• Journal of the Korean Geotechnical Society
• /
• v.21 no.8
• /
• pp.73-84
• /
• 2005

A three layered neural network model was developed using back propagation algorithm to estimate the UU undrained shear strength of Korean soft soil based on the database of actual undrained shear strengths and piezocone measurements compiled from 8 sites over the Korea. The developed model was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was also compared with conventional empirical methods. It was found that the number of neuron in hidden layer is different for the different combination of transfer functions of neural network models. However, all piezocone neural network models are successful in inferring a complex relationship between piezocone measurements and the undrained shear strength of Korean soft soils, which give relatively high coefficients of determination ranging from 0.69 to 0.72. Since neural network model has been generalized by self-learning from database of piezocone measurements and undrained shear strength over the various sites, the developed neural network models give more precise and generally reliable undrained shear strengths than empirical approaches which still need site specific calibration.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.10
• /
• pp.23-37
• /
• 2013

In this paper, the proposed movie recommender system constructs trust network, which is similar to social network, using user's trust information that users explicitly present. Recommendation on items is performed by using relation degree between users and information of recommended item is provided by a visualization method. We discover the hidden relationships via the constructed trust network. To provide visualized recommendation information, we employ Freebase which is large knowledge base supporting information such as movie, music, and people in structured format. We provide three visualization methods as the followings: i) visualization based on movie posters with the number of movies that user required. ii) visualization on extra information such as director, actor and genre and so on when user selected a movie from recommendation list. iii) visualization based on movie posters that is recommended by neighbors who a user selects from trust network. The proposed system considers user's social relations and provides visualization which can reflect user's requirements. Using the visualization methods, user can reach right decision making on items. Furthermore, the proposed system reflects the user's opinion through recommendation visualization methods and can provide rich information to users through LOD(Linked Open Data) Cloud such as Freebase, LinkedMDB and Wikipedia and so on.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.67-78
• /
• 2017

Traffic congestion cost is increasing annually. Specifically congestion caused by the CDB traffic contains more than a half of the total congestion cost. Recent advancement in the field of Big Data, AI paved the way to industry revolution 4.0. And, these new technologies creates tremendous changes in the traffic information dissemination. Eventually, accurate and timely traffic information will give a positive impact on decreasing traffic congestion cost. This study, therefore, focused on developing both recurrent and non-recurrent congestion prediction models on urban roads by adopting Recurrent Neural Network(RNN), a tribe in machine learning. Two hidden layers with scaled conjugate gradient backpropagation algorithm were selected, and tested. Result of the analysis driven the authors to 25 meaningful links out of 33 total links that have appropriate mean square errors. Authors concluded that RNN model is a feasible model to predict congestion.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.4
• /
• pp.66-74
• /
• 2016

In what way is the urban landscape of North Korea used today, and what features do people prefer in the North Korean landscape? This study analyzed the characteristics of Pyongyang landscapes and their effects, based on an analysis of Western tourists motivation for tourism in North Korea and preferred enjoyment-seeking experiences. Using data from the tourist agency specializing in Western tourism in North Korea and a location based photo-sharing service, the study interprets the visual distinctiveness of Pyongyang landscape. The study concluded that widely known risk to travelers in North Korea is in fact an attraction, making people want to visit directly. However, this risk was mitigated in practical experience by the overall intermediation of the tourism agency and locals' conscious behavior to keep their distance from foreigners. Next, the scope of National ritual attributes was expanded to the locals' daily life as well as large-scale events such as mass games and military parades only if for national holidays. Also, the most preferred factors contributing to North Korean tourism were based on departure from routine through mobilization of the residents. This indicates the extension that the nature of North Korea as a theater state. The Pyongyang landscape represents a world politically isolated, people's congregated motion to display to the world, and people's lives hidden beneath a veil. These visualities fulfill the fantasy of Westerners regarding North Korea. Furthermore, these are superficial images that help create a basis to maintain the North Korea regime.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.472-483
• /
• 2004

Many metadata registry management systems have been developed, which are based on ISO/IEC ll179. However, they do not follow the international standard, ISO/IEC ll179 nor provide some of mandatory functions. It is difficult to a develop metadata registry management system for domestic environment because of their hidden implementations. The goals of this paper are to solve the problems of the existing systems and to develop a metadata registry management systems for accumulation of primitive technologies. This paper also shows the metadata registry building process for the science and technology information field using the developed system. This system consists of Metadata Registry Layer, Core Component Layer, Extension Layer, and Service Interface Layer. The developed metadata registry management system follows ISO/IEC ll179 and contains mandatory functions for practical use. Therefore, it can be used as a guideline for building metadata registries and a development process of metadata registry management systems. We can easily reuse its components for development of metadata registry management systems in various fields because the system is designed and implemented based on the component-based development methodology. It also decreases time and cost for developing systems.

