• International Journal of Highway Engineering
• /
• v.20 no.3
• /
• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2017

The Convolutional Neural Network(CNN) can be divided into two stages: feature extraction and classification. The hyperparameters such as kernel size, number of channels, and stride in the feature extraction step affect the overall performance of CNN as well as determining the structure of CNN. In this paper, we propose a method to optimize the hyperparameter in CNN feature extraction stage using Parameter-Setting-Free Harmony Search (PSF-HS) algorithm. After setting the overall structure of CNN, hyperparameter was set as a variable and the hyperparameter was optimized by applying PSF-HS algorithm. The simulation was conducted using MATLAB, and CNN learned and tested using mnist data. We update the parameters for a total of 500 times, and it is confirmed that the structure with the highest accuracy among the CNN structures obtained by the proposed method classifies the mnist data with an accuracy of 99.28%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.209-209
• /
• 2015

상수도 관망은 대표적인 사회기반시설로 수원으로부터 수용가에 이르기까지 안정적으로 유량을 공급하는 것을 목표로 한다. 상수도 관망의 최적설계는 요구되는 절점의 수압, 관로의 유속 등 수리학적 제약조건을 만족시키는 범위 안에서 비용을 최소화하는 설계안을 얻어내는 것을 목표로 시작하였다. 하지만 비용만을 고려한 과거의 상수도 관망 최적설계는 미래의 불확실한 조건에 매우 취약하고, 사용자의 다양한 요구를 충족시키지 못한다. 이 때문에 현대의 상수도 관망의 설계시 다양한 설계인자의 고려와 함께 효율적인 최적설계기법 적용의 필요성이 대두되고 있다. 따라서 본 연구에서는 상수도 관망 최적설계에 다양한 설계인자를 동시에 고려하기 위해 다목적 최적 설계기법인 Multi-objective Harmony Search 알고리즘을 적용하였다. 또한 다목적 최적설계의 효율성 증대를 위하여 매개변수 자동보정 기법 중 하나인 Parameter-Setting-Free (PSF) 기법(Geem and Sim, 2010)을 사용하였다. PSF 기법은 최적화 알고리즘의 매개변수 설정의 번거로움을 없애고, 반복수행을 통한 해 탐색이 진행됨에 따라 가장 효율적으로 작용하는 매개변수를 자동으로 설정하여 탐색효율을 강화하도록 고안된 기법이다. 본 연구에서는 제안된 기법을 실제 상수도관망의 최적설계에 적용하였고 그 결과를 분석하였다. 그 결과 제안된 기법을 통해 관망의 비용을 포함한 다양한 설계인자를 동시에 만족시키는 최적설계안을 효과적으로 도출 할 수 있었으며, 매개변수 자동보정 기법의 적용을 통해 해 탐색의 효율성과 편의성을 향상시킬 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.1
• /
• 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.

• Investigative Magnetic Resonance Imaging
• /
• v.24 no.3
• /
• pp.123-131
• /
• 2020

Purpose: Joint label fusion (JLF) is a popular multi-atlas-based segmentation algorithm, which compensates for dependent errors that may exist between atlases. However, in order to get good segmentation results, it is very important to set the several free parameters of the algorithm to optimal values. In this study, we first investigate the feasibility of a JLF algorithm for prostate segmentation in MR images, and then suggest the optimal set of parameters for the automatic prostate segmentation by validating the results of each parameter combination. Materials and Methods: We acquired T2-weighted prostate MR images from 20 normal heathy volunteers and did a series of cross validations for every set of parameters of JLF. In each case, the atlases were rigidly registered for the target image. Then, we calculated their voting weights for label fusion from each combination of JLF's parameters (r_pxy, r_pz, r_sxy, r_sz, β). We evaluated the segmentation performances by five validation metrics of the Prostate MR Image Segmentation challenge. Results: As the number of voxels participating in the voting weight calculation and the number of referenced atlases is increased, the overall segmentation performance is gradually improved. The JLF algorithm showed the best results for dice similarity coefficient, 0.8495 ± 0.0392; relative volume difference, 15.2353 ± 17.2350; absolute relative volume difference, 18.8710 ± 13.1546; 95% Hausdorff distance, 7.2366 ± 1.8502; and average boundary distance, 2.2107 ± 0.4972; in parameters of r_pxy = 10, r_pz = 1, r_sxy = 3, r_sz = 1, and β = 3. Conclusion: The evaluated results showed the feasibility of the JLF algorithm for automatic segmentation of prostate MRI. This empirical analysis of segmentation results by label fusion allows for the appropriate setting of parameters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.2
• /
• pp.369-377
• /
• 2008

Though the Hough transform(HT) is a well-known method for detecting analytical shape represented by a number of free parameters, the basic property of the HT, the one-to-many mapping from an image spare to a Hough space, causes the innate problem, the sensitivity to noise. This basic problem also deteriorates the quality of detected lines and makes the detected line deviated from the real one or generates some bogus, multiple lines where only one real line exists. The size of Hough space also affects the quality of detected lines. In this paper, we analyzed the line distortions in the traditional Hough transform and showed that the distortions are relieved in the edge strength Hough transform(ESHT), which is a modified HT. However the usage of expanded edge and edge strength in ESHT can cause some new line distortions which do not exist in the HT. These new ones can be solved by a proper setting of decreasing and broadening parameter values and the optimal values can be determined only by some pre-determined values. We also illustrated several examples to show the distortion-decreasing property of ESHT.