• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.4
• /
• pp.109-118
• /
• 2012

Large number of part design for aircraft and automobile is preceded by functional or sectional design groups for efficiency. However, interferences and gaps can be found when the parts and sub-assemblies by those design groups are to be assembled. These interferences and gaps cause design changes and additional repair processes. While interference problem has been resolved by digital mockup and concurrent engineering methodology, gap problem has been covered by temporary treatment of filling gap with sealant. This kind of fast fix causes fatal problem of leakage when the gap is too big for filling or the treatment gets old. With this research, we have developed a program to find the gap automatically among parts of assembly so that users can find them to correct their design before manufacturing stage. By using decomposition model representation method, the developed program can search the gap among complex car body parts to be visualized with volumetric information. It can also define the boundary between the gap and exterior empty space automatically. Though we have proved the efficiency of the developed program by applying to automobile assembly, application of the program is not limited to car body only, but also can be extended to aircraft and ship design of large number of parts.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.11a
• /
• pp.313-318
• /
• 2007

Interior permanent magnet synchronous motor(IPMSM) has become a popular choice in electric vehicle applications, due to their excellent power to weight ratio. This paper proposes maximum torque control of IPMSM drive using adaptive fuzzy neural network controller and artificial neural network(ANN). This control method is applicable over the entire speed range which considered the limits of the inverter's current and voltage rated value. For each control mode, a condition that determines the optimal d-axis current $i_d$ for maximum torque operation is derived. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using Adaptive-FNN controller and ANN controller. The hybrid combination of neural network and fuzzy control will produce a powerful representation flexibility and numerical processing capability. Also, this paper reposes speed control of IPMSM using Adaptive-FNN and estimation of speed using ANN controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The proposed control algorithm is a lied to IPMSM drive system controlled Adaptive-FNN and ANN controller, the operating characteristics controlled by maximum torque control are examined in detail. Also, this paper proposes the analysis results to verify the effectiveness of the Adaptive-FNN and ANN controller.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.12
• /
• pp.6090-6097
• /
• 2013

A pneumatically-driven driving simulator that provides a realistic representation of the driving environment was developed. The motion platform for the driving simulator is a mechatronic device that gives a driver the realistic feeling of an actual vehicle. The cost of the motion platform comprises the largest part of the expenses in developing a driving simulator. In this project, to develop a low-cost motion platform, the self-built motion platform based on the Stewart platform configuration that is constructed by six pneumatic cylinders was used as its actuator. The Stewart platform that moves in response to the operating signals of the joystick showed satisfactory tracking performance. We confirmed the possibility of the driving simulator using rFactor that is a commercially available racing game software.

• Lingua Humanitatis
• /
• v.2 no.1
• /
• pp.259-284
• /
• 2002

In the history of cinema, Sergei Eisenstein is always considered as a pioneer to conceive of cinema primarily as a form of expressing thought rather than as a representation of reality. For him, montage is the indispensable method to construct an open totality of thought and image in movement. It functions as a basic thread running through two poles of filmic composition, that is, the organic and the pathetic. The organic is concerned with the composition of the film structure as a whole, while the pathetic is involved in an ongoing process of registering a leaping point in various filmic sequences. The ultimate goal of montage for Eisenstein is to create the cinema of ideas which can synthesize both emotional and intellectual elements in the filmic composition. In his system of intellectual cinema, the identity of image and thought externalizes the sensory-motor unity of nature and man along the ascending spiral of centrifugal force of the film. Indeed, in both theory and practice, Eisenstein firmly argues that nature not only provides basic laws for the organic composition of the film, but also expresses itself in the form of the whole which brings out the experience of totality in the film text, the audience, and surely Eisenstein himself.

• Journal of Power Electronics
• /
• v.16 no.2
• /
• pp.553-563
• /
• 2016

This paper presents a digital hardware implementation of a real-time simulator for a multiphase drive using a field-programmable gate array (FPGA) device. The simulator was developed with a modular and hierarchical design using very high-speed integrated circuit hardware description language (VHDL). Hence, this simulator is flexible and portable. A state-space representation model suitable for FPGA implementations was proposed for a dual three-phase induction machine (DTPIM). The simulator also models a two-level 12-pulse insulated-gate bipolar transistor (IGBT)-based voltage-source converter (VSC), a pulse-width modulation scheme, and a measurement system. Real-time simulation outputs (stator currents and rotor speed) were validated under steady-state and transient conditions using as reference an experimental test bench based on a DTPIM with 15 kW-rated power. The accuracy of the proposed digital hardware implementation was evaluated according to the simulation and experimental results. Finally, statistical performance parameters were provided to analyze the efficiency of the proposed DTPIM hardware implementation method.

