• Journal of the Korea Society of Computer and Information
• /
• v.21 no.2
• /
• pp.131-136
• /
• 2016

This study aims to present suggestions on the causes and effects between internal marketing and customer-oriented trends of social welfare halls based on the issue that internal marketing should be activated based on previous studies on the relationship between internal marketing and customer-oriented trends. For this purpose, as a result of analysing the research hypothesis through a questionnaire, this study has meaning in that it supported the results of previous studies on internal marketing and customer-oriented trends as theoretical suggestions and analysed the relationship between internal marketing and customer-oriented trends. It was politically suggested and emphasized that internal marketing is needed in social welfare halls and to encourage social welfare workers to be customer-oriented, components of internal marketing should be established in an organic and systematic manner.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1449-1461
• /
• 2019

Face sketch synthesis plays an important role in public security and digital entertainment. In this paper, we present a novel face sketch synthesis method via local similarity and nonlocal similarity regularization terms. The local similarity can overcome the technological bottlenecks of the patch representation scheme in traditional learning-based methods. It improves the quality of synthesized sketches by penalizing the dissimilar training patches (thus have very small weights or are discarded). In addition, taking the redundancy of image patches into account, a global nonlocal similarity regularization is employed to restrain the generation of the noise and maintain primitive facial features during the synthesized process. More robust synthesized results can be obtained. Extensive experiments on the public databases validate the generality, effectiveness, and robustness of the proposed algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.1
• /
• pp.44-51
• /
• 2003

Knowledge acquisition is a bottleneck in knowledge-based system implementation. Decision tree induction is a useful machine learning approach for extracting classification knowledge from a set of training examples. Many real-world data contain fuzziness due to observation error, uncertainty, subjective judgement, and so on. To cope with this problem of real-world data, there have been some works on fuzzy classification rule learning. This paper makes a survey for the kinds of fuzzy classification rules. In addition, it presents a fuzzy classification rule learning method based on decision tree induction, and shows some experiment results for the method.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1693-1696
• /
• 2002

In this paper, we analyzed the performance of OFDM system based on IEEE 802.11a specification. First, we modeled the transmitter and receiver of OFDM (Orthogonal Frequency Division Multiplexing) system. Then, we analyzed the performance of OFDM system through simulation over the JTC (Joint Technical Committee) realistic channel model. In addition we carried out the performance by using pilot training symbol, which is one of the channel estimation methods, over the same channel environments.

• Speech Sciences
• /
• v.10 no.1
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.135-138
• /
• 2005

Robotic devices have been widely used in many medical applications due to their accuracy and programming ability. One of the applications is a virtual reality medical simulator, which trains medical personnel in a computer generated environment. In this paper, we are going to present an application, an epidural anesthesia trainer. Because performing epidural injections is a delicate task, it demands a high level of skill and precision from the physician. This trainer uses a robotic device and computer controlled solenoid valve to recreate interaction forces between the needle and the various layers of tissues around the spinal cord. The robotic device is responsible for generation of interaction forces in real time and can be used to be haptic guidance that allows the user to follow a previous recorded expert procedure and feel the encountered forces.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1052-1070
• /
• 2017

For the autoencoder (AE) implemented as a construction component, this paper uses the method of greedy layer-by-layer pre-training without supervision to construct the stacked autoencoder (SAE) to extract the abstract features of the original input data, which is regarded as the input of the logistic regression (LR) model, after which the click-through rate (CTR) of the user to the advertisement under the contextual environment can be obtained. These experiments show that, compared with the usual logistic regression model and support vector regression model used in the field of predicting the advertising CTR in the industry, the SAE-LR model has a relatively large promotion in the AUC value. Based on the improvement of accuracy of advertising CTR prediction, the enterprises can accurately understand and have cognition for the needs of their customers, which promotes the multi-path development with high efficiency and low cost under the condition of internet finance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.

• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1083-1096
• /
• 2021

Compressed sensing-based matching pursuit algorithms can estimate the sparse channel of massive multiple input multiple-output systems with short pilot sequences. Although they have the advantages of low computational complexity and low pilot overhead, their accuracy remains insufficient. Simply multiplying the weight value and the estimated channel obtained in different iterations can only improve the accuracy of channel estimation under conditions of low signal-to-noise ratio (SNR), whereas it degrades accuracy under conditions of high SNR. To address this issue, an improved weighted matching pursuit algorithm is proposed, which obtains a suitable weight value u_op by training the channel data. The step of the weight value increasing with successive iterations is calculated according to the sparsity of the channel and u_op. Adjusting the weight value adaptively over the iterations can further improve the accuracy of estimation. The results of simulations conducted to evaluate the proposed algorithm show that it exhibits improved performance in terms of accuracy compared to previous methods under conditions of both high and low SNR.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.783-792
• /
• 2022

Versatile Video Coding (VVC) is the latest video coding standard, which had been developed by the Joint Video Experts Team (JVET) of ITU-T Video Coding Experts Group (VCEG) and ISO/IEC Moving Picture Experts Group (MPEG) in 2020. Although VVC can provide powerful coding performance, it requires tremendous computational complexity to determine the optimal block structures during the encoding process. In this paper, we propose a fast ternary tree decision method using two neural networks with 7 nodes as input vector based on the multi-layer perceptron structure, names STH-NN and STV-NN. As a training result of neural network, the STH-NN and STV-NN achieved accuracies of 85% and 91%, respectively. Experimental results show that the proposed method reduces the encoding complexity up to 25% with unnoticeable coding loss compared to the VVC test model (VTM).