Earticle

An active contour model has been used to detect the edges in a still image. In order to apply the active contour model to edge detection, the energy function which consists of internal, external and image energies should be defined. After defining the energy function, the edge of an object is detected through minimization of the value of the energy function. In this paper, the modified internal energy function is proposed to improve the convergence of the energy function when the active contour model is applied to the tracking of deformable objects using the greedy algorithm. In order to show the performance of the proposed energy function, experiments were carried out for the still and animated images.

Objective: This study was conducted to analyze the effect of wearable Electromyography-controlled functional electrical stimulation (EMG-controlled FES) System on Gait Function and cardiopulmonary metabolic efficiency during walking in older adults. Design: Cross-section study Methods: Total 22 older adult participants suitable to selection criteria of this study participated in this study. The EMG-controlled FES System, which functions as a wearable physical activity assist FES system was used. All participations performed randomly assigned two conditions (Non-FES assist [NFA], FES assist [FA]) of walking. In all conditions, spatio-temporal parameters and kinematics and kinetics parameters during walking was collected via 3D motion capture system and 6 minutes walking test (6MWT) and metabolic cost during walking and stairs climbing was collected via a portable metabolic device (COSMED K5, COSMED Srl, Roma, Italy). Results: In Spatio-temporal parameters aspects, The EMG-controlled FES system significantly improved gait functions measurements of older adults with sarcopenia at walking in comparison to the NFA condition (P<0.05). Hip, knee and ankle joint range of motion increased at walking in FA condition compared to the NFA condition (P<0.05). In the FA condition, moment and ground reaction force was changed like normal gait during walking of older adults in comparison to the NFA condition (P<0.05). The EMG-controlled FES system significantly reduced net cardiopulmonary metabolic energy cost, net energy expenditure measurement at stairs climbing (P<0.05). Conclusions: This study demonstrated that EMG-controlled FES is a potentially useful gait-assist system for improving gait function by making joint range of motion and moment properly.

Surface fog coating methods to porous pavements with a polymer, that contains MMA as a main ingredient, are being widely used in Japan and called 'Top-Coat Processes'. They have lots of effects such as to prevention of the pavement void choking, improvement of the water permeability of the pavements and so on. The purpose of this research is to show the characterization of the polymer to optimize the functions of the polymer fog-coat methods. This study focused on the difference of 'wetting' by water among polymers used for the fog coatings, and calculation the surface free energy from the water contact angle on each material. At the end, the water permeability test were conducted using porous asphalt mixtures that were coated with several kinds of polymers. The permeability was also measured on the specimens that were forcibly choked by muddy water and the resistance to choking was compared. It is concluded that the reduction of the surface free energy between water and a polymer improves the life of the permeability functions of porous pavements. Improvement of water permeation capacity and void-blocking controlling effects can be quantitatively evaluated using the interfacial tension ($\gamma$sl) with water for the coating material (high-viscosity asphalt and hardening resin binder). Consequently, the smaller the $\gamma$sl of the coating material the higher the water permeation capacity and void-blocking controlling effects of the porous asphalt pavements.

Background: Thoracic kyphosis leads to the narrowing of the rib cage, compression of the lungs, and reduced mobility, resulting in decreased expansion of the lungs. Purpose: This study investigates the effects of the muscle energy technique and the self-stretching exercise of the pectoralis minor muscle on the pulmonary function of young subjects with kyphosis. Study design: Design Pre-test post-test control group design. Methods: Thoracic kyphosis was determined by adding the angle of the seventh cervical vertebra and the first thoracic vertebra and the angle of the twelfth thoracic vertebra and the first lumbar vertebra. Excessive kyphosis was defined as a curvature measuring more than 40°. For the respiratory function, forced vital capacity (FVC), one-second forced expiratory volume (FEV1), and peak expiratory flow rate were measured using a Pony FX. Then, six sets of the muscle energy technique and the self-stretching exercise were performed, with three sets each for the left and right sides of the body. Each set consisted of 10 repetitions of a 10 s exercise, and 30 s breaks were given between sets. Results: Results showed that the self-stretching exercise reduced the thoracic kyphosis and significantly increased the FVC and FEV1. The muscle energy technique reduced the kyphosis and significantly increased the FVC. Conclusions: The two intervention methods, the muscle energy technique and the self-stretching exercise, can be applied as effective treatment programs to improve the pulmonary function of subjects with thoracic kyphosis.

