• Korean Journal of Weed Science
• /
• v.12 no.2
• /
• pp.144-157
• /
• 1992

The study was conducted to compare the interprete methods and examine the feasibility of mixture use of oxyfluorfen and bensulfuron in controlling principal Paddy weeds, annuals and perennials. Application ratio of both chemicals were obtained from the combinations of 5 levels(0, 5, 10, 15, 20 g ai/ha) of each chemicals, respectively. All the treatments were applied at 5 days after transplanting and water was maintained at 3.0cm in depth. Shoot fresh-weight of weeds was assessed at 35 days after treatments. Data obtained was analysed by Colby, Isobole, Calculus, Regression and EQM method, respectively. The results from the analysis of variance on the principal weeds treated with oxyfluorfen and bensulfuron showed significant interactions at 1% level on both Echinochloa crus-galli and Eleocharis Kuroguwai, and total species at 0.5% level on both Potamogeton distinctus and Cyperus serotinus, but non significant on Scirpus juncoides and Sagittaria pygmaea. Thereafter, the results of the models applied to Echinochloa crus-galli, Eleocharis kuroguwai and total species were as follows ; 1. The Colby method gave values nearly identical to regression estimate method (both multiplicative models) as provided by Akobundu et al. The Colby method and Regression method indicated synergistic toward Echinochloa curs-galli, and total species, but antagonistic toward Eleocharis kuroguwai. 2. The Isobole method shows synergism on Echinochloa crus-galli at $ID_{50}$, and total species at $ID_{60}$ on Eleochari kuroguwai. 3. The Calculus method gave positive signs for the first differentiation and negative signs for the second differentiation except for some rates on Echinochloa crus-galli and total species, but reverse on Eleocharis kuroguwai. These result does not agree with the observed values. 4. ${\theta}$ value from the EQM method was greater than one at all combinations. This result was quite different from those of other methods. 5. The various models did not show the same results, but mixture of oxyfluorfen and bensulfuron tend to have synergistic effect. Weeding effect also was high. Treatment in terms of two chemical combination was expected to reduce rates, and to enhence weeding efficacy compared with single treatment.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.41-50
• /
• 2021

Cyber Kill Chain is derived from Kill chain of traditional military terms. Kill chain means "a continuous and cyclical process from detection to destruction of military targets requiring destruction, or dividing it into several distinct actions." The kill chain has evolved the existing operational procedures to effectively deal with time-limited emergency targets that require immediate response due to changes in location and increased risk, such as nuclear weapons and missiles. It began with the military concept of incapacitating the attacker's intended purpose by preventing it from functioning at any one stage of the process of reaching it. Thus the basic concept of the cyber kill chain is that the attack performed by a cyber attacker consists of each stage, and the cyber attacker can achieve the attack goal only when each stage is successfully performed, and from a defense point of view, each stage is detailed. It is believed that if a response procedure is prepared and responded, the chain of attacks is broken, and the attack of the attacker can be neutralized or delayed. Also, from the point of view of an attack, if a specific response procedure is prepared at each stage, the chain of attacks can be successful and the target of the attack can be neutralized. The cyber command and control system is a system that is applied to both defense and attack, and should present defensive countermeasures and offensive countermeasures to neutralize the enemy's kill chain during defense, and each step-by-step procedure to neutralize the enemy when attacking. Therefore, thist paper proposed a cyber kill chain model from the perspective of defense and attack of the cyber command and control system, and also researched and presented the threat classification/analysis/prediction framework of the cyber command and control system from the defense aspect

