• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.23-29
• /
• 2019

In this paper, the mood of images was classified into eight categories through a deep convolutional neural network and video was automatically generated using proper background music. Based on the collected image data, the classification model is learned using a multilayer perceptron (MLP). Using the MLP, a video is generated by using multi-class classification to predict image mood to be used for video generation, and by matching pre-classified music. As a result of 10-fold cross-validation and result of experiments on actual images, each 72.4% of accuracy and 64% of confusion matrix accuracy was achieved. In the case of misclassification, by classifying video into a similar mood, it was confirmed that the music from the video had no great mismatch with images.

• Journal of Korea Multimedia Society
• /
• v.2 no.4
• /
• pp.490-495
• /
• 1999

In this paper, a method of improving the learning time and convergence rate is proposed to exploit the advantages of artificial neural networks and fuzzy theory to neuron structure. This method is applied to the XOR Problem, n bit parity problem which is used as the benchmark in neural network structure, and recognition of digit image in the vehicle plate image for practical image application. As a result of the experiments, it does not always guarantee the convergence. However, the network showed improved the teaming time and has the high convergence rate. The proposed network can be extended to an arbitrary layer Though a single layer structure Is considered, the proposed method has a capability of high speed 3earning even on large images.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2891-2893
• /
• 2005

In this paper, we introduce a new category of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multi-layer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. The conventional SOFPNN algorithm leads to a tendency to produce overly complex networks as well as a repetitive computation load by the trial and error method and/or the a repetitive parameter adjustment by designer. In order to generate a structurally and parametrically optimized network, such parameters need to be optimal. In this study, in solving the problems with the conventional SOFPNN, we introduce a new design approach of evolutionary optimized SOFPNN. Optimal parameters design available within FPN (viz. the no. of input variables, the order of the polynomial, input variables, and the no. of membership function) lead to structurally and parametrically optimized network which is more flexible as well as simpler architecture than the conventional SOFPNN. In addition, we determine the initial apexes of membership functions by genetic algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.9 no.4
• /
• pp.22-35
• /
• 1992

In highly automated machining centers, intelligent sensor fddeback systems are indispensable on order to monitor their operations, to ensure efficient metal removal, and to initate remedial action in the event of accident. In this study, an on-line tool wear detection system for thrning operations is developed, and experimentally evaluated. The system employs multiple sensors and the signals from these sensors are processed using a multichannel autoegressive (AR) series model. The resulting output from the signal processing block is then fed to a previously tranied artificial neural network (multiayered perceptron) to make a final decision on the state of the cutting tool. To learn the necessary input/output mapping for tool wear detection, the weithts and thresholds of the network are adjusted according to the back propagation (BP) method during off-line training. The results of experimental evaluation show that the system works well over a wide range of cutting conditions, and the ability of the system to detect tool wear is improved due to the generalization, fault-tolearant and self-ofganizing properties of the neural network.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.406-412
• /
• 2022

Scene classification of very high-resolution (VHR) imagery can attribute semantics to land cover in a variety of domains. Real-world application requirements have not been addressed by conventional techniques for remote sensing image classification. Recent research has demonstrated that deep convolutional neural networks (CNNs) are effective at extracting features due to their strong feature extraction capabilities. In order to improve classification performance, these approaches rely primarily on semantic information. Since the abstract and global semantic information makes it difficult for the network to correctly classify scene images with similar structures and high interclass similarity, it achieves a low classification accuracy. We propose a VHR remote sensing image classification model that uses extracts the global feature from the original VHR image using an EfficientNet-V2L CNN pre-trained to detect similar classes. The image is then classified using a multilayer perceptron (MLP). This method was evaluated using two benchmark remote sensing datasets: the 21-class UC Merced, and the 38-class PatternNet. As compared to other state-of-the-art models, the proposed model significantly improves performance.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2017.11a
• /
• pp.50-53
• /
• 2017

