• Journal of applied mathematics & informatics
• /
• v.26 no.5_6
• /
• pp.961-972
• /
• 2008

In this paper, we consider the global exponential stability of cellular neural networks with time-varying delays. Based on the Lyapunov function method and convex optimization approach, a novel delay-dependent criterion of the system is derived in terms of LMI (linear matrix inequality). In order to solve effectively the LMI convex optimization problem, the interior point algorithm is utilized in this work. Two numerical examples are given to show the effectiveness of our results.

• International Journal of Reliability and Applications
• /
• v.13 no.2
• /
• pp.91-104
• /
• 2012

Sarhan and Kundu (2009) introduced a new distribution named as the generalized linear failure rate distribution. This distribution generalizes several well known distributions. The probability density function of the generalized linear failure rate distribution can be right skewed or unimodal and its hazard function can be increasing, decreasing or bathtub shaped. This distribution can be used quite effectively to analyze lifetime data in place of linear failure rate, generalized exponential and generalized Rayleigh distributions. In this paper, we apply the simulated annealing algorithm to obtain the maximum likelihood point estimates of the parameters of the generalized linear failure rate distribution. Simulated annealing algorithm can not only find the global optimum; it is also less likely to fail because it is a very robust algorithm. The estimators obtained using simulated annealing algorithm have been compared with the corresponding traditional maximum likelihood estimators for their risks.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.945-952
• /
• 2006

Several accelerated life test plans use tests at only two levels of stress and thus, have practical limitations. They highly depend upon the assumption of a linear relationship between stress and time-to-failure and use only two extreme stresses that can cause irrelevant failure modes. Thus 3-level stress plans are preferable. When the lifetime distribution of test unit is exponential with mean lifetime $\theta_i$ at stress $x_i$, i=0, 1, 2, 3, we derive the optimum quadratic plan under the assumption that a quadratic relationship exists between stress and log(mean lifetime), and propose the compound linear plans, as an alternative to the optimum quadratic plan. The proposed compound linear plan is better than two other compromise plans for constant stress testing and nearly as good as the optimum quadratic plan, and has the advantage of simplicity.

• Korean Journal of Remote Sensing
• /
• v.28 no.6
• /
• pp.597-609
• /
• 2012

Leaf area index (LAI) is important in explaining the ability of the crop to intercept solar energy for biomass production and in understanding the impact of crop management practices. This paper describes a procedure for estimating LAI as a function of image-derived vegetation indices from temporal series of IKONOS, Landsat TM, and MODIS satellite images using empirical models and demonstrates its use with data collected at Missouri field sites. LAI data were obtained several times during the 2002 growing season at monitoring sites established in two central Missouri experimental fields, one planted to soybean (Glycine max L.) and the other planted to corn (Zea mays L.). Satellite images at varying spatial and spectral resolutions were acquired and the data were extracted to calculate normalized difference vegetation index (NDVI) after geometric and atmospheric correction. Linear, exponential, and expolinear models were developed to relate temporal NDVI to measured LAI data. Models using IKONOS NDVI estimated LAI of both soybean and corn better than those using Landsat TM or MODIS NDVI. Expolinear models provided more accurate results than linear or exponential models.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.525-538
• /
• 2020

A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.135-141
• /
• 2019

Recently, there has been active researches about building an artificial intelligence agent that can learn how to play a game by using re-enforcement learning. The performance of the learning can be diverse according to what kinds of deep learning activation functions they used when they train the agent. This paper compares the activation functions when we train our agent for learning how to play a 2D shooting game by using re-enforcement learning. We defined performance metrics to analyze the results and plotted them along a training time. As a result, we found ELU (Exponential Linear Unit) with a parameter 1.0 achieved best rewards than other activation functions. There was 23.6% gap between the best activation function and the worst activation function.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.520-520
• /
• 2023