• Korean Journal of Social Welfare Studies
• /
• v.44 no.1
• /
• pp.61-87
• /
• 2013

The main purpose of this paper is to analyze the quality of life of poor women. This study utilized data combined KLIPS with Time Use Survey for an analysis and analyzed time at the intersection of the class and gender. With discretionary time as center, this study investigated poverty status from the quality of life. And in order to make comparison more clearly, object was classified into 4 groups; non-poor male, poor male, non-poor female and poor female. Study results are as follows; First of all, poor women had the shortest discretionary time among all the groups and also had highest poverty rate of living quality. And this study found that deprivation of non-poor female headed householder is serious. Second, analysis of inequality level between and within groups through Theil index indicated that gender influence in poor strata was 3 times higher than that of non-poor strata. This study found that poor women experienced mixed exclusion at the point where gender and class crossed. And this study also has a meaning that an empirical analysis was conducted through above matters on secondary poverty and hidden poverty of poor women which existing researches were unable to discover.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.5
• /
• pp.593-600
• /
• 2019

The similarity in tones between speakers can lower the performance of speaker verification. To improve the performance of speaker verification systems, we propose a multi-task learning technique using deep neural network to learn speaker information and age information. Multi-task learning can improve generalization performances, because it helps deep neural networks to prevent hidden layers from overfitting into one task. However, we found in experiments that learning of age information does not work well in the process of learning the deep neural network. In order to improve the learning, we propose a method to dynamically change the objective function weights of speaker identification and age estimation in the learning process. Results show the equal error rate based on RSR2015 evaluation data set, 6.91 % for the speaker verification system without using age information, 6.77 % using age information only, and 4.73 % using age information when weight change technique was applied.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.530-536
• /
• 2021

Recently, due to the development of deep learning, end-to-end speech recognition, which directly maps graphemes to speech signals, shows good performance. Especially, among the end-to-end models, conformer shows the best performance. However end-to-end models only focuses on the probability of which grapheme will appear at the time. The decoding process uses a greedy search or beam search. This decoding method is easily affected by the final probability output by the model. In addition, the end-to-end models cannot use external pronunciation and language information due to structual problem. Therefore, in this paper conformer with lexicon transducer is proposed. We compare phoneme-based model with lexicon transducer and grapheme-based model with beam search. Test set is consist of words that do not appear in training data. The grapheme-based conformer with beam search shows 3.8 % of CER. The phoneme-based conformer with lexicon transducer shows 3.4 % of CER.

• Cross-Cultural Studies
• /
• v.48
• /
• pp.135-191
• /
• 2017

The purpose of this study was to select words with "shared cultural charge" that are unique in French culture and to study cultural content hidden in these words. It also explores the cultural phenomenon of same French borrowed words used in the Korean language. The study was conducted from two perspectives: perspective of internal French culture defined by Galisson and inter-cultural perspective. The first section of this study introduces the theory "lexiculture" and definition of the words "shared cultural charge." In the following section, among main items of 795 borrowed words in the Korean language, we examined seven words in areas such as clothing, food, and housing. We studied content of the French culture according to the following three categories: (1) dictionary definition, (2) cultural phenomena, (3) special phenomenon in idiomatic expression. Our study illustrated a special connotation beyond the dictionary definition of words. In the next section, we examined the birth of a new cultural phenomenon and process of acquiring a new meaning in the Korean language. Finally, we analyzed differences and similarities between linguistic and cultural elements in both cultures. In this study, we provide basic data for inter-cultural education between France and Korea.

• Journal of the Korean earth science society
• /
• v.40 no.2
• /
• pp.163-176
• /
• 2019

The Potosinian geological basement in central Mexico is comprised of the Upper Paleozoic metamorphic rocks, which crop out on the Sierra de Catorce nucleus located in the northeastern part of the state. The sedimentary sequence that covers unconformably the Paelozoic basement is represented by an Upper Triassic marine sedimentary sequence, correlating to the Zacatecas Formation and the Upper Triassic continental Huizachal Formation red beds, which in turn are covered either by La Joja Formation Jurassic red beds or by Upper Jurassic marine sediments. This sequence is overlain by the conformable Cretaceous calcareous marine sedimentary rocks in all the state of San Luis Potosi. The Cenozoic sequence unconformably covers some of the aforementioned rocks and is represented by undifferentiated volcanic rocks as well as by marine clastic rocks. The existing intrusive igneous rocks are felsic to intermediate composition, and they intrude the metamorphic basement and sedimentary rocks. Conglomerates with evaporitic sediments were deposited during the Pleistocene. The Quaternary sequence includes basalt flows, piedmont deposits, alluvium, and occasionally evaporites and caliche layers. In the state of San Luis Potosi, a great diversity of mineral deposit types is known as both metallic and nonmetallic. The host rocks of these deposits vary from one another including formations that represent from Paleozoic up to Tertiary. The mineralization age corresponds approximately to Tertiary (75%), and is mainly epigenetic. Conclusively, the data on geology and mineralization in San Luis Potosi, Mexico are helpful to predict a hidden ore body and select promising mineralized zone(s) when the domestic company makes inroads in the mining sector of Mexico.