• 수산해양기술연구
• /
• 제60권1호
• /
• pp.87-99
• /
• 2024

This study deals with the application of an artificial neural network (ANN) model to predict power consumption for utilizing seawater source heat pumps of recirculating aquaculture system. An integrated dynamic simulation model was constructed using the TRNSYS program to obtain input and output data for the ANN model to predict the power consumption of the recirculating aquaculture system with a heat pump system. Data obtained from the TRNSYS program were analyzed using linear regression, and converted into optimal data necessary for the ANN model through normalization. To optimize the ANN-based power consumption prediction model, the hyper parameters of ANN were determined using the Bayesian optimization. ANN simulation results showed that ANN models with optimized hyper parameters exhibited acceptably high predictive accuracy conforming to ASHRAE standards.

• 한국식생활문화학회지
• /
• 제23권1호
• /
• pp.97-104
• /
• 2008

The purpose of this study was to measuring the causal relationships among food involvement, health, mood, convenience, sensory appeal, weight control and vegetable consumption. A total of 290 questionnaires were completed. Structural equation model was used to measure the causal relationships among constructs. Results of the study demonstrated that the structural analysis result for the data also indicated excellent model fit. The effects of food involvement on health, mood, convenience, sensory appeal, weight control and vegetable consumption were statistically significant. As expected, health, mood, sensory appeal and eight control had significant effects on vegetable consumption. Moreover, health, mood, convenience, sensory appeal and weight control played mediating roles in the relationship between food involvement and vegetable consumption. In conclusion, based on structural analysis, a model was proposed of interrelations among food involvement, health, mood, convenience, sensory appeal, weight control and vegetable consumption. It should be noted that the original vegetable consumption model was modified and should, preferably, be alidated in future research. Other variables, such as attitude, subjective norm and perceived behavior control, may be incorporated to form vegetable consumption models that consist of new antecedent and consequence pairs.

• Advances in nano research
• /
• 제14권6호
• /
• pp.527-539
• /
• 2023

Measuring energy burn during intensive combat sport has been a challenging concerns for a long time. In the present article, the energy consumption during combat sports is measured by use of wearable GoBe2 equipped with nanotechnology measuring devices. In this regard, 12 professional combat athletes were asked to wear GoBe2 devices during different sessions of intensive combat exercises. The curves provided by GoBe2 nano-sensor devices are further collected and analyzed for different combat durations. On the other hand, energy consumption in these athlete is calculated using other validated methods to evaluate reliability of GoBe2 wearable devices. Based on the results obtained from these experiments a multi-parameter mathematical model is presented for estimation of combat calorie consumptions. The results show that nanotechnology in these type of sensors could help in estimation of calorie consumption during combat. Moreover, the reliability of using wearable GoBe2 sensors are satisfactory except for some specific conditions. The mathematical model provides a satisfactory results based on athlete physical condition and also duration of the combat with about 8% error margin in the results.

