• Journal of Digital Convergence
• /
• v.17 no.10
• /
• pp.251-258
• /
• 2019

In the future, various products are created in various fields using artificial intelligence. In this age, it is a very important problem to know the operation principle of artificial intelligence learning method and to use it correctly. This paper introduces artificial intelligence learning methods that have been known so far. Learning of artificial intelligence is based on the fixed point iteration method of mathematics. The GD(Gradient Descent) method, which adjusts the convergence speed based on the fixed point iteration method, the Momentum method to summate the amount of gradient, and finally, the Adam method that mixed these methods. This paper describes the advantages and disadvantages of each method. In particularly, the Adam method having adaptivity controls learning ability of machine learning. And we analyze how these methods affect digital signals. The changes in the learning process of digital signals are the basis of accurate application and accurate judgment in the future work and research using artificial intelligence.

• The Journal of Korean Institute of Information Technology
• /
• v.18 no.5
• /
• pp.55-64
• /
• 2020

Estimating the state of charge (SOC) of a battery is essential for increasing the stability and reliability of a photovoltaic system. In this study, battery SOC estimation methods were proposed using artificial neural networks (ANNs) with gradient descent (GD), Levenberg-Marquardt (LM), and scaled conjugate gradient (SCG), and an adaptive neuro-fuzzy inference system (ANFIS). The charge start voltage and the integrated charge current were used as input data and the SOC was used as output data. Four models (ANN-GD, ANN-LM, ANN-SCG, and ANFIS) were implemented for battery SOC estimation and compared using MATLAB. The experimental results revealed that battery SOC estimation using the ANFIS model had both the highest accuracy and highest convergence speed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.316-321
• /
• 2003

This paper presents a design method of the wavelet neural network based controller using direct adaptive control method to deal with a stable intelligent control of chaotic systems. The various uncertainties, such as mechanical parametric variation, external disturbance, and unstructured uncertainty influence the control performance. However, the conventional control methods such as optimal control, adaptive control and robust control may not be feasible when an explicit, faithful mathematical model cannot be constructed. Therefore, an intelligent control system that is an on-line trained WNN controller based on direct adaptive control method with adaptive learning rates is proposed to control chaotic nonlinear systems whose mathematical models are not available. The adaptive learning rates are derived in the sense of discrete-type Lyapunov stability theorem, so that the convergence of the tracking error can be guaranteed in the closed-loop system. In the whole design process, the strict constrained conditions and prior knowledge of the controlled plant are not necessary due to the powerful learning ability of the proposed intelligent control system. The gradient-descent method is used for training a wavelet neural network controller of chaotic systems. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with application to the chaotic systems.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.7
• /
• pp.63-74
• /
• 2017

Recently in the area of ICT, the M2M and IoT are in the spotlight as a cutting edge technology with the help of advancement of internet. Among those fields, the smart home is the closest area to our daily lives. Smart home has the purpose to lead a user more convenient living in the house with WLAN (Wireless Local Area Network) or other short-range communication environments using automated appliances. With an arrival of the age of IoT, this can be described as one axis of a variety of applications as for the M2H (Machine to Home) field in M2M. In this paper, we propose a novel technique for estimating the location of a terminal that freely move within a specified area using the RSSI (Received Signal Strength Indication) in the WLAN environment. In order to perform the location estimation, the Fingerprint and KNN methods are utilized and the LMS with the gradient descent method and the proposed algorithm are also used through the error correction functions for locating the real-time position of a moving user who is keeping a smart terminal. From the estimated location, the nearest fixed devices which are general electric appliances were supposed to work appropriately for self-operating of virtual smart home. Through the experiments, connection and operation success rate, and the performance results are analyzed, presenting the verification results.

• 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 Advanced Marine Engineering and Technology
• /
• v.21 no.1
• /
• pp.66-70
• /
• 1997

In this paper a new learning algorithm for curvature smoothing and improved generalization for multi-layer neural networks is proposed. To enhance the generalization ability a constraint term of hidden neuron activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. When the total cost consisted of the output error and hidden error is minimized by gradient-descent methods, the additional descent term gives not only the Hebbian learning but also the synaptic weight decay. Therefore it incorporates error back-propagation, Hebbian, and weight decay, and additional computational requirements to the standard error back-propagation is negligible. From the computer simulation of the time series prediction with Santafe competition data it is shown that the proposed learning algorithm gives much better generalization performance.

• Journal of Environmental Science International
• /
• v.30 no.12
• /
• pp.1101-1111
• /
• 2021

In this study, among the W-S-R(Wiper-Signal-Rainfall) relationship methods used to produce sensor-based rain information in real time, we sought to produce actual rainfall information by applying machine learning techniques to account for the effects of wiper operation. To this end, we used the gradient descent and threshold map methods for pre-processing the cumulative value of the difference before and after wiper operation by utilizing four sensitive channels for optical sensors which collected rain sensor data produced by five rain conditions in indoor artificial rainfall experiments. These methods produced rainfall information by calculating the average value of the threshold according to the rainfall conditions and channels, creating a threshold map corresponding to the 4 (channel) × 5 (considering rainfall information) grid and applying Optima Rainfall Intensity among the big data processing techniques. To verify these proposed results, the application was evaluated by comparing rainfall observations.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.41-44
• /
• 2002

Blind source separation (BSS) is a fundamental problem that is encountered in many practical applications. In most existing methods, stationary sources are considered higher-order statistics is necessary either explicitly or implicitly. But, many natural signals are nonstationary, and it is possible to perform BSS using only second-order statistics. Our method is based on only second order statistics. The algorithms are developed using the gradient descent method in orthogonality constraint and their performance is confirmed by numerical experiments.

• Bulletin of the Korean Mathematical Society
• /
• v.55 no.4
• /
• pp.1303-1315
• /
• 2018

For principal component analysis (PCA) to efficiently analyze large scale matrices, it is crucial to find a few singular vectors in cheaper computational cost and under lower memory requirement. To compute those in a fast and robust way, we propose a new stochastic method. Especially, we adopt the stochastic variance reduced gradient (SVRG) method [11] to avoid asymptotically slow convergence in stochastic gradient descent methods. For that purpose, we reformulate the PCA problem as a unconstrained optimization problem using a quadratic penalty. In general, increasing the penalty parameter to infinity is needed for the equivalence of the two problems. However, in this case, exact penalization is guaranteed by applying the analysis in [24]. We establish the convergence rate of the proposed method to a stationary point and numerical experiments illustrate the validity and efficiency of the proposed method.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.200-206
• /
• 2021

Fraud in e-commerce transaction increased in the last decade especially with the increasing number of online stores and the lockdown that forced more people to pay for services and groceries online using their credit card. Several machine learning methods were proposed to detect fraudulent transaction. Neural networks showed promising results, but it has some few drawbacks that can be overcome using optimization methods. There are two categories of learning optimization methods, first-order methods which utilizes gradient information to construct the next training iteration whereas, and second-order methods which derivatives use Hessian to calculate the iteration based on the optimization trajectory. There also some training refinements procedures that aims to potentially enhance the original accuracy while possibly reduce the model size. This paper investigate the performance of several NN models in detecting fraud in e-commerce transaction. The backpropagation model which is classified as first learning algorithm achieved the best accuracy 96% among all the models.