• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 추계학술대회논문집
• /
• pp.796-801
• /
• 2000

The monitoring and diagnostics of the rotating machinery have been received considerable attention for many years. The objectives are to classify the machinery condition and to find out the cause of abnormal condition. This paper describes a signal classification method for diagnosing the rotating machinery using the artificial neural network and the wavelet transform. In order to extract salient features, the wavelet transform are used from primary noise signals. Since the wavelet transform decomposes raw time-waveform signals into two respective parts in the time space and frequency domain, more and better features can be obtained easier than time-waveform analysis. In the training phase for classification, self-organizing feature map(SOFM) and learning vector quantization(LVQ) are applied, and the accuracies of them are compared with each other. This paper is focused on the development of an advanced signal classifier to automatise the vibration signal pattern recognition. This method is verified by small reciprocating compressors, for refrigerator and normal and abnormal conditions are classified with high flexibility and reliability.

• 한국유기농업학회지
• /
• 제31권4호
• /
• pp.291-307
• /
• 2023

Medicinal crops are the most representative input among agricultural products for biomaterials. The actual situation of how medicinal crops are used as inputs in the downstream industry is analyzed, and the input demand function of medicinal crops is quantitatively estimated. The proportions of intermediate demand and final demand in the total production of medicinal crops were 52.1% and 47.9% in 1995, but changed to 74% and 26% in 2019, with the proportion of intermediate demand accounting for approximately increased by 3 times. Estimation results of the demand function for medicinal crops in the medicine industry show, a 1% increase in the production of medicine is found to increase the demand for medicinal crops by 0.3369%. If the production of health functional foods increase by 1%, the demand for medicinal crops is expected to increase by 0.6221%. It is also found that a 1% increase in the amount of cosmetic production would increase in the demand for medicinal crops by 0.3932%. This indicates that market expansion in downstream industries can have a significant impact on agricultural products for biomaterials.

• 펄프종이기술
• /
• 제44권6호
• /
• pp.1-8
• /
• 2012

This study was carried out to explore optimum use of the products generated from the National Forest Management Operation (NFMO) as raw materials for kraft pulp. First of all, different wood species from NFMO were randomly mixed, and then they were used to make kraft pulp under the specified condition. All kraft pulps made from the mixed species displayed equal physical properties to those from foreign wood chips used in Moorim P&P Co. Ltd. For optical properties, most of the unbleached pulps had high brightness but the pulp made from wood species containing chestnut tree showed the lowest brightness due to its high kappa number. Finally, the products from NFMO had little negative effects on the properties of kraft pulps. This means that they could be used as complementary raw materials for kraft pulps with foreign wood chips.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권4호
• /
• pp.268-276
• /
• 2005

본 논문은 최적 통신 걸침 나무 문제(Optimum Communication Spanning Tree Problem OCST)를 다룬다. 일반적으로, OCST문제는 WP-hard 문제로 알려져 있으며 최근에 Papadimitriou 와 Yannakakis에 의해서 MAX SNP-hard로 밝혀졌다. 그럼에도 불구하고 OCST 문제를 해결하기 위한 기존의 주된 접근법은 polynomial time 알고리즘들 이었다. 본 논문에서는 OCST 문제를 해결하기 위한 진화 알고리즘을 소개한다. 특히, 진화 알고리즘을 어떤 문제에 적용할 때 가장 우선적으로 고려되어야 하는 사항은 해를 어떻게 표현할 것인가 하는 표현법(representation)에 관한 것이다. 따라서 본 논문에서는 기존에 차수 제약 걸침 나무 문제를 해결하기 위해 제안한 표현법의 단점을 개선하는 새로운 표현법을 제안하고 이 표현법을 이용해서 트리(tree)를 만들어 내는 decoding 방법 또한 소개한다. 그리고 제안하는 해 표현법에 맞는 유전 연산자를 찾기 위해 네트워크의 정보 및 부모세대가 지닌 유전 정보를 이용하는 3가지 방법을 실험하였다. 결론적으로, 다양한 실험을 통해서 제안하는 방법이 기존의 방법에 비해 우수한 결과를 보여 준다는 것을 확인할 수 있었다.

• 생물정신의학
• /
• 제12권2호
• /
• pp.165-172
• /
• 2005

Objectives:The purpose of this study is to 1) conduct a discrimination analysis of schizophrenia and bipolar affective disorder using MMPI profile through artificial neural network analysis and logistic regression analysis, 2) to make a comparison between advantages and disadvantages of the two methods, and 3) to demonstrate the usefulness of artificial neural network analysis of psychiatric data. Procedure:The MMPI profiles for 181 schizophrenia and bipolar affective disorder patients were selected. Of these profiles, 50 were randomly placed in the learning group and the remaining 131 were placed in the validation group. The artificial neural network was trained using the profiles of the learning group and the 131 profiles of the validation group were analyzed. A logistic regression analysis was then conducted in a similar manner. The results of the two analyses were compared and contrasted using sensitivity, specificity, ROC curves, and kappa index. Results:Logistic regression analysis and artificial neural network analysis both exhibited satisfactory discriminating ability at Kappa index of greater than 0.4. The comparison of the two methods revealed artificial neural network analysis is superior to logistic regression analysis in its discriminating capacity, displaying higher values of Kappa index, specificity, and AUC(Area Under the Curve) of ROC curve than those of logistic regression analysis. Conclusion:Artificial neural network analysis is a new tool whose frequency of use has been increasing for its superiority in nonlinear applications. However, it does possess insufficiencies such as difficulties in understanding the relationship between dependent and independent variables. Nevertheless, when used in conjunction with other analysis tools which supplement it, such as the logistic regression analysis, it may serve as a powerful tool for psychiatric data analysis.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.795-797
• /
• 2005

