• Convergence Security Journal
• /
• v.20 no.2
• /
• pp.123-135
• /
• 2020

Since AlphaGo's Match in 2016, there has been a growing calls for artificial intelligence applications in various industries, and research related to it has been actively conducted. The same is true in the military field, and since there has been no weapon system with artificial intelligence so far, effort to implement it are posing a challenge. Meanwhile, AlphaGo Zero, which beat AlphaGo, showed that artificial intelligence's self-training data-based approach can lead to better results than the knowledge-based approach by humans. Taking this point into consideration, this paper proposes to apply Reinforcement Learning, which is the basis of AlphaGo Zero, to the Shipboard Combat System or Combat Management System. This is how an artificial intelligence application to the Shipboard Combat System or Combat Management System that allows the optimal tactical assist with a constant win rate to be recommended to the user, that is, the commanding officer and operation personnel. To this end, the definition of the combat performance of the system, the design plan for the Shipboard Combat System, the mapping with the real system, and the training system are presented to smoothly apply the current operations.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.05a
• /
• pp.367-369
• /
• 2006

The educational contents could be better off when the visualization, personalized storytelling and interaction are combined and fused in the interface. In this paper, we analyze the specification of I/O cooperation based on MS agent framework. which can be applied to the development of educational contents.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.12
• /
• pp.623-634
• /
• 2016

Most of existing frequent pattern mining methods address time efficiency and greatly rely on the primary memory. However, in the era of big data, the size of real-world databases to mined is exponentially increasing, and hence the primary memory is not sufficient enough to mine for frequent patterns from large real-world data sets. To solve this problem, there are some researches for frequent pattern mining method based on disk, but the processing time compared to the memory based methods took very time consuming. There are some researches to improve scalability of frequent pattern mining, but their processes are very time consuming compare to the memory based methods. In this paper, we present PPFP as a novel disk-based approach for mining frequent itemset from big data; and hence we reduced the main memory size bottleneck. PPFP algorithm is based on FP-growth method which is one of the most popular and efficient frequent pattern mining approaches. The mining with PPFP consists of two setps. (1) Constructing an IFP-tree: After construct FP-tree, we assign index number for each node in FP-tree with novel index numbering method, and then insert the indexed FP-tree (IFP-tree) into disk as IFP-table. (2) Mining frequent patterns with PPFP: Mine frequent patterns by expending patterns using stack based PUSH-POP method (PPFP method). Through this new approach, by using a very small amount of memory for recursive and time consuming operation in mining process, we improved the scalability and time efficiency of the frequent pattern mining. And the reported test results demonstrate them.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.10B
• /
• pp.866-871
• /
• 2006

This paper presents the design of a reservation-based MAC protocol to support multimedia traffic over mobile ad-hoc networks and evaluates its performance. Our MAC protocol is based on a hierarchical approach consisting of two sub-layers. The lower sub-layer of the MAC protocol with reservation provides a fundamental access method using CSMA/CA in order to support asynchronous data traffic over mobile ad-hoc networks. The upper sub-layer supports real-time periodic data by making a slot reservation before transmitting actual data. The proposed protocol has been validated through simulations using ns-2. The results show that the proposed MAC protocol can offer higher throughput and lower delay than standard implementations of the IEEE 802.11.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.93-106
• /
• 2021

Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.11
• /
• pp.2284-2290
• /
• 2015

The use of human actions as context for object class recognition is quite effective in enhancing the recognition performance despite the large variation in the appearance of objects. We propose an efficient method that integrates human action information into object class recognition using a Bayesian appraoch based on a simple probabilistic graph model. The experiment shows that by using human actions ac context information we can improve the performance of the object calss recognition from 8% to 28%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.576-579
• /
• 2024

경제 위기 대비를 위해 인공지능을 활용한 주식시장 변동성 이상을 탐지하는 목적을 가지고 있다. 글로벌 이슈와 경제 위기 대비를 위해 주식시장 변동성 예측의 중요성이 부각되고 있으며, 기존의 주식시장 변동성 지수인 VIX 의 한계로 인해 더 복잡한 모델 및 인공지능을 활용한 연구에 관심이 집중되고 있다. 기존의 주식시장 변동성 예측에 관한 연구들은 통계적인 방법을 사용했으며 인공지능을 이용한 연구 또한 대부분 이상치 구간을 표시하여 예측을 목표로 하고 있으나 이러한 접근법은 라벨이 있는 데이터 수집 어려움, 클래스 불균형 문제가 있다. 본 연구는 인공지능을 활용한 주식시장 변동성 탐지에 기여하고 지도 학습 방식 대신 비지도 학습 기반의 이상탐지모델을 사용하여 주식시장 변동성을 예측하는 새로운 방법론을 제안한다. 본 연구에서 개발한 인공지능 모델은 IsolationForest 모델을 활용하며, 시계열 데이터를 전처리한 후 정상성을 확보하는 등의 과정을 거친다. 실험 결과로 인공지능 모델이 주요 경제이슈를 이상치로 검출하는 성능을 확인하였으며 재현율 약 93.6%, 정밀도 100%로 높은 성능을 달성했다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.366-366
• /
• 2022