Not only growth of importance to understanding economic trends, but also the prediction to overcome the uncertainty is coming up for long-term maritime recession. This paper discussed about the prediction of BDI with artificial neural networks (ANN). ANN is one of emerging applications that can be the finest solution to the knotty problems that may not easy to achieve by humankind. Proposed a prediction by implementing neural networks that have recurrent architecture which are a Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). And for the reason of comparison, trained Multi Layer Perceptron (MLP) from 2009.04.01 to 2017.07.31. Also made a comparison with conventional statistics, prediction tools; ARIMA. As a result, recurrent net, especially RNN outperformed and also could discover the applicability of LSTM to specific time-series (BDI).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.305-313
• /
• 2021

The upcoming warfare will be network-centric warfare with the acquiring and sharing of information on the battlefield through the connection of the entire weapon system. Therefore, the amount of information generated increases, but the technology of evaluating the information is insufficient. Threat assessment is a technology that supports a quick decision, but the information has many uncertainties and is difficult to apply to an advanced battlefield. This paper proposes a threat assessment based on artificial intelligence while removing the target uncertainty. The artificial intelligence system used was a fuzzy inference system and a multi-layer perceptron. The target was classified by inputting the unique characteristics of the target into the fuzzy inference system, and the classified target information was input into the multi-layer perceptron to calculate the appropriate threat value. The validity of the proposed technique was verified with the threat value calculated by inputting the uncertain target to the trained artificial neural network.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.193-200
• /
• 2023

Cryptanalysis can be performed by various techniques such as known plaintext attack, differential attack, side-channel analysis, and the like. Recently, many studies have been conducted on cryptanalysis using deep learning. A known-plaintext attack is a technique that uses a known plaintext and ciphertext pair to find a key. In this paper, we use deep learning technology to perform a known-plaintext attack against S-PRESENT, a reduced version of the lightweight block cipher PRESENT. This paper is significant in that it is the first known-plaintext attack based on deep learning performed on a reduced lightweight block cipher. For cryptanalysis, MLP (Multi-Layer Perceptron) and 1D and 2D CNN(Convolutional Neural Network) models are used and optimized, and the performance of the three models is compared. It showed the highest performance in 2D convolutional neural networks, but it was possible to attack only up to some key spaces. From this, it can be seen that the known-plaintext attack through the MLP model and the convolutional neural network is limited in attackable key bits.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.5
• /
• pp.765-776
• /
• 1995

This paper describes a speaker adaptation method to improve the recognition performance of MLP(multiLayer Perceptron) based HMM(Hidden Markov Model) speech recognizer. In this method, we use lst-order linear transformation network to fit data of a new speaker to the MLP. Transformation parameters are adjusted by back-propagating classification error to the transformation network while leaving the MLP classifier fixed. The recognition system is based on semicontinuous HMM's which use the MLP as a fuzzy vector quantizer. The experimental results show that rapid speaker adaptation resulting in high recognition performance can be accomplished by this method. Namely, for supervised adaptation, the error rate is signifecantly reduced from 9.2% for the baseline system to 5.6% after speaker adaptation. And for unsupervised adaptation, the error rate is reduced to 5.1%, without any information from new speakers.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.9
• /
• pp.739-746
• /
• 1991

This paper develops a modified multilayer perceptron architecture which speeds up learning as well as the net's mapping accuracy. In Phase I, a cluster partitioning algorithm like the Kohonen's self-organizing feature map or the leader clustering algorithm is used as the front end that determines the cluster to which the input data belongs. In Phase II, this cluster selects a subset of the hidden layer nodes that combines the input and outputs nodes into a subnet of the full scale backpropagation network. The proposed net has been applied to two mapping problems, one rather smooth and the other highly nonlinear. Namely, the inverse kinematic problem for a 3-link robot manipulator and the 5-bit parity mapping have been chosen as examples. The results demonstrate the proposed net's superior accuracy and convergence properties over the original backpropagation network or its existing improvement techniques.