• Journal of KIISE:Software and Applications
• /
• v.29 no.9
• /
• pp.654-668
• /
• 2002

In this paper, we present an empirical study for improving the Korean text chunking based on machine learning and feature set selection approaches. We focus on two issues: the problem of selecting feature set for Korean chunking, and the problem of alleviating the data sparseness. To select a proper feature set, we use a heuristic method of searching through the space of feature sets using the estimated performance from a machine learning algorithm as a measure of "incremental usefulness" of a particular feature set. Besides, for smoothing the data sparseness, we suggest a method of using a general part-of-speech tag set and selective lexical information under the consideration of Korean language characteristics. Experimental results showed that chunk tags and lexical information within a given context window are important features and spacing unit information is less important than others, which are independent on the machine teaming techniques. Furthermore, using the selective lexical information gives not only a smoothing effect but also the reduction of the feature space than using all of lexical information. Korean text chunking based on the memory-based learning and the decision tree learning with the selected feature space showed the performance of precision/recall of 90.99%/92.52%, and 93.39%/93.41% respectively.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.13 no.5
• /
• pp.820-830
• /
• 1989

The tire inflation and contact problem has been solved by a finite element method. The finite element formulation is derived from the equilibrium equations by the principle of virtual work in the form of an updated Lagrangian formulation for incremental analysis. Then, a contact formulation is added to the finite element formulation to calculate stress state of tire in contact with flat rigid road under the load due to the self-weight of a vehicle. In the finite element analysis, equations of effective material properties are introduced to analyze a plane strain model of the shell-like tire by considering the bending effect of reinforced steel cords. The proposed equations of effective material properties produced stress concentration around the edge of belt layers, which does not appear when other well-known equations of material properties are adopted. The result from the above algorithm demonstrates the validity of the formulation and the proposed equations for the effective elastic constants. The result fully interprets the cause of separation between belt layers by showing the stress concentration.

• Geomechanics and Engineering
• /
• v.18 no.1
• /
• pp.11-20
• /
• 2019

The purpose of this study was to propose a new approach for quantifying in situ rock mass damage, which would include a degree-of-damage and the degraded strength of a rock mass, along with its prediction based on real-time Acoustic Emission (AE) observations. The basic approach for quantifying in-situ rock mass damage is to derive the normalized value of measured AE energy with the maximum AE energy, called the degree-of-damage in this study. With regard to estimation of the AE energy, an AE crack source location algorithm of the Wigner-Ville Distribution combined with Biot's wave dispersion model, was applied for more reliable AE crack source localization in a rock mass. In situ AE wave attenuation was also taken into account for AE energy correction in accordance with the propagation distance of an AE wave. To infer the maximum AE energy, fractal theory was used for scale-independent AE energy estimation. In addition, the Weibull model was also applied to determine statistically the AE crack size under a jointed rock mass. Subsequently, the proposed methodology was calibrated using an in situ test carried out in the Underground Research Tunnel at the Korea Atomic Energy Research Institute. This was done under a condition of controlled incremental cyclic loading, which had been performed as part of a preceding study. It was found that the inferred degree-of-damage agreed quite well with the results from the in situ test. The methodology proposed in this study can be regarded as a reasonable approach for quantifying rock mass damage.

• The KIPS Transactions:PartD
• /
• v.10D no.5
• /
• pp.859-872
• /
• 2003

Class hierarchies often constitute the backbone of object-oriented software. Their quality is therefore quite crucial. Building class hierarchies with good qualify is a very important and common tasks on the object oriented software development, but such hierarchies are not so easy to build. Moreover, the class hierarchy structure under construction is frequently restructured and refined until it becomes suitable for the requirement on the iterative and incremental development lifecycle. Therefore, there has been renewal of interest in all methodologies and tools to assist the object oriented developers in this task. In this paper, we define a set of quantitative metrics which provide a wav of capturing features of a rough estimation of complexity of class hierarchy structure. In addition to, we suggest a set of algorithms that transform a original class hierarchy structure into reorganized one based on the proposed metrics for class hierarchy structure. Furthermore, we also prove that each algorithm is "object-preserving". That is, we prove that the set of objects are never changed before and after applying the algorithm on a class hierarchy. The technique presented in this paper can be used as a guidelines of the construction, restructuring and refinement of class hierarchies. Moreover, the proposed set of algorithms based on metrics can be helpful for developers as an useful instrument for the object-oriented software development.velopment.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.3
• /
• pp.155-164
• /
• 2016

For frequency pattern analysis of large databases, the new tree-based frequency pattern analysis algorithm which can compensate for the disadvantages of the Apriori method has been variously studied. In frequency pattern tree, the number of nodes is associated with memory allocation, but also affects memory resource consumption and processing speed of the growth. Therefore, reducing the number of nodes in the tree is very important in the frequency pattern mining. However, the absolute criteria which need to order the transaction items for construction frequency pattern tree has lowered the compression ratio of the tree nodes. But most of the frequency based tree construction methods adapted the absolute criteria. FP-tree is typically frequency pattern tree structure which is an extended prefix-tree structure for storing compressed frequent crucial information about frequent patterns. For construction the tree, all the frequent items in different transactions are sorted according to the absolute criteria, frequency descending order. CanTree also need to absolute criteria, canonical order, to construct the tree. In this paper, we proposed a novel frequency pattern tree construction method that does not use the absolute criteria, IRFP-tree algorithm. IRFP-tree(Intersection Rule based FP-tree). IRFP-tree is constituted with the new paradigm of the intersection rule without the use of the absolute criteria. It increased the compression ratio of the tree nodes, and reduced the tree construction time. Our method has the additional advantage that it provides incremental mining. The reported test result demonstrate the applicability and effectiveness of the proposed approach.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.

