• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.221-241
• /
• 2018

As we enter the knowledge society, the importance of information as a new form of capital is being emphasized. The importance of information classification is also increasing for efficient management of digital information produced exponentially. In this study, we tried to automatically classify and provide tailored information that can help companies decide to make technology commercialization. Therefore, we propose a method to classify information based on Korea Standard Industry Classification (KSIC), which indicates the business characteristics of enterprises. The classification of information or documents has been largely based on machine learning, but there is not enough training data categorized on the basis of KSIC. Therefore, this study applied the method of calculating similarity between documents. Specifically, a method and a model for presenting the most appropriate KSIC code are proposed by collecting explanatory texts of each code of KSIC and calculating the similarity with the classification object document using the vector space model. The IPC data were collected and classified by KSIC. And then verified the methodology by comparing it with the KSIC-IPC concordance table provided by the Korean Intellectual Property Office. As a result of the verification, the highest agreement was obtained when the LT method, which is a kind of TF-IDF calculation formula, was applied. At this time, the degree of match of the first rank matching KSIC was 53% and the cumulative match of the fifth ranking was 76%. Through this, it can be confirmed that KSIC classification of technology, industry, and market information that SMEs need more quantitatively and objectively is possible. In addition, it is considered that the methods and results provided in this study can be used as a basic data to help the qualitative judgment of experts in creating a linkage table between heterogeneous classification systems.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.145-165
• /
• 2023

Recommendation system plays a significant role on relieving difficulties of selecting information among rapidly increasing amount of information caused by the development of the Internet and on efficiently displaying information that fits individual personal interest. In particular, without the help of recommendation system, E-commerce and OTT companies cannot overcome the long-tail phenomenon, a phenomenon in which only popular products are consumed, as the number of products and contents are rapidly increasing. Therefore, the research on recommendation systems is being actively conducted to overcome the phenomenon and to provide information or contents that are aligned with users' individual interests, in order to induce customers to consume various products or contents. Usually, collaborative filtering which utilizes users' historical behavioral data shows better performance than contents-based filtering which utilizes users' preferred contents. However, collaborative filtering can suffer from cold-start problem which occurs when there is lack of users' historical behavioral data. In this paper, hybrid music recommendation system, which can solve cold-start problem, is proposed based on the playlist data of Melon music streaming service that is given by Kakao Arena for music playlist continuation competition. The goal of this research is to use music tracks, that are included in the playlists, and metadata of music tracks and playlists in order to predict other music tracks when the half or whole of the tracks are masked. Therefore, two different recommendation procedures were conducted depending on the two different situations. When music tracks are included in the playlist, LightFM is used in order to utilize the music track list of the playlists and metadata of each music tracks. Then, the result of Item2Vec model, which uses vector embeddings of music tracks, tags and titles for recommendation, is combined with the result of LightFM model to create final recommendation list. When there are no music tracks available in the playlists but only playlists' tags and titles are available, recommendation was made by finding similar playlists based on playlists vectors which was made by the aggregation of FastText pre-trained embedding vectors of tags and titles of each playlists. As a result, not only cold-start problem can be resolved, but also achieved better performance than ALS, BPR and Item2Vec by using the metadata of both music tracks and playlists. In addition, it was found that the LightFM model, which uses only artist information as an item feature, shows the best performance compared to other LightFM models which use other item features of music tracks.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.3
• /
• pp.329-335
• /
• 2011

The finite element method (FEM) has been used for various fields like mathematics and engineering. However, the FEM has a difficulty in describing the geometric shape exactly due to its property of piecewise linear discretization. Recently, however, a so-called isogeometric analysis method that uses the non-uniform rational B-spline(NURBS) basis function has been developed. The NURBS can be used to describe the geometry exactly and play a role of basis functions for the response analysis. Nevertheless, constructing the NURBS basis functions in analysis is as costly as a meshing process in the FEM. Since the isogeometric method shares geometric data with CAD, it is possible to intactly import the model data from commercial CAD tools. In this paper, we use the Rhinoceros 3D software to create CAD models and export in the form of STEP file. The information of knot vectors and control points in the NURBS is utilized in the isogeometric analysis. Through some numerical examples, the accuracy of isogeometric method is compared with that of FEM. Also, the efficiency of the isogeometric method that includes the CAD and CAE in a unified framework is verified.

• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.544-555
• /
• 2011

The acute toxicity in the rainbow trout (Oncorhynchus mykiss) was analyzed and predicted using quantitative structure-activity relationships (QSAR). The aquatic toxicity, 96h $LC_{50}$ (median lethal concentration) of 275 organic pesticides, was obtained from EU-funded project DEMETRA. Prediction models were derived from 558 2D molecular descriptors, calculated in PreADMET. The linear (multiple linear regression) and nonlinear (support vector machine and artificial neural network) learning methods were optimized by taking into account the statistical parameters between the experimental and predicted p$LC_{50}$. After preprocessing, population based forward selection were used to select the best subsets of descriptors in the learning methods including 5-fold cross-validation procedure. The support vector machine model was used as the best model ($R^2_{CV}$=0.677, RMSECV=0.887, MSECV=0.674) and also correctly classified 87% for the training set according to EU regulation criteria. The MLR model could describe the structural characteristics of toxic chemicals and interaction with lipid membrane of fish. All the developed models were validated by 5 fold cross-validation and Y-scrambling test.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.329-341
• /
• 2014

Kernel-based mean-shift object tracking has gained more interests nowadays, with the aid of its feasibility of reliable real-time implementation of object tracking. This algorithm calculates the best mean-shift vector based on the color histogram similarity between target model and target candidate models, where the color histograms are usually produced after uniform color-space quantization for the implementation of real-time tracker. However, when the image of target model has a reduced contrast, such uniform quantization produces the histogram model having large values only for a few histogram bins, resulting in a reduced accuracy of similarity comparison. To solve this problem, a non-uniform quantization algorithm has been proposed, but it is hard to apply to real-time tracking applications due to its high complexity. Therefore, this paper proposes a fast non-uniform color-space quantization method using the histogram equalization, providing an adjusted histogram distribution such that the bins of target model histogram have as many meaningful values as possible. Using the proposed method, the number of bins involved in similarity comparison has been increased, resulting in an enhanced accuracy of the proposed mean-shift tracker. Simulations with various test videos demonstrate the proposed algorithm provides similar or better tracking results to the previous non-uniform quantization scheme with significantly reduced computation complexity.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.527-536
• /
• 2017

With the recent development of smart grid industry, the necessity for efficient EMS(Energy Management System) has been increased. In particular, in order to reduce electric load and energy cost, sophisticated electric load forecasting and efficient smart grid operation strategy are required. In this paper, for more accurate electric load forecasting, we extend the data collected at demand time into high time resolution and construct an artificial neural network-based forecasting model appropriate for the high time resolution data. Furthermore, to improve the accuracy of electric load forecasting, time series data of sequence form are transformed into continuous data of two-dimensional space to solve that problem that machine learning methods cannot reflect the periodicity of time series data. In addition, to consider external factors such as temperature and humidity in accordance with the time resolution, we estimate their value at the time resolution using linear interpolation method. Finally, we apply the PCA(Principal Component Analysis) algorithm to the feature vector composed of external factors to remove data which have little correlation with the power data. Finally, we perform the evaluation of our model through 5-fold cross-validation. The results show that forecasting based on higher time resolution improve the accuracy and the best error rate of 3.71% was achieved at the 3-min resolution.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.4
• /
• pp.329-334
• /
• 2017

The structures, which are made up with the huge number of degrees-of-freedom and the assembly of substructures, have a great complexity. In order to increase the computational efficiency, the analysis models have to be simplified. Many substructuring techniques have been developed to simplify large-scale engineering problems. The techniques are very powerful for solving nonlinear problems which require many iterative calculations. In this paper, a modal derivatives-based model order reduction method, which is able to capture the stretching-bending coupling behavior in geometrically nonlinear systems, is adopted and investigated for its performance evaluation. The quadratic terms in nonlinear beam theory, such as Green-Lagrange strains, can be explained by the modal derivatives. They can be obtained by taking the modal directional derivatives of eigenmodes and form the second order terms of modal reduction basis. The method proposed is then applied to a co-rotational finite element formulation that is well-suited for geometrically nonlinear problems. Numerical results reveal that the end-shortening effect is very important, in which a conventional modal reduction method does not work unless the full model is used. It is demonstrated that the modal derivative approach yields the best compromised result and is very promising for substructuring large-scale geometrically nonlinear problems.