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.864-881
• /
• 2021

Purpose: This study aims is to provide a total care solution preventing disaster based on Big Data and AI technology and to service safety considered by individual situations and various risk characteristics. The purpose is to suggest a method that customized comprehensive index services to prevent and respond to safety accidents for calculating the living safety index that quantitatively represent individual safety levels in relation to daily life safety. Method: In this study, we use method of mixing AHP(Analysis Hierarchy Process) and Likert Scale that extracted from consensus formation model of the expert group. We organize evaluation items that can evaluate life safety prevention services into risk indicators, vulnerability indicators, and prevention indicators. And We made up AHP hierarchical structure according to the AHP decision methodology and proposed a method to calculate relative weights between evaluation criteria through pairwise comparison of each level item. In addition, in consideration of the expansion of life safety prevention services in the future, the Likert scale is used instead of the AHP pair comparison and the weights between individual services are calculated. Result: We obtain result that is weights for life safety prevention services and reflected them in the individual risk index calculated through the artificial intelligence prediction model of life safety prevention services, so the comprehensive index was calculated. Conclusion: In order to apply the implemented model, a test environment consisting of a life safety prevention service app and platform was built, and the efficacy of the function was evaluated based on the user scenario. Through this, the life safety index presented in this study was confirmed to support the golden time for diagnosis, response and prevention of safety risks by comprehensively indication the user's current safety level.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.33 no.2
• /
• pp.49-57
• /
• 2015

The purpose of this study is to provide the visual landscape modelling on Josun royal tombs and surrounding. The visual landscape of traditional heritage is illustrated by the main view points of analysis. This analysis examines limited view points and cannot reflect a reality of environments. Nowadays various equipments and methodologies are developed for the visual landscape research. This study used new tools for analysis which are Sketch up (3D simulation) and mini helicopter (UAV). With those tools, this research examines not only view points of the analysis but also axis views and disincentive environments as a complex analysis. First of all, the research examined 3D modelling for the virtual simulation and drew coordinates and routes for the UAV operating. Secondly, UAV followed this routes and took linear and continuous views that are real scenes. As a result, it drew 3D simulation could illustrate and control the changing of environments such as the forest density and seasonal variations. Thus, comparing both of them shows efficiently landscape analysis. Thirdly, the study compared virtual and real landscape. Using this 3D modelling, this paper able to elaborate heritage environment and surrounding which omitted by view point analysis. Although this study has limitation practice and exercise on the field, the results and suggestions contribute to the various historic heritage managements and conservations. Moreover, it helps to explain the complex and dimensional landscape analysis.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.23-34
• /
• 2019

Recently, the crime that utilizes the digital platform is continuously increasing. About 140,000 cases occurred in 2015 and about 150,000 cases occurred in 2016. Therefore, it is considered that there is a limit handling those online crimes by old-fashioned investigation techniques. Investigators' manual online search and cognitive investigation methods those are broadly used today are not enough to proactively cope with rapid changing civil crimes. In addition, the characteristics of the content that is posted to unspecified users of social media makes investigations more difficult. This study suggests the site-based collection and the Open API among the content web collection methods considering the characteristics of the online media where the infringement crimes occur. Since illegal content is published and deleted quickly, and new words and alterations are generated quickly and variously, it is difficult to recognize them quickly by dictionary-based morphological analysis registered manually. In order to solve this problem, we propose a tokenizing method in the existing dictionary-based morphological analysis through WPM (Word Piece Model), which is a data preprocessing method for quick recognizing and responding to illegal contents posting online infringement crimes. In the analysis of data, the optimal precision is verified through the Vote-based ensemble method by utilizing a classification learning model based on supervised learning for the investigation of illegal contents. This study utilizes a sorting algorithm model centering on illegal multilevel business cases to proactively recognize crimes invading the public economy, and presents an empirical study to effectively deal with social data collection and content investigation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.149-155
• /
• 2020