Purpose: The purpose of this study is to investigate the cardiopulmonary endurance, the energy metabolism and of breathing function in male smoker and nonsmoker in college after graded load exercise using lower cycle ergometer and respiratory measurement device. Methods: For 38 smoker male college students and nonsmoker male college students, an graded load exercise was performed with the use of lower cycle ergometer by increasing 20 watts every 2 minute using ERS 2.0 system and respiratory measurement device for the cardiopulmonary function, energy metabolism and breathing function. Results: Smoker group showed significant differences in maximum oxygen intake, ventilation per minute, and heart rate in cardiopulmonary endurance, and significant differences in body metabolic rate, maximum energy consumption, and anaerobic threshold in energy metabolism. For respiratory function, there was a difference between inhalation pressure and inhalation speed while there was no difference in respiratory function Conclusion: The results showed that smoking negatively would affect aerobic fitness factors including cardiopulmonary endurance and energy metabolism and long-term smoking is expected to aggravate functional factors in male smoking students in the future.

Brain development is a complex process, and stimuli during this devel-opment period may modulate the functional maturation of the brain. It has been shown that environmental stimuli, such as physical activity habits, have a beneficial effect on brain development. Endurance exer-cise and prolonged fasting state are known to improve brain function including cognition. The exact mechanisms of exercise improving brain function are still unknown. However, it can be considered that energy restriction and stressful challenge induced by long-lasting physical ex-ercise might cause direct effect on brain function. Upregulation of brain-derived neurotrophic factor and ketone body caused by exercise might be considered as the mechanism of exercise on brain function. In the present study, we discussed on two main topics: “exercise and BDNF” and “exercise and energy restriction.”

Background: Boron neutron capture therapy (BNCT) is a potential radiation therapy for treating refractory cancers. Measuring the neutron energy spectrum is important to evaluate the biological effect of BNCT. We have developed a novel low-energy neutron spectrometer with a 3He position-sensitive proportional counter. The effectiveness of this spectrometer remained unvalidated due to the inadequate response function. Materials and Methods: The response function of this spectrometer was evaluated by Monte Carlo simulation to perform the validation experiment of this spectrometer. The 3He(n,p)3H reaction rate for each monochromatic neutron (energy range, 0.5 eV–10 keV) was calculated. Numerical experiments were conducted to investigate the performance of this spectrometer. Several estimated values of the energy spectrum were obtained and compared with a calculated energy spectrum at the exit of the epithermal column by the Monte Carlo simulation by preparing several candidates for signals. The Bayesian estimation algorithm was utilized for the estimation. Results and Discussion: The results indicate that the spectrometer and the evaluated response functions can be utilized to measure the energy spectrum of neutrons in the low-energy range. However, the energy spectrum could not be well represented >4 keV due to the poor response function, including uncertainties in response function calculation as well as the poor energy resolution of this detector in the high-energy region. Conclusion: The response function of the low-energy neutron spectrometer for the epithermal energy region can be assessed by the Monte Carlo simulation. The numerical experiments reveal that the effectiveness of this spectrometer can be shown in the range of 0.5 eV.

영상분할 결과는 알고리즘에 관련된 매개변수들에 따라 다르기 때문에 최적 분할을 위하여 시행 착오법이 많이 이용된다. 본 논문에서는 3차원 변량 분석법을 이용하여 영역기반 active contour 방법에 관련된 최적 매개변수들을 결정하는 방법을 제안한다. 3원 변량 분석법에 의해서 추출된 결과와 사용자가 영상에서 직접 그린 결과가 상호 비교된다. 마지막으로 각 매개변수들의 주요 효과와 상호작용 효과를 측정하고 최적 값을 추출하기 위하여 점 추정 및 구간 추정 값을 계산한다. 본 논문에서 제안한 방법은 구간 상수 모델을 대상으로 영상분할시 최적 매개변수들을 추출하는데 큰 도움을 줄 것이다.

The result of imaging segmentation becomes different with the parameters involved in the segmentation algorithms; therefore, the parameters for the optimal segmentation have been found through a try and error. In this paper, we propose the method to find the best values of parameters involved in the area-based active contour method using three-way ANOVA. The segmentation result applied by three-way ANOVA is compared with the optimal segmentation which is drawn by user. We use the global consistency rate for comparing two segmentations. Finally, we estimate the main effects and interactions between each parameter using three-way ANOVA, and then calculate the point and interval estimate to find the best values of three parameters. The proposed method will be a great help to find the optimal parameters before working the motion segmentation using piecewise constant model.