During the past few years, various traffic-flow forecasting models, i.e. an ARIMA, an ANN, and so on, have been developed to predict more accurate traffic flow. However, these models analyze historical data in an attempt to predict future value of a variable of interest. They make use of the following basic strategy. Past data are analyzed in order to identify a pattern that can be used to describe them. Then this pattern is extrapolated, or extended, into the future in order to make forecasts. This strategy rests on the assumption that the pattern that has been identified will continue into the future. So ARIMA or ANN models with its traditional architecture cannot be expected to give good predictions unless this assumption is valid; The statistical models in particular, the time series models are deficient in the sense that they merely extrapolate past patterns in the data without reflecting the expected irregular and infrequent future events Also forecasting power of a single model is limited to its accurate. In this paper, we compared with an ANN model and ARIMA model and tried to combine an ARIMA model and ANN model for obtaining a better forecasting performance. In addition to combining two models, we also introduced judgmental adjustment technique. Our approach can improve the forecasting power in traffic flow. To validate our model, we have compared the performance with other models. Finally we prove that the proposed model, i.e. ARIMA + ANN + Judgmental Adjustment, is superior to the other model.

• 한국수산과학회지
• /
• 제2권1호
• /
• pp.1-15
• /
• 1969

Pagurus lanuginosus do Haan의 유생을 실험실에서 사육하며 glaucothoe기까지의 발생을 관찰 연구하였다. 1) P. lanuginosus는 4기의 Zoea기와 1기의 glaucothoe기의 유생기를 가졌다. 2) 평균 수온 $13.6^{\circ}C$와 평균 염분농도 $33.67\%_{\circ}$의 사육조건에서 알에서 부화한 zoea유생은 31-32일 후에 glaucothoe 유생으로 변태 발생했다, 3) 각 zoea기의 평균기간은 7-9일이었다. 4) zoea 유생의 가장 독특한 형태적 특징의 하나로 미선(telson)의 말만에 3쌍의 들기(1쌍의 털과 6쌍의 침)를 가지며 그 돌기의 수와 모양은 전 zoea기 동안에 변함이 없다. 5) zoea 유생의 제2 촉각의 외지의 내변에는 5개의 우상모가 나 있다. 6) glaucothoe 유생의 telson 말단에는 3쌍의 우상모가 나 있다. 7) glaucothoe 유생은 안병극을 갖지 않는다.

• 펄프종이기술
• /
• 제44권5호
• /
• pp.63-71
• /
• 2012

This study was carried out to investigate pulping properties of the forest biomass arising from the national forest management operation. The forest biomass was collected and classified into many groups according to their species and age. After the chips were made from the forest biomass, the measurement of chip size and chemical analysis were performed. To make the pulps from the forest biomass, the kraft pulping was applied and thereafter the physical and optical properties of kraft pulps were measured. The pulp fibers from the forest biomass had the similar mean fiber length, but their properties became different according to wood species and ages. Differently from the other species, kraft pulps from chestnut wood had the highest kappa number. Acacia, paulownia and chestnut woods made kraft pulps with lower tensile strength and brightness than the others. It could be concluded that acacia, paulownia and chestnut woods must be screened out in order to make a good quality of kraft pulps while being collected during Forest Management Operation.

• 동의생리병리학회지
• /
• 제17권5호
• /
• pp.1141-1146
• /
• 2003

In order to investigate different and original theories on pathology of eyes from the past main etiology of fire and heat, two texts of Si-sheng-xin-yuan written by Huang Yuan Yu and Eui-gam-jung-ma written by Lee Gyu Jun are selected and analysed in terms of pathology and prescription. Huang explained that diseases of the eyes are usually born of functional disorders of spleen and stomach(脾胃升降失調) accompanied with turbidity change of energy and blood(氣血淸濁變化). In the meantime, Lee described that the diseases are made from disorders of activities of essence, spirit, energy and blood stored in 5 viscera. So following them, the main point of treatment for the diseases of eyes is to restore and clarify the stagnated gastrointestinal(GI) function, or to supply the clear essence and blood to eyes respectively. Also they have same opinions that the fire and heat are the secondary symptoms of the optical diseases. Therefore Huang focused on cleaning the phlegm and leaking the moisture of GI tract to treat those symptoms, and Lee emphasized on nourishing essential energy of kidney and liver on the other hand. Although they preferred to use radical therapy than symptomatic one. But it can be deduced that Huang's theory is more positive and direct therapy and Lee's one is more basic but indirect treatment.

• 동력기계공학회지
• /
• 제3권3호
• /
• pp.60-69
• /
• 1999

The noise and vibration sources of rotary compressor for room air-conditioner are pressure pulsation of compression process, cavity resonance of inner space, structural radiation noise of shell and impact noise of discharge valve. Among them, pressure pulsation is very important noise and vibration source. Because it transferred various kinds of noise and vibration like as mentioned above. In this reason, muffler and resonator are used in order to absorb and remove these noises. But an analytical prediction using acoustic analysis does not coincident with the experimental result. The difference between analysis and actual state is due to the assumption of analysis. This paper covered with new concept of muffler design based on the turbulence kinetic energy of flow by using CFD. From this analysis, it is possible to decide the best position of discharge port of muffler. Therefore $2{\sim}3dB$ noise reduction effect is acquired in rotary compressor of 5000 BTU grade. Also new approach of resonator design is suggested. From this study, the characteristics of resonator and surge hole (a kind of resonator without pipe length) are identified. The former is useful for pure tone noise (narrow frequency band), and the latter is effective for broad frequency band. This paper shows that it is very available to use 3 dimensional analysis of resonator in order to predict more exact tuning frequency. The result is proved by a lot of experiments. From combination of fluid analysis and acoustic analysis, up stream position is effective location of resonator concerning turbulence motion of fluid.