• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.169-178
• /
• 2022

Morphemes are most primitive units in a language that lose their original meaning when segmented into smaller parts. In Korean, a sentence is a sequence of eojeols (words) separated by spaces. Each eojeol comprises one or more morphemes. Korean morphological analysis (KMA) is to divide eojeols in a given Korean sentence into morpheme units. It also includes assigning appropriate part-of-speech(POS) tags to the resulting morphemes. KMA is one of the most important tasks in Korean natural language processing (NLP). Improving the performance of KMA is closely related to increasing performance of Korean NLP tasks. Recent research on KMA has begun to adopt the approach of machine translation (MT) models. MT is to convert a sequence (sentence) of units of one domain into a sequence (sentence) of units of another domain. Neural machine translation (NMT) stands for the approaches of MT that exploit neural network models. From a perspective of MT, KMA is to transform an input sequence of units belonging to the eojeol domain into a sequence of units in the morpheme domain. In this paper, we propose a deep learning model for KMA. The backbone of our model is based on the BERT-fused model which was shown to achieve high performance on NMT. The BERT-fused model utilizes Transformer, a representative model employed by NMT, and BERT which is a language representation model that has enabled a significant advance in NLP. The experimental results show that our model achieves 98.24 F1-Score.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.1
• /
• pp.39-50
• /
• 2012

A voice transformation (VT) method that can make the utterance of a source speaker mimic that of a target speaker is described. Speaker individuality transformation is achieved by altering three feature parameters, which include the LPC cepstrum, pitch period and gain. The main objective of this study involves construction of an optimal sequence of features selected from a target speaker's database, to maximize both the correlation probabilities between the transformed and the source features and the likelihood of the transformed features with respect to the target model. A set of two-pass conversion rules is proposed, where the feature parameters are first selected from a database then the optimal sequence of the feature parameters is then constructed in the second pass. The conversion rules were developed using a statistical approach that employed a maximum likelihood criterion. In constructing an optimal sequence of the features, a hidden Markov model (HMM) was employed to find the most likely combination of the features with respect to the target speaker's model. The effectiveness of the proposed transformation method was evaluated using objective tests and informal listening tests. We confirmed that the proposed method leads to perceptually more preferred results, compared with the conventional methods.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.6
• /
• pp.546-552
• /
• 2013

A cantilevered piezoelectric energy harvester(PEH) and an auxiliary mass-spring unit can be integrated into a novel two-degrees-of-freedom PEH where its lowest eigenmode is not an in-phase modes but an out-of-phase mode. This typical behavior was shown to enhance output power considerably compared with its stand-alone counterpart. The objective of this study is to newly develop a continuum-based mathematical model suitable for efficient analysis of the mode-sequence reversed PEH. Once such a mathematical model is available, various physical behaviors can be analytically investigated for better designs. After a new mathematical model is developed, its validity is checked by using ANSYS results, in terms of resonant frequency, open-circuit voltage, and output power with a specified external resistance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.11a
• /
• pp.181-185
• /
• 1998

Recently, research and developmental direction of communication system is concurrent adopting voice data and face image in speaking to provide more higher recognition rate then in the case of only voice data. Therefore, we present a method of lipreading in speech image sequence by using the 3-D facial shape model. The method use a feature information of the face image such as the opening-level of lip, the movement of jaw, and the projection height of lip. At first, we adjust the 3-D face model to speeching face image sequence. Then, to get a feature information we compute variance quantity from adjusted 3-D shape model of image sequence and use the variance quality of the adjusted 3-D model as recognition parameters. We use the intensity inclination values which obtaining from the variance in 3-D feature points as the separation of recognition units from the sequential image. After then, we use discrete HMM algorithm at recognition process, depending on multiple observation sequence which considers the variance of 3-D feature point fully. As a result of recognition experiment with the 8 Korean vowels and 2 Korean consonants, we have about 80% of recognition rate for the plosives and vowels.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.5
• /
• pp.783-788
• /
• 2002

Recently, research and developmental direction of communication system is concurrent adopting voice data and face image in speaking to provide more higher recognition rate then in the case of only voice data. Therefore, we present a method of lipreading in speech image sequence by using the 3-D facial shape model. The method use a feature information of the face image such as the opening-level of lip, the movement of jaw, and the projection height of lip. At first, we adjust the 3-D face model to speeching face Image sequence. Then, to get a feature information we compute variance quantity from adjusted 3-D shape model of image sequence and use the variance quality of the adjusted 3-D model as recognition parameters. We use the intensity inclination values which obtaining from the variance in 3-D feature points as the separation of recognition units from the sequential image. After then, we use discrete HMM algorithm at recognition process, depending on multiple observation sequence which considers the variance of 3-D feature point fully. As a result of recognition experiment with the 8 Korean vowels and 2 Korean consonants, we have about 80% of recognition rate for the plosives md vowels.

