• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.603-605
• /
• 2003

Constructing a geo-spatial database of Graphic Information Systems(GIS) in various applications is suffering from the difficulty of data acquisition, which is labor-intensive and time consuming. In order to provide the spatial data rapidly and accurately, 4S-Van, a prototype mobile mapping system, has been developed. This paper presents a novel approach for an analysis for Mobile Mapping Systems. Furthermore, we discuss the accuracy of measurements using images acquired from the 4S-Van. The first part of this paper introduces accuracies of other mobile mapping systems. Then, we describe main features of the 4S-Van and our proposed method for an analysis accuracies, which can be applicable to other mobile mapping systems. The last part of paper concludes with a summary and our suggestions for implementation of mobile mapping system.

• Journal of Biosystems Engineering
• /
• 제43권4호
• /
• pp.410-419
• /
• 2018

Purpose: CLIMEX, a species distribution modeling tool, includes various types of parameters representing climatic conditions; the estimation of these parameters directly determines the model accuracy. In this study, we investigated the sensitivity of parameters for the climatic suitability calculated by CLIMEX for Metcalfa pruinosa in South Korea. Methods: We first changed 12 parameters and identified the three significant parameters that considerably affected the CLIMEX simulation response. Results: The result indicated that the simulation was highly sensitive to changes in lower optimal temperatures, lower soil moisture thresholds, and cold stress accumulation rate based on the sensitivity index, suggesting that these were the fundamental parameters to be used for fitting the simulation into the actual distribution. Conclusion: Sensitivity analysis is effective for estimating parameter values, and selecting the most important parameters for improving model accuracy.

• Steel and Composite Structures
• /
• 제31권4호
• /
• pp.397-408
• /
• 2019

In this paper, a geometrically nonlinear meshfree analysis of 3D various forms of shell structures using the double director shell theory with finite rotations is proposed. This theory is introduced in the present method to remove the shear correction factor and to improve the accuracy of transverse shear stresses with the consideration of rotational degrees of freedom.The present meshfree method is based on the radial point interpolation method (RPIM) which is employed for the construction of shape functions for a set of nodes distributed in a problem domain. Discrete system of geometrically nonlinear equilibrium equations solved with the Newton-Raphson method is obtained by incorporating these interpolations into the weak form. The accuracy of the proposed method is examined by comparing the present results with the accurate ones available in the literature and good agreements are found.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.157-165
• /
• 2022

As the stock market is affected by various circumstances including economic and political variables, predicting the stock market is considered a still open problem. When combined with corporate financial statement data analysis, which is used as fundamental analysis, and technical analysis with a short data generation cycle, there is a problem that the time domain does not match. Our proposed method, LSTE the operating profit and market outlook of a petrochemical company and estimates the sales and operating profit of the company, it was possible to solve the above-mentioned problems and improve the accuracy of stock price prediction. Extensive experiments on real-world stock data show that our method outperforms the 8.58% relative improvements on average w.r.t. accuracy.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.179-192
• /
• 2023

The widespread use of Cloud Computing, Internet of Things (IoT), and social media in the Information Communication Technology (ICT) field has resulted in continuous and unavoidable cyber-attacks on users and critical infrastructures worldwide. Traditional security measures such as firewalls and encryption systems are not effective in countering these sophisticated cyber-attacks. Therefore, Intrusion Detection and Prevention Systems (IDPS) are necessary to reduce the risk to an absolute minimum. Although IDPSs can detect various types of cyber-attacks with high accuracy, their performance is limited by a high false alarm rate. This study proposes a new technique called Fuzzy Logic - Objective Risk Analysis (FLORA) that can significantly reduce false positive alarm rates and maintain a high level of security against serious cyber-attacks. The FLORA model has a high fuzzy accuracy rate of 90.11% and can predict vulnerabilities with a high level of certainty. It also has a mechanism for monitoring and recording digital forensic evidence which can be used in legal prosecution proceedings in different jurisdictions.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.297-299
• /
• 2021

Text classification is one of the popular tasks in Natural Language Processing (NLP) used to classify text or document applications such as sentiment analysis and email filtering. Nowadays, state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms are the core engine used to perform these classification tasks with high accuracy, and they show satisfying results. This paper conducts a benchmarking performance's analysis of multiple SOTA algorithms on the first known labeled Korean voice phishing dataset called KorCCVi. Experimental results reveal performed on a test set of 366 samples reveal which algorithm performs the best considering the training time and metrics such as accuracy and F1 score.

• 한국항행학회논문지
• /
• 제27권5호
• /
• pp.685-689
• /
• 2023

The proposed system in the study aims to detect forest fires in real-time stream data received from the drone-camera. Recently, the number of wildfires has been increasing, and also the large scaled wildfires are frequent more and more. In order to prevent forest fire damage, many experiments using the drone camera and vision analysis are actively conducted, however there were many challenges, such as network speed, pre-processing, and model performance, to detect forest fires from real-time streaming data of the flying drone. Therefore, this study applied image data processing works to capture five good image frames for vision analysis from whole streaming data and then developed the object detection model based on YOLO_v2. As the result, the classification model performance of forest fire images reached upto 93% of accuracy, and the field test for the model verification detected the forest fire with about 70% accuracy.