제주도 동부 중산간 지역은 화산암으로 구성된 지하지질로 인해 지하수위의 변동폭이 크고 변동양상이 복잡하여 인공신경망(Artificial Neural Network, ANN) 모델 등을 활용한 지하수위의 예측이 어렵다. ANN에 적용되는 활성화함수에 따라 지하수의 예측성능은 달라질 수 있으므로 활성화함수의 비교분석 후 적절한 활성화함수의 사용이 반드시 필요하다. 본 연구에서는 5개 활성화함수(sigmoid, hyperbolic tangent(tanh), Rectified Linear Unit(ReLU), Leaky Rectified Linear Unit(Leaky ReLU), Exponential Linear Unit(ELU))를 제주도 동부 중산간지역에 위치한 2개 지하수 관정에 대해 비교분석하여 최적 활성화함수 도출을 목표로 한다. 또한 최적 활성화함수를 활용한 ANN의 적용성을 평가하기 위해 최근 널리 사용되고 있는 순환신경망 모델인 Long Short-Term Memory(LSTM) 모델과 비교분석 하였다. 그 결과, 2개 관정 중 지하수위 변동폭이 상대적으로 큰 관정은 ELU 함수, 상대적으로 작은 관정은 Leaky ReLU 함수가 지하수위 예측에 적절하였다. 예측성능이 가장 낮은 활성화함수는 sigmoid 함수로 나타나 첨두 및 최저 지하수위 예측 시 사용을 지양해야 할 것으로 판단된다. 도출된 최적 활성화함수를 사용한 ANN-ELU 모델 및 ANN-Leaky ReLU 모델을 LSTM 모델과 비교분석한 결과 대등한 지하수위 예측성능을 나타내었다. 이것은 feed-forward 방식인 ANN 모델을 사용하더라도 적절한 활성화함수를 사용하면 최신 순환신경망과 대등한 결과를 도출하여 활용 가능성이 충분히 있다는 것을 의미한다. 마지막으로 LSTM 모델은 가장 적절한 예측성능을 나타내어 다양한 인공지능 모델의 예측성능 비교를 위한 기준이 되는 참고모델로 활용 가능하다. 본 연구에서 제시한 방법은 지하수위 예측과 더불어 하천수위 예측 등 다양한 시계열예측 및 분석연구에 유용하게 사용될 수 있다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.43-43
• /
• 2022

유해 조류 대발생은 전국 각지의 인공호소나 하천에서 다발적으로 발생하며, 경관을 해치고 수질을 오염시키는 등 수자원에 부정적인 영향을 미친다. 본 연구에서는 인공호소에서 발생하는 유해 조류 대발생을 예측하기 위해 심층학습 기법을 이용하여 예측 모델을 개발하고자 하였다. 대상 지점은 대청호의 추동 지점으로 선정하였다. 대청호는 금강유역 중류에 위치한 댐으로, 약 150만명에 달하는 급수 인구수를 유지 중이기에 유해 남조 대발생 관리가 매우 중요한 장소이다. 학습용 데이터 구축은 대청호의 2011년 1월부터 2019년 12월까지 측정된 수질, 기상, 수문 자료를 입력 자료를 이용하였다. 수질 예측 모델의 구조는 다중 레이어 퍼셉트론(Multiple Layer Perceptron; MLP)으로, 입력과 한 개 이상의 은닉층, 그리고 출력층으로 구성된 인공신경망이다. 본 연구에서는 인공신경망의 은닉층 개수(1~3개)와 각각의 레이어에 적용되는 은닉 노드 개수(11~30개), 활성함수 5종(Linear, sigmoid, hyperbolic tangent, Rectified Linear Unit, Exponential Linear Unit)을 각각 하이퍼파라미터로 정하고, 모델의 성능을 최대로 발휘할 수 있는 조건을 찾고자 하였다. 하이퍼파라미터 최적화 도구는 Tensorflow에서 배포하는 Keras Tuner를 사용하였다. 모델은 총 3000 학습 epoch 가 진행되는 동안 최적의 가중치를 계산하도록 설계하였고, 이 결과를 매 반복마다 저장장치에 기록하였다. 모델 성능의 타당성은 예측과 실측 데이터 간의 상관관계를 R2, NSE, RMSE를 통해 산출하여 검증하였다. 모델 최적화 결과, 적합한 하이퍼파라미터는 최적화 횟수 총 300회에서 256 번째 반복 결과인 은닉층 개수 3개, 은닉 노드 수 각각 25개, 22개, 14개가 가장 적합하였고, 이에 따른 활성함수는 ELU, ReLU, Hyperbolic tangent, Linear 순서대로 사용되었다. 최적화된 하이퍼파라미터를 이용하여 모델 학습 및 검증을 수행한 결과, R2는 학습 0.68, 검증 0.61이었고 NSE는 학습 0.85, 검증 0.81, RMSE는 학습 0.82, 검증 0.92로 나타났다.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.45-49
• /
• 2022

The fourth industrial revolution, internet of things, and the expansion of online web services have increased an exponential growth and deployment in the number of cloud data centers (CDC). The cloud is emerging as new paradigm for delivering the Internet-based computing services. Due to the dynamic and non-linear workload and availability of the resources is a critical problem for efficient workload and resource management. In this paper, we propose the particle swarm optimization (PSO) based gated recurrent unit (GRU) neural network for efficient prediction the future value of the CPU and memory usage in the cloud data centers. We investigate the hyper-parameters of the GRU for better model to effectively predict the cloud resources. We use the Google Cluster traces to evaluate the aforementioned PSO-GRU prediction. The experimental shows the effectiveness of the proposed algorithm.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.