유역의 하천유량과 같은 수문 시계열을 모의 또는 예측하기 위한 수문 모델링에서 최근 기계 학습 방법을 활용한 연구가 활발하게 적용되고 있는 추세이다. 이러한 데이터 기반 모델링 접근법은 입출력 자료에서 관찰된 패턴을 학습하며, 특히, 장단기기억(Long Short-Term Memory, LSTM) 네트워크는 많은 연구에서 수문 시계열 예측에 대한 적용성이 검증되었으나, 장기간의 고품질 관측자료를 활용할 때 더 나은 예측성능을 보인다. 그러나 우리나라의 경우 장기간 관측된 고품질의 하천유량 자료를 확보하기 어려운 실정이다. 따라서 본 연구에서는 LSTM 네트워크의 학습 시 가용한 모든 유역의 자료를 통합하여 학습시켰을 때 하천유량 예측성능을 개선할 수 있는지 판단해보고자 하였다. 이를 위해, 우리나라 13개 댐 유역을 대상으로 대상 유역의 자료만을 학습한 모델의 예측성능과 모든 유역의 자료를 학습한 모델의 예측성능을 비교해 보았다. 학습은 2001년부터 2010년까지 기상자료(강우, 최저·최고·평균기온, 상대습도, 이슬점, 풍속, 잠재증발산)를 이용하였으며, 2011년부터 2020년에 대해 테스트 되었다. 다지점 통합학습을 통해 테스트 기간에 대해 예측된 각 유역의 일 하천유량의 KGE 중앙값이 0.74로 단일지점 학습을 통해 예측된 KGE(0.72)보다 다소 개선된 결과를 보여주었다. 다지점 통합학습이 하천유량 예측에 큰 개선을 달성하지는 못하였으며, 추가적인 가용 자료 확보와 LSTM 구성의 개선을 통해 추가적인 연구가 필요할 것으로 판단된다.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.173-190
• /
• 2015

The purpose of this study is to improve bankruptcy prediction models by using a novel hybrid under-sampling approach. Most prior studies have tried to enhance the accuracy of bankruptcy prediction models by improving the classification methods involved. In contrast, we focus on appropriate data preprocessing as a means of enhancing accuracy. In particular, we aim to develop an effective sampling approach for bankruptcy prediction, since most prediction models suffer from class imbalance problems. The approach proposed in this study is a hybrid under-sampling method that combines the k-Reverse Nearest Neighbor (k-RNN) and one-class support vector machine (OCSVM) approaches. k-RNN can effectively eliminate outliers, while OCSVM contributes to the selection of informative training samples from majority class data. To validate our proposed approach, we have applied it to data from H Bank's non-external auditing companies in Korea, and compared the performances of the classifiers with the proposed under-sampling and random sampling data. The empirical results show that the proposed under-sampling approach generally improves the accuracy of classifiers, such as logistic regression, discriminant analysis, decision tree, and support vector machines. They also show that the proposed under-sampling approach reduces the risk of false negative errors, which lead to higher misclassification costs.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.10a
• /
• pp.47-52
• /
• 2003

지금까지의 선형 최적화에 대한 연구는 고전적인 최적화 기법인 비선형계획법과 유동해석법을 중심으로 생물의 진화 알고리즘을 바탕으로 한 유전자 알고리즘과 인공지능에 기초를 둔 신경망이론 등이 이용되어 왔다. 또한 최근 컴퓨터의 성능이 급속도로 향상됨에 따라 전산유체역학에 기초한 시뮬레이션 평가기법도 사용되고 있다. 본 논문에서는 유전자 알고리즘을 이용한 선형 최적화 방법을 제시하였다. 그리고 광역 최적해의 효과적인 검색과 빠른 접근을 위한 방법으로 네트워크 시스템을 기반으로 한 병렬분산 유전자 알고리즘 시스템(PDGAS)을 개발하였으며 그 성능을 기존의 진화 알고리즘과 비교${\cdot}$분석함으로써 선형 최적화의 가능성을 확인하였다.