• 유통과학연구
• /
• 제11권10호
• /
• pp.55-62
• /
• 2013

Purpose - The purpose of this study is to suggest a risk factor that significantly explains foreign currency risk premia. In recent years, some studies have found that the performance of the simultaneous consumption risk model improves considerably when tested on foreign currency portfolios, which are constructed based on the international interest rates differentials. However, this paper focuses on the long-run consumption risk factor. In our empirical research, we found that the real excess returns of high interest rate currency portfolios depreciate on average, when the future American long-run consumption growth rate appears low. This makes the high interest rate currency portfolios have relatively high risk premia. Meanwhile, the real excess returns of low interest rate currency portfolios appreciate on average, under the same conditions, which results in relatively low risk premia for these portfolios. Therefore, this long-run consumption risk factor might explain why low interest rate currencies do not appreciate as much as the interest rate differential, and why high interest rate currencies do not depreciate as much as the interest rate differential. Research design, data, methodology - In our explanation, we provide new evidence on the success of long-run consumption risks in currency risk premia by focusing on the long-run consumption risks borne by American representative investors. To uncover the hidden link between exchange rates and long-run consumption growth, we set the eight currency portfolios as our basic assets, which have been built based on the foreign interest rates of eighty countries. As these eight currency portfolios are rebalanced every year, the first group always contains the lowest interest rate currencies, and the last group contains the highest interest rate currencies. Against these basic eight currency portfolios, we estimate the long-run consumption risk model. We use recursive utility framework and the stochastic discount factor that depends on the present value of expected future consumption growth rates. We find that our model is optimized in the two-year period of constructing the durable consumption expectation factor. Our main results surprisingly surpass the performance of the existing benchmark simultaneous consumption model in terms of R², relatively risk aversion coefficient γ, and p-value of J-test. Results - The performance of our model is superior. R², relatively risk aversion coefficient γ, and p-value of J-test of our long-run durable consumption model are 90%, 93%, and 65.5%, respectively, while those of EZ-DCAPM are 87%, 113%, and 62.8%, respectively. Thus, we can speculate that the risk premia in foreign currency markets have been determined by the long-run consumption risk. Conclusions - The aggregate long-run consumption growth risk explains a large part of the average change in the real excess returns of foreign currency portfolios. The real excess returns of high interest rate currency portfolios depreciate on average when American long-run consumption growth rate is low, and the real excess returns of low interest rate currency portfolios appreciate under the same conditions. Thus, the low interest rate currency portfolios allow investors to hedge against aggregate long-run consumption growth risk.

• 한국식생활문화학회지
• /
• 제22권5호
• /
• pp.582-589
• /
• 2007

The purpose of this study was to measure the causal relationships among affective belief, environmental belief, subjective norm, attitude and meat consumption behavior. A total of 318 questionnaires were completed. Structural equation model was used to measure the causal relationships among the constructs. Results of the study demonstrated that the structural analysis result for the data also indicated excellent model fit. The effects of affective belief, environmental belief and subjective norm on attitude were statistically significant. The effects of affective belief, environmental belief and subjective norm on meat consumption were statistically significant. As expected, attitude had a significant effects on behavioral intention. Moreover, attitude played a mediating role in the relationship between affective belief and meat consumption, environmental belief and meat consumption, subjective norm and meat consumption. Consumption played a mediating role in the relationship between attitude and behavioral intention. In conclusion, based on structural analysis, a model was proposed of interrelations among affective belief, environmental belief, subjective norm, attitude, meat consumption and intention. It should be noted that the original model was modified and should, preferably, be validated in future research. Other variables may be incorporated to form models that consist of new antecedent and consequence pairs.

• 한국정보통신학회논문지
• /
• 제25권4호
• /
• pp.603-610
• /
• 2021

본 논문에서는 사용자의 전력소비패턴을 추출하고 사용자의 환경 및 감성을 적용한 최적 소비패턴을 모델링한 후, 이 두 가지의 패턴을 비교 적용하여 사용자의 전력소비행위 변화를 통한 전력의 효율적 사용 방법을 제시한다. 유의미한 소비패턴을 추출하기 위하여 벡터 표준화 및 이진 데이터 변환방법을 사용하고, k-평균 군집화를 적용한 앙상블의 합집합에 대한 학습과 k값에 따른 지지도를 적용하였으며, 최적 전력소비패턴 모델은 상대적 평균 소비량이 적은 앙상블 합집합에 대한 학습 결과를 기준으로 강제 및 감성 제어를 적용하여 생성하였다. 실험을 통하여 전력소비행위 변화 유도대상 추출 시 클러스터의 수와 일치율 간의 상관관계를 파악함으로써, 사용자의 의도에 따라 강제 및 감성 기반의 제어가 가능하도록 클러스터의 수나 크기 조절을 통한 다양한 윈도우에 적용할 수 있음을 검증하였다.