The Korea Highway Traffic Authority provides statistics that analyze the causes of traffic accidents that occurred since 2015 using the Traffic Accident Analysis System (TAAS). it was reported Through TAAS that the driver's forward carelessness was the main cause of traffic accidents in 2018. As statistics on the cause of traffic accidents, 51.2 percent used mobile phones and watched DMB while driving, 14 percent did not secure safe distance, and 3.6 percent violated their duty to protect pedestrians, representing a total of 68.8 percent. In this paper, we propose a system that has improved the advanced driver assistance system ADAS (Advanced Driver Assistance Systems) by utilizing CNN (Convolutional Neural Network) among the algorithms of Deep Learning. The proposed system learns a model that classifies the movement of the driver's face and eyes using Conv2D techniques which are mainly used for Image processing, while recognizing and detecting objects around the vehicle with cameras attached to the front of the vehicle to recognize the driving environment. Then, using the learned visual steering model and driving environment data, the hazard is classified and detected in three stages, depending on the driver's view and driving environment to assist the driver with the forward and blind spots.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2000.02a
• /
• pp.148-148
• /
• 2000

지금까지 반도체 표면에 대한 연구는 주로 (1000, (111) 표면 등 낮은 밀러 지표를 가진 표면에 대해 이루어져 왔다. 이에 반해 밀러 지표가 높은 Si 면은 불안정하고, 가열하면 다른 표면, 즉 지표가 낮은 면으로 재배열하는 경향이 있는 것으로 알려져 있는데 아직 이들 높은 밀러 지표를 가진 표면에 대한 연구는 미미한 상태이다. 그러나, Si(113)면은 밀러 지표가 높으면서도 안정하기 때문에 Si(113)의 구조를 정확하게 알 수 있다면 밀러 지표가 낮은 Si 표면이 안정한 이유를 이해할 수 있을 것이다. 따라서 본 연구에서는 TOF-CAICISS 장치(Time of Flight - CoAxial Impact Collision Ion Scattering Spectroscopy) 장비와 RHEED(Reflection High Energy Electron Diffrction)를 이용하여 Si(113) 표면의 구조와 Si(113) 표면의 온도에 따른 구조 변화를 관찰하였다. TOF-CAICISS 실험결과를 보면 (3$\times$2)에서 (3$\times$1)으로 상변환하면서 Si(113) 표면에 오각형을 이루는 dimer 원자들과 adatom 원자들간의 높이차가 작아짐을 알 수 있다. RHEED 실험결과와 전산 모사 결과로부터 상온에서 Si(113)(3$\times$2) 구조를 가지다가 45$0^{\circ}C$~50$0^{\circ}C$에서 Si(113) (3$\times$1) 구조로 상변환한다는 것을 알 수 있다. 그러나, 아직 상전이 메카니즘은 명확하게 밝혀지지 않았다. 실험결과를 전산 모사와 비교함으로써 Si(113) 표면에 [33]방향으로 이온빔을 입사시켰을 경우 dabrowski 모델과 Ranke AI 모델이 적합하지 않다는 것을 알 수 있다./TEX>, shower head의 온도는 $65^{\circ}C$로 설정하였다. 증착된 Cu 박막은 SEM, XRD, AFM를 통해 제작된 박막의 특성을 비교.분석하였다. 초기 plasma 처리를 한 경우에는 그림 1에서와 같이 현저히 증가한 초기 구리 입자들이 관측되었으며, 이는 도상 표면에 활성화된 catalytic site의 증가에 기인한다고 보여진다. 이러한 특성은 Cu films의 성장률을 향상시키고, 또한 voids를 줄여 전기적 성질 및 surface morphology를 향상시키는 것으로 나타났다. 결과 필름의 잔류 응력과 biaxial elastic modulus는 필름의 두께가 감소함에 따라 감소하는 경향을 나타냈으며, 같은 두께의 필름인 경우, 식각 깊이에 따른 biaxial elastic modulus 의 변화를 통해 최적의 식각 깊이를 알 수 있었다.도의 값을 나타내었으며 X-선 회절 data로부터 분석한 박막의 변형은 증온도에 따라 7.2%에서 0.04%로 감소하였고 이 이경향은 유전손실은 감소경향과 일치하였다.는 현저하게 향상되었다. 그 원인은 SB power의 인가에 의해 활성화된 precursor 분자들이 큰 에너지를 가지고 기판에 유입되어 치밀한 박막이 형성되었기 때문으로 사료된다.을수 있었다.보았다.다.다양한 기능을 가진 신소재 제조에 있다. 또한 경제적인 측면에서도 고부가 가치의 제품 개발에 따른 새로운 수요 창출과 수익률 향상, 기존의 기능성 안료를 나노(nano)화하여 나노 입자를 제조, 기존의 기능성 안료에 대한 비용 절감 효과등을 유도 할 수 있다. 역시 기술적인 측면에서도 특수소재 개발에 있어 최적의 나노 입자 제어기술 개발 및 나노입자를 기능성 소재로 사용하여 새로운 제품의 제조와 고압 기상 분사기술의 최적화에 의한 기능성 나노 입자 제조 기술을 확립하고 2차 오염 발생원인 유기계 항균제를 무기계 항균제로 대체할 수 있다.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.701-715
• /
• 2021

