• 대한기계학회논문집
• /
• 제18권1호
• /
• pp.113-120
• /
• 1994

The dynamic characteristics of turning processes are complex, non-linear and time-varying. Consequently, the conventional techniques based on crisp mathematical model may not guarantee cutting force regulation. This paper presents a fuzzy controller which can regulate cutting force in turning process under varying cutting conditions. The fuzzy control rules are extablished from operator experience and expert knowledge about the process dynamics. Regulation which increases productivity and tool life is achieved by adjusting feedrate according to the variation of cutting conditions. The performance of the proposed controller is evaluated by cutting experiments in the converted conventional lathe. The results of experiments show that the proposed fuzzy controller has a good cutting force regulation capability in spite of the variation of cutting conditions.

• International journal of advanced smart convergence
• /
• 제8권1호
• /
• pp.133-140
• /
• 2019

In this paper, we present an algorithm for adjusting degree of belief for consistency on the evidence dependency network where various sets of evidence support different sets of hypotheses. It is common for experts to assign higher degree of belief to a hypothesis when there is more evidence over the hypothesis. Human expert without knowledge of uncertainty handling may not be able to cope with how evidence is combined to produce the anticipated belief value. Belief in a hypothesis changes as a series of evidence is known to be true. In non-monotonic reasoning environments, the belief retraction method is needed to clearly deal with uncertain situations. We create evidence dependency network from rules and apply the evidence retraction algorithm to refine belief values on the hypothesis set. We also introduce negative belief values to reflect the reverse effect of evidence combination.

• 한국정보기술학회 영문논문지
• /
• 제9권1호
• /
• pp.47-56
• /
• 2019

Treatment for hypertension is basically done through drug administration, which is likely to suffer a number of side effects. Various non-drug treatments are presented to solve this problem. In this paper, we proposed a treatment method through breathing induction known as an effective method during non-drug treatment. This treatment encourages patients to reduce the number of breaths. By reducing the number of breaths, it can lower the patient's sympathetic nerves and relax the muscles, thereby lowering blood pressure. We presented these breathing algorithms that could reduce the number of breaths on the patient's own without expert help, and we enabled patients to train their own breathing techniques through a device that implements these breathing induction algorithms.

• ETRI Journal
• /
• 제46권1호
• /
• pp.48-58
• /
• 2024

This paper presents the development of language tutoring systems for nonnative speakers by leveraging advanced end-to-end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non-native speech, high-performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End-to-end ASR is implemented and enhanced by using diverse non-native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI Peng-Talk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies.

• 대한안전경영과학회지
• /
• 제10권2호
• /
• pp.33-41
• /
• 2008

Rapid spread of the internet has made our everyday life more convenient, however it has brought some problems along with it. Especially, undergraduate student are losing their social ability as they become absorbed in the internet game, act selfishly in the cyber space and lose interest in studying. As a result, they become isolated from their friends and experience difficulty in the relationship with their parents. In this paper, the influence factors of internet game addiction is investigated using the Analytic Hierarchy Process (AHP) and statistics techniques. This study is to define the influence an important factors of internet game addiction using a questionnaire to internet game player and expert group. It is believed that this study will be more receptive to results that include the priority weights of internet game addiction among the addiction group, non-addiction group and expert group.

• 한국정보통신학회논문지
• /
• 제10권1호
• /
• pp.212-219
• /
• 2006

퍼지 논리 제어기(FLC : Fuzzy Logic Controller)를 사용할 때, 가장 중요한 것은 소속 함수의 범위를 정하는 것과 규칙의 형태를 결정하는 것이다. 소속 함수의 범위나 규칙의 형태는 자금까지 전문가가 임의로 정하는 방법을 사용하였다. 그러나 기존의 방법을 사용하면, 전문가의 주관적인 규칙과 소속 함수가 생성될 수 있고, 소속함수의 경우 최적의 범위를 정확히 예측하기 어려운 단점이 있다. 본 논문에서는 이런 단점을 보완하기 위해, 유전자 알고리즘을 사용함으로써 최적의 소속 함수와 규칙의 형태를 구하려 하였다. 제시하는 방법의 타당성을 검증하기 위해 자동차 주행 제어 문제에 적용시켜 보았다.

