• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.39-46
• /
• 2024

Many researchers make efforts to evaluate water quality using various models. Such models require a dataset without missing values, but in real world, most datasets include missing values for various reasons. Simple deletion of samples having missing value(s) could distort distribution of the underlying data and pose a significant risk of biasing the model's inference when the missing mechanism is not MCAR. In this study, to explore the most appropriate technique for handing missing values in water quality data, several imputation techniques were experimented based on existing KNN and MICE imputation with/without the generative neural network model, Autoencoder(AE) and Denoising Autoencoder(DAE). The results shows that KNN and MICE combined imputation without generative networks provides the closest estimated values to the true values. When evaluating binary classification models based on support vector machine and ensemble algorithms after applying the combined imputation technique to the observed water quality dataset with missing values, it shows better performance in terms of Accuracy, F1 score, RoC-AuC score and MCC compared to those evaluated after deleting samples having missing values.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.39-64
• /
• 2024

This study assesses the national AI competitiveness of 38 OECD countries with focus on AI human capital, AI infrastructure, and AI innovation capacity. Utilizing the fuzzy-set ideal type analysis method, these countries were categorized into eight distinct types based on their national AI competitiveness levels, leading to the derivation of pertinent implications. The analysis identified a category termed "AI Leading Country" consisting of North American, Western European, and Nordic countries, along with several Asian nations including South Korea. Remarkably, the United States demonstrated dominant global national AI competitiveness, achieving the highest fuzzy scores across all three evaluative factors. South Korea was classified as an "AI Leading Country" primarily due to its superior AI infrastructure, but its performance in AI human capital and AI innovation capacity was found to be moderate relative to other analyzed nations; thus highlighting the necessity of sustained focus on the accumulation of AI human capital and bolstering of AI innovation capacity.

• Journal of Broadcast Engineering
• /
• v.19 no.5
• /
• pp.640-655
• /
• 2014

Many of today's video systems have additional depth camera to provide extra features such as 3D support. Thanks to these changes made in multimedia system, it is now much easier to obtain depth information of the video. Depth information can be used in various areas such as object classification, background area recognition, and so on. With depth information, we can achieve even higher coding efficiency compared to only using conventional method. Thus, in this paper, we propose the 2D video coding algorithm which uses depth information on top of the next generation 2D video codec HEVC. Background area can be recognized with depth information and by performing HEVC with it, coding complexity can be reduced. If current CU is background area, we propose the following three methods, 1) Earlier stop split structure of CU with PU SKIP mode, 2) Limiting split structure of CU with CU information in temporal position, 3) Limiting the range of motion searching. We implement our proposal using HEVC HM 12.0 reference software. With these methods results shows that encoding complexity is reduced more than 40% with only 0.5% BD-Bitrate loss. Especially, in case of video acquired through the Kinect developed by Microsoft Corp., encoding complexity is reduced by max 53% without a loss of quality. So, it is expected that these techniques can apply real-time online communication, mobile or handheld video service and so on.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.2
• /
• pp.687-697
• /
• 2014

This study ranges from planning phase to the detailed design phase of steel box girder bridge and proposes ways to generate semantic information of components through Industry Foundation Classes (IFC), a data model for Building Information Modeling (BIM). The classification of components of steel box girder bridge was performed to define information items required for identifying semantic information based on IFC, and spatial information items based on topology and physical information items based on functions of components were classified to create additional properties that does not support IFC by applying user-defined property set within the IFC framework. Steel box girder bridge information model based on IFC was implemented through BIM software and semantic information input interface, which was developed in this study to examine the effectiveness of the additionally created user-defined property. Furthermore, the quantity take-off of components was performed through information model of steel box girder bridge, and the applicability of the proposed method was tested by comparing the quantity take-off based on design document with the result.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.4
• /
• pp.393-400
• /
• 2015

This study proposes a method to create and combine a superstructure module by parametric modeling, in order to improve the production efficiency of information model for modular steel bridge superstructure that can be used in planning, design and construction phase. Compound classification was performed in order to derive elements to apply the parametric modeling, and according to assembly condition, the classified elements were grouped into 13 types. In addition, three assembly conditions were derived for production of stable superstructure through combination of superstructure module, which is a production unit for modular steel bridge factory. Parameter that reflects assembly condition in compound shape when producing superstructure module through parametric modeling was deducted. Superstructure module compounds were produced according to type and parameter using interface generation based on Building Information Model(BIM) software that was developed in this study. The superstructure module produced reflects information to combine into a superstructure. To verify this, information model based on Industry Foundation Classes(IFC) was built and confirmed the application in production of superstructure by identifying the reflected property information.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.379-386
• /
• 2004

Video segmentation is a fundamental task in video indexing and it includes two kinds of shot change detections such as the abrupt transition and the gradual transition. The abrupt shot boundaries are detected by computing the image-based distance between adjacent frames and comparing this distance with a pre-determined threshold value. However, the gradual shot boundaries are difficult to detect with this approach. To overcome this difficulty, we propose the method that detects gradual transition in the MPEG compressed video using the HMM (Hidden Markov Model). We take two different HMMs such as a discrete HMM and a continuous HMM with a Gaussian mixture model. As image features for HMM's observations, we use two distinct features such as the difference of histogram of DC images between two adjacent frames and the difference of each individual macroblock's deviations at the corresponding macroblock's between two adjacent frames, where deviation means an arithmetic difference of each macroblock's DC value from the mean of DC values in the given frame. Furthermore, we obtain the DC sequences of P and B frame by the first order approximation for a fast and effective computation. Experiment results show that we obtain the best detection and classification performance of gradual transitions when a continuous HMM with one Gaussian model is taken and two image features are used together.

