• Speech Sciences
• /
• v.15 no.2
• /
• pp.55-65
• /
• 2008

Recently, the multi-model based speech recognizer has been used quite successfully for noisy speech recognition. For the selection of the reference HMM (hidden Markov model) which best matches the noise type and SNR (signal to noise ratio) of the input testing speech, the estimation of the SNR value using the VAD (voice activity detection) algorithm and the classification of the noise type based on the GMM (Gaussian mixture model) have been done separately in the multi-model framework. As the SNR estimation process is vulnerable to errors, we propose an efficient method which can classify simultaneously the SNR values and noise types. The KL (Kullback-Leibler) distance between the single Gaussian distributions for the noise signal during the training and testing is utilized for the classification. The recognition experiments have been done on the Aurora 2 database showing the usefulness of the model compensation method in the multi-model based speech recognizer. We could also see that further performance improvement was achievable by combining the probability density function of the MCT (multi-condition training) with that of the reference HMM compensated by the D-JA (data-driven Jacobian adaptation) in the multi-model based speech recognizer.

• Journal of Ocean Engineering and Technology
• /
• v.37 no.3
• /
• pp.81-88
• /
• 2023

Maneuverability is a crucial factor for the safety and success of submarine missions. This paper introduces a mathematical model that considers the large drift and angle of attack motions of submarines. Various computational fluid dynamics (CFD) simulations were performed to adapt Karasuno's fishery vessel maneuvering mathematical model to submarines. The study also presents the procedure for obtaining the physics-based hydrodynamic coefficients proposed by Karasuno through CFD calculations. Based on these coefficients, the reconstructed forces and moments were compared with those obtained from CFD and to the hydrodynamic derivatives expressed by a Taylor expansion. The study also discusses the mathematical maneuvering model that accounts for the large drift angles and angles of attack of submarines. The comparison results showed that the proposed maneuvering mathematical model based on modified Karasno's model could cover a large range of motions, including horizontal motion and vertical motions. In particular, the results show that the physics-based mathematical maneuvering model can represent the forces and moments acting on the submarine hull during large drift and angle of attack motions. The proposed mathematical model based on the Karasuno model could obtain more accurate results than the Taylor third-order approximation-based mathematical model in estimating the hydrodynamic forces acting on submarines during large drift and angle of attack motions.

• Hwankyungkyoyuk
• /
• v.19 no.3
• /
• pp.150-164
• /
• 2006

This study reviewed a recently developed environmental education model 'ENVISION' and analyzed the value of the ENVISION program with environmental education(EE) perspective. Also this study proposed a prototype model of a inquiry-based water environmental education model with watershed concepts as a result of discussion of tills research. In the review of ENVISION, this research followed the theoretical framework of 'Inquiry-Based EE' that was previously proposed by the author. The ENVISION was characterized in tills research as two directions: watershed and scientific inquiry. Tills research argued that the watershed concept has a potentially very good meaning in EE because watershed enables 'holistic' view in EE area, and that the scientific inquiry in ENVISION seeks evidence-based explanation about local watershed environmental problems. That belongs to the scientific inquiry, which is also 'Inquiry-Based EE' and has internal value under EE perspective. Finally, this research proposed a prototype EE model that is about watershed concept, and is based on inquiry as general sense (scientific and insightful inquiries) and 'Environmental Studies for EE, (ESEE)' as the inquiry directions. The proposed model can be said a combination of the watershed concept and inquiry-based EE, and it seems that the model materializes better the EE nature than the ENVISION model.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.10
• /
• pp.457-463
• /
• 2001

This paper presents a simple and new digital redesign algorithm for fuzzy-model-based controllers. In the first stage, a continuous-time TS fuzzy model is constructed for a given continuous-time nonlinear system and a corresponding continuous-time fuzzy-model-based controller is established based on the existing controller synthesis algorithms. In the second stage, the continuous-time fuzzy-model-based controller is converted to equivalent discrete-time fuzzy-model-based controller, aiming at maintaining the property of the analogue controlled system, which are called intelligent digital redesign. Finally, the proposed method is applied to the digital control of inverted pendulum system to shows the effectiveness and the effectiveness and the feasibility of the method.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.365-372
• /
• 2022

