• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.6
• /
• pp.869-877
• /
• 2022

This study aims to analyze the factors affecting the re-subscription period upon initial termination of the reverse mortgage subscription. The study utilized the Korea Housing Finance Corporation's database to extract the information regarding re-subscribers of the reverse mortgage from July 2007 to June 2021. The ordered logit model was employed and found that a set of user (subscriber) characteristics are influential towards the re-subscription period. Among the individual characteristics, changes in age group, marital status from married to single-living, maintaining single-living, and the initial subscription period were found statistically significant, highlighting that the increase in the initial subscription period decreased the re-subscription period. Among the housing (home equity) characteristics, changes in housing price and ownership type (single and partial ownership) were statistically significant, indicating that the change in ownership type decreases the re-subscription period. Lastly, the variables related to loan terms were found significant, revealing that changes in payout method and schedule were both increasing factors of the re-subscription period. Based on the findings, necessary policy implications can be considered to secure the returning subscribers of the reverse mortgage effectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.449-456
• /
• 2021

An intrusion detection system is a technology that detects abnormal behaviors that violate security, and detects abnormal operations and prevents system attacks. Existing intrusion detection systems have been designed using statistical analysis or anomaly detection techniques for traffic patterns, but modern systems generate a variety of traffic different from existing systems due to rapidly growing technologies, so the existing methods have limitations. In order to overcome this limitation, study on intrusion detection methods applying various machine learning techniques is being actively conducted. In this study, a comparative study was conducted on data preprocessing techniques that can improve the accuracy of anomaly detection using NGIDS-DS (Next Generation IDS Database) generated by simulation equipment for traffic in various network environments. Padding and sliding window were used as data preprocessing, and an oversampling technique with Adversarial Auto-Encoder (AAE) was applied to solve the problem of imbalance between the normal data rate and the abnormal data rate. In addition, the performance improvement of detection accuracy was confirmed by using Skip-gram among the Word2Vec techniques that can extract feature vectors of preprocessed sequence data. PCA-SVM and GRU were used as models for comparative experiments, and the experimental results showed better performance when sliding window, skip-gram, AAE, and GRU were applied.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.675-681
• /
• 2021

With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.342-350
• /
• 2022

In this paper, actual drone noise samples are collected for speech processing in disaster environments to build noise-corrupted speech database, and speech enhancement performance is evaluated by applying spectrum subtraction and mask-based speech enhancement techniques. To improve the performance of VoiceFilter (VF), an existing deep neural network-based speech enhancement model, we apply the Self-Attention operation and use the estimated noise information as input to the Attention model. Compared to existing VF model techniques, the experimental results show 3.77%, 1.66% and 0.32% improvements for Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligence (STOI), respectively. When trained with a 75% mix of speech data with drone sounds collected from the Internet, the relative performance drop rates for SDR, PESQ, and STOI are 3.18%, 2.79% and 0.96%, respectively, compared to using only actual drone noise. This confirms that data similar to real data can be collected and effectively used for model training for speech enhancement in environments where real data is difficult to obtain.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.11-17
• /
• 2022

In this paper, a model that can increase the efficiency of work in arranging interior furniture by applying augmented reality technology was studied. In the existing system to which augmented reality is currently applied, there is a problem in that information is limitedly provided depending on the size and nature of the company's product when outputting the image of furniture. To solve this problem, this paper presents an AR labeling algorithm. The AR labeling algorithm extracts feature points from the captured images and builds a database including indoor location information. A method of detecting and learning the location data of furniture in an indoor space was adopted using the CNN technique. Through the learned result, it is confirmed that the error between the indoor location and the location shown by learning can be significantly reduced. In addition, a study was conducted to allow users to easily place desired furniture through augmented reality by receiving detailed information about furniture along with accurate image extraction of furniture. As a result of the study, the accuracy and loss rate of the model were found to be 99% and 0.026, indicating the significance of this study by securing reliability. The results of this study are expected to satisfy consumers' satisfaction and purchase desires by accurately arranging desired furniture indoors through the design and implementation of AR labels.

