• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.143-151
• /
• 2001

This paper investigates the development of a neural network based system for automated signature authentication that relies on an autoregressive characterization for the segments of a signature. The primary contributions of this work are tow-fold: a) the development of the neural network architecture and the modalities of training it, b) adaptation of the dynamic time warping algorithm to fomulate a new method for enabling consistent segmentation of multiple signatures from the same writer. The performance of the signature verification system has been tested using a sizable database that includes a comprehensive set of simulated and realistic forgeries. False Acceptance and False Rejection error rates of 0.78% and 1.6% respectively were obtained in tests conducted using 1920 skilled forgeries.

• Journal of the Korean housing association
• /
• v.13 no.4
• /
• pp.19-26
• /
• 2002

Despite its relatively small size, at least compared to other architectural programs, the house figures large in the cultural imagination. Closely identified with the individual and nuclear family, it has been frequently considered as an expression of widely held, even universal, values. Conversely, the private house has also been emblematic of more subjective desires, that change not only from person to person but from generation to generation. Certain conclusions can be drawn about the status of the private house at the end of the century, both as cultural invention and as a product of the autonomous discipline of architecture. The contemporary loftlike living space is similarly associated with work, given its emergence as an alternative home for individuals wanting space in which to live and work. In the case of what might be called the "un-private house", it is ofen a digital presence and the change of family system. This study was conducted to define the un-private house through public/private. The architectural characteristics of un-private house are as follows; 1) Alternatives- large open space with multiple function and collective free plan 2) Dematerialization- steel and glass with visual openness and ambiguity 3) Digital & Interfaces- fold and screen using technology and program. Especially, the un-private house is designed to provide individuals with emotional, superficial, and synergistic space, focusing on the personal life-style.

• Journal of the Korean housing association
• /
• v.26 no.6
• /
• pp.1-8
• /
• 2015

This study aims to develop a solution to inter-floor noise complaints by exploring cases of noise complaints between floors and by identifying the demands and needs of the residents. For this purpose, a survey was conducted targeting residents who were sorted into groups depending on their experiences with inter-floor noise. This survey was carried out from June 11, 2014 to June 16, 2014. A total of 100 copies of the questionnaire was distributed to the residents, of which 98 were completed and collected. Data were statistically processed in accordance with SPSS WIN 18.0. The results showed that the leading causes of inter-floor noise complaints were residents' differences in schedules and their inconsideration in behavior. Thus, the solution to this issue is three-fold: first, to take social measures in order to improve communication and understanding between residents so they can be mindful of their noise levels; second, to reinforce noise control regulation; and third, to improve noise reduction design within the building architecture.

• Journal of Fashion Business
• /
• v.7 no.6
• /
• pp.10-20
• /
• 2003

The object of this research is to develop the designs with aesthetics and function for making the uniforms of specialty restaurants of Korean dishes in pursuit of the image of excellent dignity and its result is as follows: As for designs, this research chose the traditional image as the basic concept and made visual Korean lines, colors, and patterns. As for lines, it made visual the curve of the eaves, the straight line of polls, and the fret of windows and doors represented in architecture and applied them, as for color tones, it chose traditional 'Obangsaek', five direction colors. As for the patterns, it symbolized 4 trigrams( Geon, Gon, Gam, and Yi), the cloud pattern, also it tried to get the formative beauty from traditional patchwork wrapping cloth and windows and doors. The expectant effects on the design of Uniform are as follows: First, it offered basic clothes for male and female employees working in the hall and suggested two kinds of skirt and pants for the latter. It tried to find out both the function of pants and the female beauty of skirts by wrapping on pants to eliminate the feeling of rejection towards the style of them, the use of which have been recognized for man only in spite of many merits of them. Second, it sought for the characteristics of shape on collar, breast-tie, and fold etc. of Korean clothes and designed clothes according to each employee's role and finally emphasized their traditional aesthetics.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.3
• /
• pp.69-76
• /
• 2021

Precast concrete (PC) modules have been increased its use in modular buildings due to their better seismic performance than steel modules. The main issue of the PC module is to ensure structural performance with appropriate connection methods. This study proposed a PC modular beam system for simple construction and improved structural and splicing performance. This modular system consisted of modules with steel plates inserted, and it is easy to construct by bolted connection. The steel plates play the role of tensile rebar and stirrup, which has the advantage of structural performance. The structural performance of the proposed PC modular beam system was evaluated by flexural test on one reinforced concrete (RC) beam specimen consisting of a monolithic, and two PC specimens with the proposed PC modular beam system. The results demonstrated that the proposed PC modular beam system achieved approximately 86% of the structural performance compared to the RC monolithic specimen, with similar ductility of approximately 1.06 fold greater.

