• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.9
• /
• pp.23-30
• /
• 1997

In this paper, a decision feedback recurrent neural equalization (DFRNE) scheme is proposed for adaptive equalization problems. The proposed equalizer models a nonlinear infinite impulse response (IIR) filter. The modified Real-Time recurrent Learning Algorithm (RTRL) is used to train the DFRNE. The DFRNE is applied to both linear channels with only intersymbol interference and nonlinear channels for digital video cassette recording (DVCR) system. And the performance of the DFRNE is compared to those of the conventional equalizaion schemes, such as a linear equalizer, a decision feedback equalizer, and neural equalizers based on multi-layer perceptron (MLP), in view of both bit error rate performance and mean squared error (MSE) convergence. It is shown that the DFRNE with a reasonable size not only gives improvement of compensating for the channel introduced distortions, but also makes the MSE converge fast and stable.

• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.221-235
• /
• 2022

Among nondestructive damage detection methods, impedance-based methods have been recognized as an effective technique for damage identification in many kinds of structures. This paper proposes a method to detect cracks in metal structures by combining electro-mechanical impedance (EMI) responses and artificial neural networks (ANN). Firstly, the theories of EMI responses and impedance-based damage detection methods are described. Secondly, the reliability of numerical simulations for impedance responses is demonstrated by comparing to pre-published results for an aluminum beam. Thirdly, the proposed method is used to detect cracks in the beam. The RMSD (root mean square deviation) index is used to alarm the occurrence of the cracks, and the multi-layer perceptron (MLP) ANN is employed to identify the location and size of the cracks. The selection of the effective frequency range is also investigated. The analysis results reveal that the proposed method accurately detects the cracks' occurrence, location, and size in metal structures.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.2
• /
• pp.312-320
• /
• 2012

In this study, we introduce a new design methodology of a granular-oriented self-organizing polynomial neural networks (GoSOPNNs) that is based on multi-layer perceptron with Context-based Polynomial Neurons (CPNs) or Polynomial Neurons (PNs). In contrast to the typical architectures encountered in polynomial neural networks (PNN), our main objective is to develop a methodological design strategy of GoSOPNNs as follows : (a) The 1st layer of the proposed network consists of Context-based Polynomial Neuron (CPN). In here, CPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Context-based Fuzzy C-Means (C-FCM) clustering method. The context-based clustering supporting the design of information granules is completed in the space of the input data while the build of the clusters is guided by a collection of some predefined fuzzy sets (so-called contexts) defined in the output space. (b) The proposed design procedure being applied at each layer of GoSOPNN leads to the selection of preferred nodes of the network (CPNs or PNs) whose local characteristics (such as the number of contexts, the number of clusters, a collection of the specific subset of input variables, and the order of the polynomial) can be easily adjusted. These options contribute to the flexibility as well as simplicity and compactness of the resulting architecture of the network. For the evaluation of performance of the proposed GoSOPNN network, we describe a detailed characteristic of the proposed model using a well-known learning machine data(Automobile Miles Per Gallon Data, Boston Housing Data, Medical Image System Data).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.2032-2037
• /
• 2011

Marker genes are defined as genes in which the expression level characterizes a specific experimental condition. Such genes in which the expression levels differ significantly between different groups are highly informative relevant to the studied phenomenon. In this paper, first the system can detect marker genes that are selected by ranking genes according to statistics after normalizing data with methods that are the most widely used among several normalization methods proposed the while, And it compare and analyze a performance of each of normalization methods with mult-perceptron neural network layer. The Result that apply Multi-Layer perceptron algorithm at Microarray data set including eight of marker gene that are selected using ANOVA method after Lowess normalization represent the highest classification accuracy of 99.32% and the lowest prediction error estimate.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.4
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.848-857
• /
• 2021

This paper proposes an efficient approach based on a machine learning technique to predict the local stresses on mooring chain links. Three-link and multi-link finite element analyses were conducted for a target chain link of D107 with steel grade R4; 24,000 and 8000 analyses were performed, respectively. Two serial Artificial Neural Network (ANN) models based on a deep multi-layer perceptron technique were developed. The first ANN model corresponds to multi-link analyses, where the input neurons were the tension force and angle and the output neurons were the interlink angles. The second ANN model corresponds to the three-link analyses with the input neurons of the tension force, interlink angle, and the local stress positions, and the output neurons of the local stress. The predicted local stresses for the untrained cases were reliable compared to the numerical simulation results.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.21-24
• /
• 2001

