• Environmental Engineering Research
• /
• 제22권2호
• /
• pp.175-185
• /
• 2017

As the energy and environmental problems are increasingly severe, researches about carbon dioxide emissions has aroused widespread concern. The accurate prediction of carbon dioxide emissions is essential for carbon emissions controlling. In this paper, we analyze the relationship between carbon dioxide emissions and influencing factors in a comprehensive way through correlation analysis and regression analysis, achieving the effective screening of key factors from 16 preliminary selected factors including GDP, total population, total energy consumption, power generation, steel production coal consumption, private owned automobile quantity, etc. Then fruit fly algorithm is used to optimize the parameters of least squares support vector machine. And the optimized model is used for prediction, overcoming the blindness of parameter selection in least squares support vector machine and maximizing the training speed and global searching ability accordingly. The results show that the prediction accuracy of carbon dioxide emissions is improved effectively. Besides, we conclude economic and environmental policy implications on the basis of analysis and calculation.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 공동추계학술대회
• /
• pp.516-525
• /
• 2005

Case-based reasoning (CBR) has been widely used in various areas due to its convenience and strength in complex problem solving. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. Most prior studies have tried to optimize the weights of the features or selection process of appropriate instances. But, these approaches have been performed independently until now. Simultaneous optimization of these components may lead to better performance than in naive models. In particular, there have been few attempts to simultaneously optimize the weight of the features and selection of the instances for CBR. Here we suggest a simultaneous optimization model of these components using a genetic algorithm (GA). We apply it to a customer classification model which utilizes demographic characteristics of customers as inputs to predict their buying behavior for a specific product. Experimental results show that simultaneously optimized CBR may improve the classification accuracy and outperform various optimized models of CBR as well as other classification models including logistic regression, multiple discriminant analysis, artificial neural networks and support vector machines.

• 웰빙융합연구
• /
• 제6권2호
• /
• pp.27-31
• /
• 2023

Purpose: Establishment of a real-time monitoring system for odor control in traditional markets in Gangwon-do and a system for linking prevention facilities. Research design, data and methodology: Build server and system logic based on data through real-time monitoring device (sensor-based). A temporary data generation program for deep learning is developed to develop a model for odor data. Results: A REST API was developed for using the model prediction service, and a test was performed to find an algorithm with high prediction probability and parameter values optimized for learning. In the deep learning algorithm for AI modeling development, Pandas was used for data analysis and processing, and TensorFlow V2 (keras) was used as the deep learning library. The activation function was swish, the performance of the model was optimized for Adam, the performance was measured with MSE, the model method was Functional API, and the model storage format was Sequential API (LSTM)/HDF5. Conclusions: The developed system has the potential to effectively monitor and manage odors in traditional markets. By utilizing real-time data, the system can provide timely alerts and facilitate preventive measures to control and mitigate odors. The AI modeling component enhances the system's predictive capabilities, allowing for proactive odor management.

• 시스템엔지니어링학술지
• /
• 제7권1호
• /
• pp.43-51
• /
• 2011

SE generally defines approaching ways of conducting identification, verification and integration of an optimized product and process solution to meet customer's needs by leveraging organizational competency in engineering and management. To successfully develop a new product under mass production contract, it is important to efficiently carry out the program by ensuring that three major competencies are secured; core technology, system integration, and program management. For successful implementation of tasks in the three areas, systematic execution is called for, which requires identifying risk factors in advance. In particular, comprehensive risk management role and responsibility is required for program management. Success of a development program is determined by complex elements of human resources, organization culture, and overall competency of an organization in technology and program management, including capability of the program manager. In this paper, a risk management solution is suggested to lead a program to success with a more efficient way through actual risk management by the concept of SE around the above three areas.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2014년도 춘계 학술논문 발표대회
• /
• pp.190-191
• /
• 2014

Recent construction sector integration and fusion technologies in various areas of research and planning systemis being maintained by the system. Past experience of conservative management in this emerging technology-driven business management through the convergence of various technologies and to find synergies to secure the future of construction technology because it is a need. The purpose of this study is builton the basis of technical and Technology Management Contact optimized system for integrated management of the area you want to build.

• 국제학술발표논문집
• /
• The 1th International Conference on Construction Engineering and Project Management
• /
• pp.371-376
• /
• 2005

Administrative works of local governments in Japan always have been led by central government. Local government organizations have gotten used to control of central government, whose organization is divided vertically into divisions. Such organizations as lack of cooperation of each administrative division could not define strategic goal appropriate for their district independently and could not give an efficient and optimized solution to their strategic goal. Under existing management system, it will be difficult for local governments to rapidly adapt to changing society. Under these circumstances, it is necessary for local governments to structure new management system independent on central government's instructions in order to manage appropriately.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2012년 추계학술대회
• /
• pp.121-131
• /
• 2012

This study is an analysis about BOD, COD, SS, T-N, T-P of 4Stage-BNR, MLE + CS(Coagulating Sedimentation), Bio-SAC BNR method of construction for 3 largest sewage treatment plants among 12 sewage treatment plants in Incheon. The purpose of this study is improving the operational effectiveness for Incheon sewage treatment plant by introducing the optimized method for quality of the discharged water.

