• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• The KIPS Transactions:PartB
• /
• v.12B no.2 s.98
• /
• pp.209-214
• /
• 2005

The use of protein interaction data is highly reliable for predicting functions to proteins without function in proteomics study. The computational studies on protein function prediction are mostly based on the concept of guilt-by-association and utilize large-scale interaction map from revealed protein-protein interaction data. This study compares graph-based approaches such as neighbor-counting and $\chi^2-statistics$ methods using protein-protein interaction data and proposes an approach that is effective in analyzing large-scale protein interaction data. The proposed approach is also based protein interaction map but sequence similarity and heuristic knowledge to make prediction results more reliable. The test result of the proposed approach is given for KDD Cup 2001 competition data along with those of neighbor-counting and $\chi^2-statistics$ methods.

• Journal of Navigation and Port Research
• /
• v.28 no.6
• /
• pp.517-523
• /
• 2004

The container load planning is one of key factors for efficient operations of handling equipments at container ports. When the number of containers are large, finding a good solution using the conventional genetic algorithm is very time consuming. To obtain a good solution with considerably small effort, in this paper a pseudo-parallel genetic algorithm(PPGA) based on both the migration model and the ring topology is developed The performance of the PPGA is demonstrated through a test problem of determining the optimal loading sequence of the containers.

• Korean Journal of Materials Research
• /
• v.4 no.3
• /
• pp.301-311
• /
• 1994

The growth of amorphous and first crystalline phase, and phase sequence by solid state reaction were examined in Co/Si multilayer thin films by DSC and XRD. The experimental results were compared with the results expected by effective driving force models, PDF and effective heat of formation models.Amorphous phase growth was not observed in Co/Si system and it was consistent with the predicted result by effective driving force. It was observed that the first crystalline phase is CoSi. According to the PDF and effective heat of formation models, the first crystalline phases were CoSi and $CO_2Si$, respectively. The experiemental results were coincident with the PDF model considering structure factors. In case of the atomic concentration ratios of 2Co : 1Si and 1Co : 2Si, the phases sequences were $CoSi\to Co_2Si$ and $CoSi \to Co_2Si \to CoSi \to CoSi_2$, respectively and it was analysized through the effective heat of formation model. The formations of CoSi, $CO_2Si$ and $COSi_2$ in initial stage were controlled by nucleation and the activation energies for the nucleation of three phases were 1.71, 2.34 and 2.79eV.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.379-387
• /
• 2003

A lot of microbial genome projects have been completed to pour the enormous amount of genomic sequence data. In this context. the problem of identifying promoters in genomic DNA sequences by computational methods has attracted considerable research attention in recent years. In this paper, we propose a new model of prokaryotic core promoter region including the -10 region and transcription initiation site, that is Dependency-Reflecting Decomposition Model (DRDM), which captures the most significant biological dependencies between positions (allowing for non-adjacent as well as adjacent dependencies). DRDM showed a good result of performance test and it will be employed effectively in predicting promoters in long microbial genomic Contigs.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.21 no.1
• /
• pp.63-78
• /
• 2009

This paper presents the development of dynamically combined Typhoon generated surge-tide-wave numerical model which is applicable to shallow water. The newly developed model is based on both POM (Princeton Ocean Model) for the surge and tide and WAM (WAve Model) for wind-generated waves, but is modified to be applicable to shallow water. In this paper which is the first paper of the two in a sequence, we verified the accuracy and numerical stability of the hydrodynamic part of the model which is responsible for the simulation of Typhoon generated surge and tide. In order to improve the accuracy and numerical stability of the combined model, we modified algorithms responsible for turbulent modeling as well as vertical velocity computation routine of POM. Verification of the model performance had been conducted by comparing numerical simulation results with analytic solutions as well as data obtained from field measurement. The modified POM is shown to be more accurate and numerically stable compare to the existing POM.

• Journal of Broadcast Engineering
• /
• v.3 no.1
• /
• pp.50-60
• /
• 1998

This paper addresses a problem of extraction of parameteric motion estimation and structural motion segmentation for compact image sequence representation and object-based generic video coding. In order to extract meaningful motion structure from image sequences, a direct parameteric motion estimation based on a pre-segmentation is proposed. The pre-segmentation which considers the motion of the moving objects is canied out based on probabilistic clustering with mixture models using optical flow and image intensities. Parametric motion segmentation can be obtained by iterated estimation of motion model parameters and region reassignment according to a criterion using Gauss-Newton iterative optimization algorithm. The efficiency of the proposed methoo is verified with computer simulation using elF real image sequences.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.639-646
• /
• 2003

This paper proposes a neural network model for extracting optical illusions produced by a sequence of discontinuous dot stimuli. The proposed model is based on visual cell's characters founded by visual information processing path. This study approaches on the basis of physiological observation of the perceptual phenomena that some simple ways of discrete dots are perceived as a continuous virtual contour rather than as separate dots. This paper presents the implementation of the optical illusions from discrete dot stimuli that are composed of virtual polygons from 6 to 10 dots. This experimental data are similar to those of Smith & Vos's physiological experiments. The proposed model shows that it can extract continuous illusion contours from discrete dot stimuli successfully.

• Journal of Information Technology Services
• /
• v.21 no.2
• /
• pp.109-126
• /
• 2022

The number and variety of products and services offered by companies have increased dramatically, providing customers with more choices to meet their needs. As a solution to this information overload problem, the provision of tailored services to individuals has become increasingly important, and the personalized recommender systems have been widely studied and used in both academia and industry. Existing recommender systems face important problems in practical applications. The most important problem is that it cannot clearly explain why it recommends these products. In recent years, some researchers have found that the explanation of recommender systems may be very useful. As a result, users are generally increasing conversion rates, satisfaction, and trust in the recommender system if it is explained why those particular items are recommended. Therefore, this study presents a methodology of providing an explanatory function of a recommender system using a review text left by a user. The basic idea is not to use all of the user's reviews, but to provide them in a summarized form using only reviews left by similar users or neighbors involved in recommending the item as an explanation when providing the recommended item to the user. To achieve this research goal, this study aims to provide a product recommendation list using user-based collaborative filtering techniques, combine reviews left by neighboring users with each product to build a model that combines text summary methods among deep learning-based natural language processing methods. Using the IMDb movie database, text reviews of all target user neighbors' movies are collected and summarized to present descriptions of recommended movies. There are several text summary methods, but this study aims to evaluate whether the review summary is well performed by training the Sequence-to-sequence+attention model, which is a representative generation summary method, and the BertSum model, which is an extraction summary model.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.3
• /
• pp.141-148
• /
• 2017

The current advancement of mobile devices enables users to collect a sequence of user positions by use of the positioning technology and thus the related research regarding positioning or location information are quite arising. An individual mobility model based on positioning data and time data are already established while group mobility model is not done yet. In this research, group mobility model, an extension of individual mobility model, and the process of establishment of group mobility model will be studied. Based on the previous research of group mobility model from two individual mobility model, a group mobility model with more than two individual model has been established and the transition pattern of the model is represented by Markov chain. In consideration of real application, the computing time to establish group mobility mode from huge positioning data has been drastically improved by use of GPGPU comparing to the use of traditional multicore systems.