• Archives of design research
• /
• v.18 no.4 s.62
• /
• pp.165-174
• /
• 2005

The development of digital technologies transforms the design targets, characteristics of the targets and the role of designers. The paper highlights the role of prototyping in the interactive digital product design process and presents the survey and analysis of prototyping tools that can be used by designers in designing such products. From the review of tools in design related fields. the classification framework for the tools were presented. The framework has the criteria of the fidelity of prototypes, the stage when the prototyping is used, and design targets. Based on the analysis, the implications for using the tools are suggested. They includes that prototyping is important in the concept stage for designers and different tools and methods are to be applied according to design targets and objectives. Prototyping tools need to support exploring design concepts without being constrained by implementation technologies The collaboration with other professionals can also help effective prototyping. Existing tools familiar to designers can be effective platforms for the new design problems. The results can be guidlines with which designers choose more appropriate prototyping tools when they face new design problems. It also make practical contribution in improving design efficiency and design education for interactive product design projects.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1617-1617
• /
• 2001

It is well known now that near infrared spectroscopy (NIRS) is a fast, no destructive, and inexpensive analytical technique that could be used to classify, identify, and authenticate a wide range of foods and food items. Therefore, the main aims of this study were to provide a new insight into the authentication of five strawberry (Fragaria x ananassa) varieties and to correlate them with geographical zones and the propagating methods used. Three weeks plants of five different strawberry varieties (F. x ananassa Duch. cv Camarosa, Seascape, Chandler, F. Chiloensis, and F. Virginiana) were cultivated in vitro first and then transferred to pots with special soil, and grown in a greenhouse at CINVESTAV, all varieties were acquired from California (USA). After 18 months, ten leaves from each variety were collected. Transmission spectra from each leave were recorded over a range of 10, 000-4, 000 cm$-^{1}$, 32 scans of each strawberry leave were collected using a resolution of 4 cm$-^{1}$ with a Paragon IdentiCheck FT-NIR System Spectrometer. Triplicates of each strawberry leave were used. All spectra were analyzed using principal component analysis (PCA) and soft independent modeling class analogy (SIMCA). The optimum number of components to be used in the regression was automatically determined by the software. Camarosa was the only variety grown from the same shoot but propagated by a different method (direct or in vitro). Five different classes (varieties) or clusters were observed among samples, however, larger inter class distances were presented by the two wildtype samples (F. Chiloensis and F. Virginiana). Camarosa direct and Camarosa in vitro displayed a small overlapping region between them. On the other hand, Seascape variety presented the smallest rejection percentage among all varieties (more similarities with the rest of the samples). Therefore, it can be concluded that the application of NIRS technique allowed the authentication of all strawberry varieties and geographical origin as well. It was also possible to form subclasses of the same materials. The results presented here demonstrate that NIRS is a very powerful and promising analytical tool since all materials were authenticated and classified based on their variety, origin, and treatment. This is of a tremendous relevance since the variety and origin of a plant material can be established even before it gives its typical fruit or flower.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.6
• /
• pp.723-731
• /
• 2020

The design of offshore plants should reflect the various requirements of the owner and the classification society. For a topside module mounted on an of shore structure, the design process is very demanding because of the large spatial constraints and the many requirements related to marine environmental conditions and safety such as the movement of the structure. In this study, the load acting on the hydraulic power unit, which is one of the main equipment in the topside module, was calculated according to the DNVGL rule; the structural safety was evaluated according to each load condition and the structural reliability of the developed product was improved. For structural analysis, MSC software was used, and structural analysis was performed under five load conditions to review structural safety for various movements. The results show that the maximum stress occurred during pitching toward the stern (Load Case 5). The stress level was approximately 85 % of the allowable stress, and the maximum deformation was approximately 5 % of the allowable value. The structural safety was confirmed, and no intermember interference occurred.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.274-281
• /
• 2020

N-gram analysis casts a new look at the n-word cluster in use different from the previously known idioms. It analyzes a corpus of English textbooks for frequently occurring n consecutive words mechanically using a concordance software, which is different from the previously known idioms. The current paper aims at extracting and comparing 4-gram words clusters between South Korean high school English textbooks and its North Korean counterpart. The classification criteria includes number of tokens and types between the two across oral and written languages in the textbooks. The criteria also use the grammatical categories and functional categories to classify and compare the 4-gram words clusters. The grammatical categories include noun phrases, verb phrases, prepositional phrases, partial clauses and others. The functional categories include deictic function, text organizers, stance and others. The findings are: South Korean high school English textbook contains more tokens and types in both oral and written languages. Verb phrase and partial clause 4-grams are grammatically most frequently encountered categories across both South and North Korean high school English textbooks. Stance is most dominant functional category in both South and North Korean English textbooks.