• ETRI Journal
• /
• v.35 no.2
• /
• pp.193-199
• /
• 2013

This paper addresses nonnegative independent component analysis (NICA), with the aim to realize the blind separation of nonnegative well-grounded independent source signals, which arises in many practical applications but is hardly ever explored. Recently, Bertrand and Moonen presented a multiplicative NICA (M-NICA) algorithm using multiplicative update and subspace projection. Based on the principle of the mutual correlation minimization, we propose another novel cost function to evaluate the diagonalization level of the correlation matrix, and apply the multiplicative exponentiated gradient (EG) descent update to it to maintain nonnegativity. An efficient approach referred to as the EG-NICA algorithm is derived and its validity is confirmed by numerous simulations conducted on different types of source signals. Results show that the separation performance of the proposed EG-NICA algorithm is superior to that of the previous M-NICA algorithm, with a better unmixing accuracy. In addition, its convergence speed is adjustable by an appropriate user-defined learning rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.12
• /
• pp.2418-2425
• /
• 1994

Although the error backpropagation(EBP) algorithm based on the gradient descent method is a widely-used learning algorithm of neural networks, learning sometimes takes a long time to acquire accuracy. This paper develops a novel learning method to alleviate the problems of EBP algorithm such as local minima, slow speed, and size of structure and thus to improve performance by adopting other new networks. Gaussian Potential Function networks(GPFN), in parallel with multilayer neural networks. Empirical simulations show the efficacy of the proposed algorithm in function approximation, which enables us to train networks faster with the better generalization capabilities.

• Journal of the Society of Naval Architects of Korea
• /
• v.39 no.4
• /
• pp.17-23
• /
• 2002

The present paper describes the optimum inverse design of 2-D linear cascade airfoil. The pressure coefficient of an airfoil surface is taken as the objective function, and non-orthogonal incompressible Navier-Stokes equation is applied to calculate the pressure coefficient. Both of steepest descent and conjugate gradient method have been used to make the objective function go to zero. The 1st order finite differential method is applied to the searching direction and the golden section method is used to compute the searching distance. As a result of the present work, a good convergence to the target airfoil has been obtained.

• Journal of information and communication convergence engineering
• /
• v.13 no.2
• /
• pp.123-131
• /
• 2015

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

• Journal of Korea Multimedia Society
• /
• v.7 no.6
• /
• pp.841-850
• /
• 2004

This paper proposes a GA and GDM-based method for removing unnecessary rules and generating relevant rules from the fuzzy rules corresponding to several fuzzy partitions. The aim of proposed method is to find a minimum set of fuzzy rules that can correctly classify all the training patterns. When the fine fuzzy partition is used with conventional methods, the number of fuzzy rules has been enormous and the performance of fuzzy inference system became low. This paper presents the application of GA as a means of finding optimal solutions over fuzzy partitions. In each rule, the antecedent part is made up the membership functions of a fuzzy set, and the consequent part is made up of a real number. The membership functions and the number of fuzzy inference rules are tuned by means of the GA, while the real numbers in the consequent parts of the rules are tuned by means of the gradient descent method. It is shown that the proposed method has improved than the performance of conventional method in formulating and solving a combinatorial optimization problem that has two objectives: to maximize the number of correctly classified patterns and to minimize the number of fuzzy rules.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.129-143
• /
• 2021

This paper proposes actuator fault detection and adaptive fault-tolerant control algorithms using performance index and human-like learning for longitudinal autonomous vehicles. Conventional longitudinal controller for autonomous driving consists of supervisory, upper level and lower level controllers. In this paper, feedback control law and PID control algorithm have been used for upper level and lower level controllers, respectively. For actuator fault-tolerant control, adaptive rule has been designed using the gradient descent method with estimated coefficients. In order to adjust the control parameter used for determination of adaptation gain, human-like learning algorithm has been designed based on perceptron learning method using control errors and control parameter. It is designed that the learning algorithm determines current control parameter by saving it in memory and updating based on the cost function-based gradient descent method. Based on the updated control parameter, the longitudinal acceleration has been computed adaptively using feedback law for actuator fault-tolerant control. The finite window-based performance index has been designed for detection and evaluation of actuator performance degradation using control error.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.63-72
• /
• 2021

