• 한국전자통신학회논문지
• /
• 제18권6호
• /
• pp.1269-1276
• /
• 2023

작물 수확량 예측은 토양, 비, 기후, 대기 및 이들의 관계와 같은 다양한 측면으로 인해 다국적 식사와 강력한 수요에 필수적이며, 기후 변화는 농업 생산량에 영향을 미친다. 본 연구에서는 온도, 강수량, 습도 등의 데이터 세트를 운영한다. 현재 연구는 농부와 농업인을 지원하기 위해 다양한 분류기를 사용한 기능 선택에 중점을 두고 있다. 특징 선택 접근법을 활용한 작물 수확량 추정은 96% 정확도를 나타내었다. 특징 선택은 기계학습 모델의 성능에 영향을 미친다. 현재 그래프 분류기의 성능은 81.5%를 나타내며, 특징 선택이 없는 Random Forest 회귀 분석은 78%의 정확도를 나타냈다. 또한, 특징 선택이 없는 의사결정 트리 회귀 분석은 67%의 정확도를 유지하였다. 본 논문은 제시된 10가지 알고리즘을 대상으로 특징 선택 중요성에 대한 실험결과를 나타내었다. 이러한 결과는 작물 분류 연구에 적합한 모델을 선택하는 데 도움이 될 것으로 기대된다.

• Asia pacific journal of information systems
• /
• 제30권3호
• /
• pp.614-635
• /
• 2020

This study aims at understanding gender difference in trust and the related factors affecting the intention to purchase voice speakers VS. VS are one of the innovations that are emerging at a fast pace in the market. Although it seems to be widely embraced by both genders, people do not intend to use them in some cases due to a lack of trust and the rumors circling these types of technologies. Nevertheless, there are particular barriers to the acceptance of VS technology between females and males due to unfamiliarity with the effective components of such technologies. Therefore, assuming that increasing the knowledge-based familiarity with an effective technique is essential for accepting it. So far, only little is known about VS and its concepts to increase the familiarity and, as a consequence, the acceptance of effective technology. Technology adoption in gender has been studied for many years, and there are many general models in the literature describing it. However, having more customized models for emerging technologies upon their features seems necessary. This study is based on Theory of Reasoned Action and trust-based acceptance which provides a background for understanding the relationships between beliefs, attitude, intentions, and subject norms and how it's affecting gender trust in VS. The statistical analysis results indicate that perceived system quality and perceived interaction quality have stronger influences on trust for males, while privacy concern and emotional trust have stronger influences on trust for females with the intention of purchase for both genders. Our study can be beneficial for future research in the areas of Perceived risk and Perceived utility and behavioral intention to use and human-technology interaction and psychology.

• International Journal of Control, Automation, and Systems
• /
• 제1권3호
• /
• pp.321-331
• /
• 2003

Experimental software datasets describing software projects in terms of their complexity and development time have been the subject of intensive modeling. A number of various modeling methodologies and modeling designs have been proposed including such approaches as neural networks, fuzzy, and fuzzy neural network models. In this study, we introduce the concept of the Rule-based fuzzy polynomial neural networks (RFPNN) as a hybrid modeling architecture and discuss its comprehensive design methodology. The development of the RFPNN dwells on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The architecture of the RFPNN results from a synergistic usage of RFNN and PNN. RFNN contribute to the formation of the premise part of the rule-based structure of the RFPNN. The consequence part of the RFPNN is designed using PNN. We discuss two kinds of RFPNN architectures and propose a comprehensive learning algorithm. In particular, it is shown that this network exhibits a dynamic structure. The experimental results include well-known software data such as the NASA dataset concerning software cost estimation and the one describing software modules of the Medical Imaging System (MIS).

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 추계학술발표회 논문집
• /
• pp.181-186
• /
• 2003

As the approach close-range digital photogrammetry has a variety of merits, the application of precision requiting fields is in Increase for its scope expansion. In the meantime, in case of photographic surveying by use of films, a lot of studies on experiment analysis and theoretical forecast models about a change of the exactness as per photographing coordinates have been conducted, but experiments about approach close-range digital photogrammetry are not enough yet. In consequence, this study has made photographing respectively by changing the photographic distance, converging angle, picturing direction by use of Rollei d7 metric and d7 metric$\^$5/ that is a measurement digital camera. And also in order to minimize the errors happened at the relative orientation, we have sorted out the prototype target that the relative orientation is automatically on the programming and have calculated RMSE by carrying out the bundle adjustment. We think that such a study could be used as very important basic data necessary in deriving the optimal photographic conditions by the close-range digital photogrammetry and in judging such a degree.

• 복식문화연구
• /
• 제25권2호
• /
• pp.237-251
• /
• 2017

In this study, causes and consequences of bullying were explored, focusing on victim personality and appearance factors. The research model included the relationships among bullying, important causes of bullying (aggression, cleanliness, and obesity of victims) and consequences of bullying (self-esteem and depression) and was tested through survey data from 594 (194 male and 404 female) middle school students. Data were analyzed using descriptive statistics, confirmatory factor analysis, and path analysis with SPSS and AMOS. In the results of the model tests, victims who are more aggressive, less clean, and more overweight are more likely to be bullied. In addition, adolescents bullied by others tend to have lower self-esteem and more depression. Furthermore, the model comparison was assessed by gender and a difference between the two gender models was found. In the check of critical ratio for difference, it was concluded that the cleanliness of the victim is a more important cause of bullying for male adolescents than for female adolescents. It is meaningful to confirm the effects of the victim's appearance factors on bullying in the literature focusing on personality issues of victims. Educators and counselors may refer to the findings in developing counseling guidelines and manuals to prevent bullying in school.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권3호
• /
• pp.197-203
• /
• 2011