There have been many studies regarding development of autonomous excavation system which is helpful in construction sites where repetitive jobs are necessary. Unfortunately, bucket trajectory planning was excluded from the previous studies. Since, the best use of excavator is to dig efficiently; purpose of this research was set to determine an optimized bucket trajectory in order to get best digging performance. Among infinite ways of digging any given path, criterion for either optimal or efficient bucket moves is required to be established. One method is to adopt work know-how from experienced excavator operator; However the work pattern varies from every worker to worker and it is hard to be analyzed. Thus, other than the work pattern taken from experienced operator, we developed an efficiency model to solve this problem. This paper presents a method to derive a bucket trajectory from optimization theory with empirical CLUB soil model. Path is greatly influenced by physical constraints such as geometry, excavator dimension and excavator workspace. By minimizing a energy function under these constraints, an optimal bucket trajectory could be obtained.

이 연구는 대표적인 면진장치인 납고무베어링(LRB)의 유한요소모델의 신뢰성을 향상시키기 위하여 주재료인 고무의 재료특성에 대하여 연구하였다. 고무는 일반적인 탄성재료와는 달리 대변형, 비선형특성을 가지는 초탄성 재료이다. 본 연구에서는 고무를 초탄성 재료로 가정하고 그의 재료특성을 변형률에너지함수로 표현하여 LRB의 유한요소모델을 개발하였다. 연구를 위하여 여러 변형률에너지함수 중 몇 가지를 선별하고 이를 이용하여 고무의 재료특성을 예측하였다. 변형률에너지함수를 이용하여 결정된 고무의 재료특성과 표준적인 납의 재료특성을 이용하여 LRB의 유한요소모델을 개발하고, 수평방향과 수직방향의 힘-변위 관계를 해석하였다. LRB의 유한요소모델을 통하여 해석으로 예측한 수평과 수직방향 강성을 실험결과와 비교함으로써 개발된 유한요소모델의 적합성을 검증하였다.

The material property of the rubber has been studied in order to improve the reliability of the finite element model of a lead rubber bearing (LRB) which is a typical base isolator. Rubber exhibits elastic behaviour even within the large strain range, unlike the general structural material, and has a hyper-elastic characteristics that shows non-linear relationship between load and deformation. This study represents the mechanical characteristics of the rubber by strain energy function in order to develop a finite element (FE) model of LRB. For the study, several strain energy functions were selected and mechanical properties of the rubber were estimated with the energy functions. A finite element model of LRB has been developed by using material properties of rubber and lead which were identified by stress tests. This study estimated the horizontal and vertical force-displacement relationship with the FE model. The adequacy of the FE model was validated by comparing the analytical results with the experimental data.

본 연구에서는 파랑의 에너지 및 에너지 수송과 관련된 변량들의 계산과 그 비선형효과의 분석을 능률적으로 수행하기 위하여 설계파에 대한 비선형 흐름함수파이론을 도입한다. 흐름함수파이론은 비대칭성 파형을 갖는 실측파와 이론적인 대칭 파형을 갖는 설계파. 두 경우 모두에 사용할 수 있는 이론으로 Dean에 의해 처음 창안되었다. 후에 Dalrymple이 특정한 파고의 조건과 0의 평균해수면 변위의 조건을 만족하도록 하는 두 라그란지 승수를 사용하여 기존의 수치계산 과정을 개량함으로써 수치계산이 좀 더 효율적으로 수행되도록 하였다. 그리고 흐름함수의 계수 (Stream function coeffiicient)들은 본 연구를 위해 개량한 Marquardt algorithm을 사용하여 수치계산된다. 본 연구의 결과로서 평균 위치에너지와 평균 운동에너지, 평균 전에너지의 비선형효과는$L^*/L_O$의 감소와 $H/H_B$의 증가에 한결같이 증가하여 흐름함수이론과 비교하여 선형파이론이 항상 과대평가된다. 군속도와 파장의 비선형효과는 $H/H_B$의 증가에 한결같이 증가하되 선형파이론이 항상 과소평가된다. 마지막으로 평균 전에너지 Flux의 비선형효과는 천해파(shallow-water waves)에 대해서는 선형파이론이 과대평가되고 심해파 (deep-water waves)에 대해서는 선행파이론이 과소평가되는 양면성을 지닌다.