The drastic advance of recent deep learning technologies is heavily dependent on training datasets which are essential to train models by themselves with less human efforts. In comparison with the work to design deep learning models, preparing datasets is a long haul; at the moment, in the domain of vision intelligent, datasets are still being made by handwork requiring a lot of time and efforts, where workers need to directly make labels on each image usually with GUI-based labeling tools. In this paper, we overview the current status of vision datasets focusing on what datasets are being shared and how they are prepared with various labeling tools. Particularly, in order to relieve the repetitive and tiring labeling work, we present an interactive smart image annotating system with which the annotation work can be transformed from the direct human-only manual labeling to a correction-after-checking by means of a support of automatic labeling. In an experiment, we show that automatic labeling can greatly improve the productivity of datasets especially reducing time and efforts to specify regions of objects found in images. Finally, we discuss critical issues that we faced in the experiment to our annotation system and describe future work to raise the productivity of image datasets creation for accelerating AI technology.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.307-332
• /
• 2022

One of the most intensively conducted research areas in business application study is a bankruptcy prediction model, a representative classification problem related to loan lending, investment decision making, and profitability to financial institutions. Many research demonstrated outstanding performance for bankruptcy prediction models using artificial intelligence techniques. However, since most machine learning algorithms are "black-box," AI has been identified as a prominent research topic for providing users with an explanation. Although there are many different approaches for explanations, this study focuses on explaining a bankruptcy prediction model using a counterfactual example. Users can obtain desired output from the model by using a counterfactual-based explanation, which provides an alternative case. This study introduces a counterfactual generation technique based on a genetic algorithm (GA) that leverages both domain knowledge (i.e., causal feasibility) and feature importance from a black-box model along with other critical counterfactual variables, including proximity, distribution, and sparsity. The proposed method was evaluated quantitatively and qualitatively to measure the quality and the validity.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1215-1225
• /
• 2021

Although Artificial Intelligence (AI) techniques have shown impressive performance in various fields, they are vulnerable to adversarial examples which induce misclassification by adding human-imperceptible perturbations to the input. Previous studies to defend the adversarial examples can be classified into three categories: (1) model retraining methods; (2) input transformation methods; and (3) adversarial examples detection methods. However, even though the defense methods against adversarial examples have constantly been proposed, there is no research to classify the type of adversarial attack. In this paper, we proposed an adversarial attack family classification method based on dimensionality reduction and clustering. Specifically, after extracting adversarial perturbation from adversarial example, we performed Linear Discriminant Analysis (LDA) to reduce the dimensionality of adversarial perturbation and performed K-means algorithm to classify the type of adversarial attack family. From the experimental results using MNIST dataset and CIFAR-10 dataset, we show that the proposed method can efficiently classify five tyeps of adversarial attack(FGSM, BIM, PGD, DeepFool, C&W). We also show that the proposed method provides good classification performance even in a situation where the legitimate input to the adversarial example is unknown.