• Journal of Radiation Protection and Research
• /
• v.16 no.2
• /
• pp.41-54
• /
• 1991

This paper aimed to analyse dose sensitivity to the controllable parameters of indoor radon $(^{222}Rn)$ and its decay products (Rn-D) by applying the input~output linear system theory. Physical behaviors of $^{222}Rn\;&\;Rn-D$ were analyzed in terms of $(^{222}Rn)$ gas -generation, -migation and -infiltration to indoor environments, and the performance output-function, i. e. mean dose equivalent to Tracho-Bronchial (TB) lung region, was assessed to the following extented ranges of the controllable paramenters; a) the ventilation rate $constant({\lambda}_v)\;:\;0{\sim}50[h^{-l}].\;b)$ the attachment rate $constant({\lambda}_a)\;:\;0{\sim}500[h^{-l}].\;c)$ the unattached-deposition rate constant (${\lambda}^u_d)\;:\;0-50[h-l]$. A linear input-output model was reconstructed from the original models in literatures, as follows, which was modified into the matrices consisting of 111 nodal equations; a) indoor $^{222}Rn\;&\;Rn-D$ Behaviour; Jacobi-Porstendoerfer-Bruno model.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1101-1117
• /
• 2018

The clear sky radiance (CSR) is one of the baseline products of the Himawari-8 which was launched on October, 2014. The CSR contributes to numerical weather prediction (NWP) accuracy through the data assimilation; especially water vapor channel CSR has good impact on the forecast in high level atmosphere. The focus of this study is the quality analysis of the CSR of the Himawari-8 geostationary satellite. We used the operational CSR (or clear sky brightness temperature) products in JMA (Japan Meteorological Agency) as observation data; for a background field, we employed the CSR simulated using the Radiative Transfer for TOVS (RTTOV) with the atmospheric state from the global model of KMA (Korea Meteorological Administration). We investigated data characteristics and analyzed observation minus background statistics of each channel with respect to regional and seasonal variability. Overall results for the analysis period showed that the water vapor channels (6.2, 6.9, and $7.3{\mu}m$) had a positive mean bias where as the window channels(10.4, 11.2, and $12.4{\mu}m$) had a negative mean bias. The magnitude of biases and Uncertainty result varied with the regional and the seasonal conditions, thus these should be taken into account when using CSR data. This study is helpful for the pre-processing of Himawari-8/Advanced Himawari Imager (AHI) CSR data assimilation. Furthermore, this study also can contribute to preparing for the utilization of products from the Geo-Kompsat-2A (GK-2A), which will be launched in 2018 by the National Meteorological Satellite Center (NMSC) of KMA.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.1-7
• /
• 2021

Detect and avoid (DAA) system, which is essential for the operation of UAS, detects intruding aircraft and offers the ranges of turn and climb/descent maneuver that are required to avoid the intruder. This paper uses detect and avoid alerting logic for unmanned systems (DAIDALUS) developed at NASA as a DAA algorithm. Since DAIDALUS offers ranges of avoidance maneuvers, the actual avoidance maneuver must be decided by the UAS pilot as well as the timing and method of returning to the original route. It can be readily used in real-time human-in-the-loop (HiTL) simulations where a human pilot is making the decision, but a pilot decision model is required in fast-time simulations that proceed without human pilot intervention. This paper proposes a pilot decision model that maneuvers the aircraft based on the DAIDALUS avoidance maneuver range. A series of tests were conducted using test vectors from radio technical commission for aeronautics (RTCA) minimum operational performance standards (MOPS). The alert levels differed by the types of encounters, but loss of well clear (LoWC) was avoided. This model will be useful in fast-time simulation of high-volume traffic involving UAS.