Mobile crowd-sensing (MCS) is a promising sensing paradigm that leverages mobile users with smart devices to perform large-scale sensing tasks in order to provide services to specific applications in various domains. However, MCS sensing tasks may not always be successfully completed or timely completed for various reasons, such as accidentally leaving the tasks incomplete by the users, asynchronous transmission, or connection errors. This results in missing sensing data at specific locations and times, which can degrade the performance of the applications and lead to serious casualties. Therefore, in this paper, we propose a missing data inference approach, called missing data approximation with probabilistic tensor factorization (MDI-PTF), to approximate the missing values as closely as possible to the actual values while taking asynchronous data transmission time and different sensing locations of the mobile users into account. The proposed method first normalizes the data to limit the range of the possible values. Next, a probabilistic model of tensor factorization is formulated, and finally, the data are approximated using the gradient descent method. The performance of the proposed algorithm is verified by conducting simulations under various situations using different datasets.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.352-358
• /
• 2022

Text mining is an important process used for analyzing the data collected from different sources like videos, audio, social media, and so on. The tools like Natural Language Processing (NLP) are mostly used in real-time applications. In the earlier research, text mining approaches were implemented using long-short memory (LSTM) networks. In this paper, text mining is performed using average-stochastic gradient descent weight-dropped (AWD)-LSTM techniques to obtain better accuracy and performance. The proposed model is effectively demonstrated by considering the internet movie database (IMDB) reviews. To implement the proposed model Python language was used due to easy adaptability and flexibility while dealing with massive data sets/databases. From the results, it is seen that the proposed LSTM plus weight dropped plus embedding model demonstrated an accuracy of 88.36% as compared to the previous models of AWD LSTM as 85.64. This result proved to be far better when compared with the results obtained by just LSTM model (with 85.16%) accuracy. Finally, the loss function proved to decrease from 0.341 to 0.299 using the proposed model

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.186-186
• /
• 2022

강수 및 침투 등으로 발생하는 지하수위의 변동을 예측하는 것은 지하수 자원의 활용 및 관리에 필수적이다. 지하수위의 변동은 지하수 자원의 활용 및 관리뿐만이 아닌 홍수 발생과 지반의 응력상태 등에 직접적인 영향을 미치기 때문에 정확한 예측이 필요하다. 본 연구는 인공신경망 중 다층퍼셉트론(Multi Layer Perceptron, MLP)을 이용한 지하수위 예측성능 향상을 위해 MLP의 구조 중 Optimizer를 개량하였다. MLP는 입력자료와 출력자료간 최적의 상관관계(가중치 및 편향)를 찾는 Optimizer와 출력되는 값을 결정하는 활성화 함수의 연산을 반복하여 학습한다. 특히 Optimizer는 신경망의 출력값과 관측값의 오차가 최소가 되는 상관관계를 찾는 연산자로써 MLP의 학습 및 예측성능에 직접적인 영향을 미친다. 기존의 Optimizer는 경사하강법(Gradient Descent, GD)을 기반으로 하는 Optimizer를 사용했다. 하지만 기존의 Optimizer는 미분을 이용하여 상관관계를 찾기 때문에 지역탐색 위주로 진행되며 기존에 생성된 상관관계를 저장하는 구조가 없어 지역 최적해로 수렴할 가능성이 있다는 단점이 있다. 본 연구에서는 기존 Optimizer의 단점을 개선하기 위해 지역탐색과 전역탐색을 동시에 고려할 수 있으며 기존의 해를 저장하는 구조가 있는 메타휴리스틱 최적화 알고리즘을 이용하였다. 메타휴리스틱 최적화 알고리즘 중 구조가 간단한 화음탐색법(Harmony Search, HS)과 GD의 결합모형(HS-GD)을 MLP의 Optimizer로 사용하여 기존 Optimizer의 단점을 개선하였다. HS-GD를 이용한 MLP의 성능검토를 위해 이천시 지하수위 예측을 실시하였으며 예측 결과를 기존의 Optimizer를 이용한 MLP 및 HS를 이용한 MLP의 예측결과와 비교하였다.