• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.7
• /
• pp.283-290
• /
• 2015

In this paper, we propose a hybrid method for the recognition of answer types in the WiseQA system. The answer types are classified into two categories: the lexical answer type (LAT) and the semantic answer type (SAT). This paper proposes two models for the LAT detection. One is a rule-based model using question focuses. The other is a machine learning model based on sequence labeling. We also propose two models for the SAT classification. They are a machine learning model based on multiclass classification and a filtering-rule model based on the lexical answer type. The performance of the LAT detection and the SAT classification shows F1-score of 82.47% and precision of 77.13%, respectively. Compared with IBM Watson for the performance of the LAT, the precision is 1.0% lower and the recall is 7.4% higher.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.1
• /
• pp.25-37
• /
• 2015

This paper suggests a decision tree based approach for flexible job shop scheduling with multiple process plans. The problem is to determine the operation/machine pairs and the sequence of the jobs assigned to each machine. Two decision tree based scheduling mechanisms are developed for static and dynamic flexible job shops. In the static case, all jobs are given in advance and the decision tree is used to select a priority dispatching rule to process all the jobs. Also, in the dynamic case, the jobs arrive over time and the decision tree, updated regularly, is used to select a priority rule in real-time according to a rescheduling strategy. The two decision tree based mechanisms were applied to a flexible job shop case with reconfigurable manufacturing cells and a conventional job shop, and the results are reported for various system performance measures.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.9B
• /
• pp.914-922
• /
• 2009

In this paper, we propose a matrix based real-time pattern matching method, called MDPI, for real-time intrusion detection on several Gbps network traffic. Particularly, in order to minimize a kind of overhead caused by buffering, reordering, and reassembling under the circumstance where the incoming packet sequence is disrupted, MDPI adopts independent partial matching in the case dealing with pattern matching matrix. Consequently, we achieved the performance improvement of the amount of 61% and 50% with respect to TCAM method efficiency through several experiments where the average length of the Snort rule set was maintained as 9 bytes, and w=4 bytes and w=8bytes were assigned, respectively, Moreover, we observed the pattern scan speed of MDPI was 10.941Gbps and the consumption of hardware resource was 5.79LC/Char in the pattern classification of MDPI. This means that MDPI provides the optimal performance compared to hardware complexity. Therefore, by decreasing the hardware cost came from the increased TCAM memory efficiency, MDPI is proven the cost effective high performance intrusion detection technique.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.9
• /
• pp.1120-1131
• /
• 2016

In this paper, we propose a smoker recognition algorithm, detecting smokers in a video sequence in order to prevent fire accidents. We use description-based method in hierarchical approaches to recognize smoker's activity, the algorithm consists of background subtraction, object detection, event search, event judgement. Background subtraction generates slow-motion and fast-motion foreground image from input image using Gaussian mixture model with two different learning-rate. Then, it extracts object locations in the slow-motion image using chain-rule based contour detection. For each object, face is detected by using Haar-like feature and smoke is detected by reflecting frequency and direction of smoke in fast-motion foreground. Hand movements are detected by motion estimation. The algorithm examines the features in a certain interval and infers that whether the object is a smoker. It robustly can detect a smoker among different objects while achieving real-time performance.

• Korean Journal of Materials Research
• /
• v.4 no.1
• /
• pp.9-23
• /
• 1994

Epitaxial $CoSi_2$ layer has been grown on NaCl(100) substrate at low deposition temperature($200^{\circ}C$) by multitarget bias cosputter deposition(MBCD). The phase sequence and crystallinity of deposited silicide as a function of deposition temperature and substrate bias voltage were studied by X-ray diffraction(XRD) and transmission electron microscopy(TEM) analysis. Crystalline Si was grown at $200^{\circ}C$ by metal induced crystallization(M1C) and self bias effect. In addition to, the MIC was analyzed both theoretically and experimentally. The observed phase sequence was $Co_2Si \to CoSi \to Cosi_2$ and was in good agreement with that predicted by effective heat of formation rule. The phase sequence, the CoSi(l11) preferred orientation, and the crystallinity had stronger dependence on the substrate bias voltage than the deposition temperature due to the collisional cascade mixing, the in-situ cleaning, and the increase in the number of nucleation sites by ion bombardment of growing surface. Grain growth induced by ion bombardment was observed with increasing substrate bias voltage at $200^{\circ}C$ and was interpreted with ion bombardment dissociation model. The parameters of $E_{Ar}\;and \alpha(V_s)$ were chosen to properly quantify the ion bombardment effect on the variation in crystallinty at $200^{\circ}C$ with increasing substrate bias voltage using Langmuir probe.