• Journal of the Korea Concrete Institute
• /
• v.19 no.6
• /
• pp.803-810
• /
• 2007

An analytical method capable of predicting various stress-strain responses in axially loaded concrete confined with FRP (fiber reinforced polymers) composites in a rational manner is presented. Its underlying idea is that the volumetric expansion due to progressive microcracking in mechanically loaded concrete is an important measure of the extent of damage in the material microstructure, and can be utilized to estimate the load-carrying capacity of concrete by considering the corresponding accumulated damage. Following from this, an elastic modulus expressed as a function of area strain and concrete porosity, the energy-balance equation relating the dilating concrete to the confining device interactively, the varying confining pressure, and an incremental calculation algorithm are included in the solution procedure. The proposed method enables the evaluation of lateral strains consecutively according to the related mechanical model and the energy-balance equation, rather than using an empirically derived equation for Poisson's ratio or dilation rate as in other analytical methods. Several existing analytical methods that can predict the overall response were also examined and discussed, particularly focusing on the way of considering the volumetric expansion. The results predicted by the proposed and Samaan's bilinear equation models correlated with observed results with a reasonable degree, however it can be judged that the latter is not capable of predicting the response of lateral strains correctly due to incorporating the initial Poisson's ratio and the final converged dilation rate only. Further, the proposed method seems to have greater benefits in other applications by the use of the fundamental principles of mechanics.

• Journal of Embryo Transfer
• /
• v.29 no.3
• /
• pp.289-296
• /
• 2014

The pedigree information and race records of 1,000 m finishing time of Jeju race horses at KRA were used to study the effect of amount of pedigree information and parental misidentification on the estimates of genetic parameters. The modified data sets were made at the range of 2.5 to 25% parental misidentifications or loss of parental information of individuals with an increment of 2.5 percent. For each incremental level, 20 randomly replicated data sets were obtained and analyzed by single-trait analysis with a DF-REML(AI) algorithm. As the rate of misidentification increased or the amount of pedigree information decreased, the estimates of fraction of additive genetics variance component gradually decreased almost linearly (p<0.05), while the estimated fractions of error variance and permanent environmental variance components gradually increased for the finishing time. Regression coefficients of the percentage amount of both parents' information loss and incorrect pedigree information on additive genetic variances were -0.079 and -0.114, respectively (p<0.01). The estimate of heritability decreased by 0.92% for one percent loss of both parents' information and 1.39% for one percent increase of both parental misidentifications of progeny (p<0.01). For the consideration of probable incorrect and missing parent information of progeny in this early population of Jeju horses, the estimates of additive genetic parameters would be biased downward about ten percent. This results indicate that the amount of pedigree information loss and misidentification of progeny would severely affect estimates of genetic parameters and would reduce genetic gains for selection in Jeju horse population.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.7 no.1
• /
• pp.75-90
• /
• 1995

A mathematical model for the dynamic analysis of a riser system with the inclusion of internal flow and nonlinear effects due to large structural displacements is developed to investigate the effect of internal flow on marine riser dynamics. The riser system accounts fir the nonlinear boundary conditions and includes a steady flow inside the pipe which is modeled as an extensible or inextensible. tubular beam subject to nonlinear three dimensional hydrodynamic loads such as current or wave excitation. Galerkin's finite element approximation and time incremental operator are implemented to derive the matrix equation of equilibrium for the finite element system and the extensibility or inextensibility condition is used to reduce degree of freedom of the system and the required computational time in the case of a nonlinear model. The algorithm is implemented to develop computer programs used in several numerical applications. The investigations of the effect of infernal flow on riser vibration due to current or wave loading are performed according to the change of various parameters such as top tension, internal flow velocity, current velocity, wave period, and so on. It is found that the effect of internal flow can be controlled by the increase of top tension. However, careful consideration has to be given in the design point particularly for the long riser under the harmonic loading such as waves. And it is also found that the consideration of nonlinear effects due to large structural displacements increases the effect of internal flow on riser dynamics.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.163-170
• /
• 2006

With rapidly developing Internet applications, an e-mail has been considered as one of the most popular methods for exchanging information. The e-mail, however, has a serious problem that users ran receive a lot of unwanted e-mails, what we called, spam mails, which cause big problems economically as well as socially. In order to block and filter out the spam mails, many researchers and companies have performed many sorts of research on spam filtering. In general, users of e-mail have different criteria on deciding if an e-mail is spam or not. Furthermore, in e-mail client systems, users do different actions according to a spam mail or not. In this paper, we propose a mail filtering system using such user actions. The proposed system consists of two steps: One is an action inference step to draw user actions from an e-mail and the other is a mail classification step to decide if the e-mail is spam or not. All the two steps use incremental learning, of which an algorithm is IB2 of TiMBL. To evaluate the proposed system, we collect 12,000 mails of 12 persons. The accuracy is $81{\sim}93%$ according to each person. The proposed system outperforms, at about 14% on the average, a system that does not use any information about user actions.