• Journal of Platform Technology
• /
• v.6 no.4
• /
• pp.26-33
• /
• 2018

In this paper, we propose an image retrieval algorithm for real-time processing and design it as hardware. The proposed method is based on the classification of BoWs(Bag of Words) algorithm and proposes an image search algorithm using bit stream. K-fold cross validation is used for the verification of the algorithm. Data is classified into seven classes, each class has seven images and a total of 49 images are tested. The test has two kinds of accuracy measurement and speed measurement. The accuracy of the image classification was 86.2% for the BoWs algorithm and 83.7% the proposed hardware-accelerated software implementation algorithm, and the BoWs algorithm was 2.5% higher. The image retrieval processing speed of BoWs is 7.89s and our algorithm is 1.55s. Our algorithm is 5.09 times faster than BoWs algorithm. The algorithm is largely divided into software and hardware parts. In the software structure, C-language is used. The Scale Invariant Feature Transform algorithm is used to extract feature points that are invariant to size and rotation from the image. Bit streams are generated from the extracted feature point. In the hardware architecture, the proposed image retrieval algorithm is written in Verilog HDL and designed and verified by FPGA and Design Compiler. The generated bit streams are stored, the clustering step is performed, and a searcher image databases or an input image databases are generated and matched. Using the proposed algorithm, we can improve convenience and satisfaction of the user in terms of speed if we search using database matching method which represents each object.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.4
• /
• pp.81-88
• /
• 2023

Numerous factors contribute to the deterioration of reinforced concrete structures. Elevated temperatures significantly alter the composition of the concrete ingredients, consequently diminishing the concrete's strength properties. With the escalation of global CO2 levels, the carbonation of concrete structures has emerged as a critical challenge, substantially affecting concrete durability research. Assessing and predicting concrete degradation due to thermal effects and carbonation are crucial yet intricate tasks. To address this, multiple prediction models for concrete carbonation and compressive strength under thermal impact have been developed. This study employs seven machine learning algorithms-specifically, multiple linear regression, decision trees, random forest, support vector machines, k-nearest neighbors, artificial neural networks, and extreme gradient boosting algorithms-to formulate predictive models for concrete carbonation and thermal impact. Two distinct datasets, derived from reported experimental studies, were utilized for training these predictive models. Performance evaluation relied on metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analytical outcomes demonstrate that neural networks and extreme gradient boosting algorithms outshine the remaining five machine learning approaches, showcasing outstanding predictive performance for concrete carbonation and thermal effect modeling.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

• Korea Science and Art Forum
• /
• v.37 no.5
• /
• pp.119-133
• /
• 2019

This study is as skyscrapers are becoming increasingly taller, more constructors have decided the height alone cannot be a sufficient differentiator. As a result, atypical architecture is emerging as a new competitive factor. Also, it can be used for symbolizing the economic competitiveness of a country, city, or business through its form. Before the introduction of digital media, there was a discrepancy between the structure and form of a building and correcting this discrepancy required a separate structural medium. Since the late 1980s, however, digitally-based atypical form development began to be used experimentally, and, until the 2000s, it was used mostly for super-tall skyscrapers for offices or for industrial chimneys and communication towers. Since the 2000s, many global brand hotels and commercial and residential buildings have been built as super-tall skyscrapers, which shows the recent trend in architecture that is moving beyond the traditional limits. Complex atypical structure is formed and the formative characteristics of diagonal lines and curved surfaces, which are characteristics of atypical architecture, are created digitally. Therefore, it's goal is necessary to identify a new relationship between the structure and forms. According to the data of Council on Tall Buildings and Urban Habitat (CTBUH), 100-story and taller buildings were classified into typical, diagonal, curved, and segment types in order to define formative shapes of super-tall skyscrapers and provide a ground of the design process related to the initial formation of the concept. The purpose of this study was to identify the correlation between different forms for building atypical architectural shapes that are complex and diverse. The study results are presented as follows: Firstly, complex function follows convergence form characteristics. Secondly, fold has inside of architecture with repeat. Thirdly, as curve style which has pure twist, helix twist, and spiral twist. The findings in this study can be used as basic data for classifying and predicting trends of the future super-tall skyscrapers.