• Economic and Environmental Geology
• /
• v.5 no.2
• /
• pp.77-86
• /
• 1972

The system NaAlSiO_4-KAlSiO_4-SiO_2-H_2O, Bowen's "Petrogeny's Residua System" of course is extremely important in understanding the phase relationships of igneous and metamorphic rock in the continental crust. The phase relationships in this system, however, have not been completely established in the P-T range above the Mohorovicic discontinuity. They need to be established. In this study, the most probable sequence of P-T curves around a quaternary invariant point(~5Kb/${\sim}635^{\circ}C$) in the system using Schreinemakers' rule, is deduced, essentially on the basis of Morse's(1969a and b) experimental data. Possible modifications of the sequence of the P-T curves considering likely changes of the invariant chemogram are also considered. It is concluded that the sequence of P-T curves around the invariant point (~5Kb/${\sim}635^{\circ}C$) is (L), (Anl), (Or), (V), (Ne) and (Ab) on the P-T projection, where the P-T curve (L) is extended towards lower P-T regions, and the (Anl) curve is extended towards a region of higher temperature and lower pressure from the invariant point respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.125-132
• /
• 2022

Sentence compression is a natural language processing task that generates concise sentences that preserves the important meaning of the original sentence. For grammatically appropriate sentence compression, early studies utilized human-defined linguistic rules. Furthermore, while the sequence-to-sequence models perform well on various natural language processing tasks, such as machine translation, there have been studies that utilize it for sentence compression. However, for the linguistic rule-based studies, all rules have to be defined by human, and for the sequence-to-sequence model based studies require a large amount of parallel data for model training. In order to address these challenges, Deleter, a sentence compression model that leverages a pre-trained language model BERT, is proposed. Because the Deleter utilizes perplexity based score computed over BERT to compress sentences, any linguistic rules and parallel dataset is not required for sentence compression. However, because Deleter compresses sentences only considering perplexity, it does not compress sentences by reflecting the linguistic information of the words in the sentences. Furthermore, since the dataset used for pre-learning BERT are far from compressed sentences, there is a problem that this can lad to incorrect sentence compression. In order to address these problems, this paper proposes a method to quantify the importance of linguistic information and reflect it in perplexity-based sentence scoring. Furthermore, by fine-tuning BERT with a corpus of news articles that often contain proper nouns and often omit the unnecessary modifiers, we allow BERT to measure the perplexity appropriate for sentence compression. The evaluations on the English and Korean dataset confirm that the sentence compression performance of sentence-scoring based models can be improved by utilizing the proposed method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1100-1108
• /
• 2015

A camera-based real-time hand posture and gesture recognition system is proposed for controlling various devices inside automobiles. It uses an imaging system composed of a camera with a proper filter and an infrared lighting device to acquire images of hand-motion sequences. Several steps of pre-processing algorithms are applied, followed by a background normalization process before segmenting the hand from the background. The hand posture is determined by first separating the fingers from the main body of the hand and then by finding the relative position of the fingers from the center of the hand. The beginning and ending of the hand motion from the sequence of the acquired images are detected using pre-defined motion rules to start the hand gesture recognition. A set of carefully designed features is computed and extracted from the raw sequence and is fed into a decision tree-like decision rule for determining the hand gesture. Many experiments are performed to verify the system. In this paper, we show the performance results from tests on the 550 sequences of hand motion images collected from five different individuals to cover the variations among many users of the system in a real-time environment. Among them, 539 sequences are correctly recognized, showing a recognition rate of 98%.

• Genomics & Informatics
• /
• v.17 no.4
• /
• pp.39.1-39.20
• /
• 2019

Analyzing patterns in data points embedded in linear and non-linear feature spaces is considered as one of the common research problems among different research areas, for example: data mining, machine learning, pattern recognition, and multivariate analysis. In this paper, data points are heterogeneous sets of biosequences (composite data points). A composite data point is a set of ordinary data points (e.g., set of feature vectors). We theoretically extend the derivation of the largest generalized eigenvalue-based distance metric D_ij(γ₁) in any linear and non-linear feature spaces. We prove that D_ij(γ₁) is a metric under any linear and non-linear feature transformation function. We show the sufficiency and efficiency of using the decision rule $\bar{{\delta}}_{{\Xi}i}$(i.e., mean of D_ij(γ₁)) in classification of heterogeneous sets of biosequences compared with the decision rules min_𝚵iand median_𝚵i. We analyze the impact of linear and non-linear transformation functions on classifying/clustering collections of heterogeneous sets of biosequences. The impact of the length of a sequence in a heterogeneous sequence-set generated by simulation on the classification and clustering results in linear and non-linear feature spaces is empirically shown in this paper. We propose a new concept: the limiting dispersion map of the existing clusters in heterogeneous sets of biosequences embedded in linear and nonlinear feature spaces, which is based on the limiting distribution of nucleotide compositions estimated from real data sets. Finally, the empirical conclusions and the scientific evidences are deduced from the experiments to support the theoretical side stated in this paper.

• The Journal of the Korea Contents Association
• /
• v.13 no.5
• /
• pp.37-47
• /
• 2013

The objective of this research is to discover the rule of gameplay related to the task interdependence to analyse the behavior pattern of social gameplay. Previous literatures related to the gameplay were reviewed and game which was suitable for the gameplay of the task interdependence was selected. A party-play includes a team of five people in the experiment during the gameplay with think-aloud method and video/audio data about action protocol and verbal report were collected. The video observation and protocol analysis were conducted to analyse data. The objective coding scheme were developed from consolidated sequence model task analysis. The player's behavior was analysed. The result was revealed that four rules and four modified rules were included into the total eight behavior pattern. A behavior graph integrated with five gameplay was written. The excellent cooperative spot and error and failure place could be identified. The social gameplay behavior graph is expected to be the key practical design guideline on whether the level design and balance design are proper.