• 한국산학기술학회논문지
• /
• 제21권10호
• /
• pp.8-15
• /
• 2020

딥러닝을 사용한 예측 방법은 동일한 예측 모델과 파라미터를 사용한다 하더라도 데이터셋의 특성에 따라 결과가 일정하지 않다. 예를 들면, 데이터셋 A에 최적화된 예측 모델 X를 다른 특성을 가진 데이터셋 B에 적용하면 데이터셋 A와 같이 좋은 예측 결과를 기대하기 어렵다. 따라서 높은 정확도를 갖는 예측 모델을 구현하기 위해서는 데이터셋의 성격을 고려하여 예측 모델을 최적화하는 것이 필요하다. 본 논문에서는 하루 대학 캠퍼스 전력사용량을 1시간 단위로 예측하기 위해 데이터셋의 특성이 고려된 예측 모델이 도출되는 일련의 방법을 단계적으로 제시한다. 데이터 전처리 과정을 시작으로, 이상치 제거와 데이터셋 분류 과정 그리고 합성곱 신경망과 장기-단기 기억 신경망이 결합된 알고리즘(CNN-LSTM: Convolutional Neural Networks-Long Short-Term Memory Networks) 기반 하이퍼파라미터 튜닝 과정을 소개한다. 본 논문에서 제안하는 예측 모델은, 각 시간별 24개 포인트에서 2%의 평균 절대비율 오차(MAPE: Mean Absolute Percentage Error)를 보인다. 단순히 예측 알고리즘만을 적용한 모델과는 달리, 단계적 방법을 통해 최적화된 예측 모델을 사용하여 단일 전력 입력 변수만을 사용해서 높은 예측 정확도를 도출한다. 이 예측 모델은 모바일 에너지관리시스템(Energy Management System: EMS) 어플리케이션에 적용되어 관리자나 소비자에게 최적의 전력사용 방안을 제시할 수 있으며 전력 사용 효율 개선에 크게 기여할 것으로 기대된다.

• 한국컴퓨터정보학회논문지
• /
• 제18권12호
• /
• pp.197-205
• /
• 2013

본 연구에서는 동적 임분 생장모델과 Simulated Annealing 휴리스틱 기법을 적용하여 최적의 산림시업체계를 도출하기 위한 임분탄소최적화 프로그램을 개발하였다. SA 휴리스틱 알고리즘은 다양한 경영목표를 다룰 때 비교적 짧은 시간 내에 만족할만한 수준의 경영안을 제공할 수 있는 최적화 기법으로서, 더 이상 최적해를 찾지 못하고 목표 값이 어떤 일정한 값(Local Optimum)에 계속 머무는 현상을 해결하기 위해 열균형 테스트를 이용하고 있다. 열균형 테스트에 적용되는 온도저감율 파라미터 값이 최적화 프로세스의 목적함수 값과 반복횟수에 미치는 영향을 분석하기 위해 본 연구에서는 온도저감율에 따른 민감도 분석을 실시하였다. 개발된 프로그램을 이용하여 기존의 산림경영에 주로 적용되고 있는 시업체계(베이스라인), 목재수확량 최대와 탄소저장량 최대의 3가지 산림시업 시나리오에 대해 비교 분석을 한 결과, 목재수확량 최대를 목표로 한 시나리오가 3개 시나리오 가운데 목재수확량이 가장 높은 것으로 나타났으며, 또한 탄소저장량을 최대로 하는 시나리오가 탄소저장량이 가장 높은 것으로 나타나, 본 연구에서 개발된 프로그램이 최적화된 결과를 도출하는 것으로 판단됐다. 온도저감율 파라미터 값에 대한 민감도 분석에서는 온도저감율에 따라 목적함수의 최적 값과 최적화 프로세스 반복횟수가 뚜렷한 영향을 받는 것으로 나타났다. 본 연구를 통해 개발된 임분탄소 최적화 프로그램은 앞으로 우리나라 산림의 탄소 최적화 시업체계 개발에 활용 될 것으로 기대된다.

• Journal of Construction Engineering and Project Management
• /
• 제4권3호
• /
• pp.47-52
• /
• 2014

In the last decades, Facility Management (FM) has established itself as a key building service factor.FM includes supporting services and organizing functions essential for maintaining, operating and managing physical component and material. The purpose of the paper is to develop an economical analysis for building facilities management during its service life based on limited cost. This method helps to facilities managers and engineers to make better decisions for reducing of facilities assessment costs and increasing the facilities' service life. This paper presents the preliminary development of a model involves three stages process namely data collection, economic computation and economic process optimization. This process was tested for fiberglass doors example in a building interior and exterior system. If executives can manage essential points effectively and make decisions according to a key performance index, cost can be optimized and safety can be enhanced for installation building.