• The Journal of the Convergence on Culture Technology
• /
• v.3 no.4
• /
• pp.165-169
• /
• 2017

CNN(Convolutional Nerual Network) is one of the algorithms that show superior performance in image recognition and classification among machine learning algorithms. CNN is simple, but it has a large amount of computation and it takes a lot of time. Consequently, in this paper we performed an parallel processing unit for the convolution layer, pooling layer and the fully connected layer, which consumes a lot of handling time in the process of CNN, through the SIMT(Single Instruction Multiple Thread)'s structure of GPGPU(General-Purpose computing on Graphics Processing Units).And we also expect to improve performance by reducing the number of memory accesses and directly using the output of convolution layer not storing it in pooling layer. In this paper, we use MNIST dataset to verify this experiment and confirm that the proposed CNN structure is 12.38% better than existing structure.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.7
• /
• pp.1387-1393
• /
• 2007

Even if the linearly separable patterns can be classified by the conventional single layer perceptron, the non-linear problems such as XOR can not be classified by it. A fuzzy single layer perceptron can solve the conventional XOR problems by applying fuzzy membership functions. However, in the fuzzy single layer perception, there are a couple disadvantages which are a decision boundary is sometimes vibrating and a convergence may be extremely lowered according to the scopes of the initial values and learning rates. In this paper, for these reasons, we proposed an enhanced fuzzy single layer perceptron algorithm that can prevent from vibration the decision boundary by introducing a bias term and can also reduce the learn time by applying the modified delta rule which include the learning rates and the momentum concept and applying the new linear activation function. Consequently, the simulation results of the XOR and pattern classification problems presented that the proposed method provided the shorter learning time and better convergence than the conventional fuzzy single layer perceptron.

• Electronics and Telecommunications Trends
• /
• v.35 no.5
• /
• pp.14-29
• /
• 2020

The 6G mobile communication system will become a backbone infrastructure around 2030 for the future digital world by providing distinctive services such as five-sense holograms, ultra-high reliability/low-latency, ultra-high-precision positioning, ultra-massive connectivity, and gigabit-per-second data rate for aerial and maritime terminals. The recent remarkable advances in machine learning (ML) technology have recognized its efficiency in wireless networking fields such as resource management and cell-configuration optimization. Further innovation in ML is expected to play an important role in solving new problems arising from 6G network management and service delivery. In contrast, an approach to apply ML to a physical-layer (PHY) target tackles the basic problems in radio links, such as overcoming signal distortion and interference. This paper reviews the methodologies of ML-based PHY, relevant industrial trends, and candiate technologies, including future research directions and standardization impacts.

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.49-59
• /
• 2009

Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.939-942
• /
• 1996

This paper presents a stable learning algorithm for diagonal recurrent neural network(DRNN). DRNN is applied to a problem of controlling nonlinear dynamical systems. A architecture of DRNN is a modified model of the Recurrent Neural Network(RNN) with one hidden layer, and the hidden layer is comprised of self-recurrent neurons. DRNN has considerably fewer weights than RNN. Since there is no interlinks amongs in the hidden layer. DRNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. To guarantee convergence and for faster learning, an adaptive learning rate is developed by using Lyapunov function. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed algorithm is demonstrated by computer simulation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.561-562
• /
• 2021

CNN (Convolutional Neural Network) is widely used to recognize various images. In this presentation, a single digit handwritten by humans was recognized by applying the CNN technique of deep learning. The deep learning network consists of a convolutional layer, a pooling layer, and a platen layer, and finally, we set an optimization method, learning rate and loss functions.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.95-103
• /
• 2006

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize EEG pattern vectors. The frequency and amplitude of alpha rhythms and beta rhythms are used to compose the input pattern vectors. And the algorithm for EEG pattern recognition is used SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of the subclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ algorithm, and pattern vectors is classified into subclasses by neurons which is being in the subclass layer, and the weights between subclass layer and output layer is learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors of EEG, the proposed algorithm is simulated with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional LVQ.

• Current Optics and Photonics
• /
• v.2 no.2
• /
• pp.153-164
• /
• 2018

In semiconductor manufacturing, critical dimensions indicate the features of patterns formed by the semiconductor process. The purpose of measuring critical dimensions is to confirm whether patterns are made as intended. The deposition process for an organic light emitting diode (OLED) forms a luminous organic layer on the thin-film transistor electrode. The position of this organic layer greatly affects the luminescent performance of an OLED. Thus, a system for measuring the position of the organic layer from outside of the vacuum chamber in real-time is desired for monitoring the deposition process. Typically, imaging from large stand-off distances results in low spatial resolution because of diffraction blur, and it is difficult to attain an adequate industrial-level measurement. The proposed method offers a new superresolution single-image using a conversion formula between two different optical systems obtained by a deep learning technique. This formula converts an image measured at long distance and with low-resolution optics into one image as if it were measured with high-resolution optics. The performance of this method is evaluated with various samples in terms of spatial resolution and measurement performance.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.2
• /
• pp.699-707
• /
• 2015

Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model's hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.

• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.5
• /
• pp.297-304
• /
• 2020

In this study, the prediction method was reviewed to process a cylindrical plate forming using machine learning as a data-driven approach by roll bending equipment. The calculation of the forming variables was based on the analysis using the mechanical relationship between the material properties and the roll bending machine in the bending process. Then, by applying the finite element analysis method, the accuracy of the deformation prediction model was reviewed, and a large number data set was created to apply to machine learning using the finite element analysis model for deformation prediction. As a result of the application of the machine learning model, it was confirmed that the calculation is slightly higher than the linear regression method. Applicable results were confirmed through the machine learning method.