• 한국도로학회논문집
• /
• 제20권3호
• /
• pp.59-64
• /
• 2018

PURPOSES : We propose a parameter-setting-free harmony-search (PSF-HS) algorithm to determine the individual sound power levels of noise sources in the cases of industrial or road noise environment. METHODS :In terms of using methods, we use PSF-HS algorithm because the optimization parameters cannot be fixed through finding the global minimum. RESULTS:We found that the main advantage of the PSF-HS heuristic algorithm is its ability to find the best global solution of individual sound power levels through a nonlinear complex function, even though the parameters of the original harmony-search (HS) algorithm are not fixed. In an industrial and road environment, high noise exposure is harmful, and can cause nonauditory effects that endanger worker and passenger safety. This study proposes the PSF-HS algorithm for determining the PWL of an individual machine (or vehicle), which is a useful technique for industrial (or road) engineers to identify the dominant noise source in the workplace (or road field testing case). CONCLUSIONS : This study focuses on providing an efficient method to determine sound power levels (PWLs) and the dominant noise source while multiple machines (or vehicles) are operating, for comparison with the results of previous research. This paper can extend the state-of-the-art in a heuristic search algorithm to determine the individual PWLs of machines as well as loud machines (or vehicles), based on the parameter-setting-free harmony-search (PSF-HS) algorithm. This algorithm can be applied into determining the dominant noise sources of several vehicles in the cases of road cross sections and congested housing complex.

• 한국지능시스템학회논문지
• /
• 제27권1호
• /
• pp.22-28
• /
• 2017

Convolutional Neural Network(CNN)는 특징 추출과 분류의 두 단계로 나눌 수 있다. 그 중 특징 추출 단계의 커널의 크기, 채널의 수, stride 등의 hyperparameter는 CNN의 구조를 결정할 뿐만 아니라 특징을 추출하는 데에도 영향을 주기 때문에 CNN의 전체적인 성능에도 영향을 준다. 본 논문에서는 Parameter-Setting-Free Harmony Search(PSF-HS) 알고리즘을 이용하여 CNN의 특징 추출 단계에서의 hyperparameter를 최적화 하는 방법을 제안하였다. CNN의 전체 구조를 설정한 뒤 hyperparameter를 변수로 설정하였고 PSF-HS 알고리즘을 적용하여 hyperparameter를 최적화 하였다. 시뮬레이션은 MATLAB을 이용하여 진행하였고 CNN은 mnist 데이터를 이용하여 학습과 테스트를 했다. 총 500번 동안 변수를 업데이트했고 제안하는 방법을 이용하여 구한 CNN 구조 중 가장 높은 정확도를 가지는 구조는 99.28%의 정확도로 mnist 데이터를 분류하는 것을 확인할 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• 제7권1호
• /
• pp.109-114
• /
• 2012

In this paper, we utilize training strategy of hidden Markov model (HMM) to use in versatile issues such as classification of time-series sequential data such as electric transient disturbance problem in power system. For this, an automatic means of optimizing HMMs would be highly desirable, but it raises important issues: model interpretation and complexity control. With this in mind, we explore the possibility of using genetic algorithm (GA) and harmony search (HS) algorithm for optimizing the HMM. GA is flexible to allow incorporating other methods, such as Baum-Welch, within their cycle. Furthermore, operators that alter the structure of HMMs can be designed to simple structures. HS algorithm with parameter-setting free technique is proper for optimizing the parameters of HMM. HS algorithm is flexible so as to allow the elimination of requiring tedious parameter assigning efforts. In this paper, a sequential data analysis simulation is illustrated, and the optimized-HMMs are evaluated. The optimized HMM was capable of classifying a sequential data set for testing compared with the normal HMM.