This paper introduces the nonlinear Stream Function Wave Theory for design waves efficiently to compute the wave energy and energy transport quantities and to analyze the effects of nonlinearities on them. The Stream Function Wave Theory was developed by Dean for case of the observed waves with assymmetric wave profiles and of the design waves with symmetric theoretical wave profiles. Dalrymple later improved the computational procedure by adding two Lagrangian constraints so that more efficient convergence of the iterative numerical method to a specified wave height and to a zero mean free surface displacement resulted. And the Stream Function coefficients are computed numerically by the improved Marquardt algorithm developed for this study. As the result of this study the effects of nonlinearities on the wave quantities of the average potential energy density, the average kinetic energy density result in overestimation by linear wave theory compared to the Stream Function Wave Theory and increase monotonically with decreasing $L^*/L_O$ and with increasing $H/H_B$. The effects of nonlinearities on the group velocity and the wavelength quantities result in underestimation by linear wave theory and increase monotonically with increasing $H/H_B$. Finally the effect of nonlinearity on the average total energy flux results in overestimation for shallow water waves and underestimation for deep water waves by linear wave theory.

The blackout occurred in September 2011 showed that it causes extensive damage to the whole society. Especially important facilities like hospitals even suffer worse situations which cause casualty. This lab selected twelve hospitals in Daegu city and inspected the selection of hospitals on power supply installation status, energy load model which we compared to the emergency power standards by a literature search. Considering the current equipment status and management status of the hospital buildings, we offer three suggestions for emergency maintenance functions.

In this study, a bistable energy harvester (BEH) with a piecewise potential function is proposed to improve its energy harvesting performance. A mathematical model of the piecewise BEH (PWBEH) system is established first and a series of numerical simulation are performed, based on the developed model, in order to investigate the nonlinear dynamic behaviors and energy-harvesting performance of the system. The analysis results for the proposed PWBEH system are compared with a conventional BEH (CBEH). The frequency response results show the stiffness-softening interwell motion of the PWBEH, due to the piecewise potential energy function, which is contrary to the stiffness-hardening behavior of the CBEH. Such softening behavior of interwell motion tends to reduce the operating frequency of the BEH, while significantly increasing the output power. This observation indicate that the introduction of the piecewise potential function to a BEH would be beneficial to the system design for enhancing enegy-harvesting performance at the cost of redundant frequency band, which depends on the characteristics of environmental vibration sources.