• Journal of Power Electronics
• /
• v.13 no.3
• /
• pp.419-428
• /
• 2013

The modular multilevel cascade converter (MMCC) is a new family of multilevel power converters with modular realization and a cascaded pattern for submodules. The MMCC family can be classified by basic configurations and submodule types. One member of this family, the Hexverter, is configured as Double-Delta Full-Bridge (DDFB). It is a novel multilevel AC/AC converter with direct power conversion and comparatively fewer required components. It is appropriate for connecting two three-phase systems with different frequencies and driving an AC motor directly from a utility grid. This paper presents the dq model of a Hexverter with both of its AC systems by state-space representation, which then simplifies the continuous time-varying model into a periodic discrete time-invariant one. Then a generalized multivariable optimal control strategy for regulating the Hexverter's independent currents is developed. The resulting control structure can be adapted to other MMCCs and is flexible enough to include other control criterion while guaranteeing the original controller performance. The modeling method and control design are verified by simulation results.

• Educational Technology International
• /
• v.13 no.2
• /
• pp.283-312
• /
• 2012

Problem-solving ability is one of the most important learning outcomes for students to compete and accomplish in a knowledge-based society. It has been empirically proven that visualization plays a central role in problem-solving. The best performing problem-solver might have a strong visualization tendency. However, there is little research as to what factors of visualization tendency primarily related to problem-solving ability according to phases of problem-solving. The purpose of this study is to identify the relationship between visualization tendency and problem-solving ability, to determine which factors of visualization tendency influence problem-solving ability in each phase of problem-solving, and to examine different problem-solving ability from the perspective of the levels of visualization tendency. This study has found out that visualization tendency has a significant correlation with problem-solving ability. Especially, Generative Visualization and Spatial-Motor Visualization as sub-visualization tendency were more strongly related to each phase of problem-solving. It indicates that visualization tendency to generate and operate mental processing can be considered a major cognitive skill to improve problem-solving ability. Furthermore, students who have high visualization tendency also have significantly higher problem-solving ability than students with low visualization tendency. It shows that the levels of visualization tendency can predict variables related to students' problem-solving ability.

• Phonetics and Speech Sciences
• /
• v.9 no.4
• /
• pp.123-128
• /
• 2017

This study aims to compare the performance of syllable identification task according to auditory and visual stimuli presentation methods and syllable position. Twenty-two typically developing children (age 4-6) participated in the study. Three-syllable words were used to identify the first syllable and the final syllable in each word with auditory and visual stimuli. For the auditory stimuli presentation, the researcher presented the test word only with oral speech. For the visual stimuli presentation, the test words were presented as a picture, and asked each child to choose appropriate pictures for the task. The results showed that when tasks were presented visually, the performances of phonological awareness were significantly higher than in presenting with auditory stimuli. Also, the performances of the first syllable identification were significantly higher than those of the last syllable identification. When phonological awareness task are presented by auditory stimuli, it is necessary to go through all the steps of the speech production process. Therefore, the phonological awareness performance by auditory stimuli may be low due to the weakness of the other stages in the speech production process. When phonological awareness tasks are presented using visual picture stimuli, it can be performed directly at the phonological representation stage without going through the peripheral auditory processing, phonological recognition, and motor programming. This study suggests that phonological awareness skills can be different depending on the methods of stimulus presentation and syllable position of the tasks. The comparison of performances between visual and auditory stimulus tasks will help identify where children may show weakness and vulnerability in speech production process.

• Speech Sciences
• /
• v.1
• /
• pp.153-200
• /
• 1997

In languages such as Japanese, it is very common to observe that short peripheral vowel are completely voiceless when surrounded by voiceless consonants. This phenomenon has been known as Montreal French, Shanghai Chinese, Greek, and Korean. Traditionally this phenomenon has been described as a phonological rule that either categorically deletes the vowel or changes the [+voice] feature of the vowel to [-voice]. This analysis was supported by Sawashima (1971) and Hirose (1971)'s observation that there are two distinct EMG patterns for voiced and devoiced vowel in Japanese. Close examination of the phonetic evidence based on acoustic data, however, shows that these phonological characterizations are not tenable (Jun & Beckman 1993, 1994). In this paper, we examined the vowel devoicing phenomenon in Korean using data from ENG fiberscopic and acoustic recorders of 100 sentences produced by one Korean speaker. The results show that there is variability in the 'degree of devoicing' in both acoustic and EMG signals, and in the patterns of glottal closing and opening across different devoiced tokens. There seems to be no categorical difference between devoiced and voiced tokens, for either EMG activity events or glottal patterns. All of these observations support the notion that vowel devoicing in Korean can not be described as the result of the application of a phonological rule. Rather, devoicing seems to be a highly variable 'phonetic' process, a more or less subtle variation in the specification of such phonetic metrics as degree and timing of glottal opening, or of associated subglottal pressure or intra-oral airflow associated with concurrent tone and stricture specifications. Some of token-pair comparisons are amenable to an explanation in terms of gestural overlap and undershoot. However, the effect of gestural timing on vocal fold state seems to be a highly nonlinear function of the interaction among specifications for the relative timing of glottal adduction and abduction gestures, of the amplitudes of the overlapped gestures, of aerodynamic conditions created by concurrent oral tonal gestures, and so on. In summary, to understand devoicing, it will be necessary to examine its effect on phonetic representation of events in many parts of the vocal tracts, and at many stages of the speech chain between the motor intent and the acoustic signal that reaches the hearer's ear.