• 대한간호학회지
• /
• 제45권3호
• /
• pp.429-438
• /
• 2015

Purpose: This study was conducted to develop key performance indicators (KPIs) for home care nursing (HCN) based on a balanced scorecard, and to construct a performance prediction model of strategic objectives using the Bayesian Belief Network (BBN). Methods: This methodological study included four steps: establishment of KPIs, performance prediction modeling, development of a performance prediction model using BBN, and simulation of a suggested nursing management strategy. An HCN expert group and a staff group participated. The content validity index was analyzed using STATA 13.0, and BBN was analyzed using HUGIN 8.0. Results: We generated a list of KPIs composed of 4 perspectives, 10 strategic objectives, and 31 KPIs. In the validity test of the performance prediction model, the factor with the greatest variance for increasing profit was maximum cost reduction of HCN services. The factor with the smallest variance for increasing profit was a minimum image improvement for HCN. During sensitivity analysis, the probability of the expert group did not affect the sensitivity. Furthermore, simulation of a 10% image improvement predicted the most effective way to increase profit. Conclusion: KPIs of HCN can estimate financial and non-financial performance. The performance prediction model for HCN will be useful to improve performance.

• 대한교통학회지
• /
• 제14권1호
• /
• pp.51-67
• /
• 1996

The optimal path-finding problem becomes complicated when multiple variables are simultaneously considered such as physical route length, degree of congestion, traffic capacity of intersections, number of intersections and lanes, and existence of free ways. Therefore, many researchers in various fields (management science, computer science, applied mathematics, production planning, satellite launching) attempted to solve the problem by ignoring many variables for problem simplification, by developing intelligent algorithms, or by developing high-speed hardware. In this research, an integration of expert system technique and case-based reasoning in high level with a conventional algorithms in lower level was attempted to develop an optimal path-finding system. Early application of experienced driver's knowledge and case data accumulated in case base drastically reduces number of possible combinations of optimal paths by generating promising alternatives and by eliminating non-profitable alternatives. Then, employment of a conventional optimization algorithm provides faster search mechanisms than other methods such as bidirectional algorithm and $A^*$ algorithm. The conclusion obtained from repeated laboratory experiments with real traffic data in Seoul metropolitan area shows that the integrated approach to finding optimal paths with consideration of various real world constraints provides reasonable solution in a faster way than others.

• 소성∙가공
• /
• 제6권5호
• /
• pp.446-455
• /
• 1997

A Combined extrusion operation consists of forward and backward extrusion forming and it is possible to make the process be simple by employing it. But the metal flow pattern induced by the operation is hard to analyze accurately because the flows are non-steady, which have at least two directions dependent upon each other. So engineers in the industrial factories had conducted the two extrusion operations separately. A new process was designed by the industrial expert for forming of an alu-minum preform using the combined extrusion operation. In this study, experiments and finite element analysis was carried out to determine the process parameters. Through the preliminary experiment, it was shown that warm forming condition was more desirable than cold or hot ones. And optimal shape of initial billet could be also determined. From the compatibility test, bonde-lube was chosen as the optimal lubricant and 20$0^{\circ}C$ as the material temperature by the inspection of micro-structure. The operation was simulated by the rigid-plastic finite element method to examine the metal flow. Disap-pearing of dead metal zone was observed as the punch fell down and desirable shape was obtained from the one operation. As a result of this study, 7 operations could be reduced and 225% of material saved.

• 제어로봇시스템학회논문지
• /
• 제2권3호
• /
• pp.236-241
• /
• 1996

This paper presents a new eddy current testing system for inspecting tubes of steam generator in nuclear power plant. The proposed system adopted embedded expert system concept to automate tasks of the inspection such as inspection planning and flaw signal interpretation, and integrated all the tasks into a client/server type computing architecture using database management system. Therefore, human factor errors occurred during inspection could be minimized and the inspection data could be transferred in real-time. As a result, we can increase the level of inspection confidence and the productivity of a personal inspector. A prototype of the proposed system has been developed for 5 years and the test operation has been performed in domestic nuclear power plants.