중국은 1979년 이후 지속적인 경제성장으로 2010년 세계 2대 경제대국으로 부상했지만, 그동 안 환경보존의 중요성에 대한 인식 부족과 느슨한 환경규제로 심각한 오염 문제에 직면하고 있다. 한편, 지속적인 산업고도화의 진전에 따라 중국의 철강산업은 국가 기간산업으로 급속하게 발전해왔다. 특히, 1996년 중국은 세계 최대 철강생산국으로 자리매김했지만, 화석연료 등의 과다소비로 인하여 각종 대량 의 환경오염물질 배출을 초래하기도 하였다. 현재 중국은 세계 최대 철강생산국이기도 하지만 세계 최대 철강소비국이기도 하다. 또한, 중국 철강산업의 에너지 소비구조는 석탄과 코크스가 에너지의 89% 이상 을 차지하기 때문에 CO2 배출은 심각한 환경오염을 더욱 가중시킬 수밖에 없다. 이에 따라 중국은 철강산업의 에너지 절약과 CO2 배출 감축을 위하여 에너지효율성을 향상시키고, 경 쟁력을 유지하는 것은 국가적으로 매우 중요한 문제이다. 따라서 철강산업의 지속가능한 온실가스 감축 목표는 경제적 잠재감축량에 대한 목표설정 이외에는 에너지생산성 증가나 기술효율성 향상을 중심으로 추구하고 있다. 본 연구의 목적은 첫째, 확률변경 초월대수함수를 기반으로 쌍곡선 거리함수(hyperbolic distance function)를 이용하여 중국 철강산업의 에너지효율성을 측정하고, 이 모형에 기초하여 중국 29개 성(省) 과 지역별(동부･중부･서부) 에너지효율성을 비교하는 데 있다. 둘째, 다수의 산출요소를 반영하여 쌍곡 선 거리함수를 결합한 초월대수 확률변경함수(translog stochastic frontier function)를 사용하였다. 특히, 거리함수를 이용하여 녹색생산성을 분해하고 지역간 생산성을 비교하는 동시에 탄소배출 오염 여부를 고려하여 생산성 변화와 녹색생산성 변화를 측정･비교하는 데 있다. 이에 본 연구는 2003년부터 2016년 까지 중국 29개 성의 철강산업을 대상으로 화석에너지 투입, 탄소배출량, 에너지효율성, 생산성을 연계하 여 에너지효율성, 탄소배출을 고려한 녹색생산성, 녹색기술효율성 그리고 기술혁신 변화 등을 측정하였 다. 분석결과에 의하면 첫째, 온실가스 배출량은 철강산업 생산과 유의한 역 U자 형태를 가지며, 또한 자본스톡과 노동 그리고 화석에너지에 대한 사용량을 증가시키면 철강생산을 증가시키지만 효율적 프론 티어로부터 대상평가 성과와의 거리를 확대시키므로 에너지효율성에 부정적으로 영향을 미치는 것으로 나타났다. 둘째, 분석대상 기간 중국 29개 성의 화석에너지효율성은 평균 0.483으로 나타났으며, 매년 화 석에너지효율성은 조금씩 향상되는 것으로 나타났다. 셋째, 중국 철강산업의 녹색생산성을 3개 지역으로 분류하여 평가할 때 동부지역, 중부지역 그리고 서부지역의 녹색생산성은 2004년부터 2016년 기간 동안 평균이 각각 0.821, 0.938, 0.969를 기록하였으며, 모든 지역이 매년 증가하는 추세를 보이고 있다. 그리고 녹색생산성의 향상은 주로 녹색기술효율성의 변화가 아닌 녹색기술의 변화에 기인하는 것으로 나타났다. 본 연구결과를 바탕으로 정책적 시사점을 도출하면 다음과 같다. 철강산업은 많은 환경오염물질을 배 출하고 있는 산업이다. 특히, 철강산업에서 발생하는 이산화탄소 배출량은 전 세계 이산화탄소 배출량의 3.1%, 전체 산업의 15%에 이르고 있다. 최근에는 환경규제가 본격적으로 강화되고 있어서 환경친화적인 설비와 기술을 선택하고 개발하는 것이 철강산업의 중요한 과제로 부상하고 있다. 이제 중국의 철강산업 은 당면한 환경 문제를 극복하지 않고서는 글로벌 경쟁에서 뒤처질 수밖에 없다. 이에 중국 정부는 다른 산업 분야보다 환경규제에 대한 대응과 친환경기술개발에 대한 집중적인 투자가 요구된다.

China has emerged as the world’s second largest economy in 2010 according to continued economic growth since 1979, but has faced serious pollution problems due to lack of awareness of the importance of environmental preservation and loose environmental regulations. On the other hand, China’s iron and steel industry has rapidly developed into a national infrastructure industry as the industrial advancement continues. In particular, in 1996, China was established as the world’s largest iron and steel producer, but caused excessive amounts of environmental pollutants due to excessive consumption of fossil fuels. At present, China is not only the world’s largest iron and steel producer but also the world’s largest iron and steel consumer. In addition, in the energy consumption structure of the Chinese iron and steel industry, since coal and coke account for more than 89% of the energy, the emission is bound to further increase the serious environmental pollution. Accordingly, it is a very important issue in the country to improve energy efficiency and maintain competitiveness to save energy and reduce emissions in the iron and steel industry. Therefore, the goal of the sustainable reduction of greenhouse gases in the steel industry is to focus on increasing energy productivity or improving technical efficiency other than setting targets for economic potential reduction. This paper extends recently developed parametric hyperbolic distance functions to the analysis of energy efficiency for a panel data of 29 provinces in China’s iron and steel industry from 2003-2016, and then decomposes the growth of green total factor productivity into two component measures, namely, energy efficiency change and energy technical change based on the estimated hyperbolic distance functions. We find that firstly, the increase of capital stock, labor and fossil fuel inputs makes industrial output increase significantly. Secondly, the energy efficiency of China’s iron and steel industry was 0.483 on average across the 29 provinces for 2004-2016, and there exists a great dispersion in energy efficiencies across provinces and regions. Thirdly, the growth of green total factor productivity is almost due to the environmental technical change rather than the environmental efficiency change. Moreover, the energy productivity growth in China’s iron and steel industry may be underestimated if CO2 emissions is ignored. Based on the results of this study, the policy implications are as follows. The iron and steel industry is an industry that emits many environmental pollutants. In particular, carbon dioxide emissions from the iron and steel industry account for 3.1% of global carbon dioxide emissions and 15% of the total industry. In recent years, environmental regulations have been strengthened in earnest, so selecting and developing environmentally friendly facilities and technologies is emerging as an important task for the iron and steel industry. Chinese iron and steel industry is now forced to lag behind in global competition without overcoming its immediate environmental problems. Therefore, the Chinese government needs more intensive investment in developing environmentally friendly technologies and responding to environmental regulations than other industries.