• Asia pacific journal of information systems
• /
• 제31권2호
• /
• pp.185-196
• /
• 2021

The paper aims to analyze and predict sales of liquor in the state of Iowa by applying machine learning algorithms to models built for prediction. We have taken recourse of Azure ML and Spark ML for our predictive analysis, which is legacy machine learning (ML) systems and Big Data ML, respectively. We have worked on the Iowa liquor sales dataset comprising of records from 2012 to 2019 in 24 columns and approximately 1.8 million rows. We have concluded by comparing the models with different algorithms applied and their accuracy in predicting the sales using both Azure ML and Spark ML. We find that the Linear Regression model has the highest precision and Decision Forest Regression has the fastest computing time with the sample data set using the legacy Azure ML systems. Decision Tree Regression model in Spark ML has the highest accuracy with the quickest computing time for the entire data set using the Big Data Spark systems.

• 한국측량학회지
• /
• 제28권1호
• /
• pp.65-72
• /
• 2010

본 연구에서는 MMS인 경우 고성능의 중급 IMU가 사용되고 보행자 항법시스템에서는 MEMS형의 저급 IMU가 사용된다고 가정한 후 GPS 신호가 단절되었을 경우 IMU에 의해 생성되는 위치 및 자세 오차를 시뮬레이션을 통하여 계산하였다. 또한 GPS 신호 단절 시에 고도계, 전자나침반 및 2가지 센서를 동시에 이용하는 MultiSensor를 이용하여 중급 및 저급 IMU를 보정하였을 경우의 정확도 향상 효과를 분석하였다. 실험 결과 중급 IMU의 경우 MMS에서 요구되는 3차원 위치오차 정확도가 5m라고 가정할 경우 GPS 단절 시간이 30초가 넘으면 요구 정확도를 만족하지 못하였다. 하지만 GPS 단절 구간에서 고도계 전자나침반 그리고 MultiSensor를 이용하여 IMU 보정을 수행할 경우 약 60초까지 요구정확도를 만족하였다. 또한 고도계 및 전자나침반을 동시에 사용할 경우 고도계에 의한 영향이 더욱 큰 것으로 판단된다 MEMS IMU와 같은 저급 IMU가 사용되는 보행자 항법 시스템의 요구 위치 정확도가 약 20m라고 가정할 경우 4초 이후에는 요구 정확도를 만족하지 못하였으며 자세 오차도 매우 급증하였다. 하지만 GPS 신호 단절시 보조센서를 이용하여 저급 IMU 보정을 수행하였을 경우 약 15초까지 요구 정확도를 만족할수 있을 것으로 시뮬레이션 결과 예측되었으며 또한 중급 IMU 실험과는 반대로 보행자 항법과 같은 속도가 느린 시스템에서 고도계 및 전자나침반 2가지 센서를 동시에 사용할 경우 전자나침반에 의한 영향이 더욱 큰 것으로 나타났다. 본 연구는 GPS 신호 단절이 발생할 수 있는 지역에 대하여 MMS 또는 보행자 항법시스템을 운용할 경우 요구 정확도에 따른 보조센서 통합을 이용하여 정확도를 높이는 자료로써 사용될 수 있을 것으로 예상된다.

• 대한인간공학회지
• /
• 제36권5호
• /
• pp.569-578
• /
• 2017

Objective: The purposes of this experiment are an analysis of accuracy between target force level and subjective rating for the Target Force Level and an analysis of the patterns of subjective rating depending on target force level when there is no feedback from males for analysis. Background: The study of perceived exertion about the static contraction is processed with using among the matching procedure method between contralateral limbs, Exertion vs. Borg CR-10 scale and Exertion vs. %MVC (Maximum Voluntary Contraction). However, when there is no feedback, there is lack of the study on whether the subject can distinguish the subjective rating of the force depending on the target force levels. Method: Total 30 males, healthy subjects are measured the maximum grip strength, MVC, and then, each subject is measured the subjective rating and the accuracy with the random target force level (10, 20, 30, 40, 50, 60, 70, 80, and 90% MVC). Results: In the MVC study, males exerted 256.87N (${\pm}51.33$). In the subjective rating of grip strength increased for each Target Force Level (9 levels), higher subjective rating evaluated (p<0.05). In accuracy examination between target force level and subjective rating of grip strength by each %MVC, 10, 30, 40, 50, 70, 90% target force levels showed accurate strength (p>0.05). However, at 20% target force level, the subjects evaluated less subjective rating of grip strength than the target force (Underestimation), and at 60% and 80% target force level, the subjects evaluated more subjective rating of grip strength than the target force (Overestimation) (p<0.05). Conclusion: In the experiment, the MVC showed 256.87N (${\pm}51.33$) for the male adults and as the subjective rating value increased for each Target Force Level (9 levels), higher subjective rating evaluated (p<0.05). Moreover, the results of the accuracy test between target forces and subjective rating of the subjects showed that most participants rated a fairly accurate assessment of subjective rating of grip strength for Target Force Level (9 levels), except for 20%, 60%, and 80%MVC. Application: This experimental result would be used for basic data for the subjective rating of grip strength pattern by the target force level when the voluntary muscle is contracted.