• Communications for Statistical Applications and Methods
• /
• v.6 no.2
• /
• pp.601-610
• /
• 1999

Crossover design is officially except for special occasions recommended by KFDA and FDA for assessing Bioequivalence between two drugs one for reference and the other for innovator. Such design is regarded as a special case of latin square split-polt or repeated measurement design and its main difference with other designing methods is that each subject in an experiment is exposed two drugs in sequence. Therefore general statistical analysis is not suitable since the model for this experiment includes carryover effect in addition to period and sequence effect. in this paper analysis for crossover model with two drugs and its interpretation are mainly discussed and an example is given for illustration.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.338-342
• /
• 1988

Recently, in sequence control systems, high flexibility and maintenance of control software are required. This is because product life cycles become shorter and control specification must be changed frequently. The authors extend the concept of Safe Petri Net to develop the design and analysis tool for sequence control systems taking the safeness and notation of input/output functions into consideration. Extended Safe Petri Net (S-Net) is proposed as such a new graph model and real time scanning algorithm based on S-Net is developed.

• Journal of Convergence for Information Technology
• /
• v.12 no.2
• /
• pp.47-53
• /
• 2022

Recently, with the change of the intelligent security paradigm, study to apply various information generated from various information security systems to AI-based anomaly detection is increasing. Therefore, in this study, in order to convert log-like time series data into a vector, which is a numerical feature, the CBOW and Skip-gram inference methods of deep learning-based Word2Vec model and statistical method based on the coincidence frequency were used to transform the published ADFA system call data. In relation to this, an experiment was carried out through conversion into various embedding vectors considering the dimension of vector, the length of sequence, and the window size. In addition, the performance of the embedding methods used as well as the detection performance were compared and evaluated through GRU-based anomaly detection model using vectors generated by the embedding model as an input. Compared to the statistical model, it was confirmed that the Skip-gram maintains more stable performance without biasing a specific window size or sequence length, and is more effective in making each event of sequence data into an embedding vector.

• Journal of Korean Society of Transportation
• /
• v.20 no.5
• /
• pp.67-79
• /
• 2002

In this paper, observed trajectories of a vehicle platoon are viewed as one realization of a finite sequence of random trajectories. In this point of view, we develop novel and mathematically rigorous concept of traffic flow variables such as local traffic density, instantaneous traffic flow, and velocity field and investigate their nature on a general probability space of a sequence of random trajectories which represent vehicle trajectories. We present a simple model of random trajectories as an illustrative example and, derive the values of traffic flow variables based on the new definitions in this model. In particular, we construct the model for the sequence of random vehicle trajectories with a system of stochastic differential equations. Each equation of the system nay represent microscopic random maneuvering behavior of each vehicle with properly designed drift coefficient functions and diffusion coefficient functions. The system of stochastic differential equations nay generate a well-defined probability space of a sequence of random vehicle trajectories. We derive the partial differential equation for the expected cumulative plot with appropriate initial conditions. By solving the equation with numerical methods, we obtain the values of expected cumulative plot, local traffic density, and instantaneous traffic flow. In addition, we derive the partial differential equation for the expected travel time to a certain location with appropriate initial and/or boundary conditions, which is solvable numerically. We apply this model to a case of single vehicle trajectory.

• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.554-561
• /
• 2008

Prediction technique of user's intention can be used as a post-processing method for reducing the search space of an automatic speech recognizer. Prediction technique of system's intention can be used as a pre-processing method for generating a flexible sentence. To satisfy these practical needs, we propose a statistical model to predict speakers' intentions that are generalized into pairs of a speech act and a concept sequence. Contrary to the previous model using simple n-gram statistic of speech acts, the proposed model represents a dialogue history of a current utterance to a feature set with various linguistic levels (i.e. n-grams of speech act and a concept sequence pairs, clue words, and state information of a domain frame). Then, the proposed model predicts the intention of the next utterance by using the feature set as inputs of CRFs (Conditional Random Fields). In the experiment in a schedule management domain, The proposed model showed the precision of 76.25% on prediction of user's speech act and the precision of 64.21% on prediction of user's concept sequence. The proposed model also showed the precision of 88.11% on prediction of system's speech act and the Precision of 87.19% on prediction of system's concept sequence. In addition, the proposed model showed 29.32% higher average precision than the previous model.