• MALSORI
• /
• no.52
• /
• pp.145-160
• /
• 2004

In this paper, a new noise compensation method based on the eigenvoice framework in feature space is proposed to reduce the mismatch between training and testing environments. The difference between clean and noisy environments is represented by the linear combination of K eigenvectors that represent the variation among environments. In the proposed method, the performance improvement of speech recognition systems is largely affected by how to construct the noisy models and the bias vector set. In this paper, two methods, the one based on MAP adaptation method and the other using stereo DB, are proposed to construct the noisy models. In experiments using Aurora 2 DB, we obtained 44.86% relative improvement with eigen-environment method in comparison with baseline system. Especially, in clean condition training mode, our proposed method yielded 66.74% relative improvement, which is better performance than several methods previously proposed in Aurora project.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.300-303
• /
• 2003

An Algorithm based on direct implementation of variable structure systems theory approach is proposed for on-line training of multilayer perceptrons. Network structures which have multiple inputs, single output and one hidden layer are considered and the weights are assumed to have capabilities for continuous time adaptation. The zero level set of the network learning error is regarded as a sliding surface in the learning parameters space. A sliding mode trajectory can be brought on and reached in finite time on such a sliding manifold. Results from simulated on-line identification task for a two-link planar manipulator dynamics are also presented.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.137-141
• /
• 2003

LS-SVM(least squares support vector machine) is a widely applicable and useful machine learning technique for classification and regression analysis. LS-SVM can be a good substitute for statistical method but computational difficulties are still remained to operate the inversion of matrix of huge data set. In modern information society, we can easily get huge data sets by on line or batch mode. For these kind of huge data sets, we suggest an on line pruning regression method by LS-SVM. With relatively small number of pruned support vectors, we can have almost same performance as regression with full data set.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.106-109
• /
• 1998

Wireless communication systems, in particular, must operate in a crowded electro-magnetic environmnet where in-band undesired signals are treated as noise by the receiver. These interfering signals are often random but not Gaussian Due to nongaussian noise, the distribution of the observables cannot be specified by a finite set of parameters; instead r-dimensioal sample space (pure noise samples) is equiprobably partitioned into a finite number of disjointed regions using quantiles and a vector quantizer based on training samples. If we assume that the detected symbols are correct, then we can observe the pure noise samples during the training and transmitting mode. The algorithm proposed is based on a piecewise approximation to a regression function based on quantities and conditional partition moments which are estimated by a RMSA (Robbins-Monro Stochastic Approximation) algorithm. In this paper, we develop a diversity combiner with modified detector, called Non-Linear Detector, and the receiver has a differential phase detector in each diversity branch and at the combiner each detector output is proportional to the second power of the envelope of branches. Monte-Carlo simulations were used as means of generating the system performance.

• Journal of Navigation and Port Research
• /
• v.34 no.9
• /
• pp.693-698
• /
• 2010

In port and its approach channel, traffic accidents such as collision, aground, minor collision have reached about 77% of total marine casualty in the area. In this paper, an attempt to enhance the safe navigation was proposed by offering marine traffic supporting system which helps VTS operator assist vessel effectively with the quantitative assessment on difficulty of each vessel. The system collects navigation data from onboard AIS, assesses the data in assessment mode to analyze the navigation difficulties of each vessel and displays the degree of danger of each vessel on the ECDIS in real-time to decide the intervention time or order of priority for VTS operator. The effectiveness of the system was verified by the VTS operators in Korea.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.129-133
• /
• 2003

The work described in this paper deals with the proposed application of an Artificial Neural Network Model for the Advanced Pressurized Water Reactor APR-1400 transient identification. The approach adopted for testing the network take note of the expectation which should be fulfilled by a network for real-time application, like testing with data in on-line mode and use of actual or real-life patterns for training. The recall test performed demonstrates that use of neural network for transient identification is indeed an attractive preposition.

