prediction accuracy of UPV was significantly high (R²=0.889) but the prediction accuracy of f_c and f_r was low (R²f_c=0.612 and R²f_f=0.334).

• Asia-Pacific Journal of Business
• /
• v.14 no.1
• /
• pp.365-379
• /
• 2023

Purpose - Our previous study (Chang & Lee, 2023) presented observations on the recent changes in the year-on-year (YoY) Consumer Price Index (CPI) of the Republic of Korea (ROK) after the COVID-19 pandemic. The purpose of this article is to present an integrated analysis and interpretation of the recent changes in CPI and the Aggregate Import Price Index (IPI) by incorporating recent data, specifically data from September 2022 to December 2022. Design/methodology/approach - This study collected CPI (YoY) data in the ROK from January 2019 to December 2022 using e-National Indicator System provided by the ROK. Statistical analysis was employed to analyze the data. Findings - First, we confirm the extended results of the existing study by Chang and Lee (2023). Second, we demonstrate that the Aggregate IPI in ROK increased significantly in 2022 compared to 2021. We then provide an integrated interpretation on the significant increase in CPI and aggregate IPI in ROK, which complements Chang and Lee (2023) that limits their discussion to YoY CPI. Moreover, we show that the IPI of the semiconductor in ROK decreased significantly in 2022 compared to 2021. Research implications or Originality - Our results provide important insights into the recent changes in the CPI in the ROK. The results suggest that these changes can be partially attributed to various factors, such as the global supply chain disruptions resulting from the spread of the COVID-19 pandemic and the prolonged war between Russia and Ukraine, the side effect of quantitative easing by the US Federal Reserve, heat waves and droughts caused by climate change in ROK, a surge in demand following a gradual daily recovery, US-China trade conflict, etc. Our study shows statistically comprehensive results compared to the studies that limit their discussion to YoY average growth rate.

• Steel and Composite Structures
• /
• v.48 no.2
• /
• pp.179-190
• /
• 2023

Many recent attempts have sought accurate prediction of pile pullout resistance (P_ul) using classical machine learning models. This study offers an improved methodology for this objective. Adaptive neuro-fuzzy inference system (ANFIS), as a popular predictor, is trained by a capable metaheuristic strategy, namely equilibrium optimizer (EO) to predict the P_ul. The used data is collected from laboratory investigations in previous literature. First, two optimal configurations of EO-ANFIS are selected after sensitivity analysis. They are next evaluated and compared with classical ANFIS and two neural-based models using well-accepted accuracy indicators. The results of all five models were in good agreement with laboratory P_uls (all correlations > 0.99). However, it was shown that both EO-ANFISs not only outperform neural benchmarks but also enjoy a higher accuracy compared to the classical version. Therefore, utilizing the EO is recommended for optimizing this predictive tool. Furthermore, a comparison between the selected EO-ANFISs, where one employs a larger population, revealed that the model with the population size of 75 is more efficient than 300. In this relation, root mean square error and the optimization time for the EO-ANFIS (75) were 19.6272 and 1715.8 seconds, respectively, while these values were 23.4038 and 9298.7 seconds for EO-ANFIS (300).