The aim of this paper is to develop an efficient and a powerful Matlab based graphical user interface to address the problem of image segmentation. We propose two approaches for segmenting images: An automatic marker controlled watershed segmentation for segmenting an entire image or a scene and a semiautomatic graph cut based segmentation using fixation points. Automatic Watershed segmentation with a Sobel edge detector is used to detect the gradient of an input image resulting in an image less sensitive to noise. To deal with the usual problem of over segmentation using watershed, marker controlled watershed transformation is applied further for segmenting an image. Fixation based graph cut segmentation allows the user to analyze the input image displayed on the screen and specify some hard constraints indicating the object of interest or target object by using the mouse interaction. Experiments are done on the publically available dataset and the results of the supervised evaluation methods are observed to be satisfactory and are demonstrated along with the manually segmented reference image or a ground truth image obtained from segmentation evaluation database

Sky detection is an important problem in computer vision. Generally, the color and gradient of the pixel in sky border change greatly. So, sky in the scene can be detected by measuring the sky border points. In this paper, a new method for sky detection based on border points is proposed, where the border points in each column of image can be detected to complete complex sky region identification in image. Different to the existing sky detection methods, the proposed algorithm is efficient in detecting sky in scenes of complex structure, for example, sky which are separated by buildings or flags. Furthermore, the paper introduced the concept of sky border for the sky detection, which made the proposed scheme effective. The proposed method is able to handle even more complex sky conditions, including a cloudy sky and a sunny sky. Experimental results have proven that the effectiveness of this method.

In this paper, we propose an automatic left ventricle segmentation method in computed tomography angiography (CTA) using separating energy function. First, we smooth the images by applying anisotropic diffusion filter to remove noise. Secondly, the volume of interest (VOI) is detected by using k-means clustering. Thirdly, we divide the left and right heart with split energy function. Finally, we extract only left ventricle from left and right heart with optimizing cost function including orientation term.

홉필드 네트웍은 패턴 매칭과 더불어 최적화 문제를 푸는 도구로 사용될 수 있다. 특히 Zhang과 Ali는 홉필드 네트웍의 노드를 2차원으로 확장하여 최적화 문제를 해결하였다. 잠재적 브랜치의 총합인 노드의 제곱만큼 뉴런이 필요한 Ali 알고리즘은 탐색 네트워크가 커지면 많은 시간이 소요되는 단점이 있다. 본 논문에서는 Ali의 방식을 개선하여 계산량을 대폭 줄이고 효과적으로 최적 경로를 탐색할 수 있는 방식을 제안한다. 효과적인 최적 경로 탐색을 위하여 2단계로 구분하여 진행된다. 1단계에는 홉필드 네트웍을 2단계에는 eSPN 알고리즘을 사용하여 최적 경로를 탐색할 수 있다. 제안된 방식은 샘플 네트웍을 통하여 최적 경로 탐색이 확인되었으며, Ali 알고리즘보다 빠르고 간단하여 실제 최적화에 적용하기기 용이하다. 특히, 네트웍의 브랜치 비용이 변화할 경우에도 홉필드 네트웍의 연결 시냅스가 아닌 입력 바이어스를 조정하므로 동적으로 변화하는 네트웍의 최적 경로 탐색에도 유용하다.

Hopfield networks have been proposed as a new computational tool for finding the shortest path of networks. Zhang and Ali studied the method of finding shortest path by expended neurons of Hopfield networks. Ali Algorithm is well known as the tool with the neurons of branch numbers. Where a network grows bigger, it needs much more time to solve the problem by Ali algorithm. This paper modifies the method to find the synapse matrix and the input bias vector. And it includes the eSPN algorithm after proper iterations of the Hopfield network. The proposed method is a tow-stage method and it is more efficient to find the shortest path.The proposed method is verified by three sample networks. And it could be more applicable then Ali algorithm because it's fast and easy. When the cost of brach is changed, the proposed method works properly. Therefore dynamic cost-varing networks could be used by the proposed method.