• The Journal of the Korea Contents Association
• /
• v.3 no.3
• /
• pp.19-33
• /
• 2003

Computer simulation has used to a area of military training from about several years ago. War game mode(or computer simulation) endow a military man with lied training such as combat experience without operating combat strength or capabilities. To sanely construct simulation environment against actual combat environment associate among federates on network. us construct virtual combat environment enabling to efficiently manage network traffic among federates(or active nodes) by using active network technique on virtual military training space such as urgent combat field needed to rapidly transfer combat information including image and video, verify its validity by the help of simulation

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.949-958
• /
• 2004

race detection using a boosting based algorithm requires a very large size of face and nonface data. In addition, the fact that there always occurs a need for adding additional training data for better detection rates demands an efficient incremental teaming algorithm. In the design of incremental teaming based classifiers, the final classifier should represent the characteristics of the entire training dataset. Conventional methods have a critical problem in combining intermediate classifiers that weight updates depend solely on the performance of individual dataset. In this paper, for the purpose of application to face detection, we present a new method to combine an intermediate classifier with previously acquired ones in an optimal manner. Our algorithm creates a validation set by incrementally adding sampled instances from each dataset to represent the entire training data. The weight of each classifier is determined based on its performance on the validation set. This approach guarantees that the resulting final classifier is teamed by the entire training dataset. Experimental results show that the classifier trained by the proposed algorithm performs better than by AdaBoost which operates in batch mode, as well as by ${Learn}^{++}$.

• Archives of Plastic Surgery
• /
• v.46 no.3
• /
• pp.228-234
• /
• 2019

Background The management of flexor tendon injuries has evolved in recent years through industrial improvements in suture materials, refinements of repair methods, and early rehabilitation protocols. However, there is no consensus on the ideal suture material and technique. This study was conducted to compare the tensile strength, repair time, and characteristics of 4-strand cruciate, modified Kessler, and 4-strand horizontal intrafiber barbed sutures for flexor tenorrhaphy with a 12-mm suture purchase length in an animal model. Methods The right third deep flexors of 60 adult Leghorn chicken feet were isolated and repaired with a 12-mm suture purchase length. The tendons were randomly assigned to three groups of equal number (n=20 each). Groups 1 and 2 received 4-strand cruciate and modified Kessler repair with conventional suture materials, respectively. A 4-strand horizontal intrafiber barbed suture technique was used in group 3. The repaired tendons were biomechanically tested for tensile strength, 2-mm gap resistance, and mode of failure. Repair times were also recorded. Results The maximum tensile strength until failure was $44.6{\pm}4.3N$ in group 1, $35.7{\pm}5.2N$ in group 2, and $56.7{\pm}17.3N$ in group 3. The barbed sutures were superior to the other sutures in terms of the load needed for 2-mm gap formation (P<0.05). Furthermore, the barbed sutures showed the shortest repair time (P<0.05). Conclusions This study found that 4-strand horizontal intrafiber barbed suture repair with a 12-mm purchase length in a chicken flexor tendon injury model showed promising biomechanical properties and took less time to perform than other options.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.2
• /
• pp.613-619
• /
• 2012

We applied several machine learning methods for developing QSAR models for prediction of acute toxicity to fathead minnow. The multiple linear regression (MLR) and artificial neural network (ANN) method were applied to predict 96 h $LC_{50}$ (median lethal concentration) of 555 chemical compounds. Molecular descriptors based on 2D chemical structure were calculated by PreADMET program. The recursive partitioning (RP) model was used for grouping of mode of actions as reactive or narcosis, followed by MLR method of chemicals within the same mode of action. The MLR, ANN, and two RP-MLR models possessed correlation coefficients ($R^2$) as 0.553, 0.618, 0.632, and 0.605 on test set, respectively. The consensus model of ANN and two RP-MLR models was used as the best model on training set and showed good predictivity ($R^2$=0.663) on the test set.