In this paper, we present a fast face detection algorithm by estimating the eye region using neural network. To implement a real time face detection system, it is necessary to reduce search space. We limit the search space just to a few pairs of eye candidates. For the selection of them, we first isolate possible eye regions in the fast and robust way by modified histogram equalization. The eye candidates are paired to form an eye pair and each of the eye pair is estimated how close it is to a true eye pair in two aspects : One is how similar the two eye candidates are in shape and the other is how close each of them is to a true eye image A multi-layer perceptron neural network is used to find the eye candidate region's closeness to the true eye image. Just a few best candidates are then verified by eigenfaces. The experimental results show that this approach is fast and reliable. We achieved 94% detection rate with average 0.1 sec Processing time in Pentium III PC in the experiment on 424 gray scale images from MIT, Yale, and Yonsei databases.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.4E
• /
• pp.112-119
• /
• 2004

This paper presents a method for the automatic recognition of pitch accents with no prior knowledge about the phonetic content of the signal (no knowledge of word or phoneme boundaries or of phoneme labels). The recognition algorithm used in this paper is a time-delay recurrent neural network (TDRNN). A TDRNN is a neural network classier with two different representations of dynamic context: delayed input nodes allow the representation of an explicit trajectory F0(t), while recurrent nodes provide long-term context information that can be used to normalize the input F0 trajectory. Performance of the TDRNN is compared to the performance of a MLP (multi-layer perceptron) and an HMM (Hidden Markov Model) on the same task. The TDRNN shows the correct recognition of $91.9{\%}\;of\;pitch\;events\;and\;91.0{\%}$ of pitch non-events, for an average accuracy of $91.5{\%}$ over both pitch events and non-events. The MLP with contextual input exhibits $85.8{\%},\;85.5{\%},\;and\;85.6{\%}$ recognition accuracy respectively, while the HMM shows the correct recognition of $36.8{\%}\;of\;pitch\;events\;and\;87.3{\%}$ of pitch non-events, for an average accuracy of $62.2{\%}$ over both pitch events and non-events. These results suggest that the TDRNN architecture is useful for the automatic recognition of pitch accents.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.329-338
• /
• 2021

This study predicts the amount of wind power generation for rational operation plan of wind power generation and capacity calculation of ESS. For forecasting, we present a method of predicting wind power generation by combining a physical approach and a statistical approach. The factors of wind power generation are analyzed and variables are selected. By collecting historical data of the selected variables, the amount of wind power generation is predicted using deep learning. The model used is a hybrid model that combines a bidirectional long short term memory (LSTM) and a convolution neural network (CNN) algorithm. To compare the prediction performance, this model is compared with the model and the error which consist of the MLP(:Multi Layer Perceptron) algorithm, The results is presented to evaluate the prediction performance.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.277-283
• /
• 2023

Vital signals provide essential information regarding the health status of individuals, thereby contributing to health management and medical research. Present monitoring methods, such as ECGs (Electrocardiograms) and smartwatches, demand proximity and fixed postures, which limit their applicability. To address this, Non-contact vital signal measurement methods, such as CW (Continuous-Wave) radar, have emerged as a solution. However, unwanted signal components and a stepwise processing approach lead to errors and limitations in heart rate detection. To overcome these issues, this study introduces an integrated neural network approach that combines noise removal, demodulation, and dominant-frequency detection into a unified process. The neural network employed for signal processing in this research adopts a MLP (Multi-Layer Perceptron) architecture, which analyzes the in-phase and quadrature signals collected within a specified time window, using two distinct input layers. The training of the neural network utilizes CW radar signals and reference heart rates obtained from the ECG. In the experimental evaluation, networks trained on different datasets were compared, and their performance was assessed based on loss and frequency accuracy. The proposed methodology exhibits substantial potential for achieving precise vital signals through non-contact measurements, effectively mitigating the limitations of existing methodologies.