• Journal of Korean Society of Disaster and Security
• /
• v.16 no.1
• /
• pp.1-11
• /
• 2023

The comprehensive natural disaster reduction plan, the highest plan in the disaster prevention field, was implemented by local governments. second plan is currently being formulated. In order to minimize human and property damage, structural and non-structural measures for each of the nine disaster types are established and implemented for 10 years. Structural measures are based on engineering and quantitative analysis, and the criteria for setting reduction measures are clear. Non-structural measures, however, currently lack the set criteria. the basic disaster and safety management law included the safety vulnerable class in 2018. Currently, the safety vulnerable class of the detailed establishment criteria of the comprehensive natural disaster reduction plan is being established, including children, the elderly, and the disabled. However, due to the lack of data securing and database construction by local governments, it is difficult to prepare a location map for establishing reduction measures for the safety vulnerable. Therefore, in this study, OPEN API data of the safety vulnerable class were collected and statistical information and GIS of SGIS information services were used. The distribution diagram of the safety vulnerable class in Samcheok, Gangwon-do, which is a sample area, and the distribution diagram of the safety vulnerable class in units of the output area (OA) in Geundeok-myeon were prepared.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.267-274
• /
• 2023

In this paper, a method for estimating the illuminant chromaticity of a scene for an input image is proposed. The illuminant chromaticity is estimated using the illuminant reference region. The conventional method uses a certain number of reference lighting information. By comparing the chromaticity distribution of pixels from the input image with the chromaticity set prepared in advance for the reference illuminant, the reference illuminant with the largest overlapping area is regarded as the scene illuminant for the corresponding input image. In the process of calculating the overlapping area, the weights for each reference light were applied in the form of a Gaussian distribution, but a clear standard for the variance value could not be presented. The proposed method extracts an independent reference chromaticity region from a given reference illuminant, calculates the characteristic values in the r-g chromaticity plane of the RGB color coordinate system for all pixels of the input image, and then calculates the independent chromaticity region and features from the input image. The similarity is evaluated and the illuminant with the highest similarity was estimated as the illuminant chromaticity component of the image. The performance of the proposed method was evaluated using the database image and showed an average of about 60% improvement compared to the conventional basic method and showed an improvement performance of around 53% compared to the conventional Gaussian weight of 0.1.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.703-709
• /
• 2023

It is most desirable to train with a real crane in an environment similar to that of a port for crane operation training in charge of loading and unloading in a port, but it has time and space limitations and cost problems. In order to overcome these limitations, VR(Virtual Reality) based crane training programs and related devices are receiving a lot of attention. In this paper, we designed and implemented a VR-based harbor crane simulator operating on an HMD. The simulator developed in this paper consists of a crane simulator program that operates on the HMD, an IoT driving terminal that processes trainees' crane operation input, and a training server that stores trainees' training information. The simulator program provides VR-based crane training scenarios implemented with Unity3D, and the IoT driving terminal developed based on Arduino is composed of two controllers and transmits the user's driving operation to the HMD. In particular, the crane simulator in this paper uses a training server to create a database of environment setting values for each educator, progress and training time, and information on driving warning situations. Through the use of such a server, trainees can use the simulator in a more convenient environment and can expect improved educational effects by providing training information.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3C
• /
• pp.115-125
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by insitu test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network (NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. It was already found that NN model can come over the site dependency and prediction accuracy is greatly improved when compared with present theoretical and empirical models. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network (CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. Prediction results of CNN model are compared with those of conventional empirical and theoretical models and multi-layered neural network model, which has the optimized structure. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.4D
• /
• pp.545-551
• /
• 2008

The MOCT(Ministry of Construction & Transportation) gave a order named as "The guideline for computerization and application of geotechnical investigation result" to an affiliated organization in March 2007. Today, pilot project of construction of geotechnical information database is in process to be stable for its system after applying this guideline, and discipline how to input investigated data for related users. We have developed standard for geotechnical investigation result-format, metadata for distribution of geotechnical information and to coordinate based on world geodetic system. Also, We had a introduce to status with respect to use the input system, collect a statistics of input contents. At a result, improvement items of input system is proposed. It was analyzed that most users put to practical use easily as a result of education for making use of on the spot of the developed GIIS. But There were problems with the GIIS as well as complexity of metadata formation, such as error of moving part of information window, and a part of recognition error of install program in accordance with computer OS circumstances. Particularly, to improve some parts of GIIS is needed, because of use of or KNHC (Korea National Housing Corporation)-specific format and difference of input process followed by MOCT's guideline. In this study, it is planning to make up for occurred problems, and improvements when operating and managing the Geotechnical Information DB center in 2008.