• 전기전자학회논문지
• /
• 제13권3호
• /
• pp.39-46
• /
• 2009

무선 센서 네트워크는 무선 네트워크 기능이 있는 소형 장치로 구성된다. 실제 현장에서 센서 네트워크의 응용 영역을 증가시키기 위해서는 에너지 소모를 최소화 하는 것이 가장 큰 문제이다. 그러므로 센서 네트워크의 평가를 위해서 정확한 에너지 모델이 필요하다. 본 논문에서는 센서 네트워크의 전력 소모를 분석한다. 전력 소모 모델을 개발하기 위해서 TelosB를 기반으로 하는 상용 제품인 Kmote의 전력 특성을 측정한다. 제안한 모델로부터 PIR 센서를 이용하는 인체 감지 응용에서 건전지를 사용하는 센서 노드는 약 6.9개월의 수명을 예상할 수 있다. 이러한 결과를 바탕으로 독거노인 모니터링 시스템에 적용 가능함을 확인하였다.

• Journal of Biosystems Engineering
• /
• 제35권1호
• /
• pp.1-9
• /
• 2010

A mathematical model was developed to predict the fuel consumption rate consumed by agricultural tractors under arbitrary loaded conditions. The model utilizes the measured data on the fuel consumptions at the full load and at the rated engine speed with partial loads, which can easily be obtained from the official OECD tractor test reports. It was found from the analysis of the measured fuel consumption data that the fuel consumptions at two different speeds does not change with power. The model was developed based on this fact and validated with the measured data of the 159 tractor test reports. The fuel consumptions predicted by the model were compared with those measured under the partially loaded conditions specified in the official OECD tractor test code II. The percent errors of the predicted fuel consumptions were in a range from 0.36 to 2.86% which assured that the developed fuel consumption model can be used practically to predict the fuel consumptions at any speed and power combinations. It was also shown that the developed model predicts the fuel consumption rate better than the Grisso's model.

• Advances in Computational Design
• /
• 제7권2호
• /
• pp.113-128
• /
• 2022

Water consumption is strongly affected by numerous factors, such as population, climatic, geographic, and socio-economic factors. Therefore, the implementation of a reliable predictive model of water consumption pattern is challenging task. This study investigates the performance of predictive models based on multi-layer perceptron (MLP), multiple linear regression (MLR), and support vector regression (SVR). To understand the significant factors affecting water consumption, the stepwise regression (SW) procedure is used in MLR to obtain suitable variables. Then, this study also implements three predictive models based on these significant variables (e.g., SWMLR, SWMLP, and SWSVR). Annual data of water consumption in Thailand during 2006 - 2015 were compiled and categorized by provinces and distributors. By comparing the predictive performance of models with all variables, the results demonstrate that the MLP models outperformed the MLR and SVR models. As compared to the models with selected variables, the predictive capability of SWMLP was superior to SWMLR and SWSVR. Therefore, the SWMLP still provided satisfactory results with the minimum number of explanatory variables which in turn reduced the computation time and other resources required while performing the predictive task. It can be concluded that the MLP exhibited the best result and can be utilized as a reliable water demand predictive model for both of all variables and selected variables cases. These findings support important implications and serve as a feasible water consumption predictive model and can be used for water resources management to produce sufficient tap water to meet the demand in each province of Thailand.

• 한국분무공학회지
• /
• 제22권2호
• /
• pp.47-54
• /
• 2017

$CO_2$ emission regulation will be prescribed and main issue in automotive industry. Mostly, vehicle's fuel efficiency deeply related to $CO_2$ emission is regulated by qualified driving test cycle by using chassis dynamometer and exhaust gas analyser. But, real driving fuel consumption rate depends so much on the individual usage profile and where it is being driven: city traffic, road conditions. In this study, vehicle model of fuel consumption rate for ICEV and PHEV was developed through co-simulation with CRUISE model and Simulink based on driving control model. The simulation results of fuel consumption rate were analysed with on-road vehicle data and compared with its official level.