The accurate object recognition is important for the precise and accurate manipulation. To enhance the recognition performance, we can use various types of sensors. In general, acquired data from sensors have a high sampling rate. So, in the past, the RNN-based model is commonly used to handle and analyze the time-series sensor data. However, the RNN-based model has limitations of excessive parameters. CNN-based model also can be used to analyze time-series input data. However, CNN-based model also has limitations of the small receptive field in early layers. For this reason, when we use a CNN-based model, model architecture should be deeper and heavier to extract useful global features. Thus, traditional methods like RN N -based and CN N -based model needs huge amount of learning parameters. Recently studied result shows that Fast Fourier Convolution (FFC) can overcome the limitations of traditional methods. This operator can extract global features from the first hidden layer, so it can be effectively used for feature extracting of sensor data that have a high sampling rate. In this paper, we propose the algorithm to recognize objects using tactile sensor data and the FFC model. The data was acquired from 11 types of objects to verify our posed model. We collected pressure, current, position data when the gripper grasps the objects by random force. As a result, the accuracy is enhanced from 84.66% to 91.43% when we use the proposed FFC-based model instead of the traditional model.

• Journal of Information Technology Applications and Management
• /
• v.29 no.3
• /
• pp.43-55
• /
• 2022

In this study, with the goal of developing a deep learning-based product recommendation model for effective matching of influencers and products, a deep learning model with a collaborative filtering model combined with generalized matrix decomposition(GMF), a collaborative filtering model based on multi-layer perceptron (MLP), and neural collaborative filtering and generalized matrix Factorization (NeuMF), a hybrid model combining GMP and MLP was developed and tested. In particular, we utilize one-class problem free boosting (OCF-B) method to solve the one-class problem that occurs when training is performed only on positive cases using implicit feedback in the deep learning-based collaborative filtering recommendation model. In relation to model selection based on overall experimental results, the MLP model showed highest performance with weighted average precision, weighted average recall, and f1 score were 0.85 in the model (n=3,000, term=15). This study is meaningful in practice as it attempted to commercialize a deep learning-based recommendation system where influencer's promotion data is being accumulated, pactical personalized recommendation service is not yet commercially applied yet.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2016-2021
• /
• 2003

This paper deals with a control technique of eliminating the transient vibration with respect to a waist axis of an articulated robot. This control technique is based on a model-based control in order to establish the damping effect on the driven mechanical part. The control model is composed of reduced-order electrical and mechanical parts related to the velocity control loop. The parameters of the control model can be obtained from design data or experimental data. This model estimates a load speed converted to the motor shaft. The difference between the estimated load speed and the motor speed is calculated dynamically, and it is added to the velocity command to suppress the transient vibration. This control method is applied to an articulated robot regarded as a time-invariant system. The effectiveness of the model-based control integrated into the position control loop is verified by simulations. Simulations show satisfactory control results to reduce the transient vibration at the end-effector.

• Journal of Engineering Education Research
• /
• v.14 no.1
• /
• pp.55-63
• /
• 2011

This paper deals with how to apply PBL(Problem-based learning model) model to interdisciplinary field such as engineering accounting. The PBL approach can provide a solution about educational issue for engineering accounting with a systematic view. A web-based practice system, which is a core element of PBL model and a learning object and practical exercise for engineering students, is developed.

• Journal of the Korean Society of Systems Engineering
• /
• v.5 no.2
• /
• pp.57-62
• /
• 2009

An embedded system is a computer system designed to perform one or a few dedicated functions often with real-time computing constraints. A traditional design process of embedded systems is the development of document-centric approach, and it is difficult to develop an embedded system efficiently because communication between teams or steps is not smooth. So the Model Based Design Process are applied to the development of embedded systems. This paper will compare the Model Based Design Process and the traditional design process, and introduce example of development of vehicle device applied the Model Based Design Process.

• Communications for Statistical Applications and Methods
• /
• v.10 no.3
• /
• pp.637-645
• /
• 2003

Small area estimation had been studied using data-based methods such as Direct, Indirect, Synthetic methods. However recently, model-based such as based on regression or time series estimation methods are applied to the study. In this paper we investigate a model-data based small area estimation which takes into account the spatial relation among the areas. The Economic Active Population Survey in 2001 are used for analysis and the results from the model based and model-data based estimation are compared with using MSE(Mean squared error), MAE(Mean absolute error) and MB(Mean bias).