Personal Identifiable Information (PII) is considered information that identifies or can be used to identify, contact, or locate a person to whom such information pertains or that is or might be linked to a natural person directly or indirectly. In order to recognize such data processed within information and communication technologies such as PII, it should be determined at which stage the information identifies, or can be associated with, an individual. For this, there has been ongoing research for privacy protection mechanism to protect PII, which now becomes one of hot issues in the International Standard as privacy framework and privacy reference architecture. Data processing flow models should be developed as an integral component of privacy risk assessments. Such diagrams are also the basis for categorizing PII. The data processing flow may not only show areas where the PII has a certain level of sensitivity or importance and, as a consequence, requires the implementation of stronger safeguarding measures. This paper propose a standard format for satisfying the ISO/IEC 29100 "Privacy Framework" and shows an implementation example for privacy reference architecture implementing privacy controls for the processing of PII in information and communication technology.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.365-371
• /
• 2004

Generally, fracture of a material is influenced by plastic zone size developed near the crack tip. Hence, according to the relative size of plastic zone in the material, the mechanics as a tool for analyzing the fracture process are classified into three kinds, that is, Linear Elastic Fracture Mechanics, Elastic Plastic Fracture Mechanics, Large Deformation Fracture Mechanics. Even though the plastic zone size is such an important parameter, the practical measurement techniques are very limited and the one for in-situ measurement is not virtually available. Therefore, elastic-plastic FEA has been performed to estimate the plastic zone size. In this study, it is noticed that side necking at the surface is a consequence of plastic deformation and lateral contraction and the relation between the plastic zone and side necking is investigated. FEA for modified boundary layer models with finite thickness, various mode mixities $0^{\circ}$, $30^{\circ}$, $60^{\circ}$, $90^{\circ}$ and strain hardening exponent n=3, 10 are performed. The results are presented and the implication regarding to application to experiment is discussed.

• Toxicological Research
• /
• 제17권
• /
• pp.41-45
• /
• 2001

The methods used for risk assessment from exposure to chemicals are well established. in most cases where toxicity other than carcinogenesis is being considered, the standard method relies on establishing the No Observed Adverse Effect Level (NOAEL) in the most sensitive animal toxicity study and using an appropriate safety factor (SF) to determine the exposure which would be associated with an acceptable risk. For carcinogens a different approach is used because it has been argued there is no threshold of effect. Thus mathematical equations are used to extrapolate from the high doses used in ani-mal experiments. These methods have been strongly criticised in recent years on several grounds. The most cogent criticisms are a) the equations are not based on a thorough understanding of the mechanisms of carcinogenesis and b) the outcome of a risk assessment based on such models varies more as a consequence of changes to the assumptions and equation used than it does from the data derived from carcinogenicity experiments. Other criticisms include the absence of any measure of the variance on the risk assessment and the selection of default values that are very conservative. Recent advances in the application of risk assessment emphasise that measures of both the exposure and the hazard should be considered as a distribution of values. The outcome of such a risk assessment provides an estimate of the distribution of the risks.

• Steel and Composite Structures
• /
• 제14권4호
• /
• pp.367-377
• /
• 2013

Damage in structures often leads to failure. Thus it is very important to monitor structures for the occurrence of damage. When damage happens in a structure the consequence is a change in its modal parameters such as natural frequencies and mode shapes. Artificial Neural Networks (ANNs) are inspired by human biological neurons and have been applied for damage identification with varied success. Natural frequencies of a structure have a strong effect on damage and are applied as effective input parameters used to train the ANN in this study. The applicability of ANNs as a powerful tool for predicting the severity of damage in a model steel girder bridge is examined in this study. The data required for the ANNs which are in the form of natural frequencies were obtained from numerical modal analysis. By incorporating the training data, ANNs are capable of producing outputs in terms of damage severity using the first five natural frequencies. It has been demonstrated that an ANN trained only with natural frequency data can determine the severity of damage with a 6.8% error. The results shows that ANNs trained with numerically obtained samples have a strong potential for structural damage identification.

• Earthquakes and Structures
• /
• 제4권2호
• /
• pp.157-179
• /
• 2013

Vulnerability studies on the existing building stock require that a large number of buildings is analyzed to obtain statistically significant evaluations of the seismic performance. Therefore, analytical evaluation methods need to be based on simplified methodologies of analysis which can afford the treatment of a large building population with a reasonable computational effort. Simplified Pushover-Based Earthquake Loss Assessment approach (SP-BELA), where a simplified methodology to identify the structural capacity of the building through the definition of a pushover curve is adopted, was developed on these bases. Main objective of the research work presented in this paper is to validate the simplified methodology implemented in SP-BELA against the results of more sophisticated nonlinear dynamic analyses (NLDAs). The comparison is performed for RC buildings designed only to vertical loads, representative of the "as built" in Italy and in Mediterranean countries with a building stock very similar to the Italian one. In NLDAs the non linear and degrading behaviour, typical of the structures under consideration when subjected to high seismic loads, is evaluated using models able to capture, with adequate accuracy, the non linear behaviour of RC structural elements taking into account stiffness degradation, strength deterioration, and pinching effect. Results show when simplified analyses are in good agreement with NLDAs. As a consequence, unsatisfactory results from simplified analysis are pointed out to address their current applicability limits.