• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.76-82
• /
• 2005

Speech signal has various features of speakers. This feature is extracted from speech signal processing. The speaker is identified by the speaker identification system. In this paper, we propose the speaker identification system that uses the incremental learning based on neural network. Recorded speech signal through the microphone is blocked to the frame of 1024 speech samples. Energy is divided speech signal to voiced signal and unvoiced signal. The extracted 12 orders LPC cpestrum coefficients are used with input data for neural network. The speakers are identified with the speaker identification system using the neural network. The neural network has the structure of MLP which consists of 12 input nodes, 8 hidden nodes, and 4 output nodes. The number of output node means the identified speakers. The first output node is excited to the first speaker. Incremental learning begins when the new speaker is identified. Incremental learning is the learning algorithm that already learned weights are remembered and only the new weights that are created as adding new speaker are trained. It is learning algorithm that overcomes the fault of neural network. The neural network repeats the learning when the new speaker is entered to it. The architecture of neural network is extended with the number of speakers. Therefore, this system can learn without the restricted number of speakers.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1998.04a
• /
• pp.291-300
• /
• 1998

This paper demonstrates how ambient vibration measurements at a limited number of locations can be effectively utilized to estimate parameters of a finite element model of a large-scale structural system involving a large number of elements. System identification using ambient vibration measurements presents a challenge requiring the use of special identification techniques, which ran deal with very small magnitudes of ambient vibration contaminated by noise without the knowledge of input farces. In the present study, the modal parameters such as natural frequencies, damping ratios, and mode shapes of the structural system were estimated by means of appropriate system identification techniques including the random decrement method. Moreover, estimation of parameters such as the stiffness matrix of the finite element model from the system response measured by a limited number of sensors is another challenge. In this study, the system stiffness matrix was estimated by using the quadratic optimization involving the computed and measured modal strain energy of the system, with the aid of a sensitivity relationship between each element stiffness and the modal parameters established by the second order inverse modal perturbation theory. The finite element models thus identified represent the actual structural system very well, as their calculated dynamic characteristics satisfactorily matched the observed ones from the ambient vibration test performed on a large-scale structural system subjected primarily to ambient wind excitations. The dynamic models identified by this study will be used for design of an active mass damper system to be installed on this structure fer suppressing its wind vibration.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.427-429
• /
• 2005

This paper presents the use of Point Number Algorithm (PNA) for real-time image processing for position identification of mobile robot. PNA can get how many points in the image gotten from the robot vision and can calculate the distance between the robot and the wall by the number of the points. The algorithm can be applied to a robot vision system enable to identify where it is in the workspace. In the workspace, the walls are made up by white background with many black points on them evenly. The angle of the vision is set invariable. So the more black points in the vision, the longer the distance is from the robot to the wall. But when the robot does not face the wall directly, the number of the black points is different. When the robot faces the wall, the least number of the black points can be gotten. The simulation results are presented at the end of this paper.

• KIISE Transactions on Computing Practices
• /
• v.22 no.1
• /
• pp.56-60
• /
• 2016

Peptide identification in tandem mass spectrometry is usually done by searching the spectra against target databases consisting of reference protein sequences. To control false discovery rates for high-confidence peptide identification, spectra are also searched against decoy databases constructed by permuting reference protein sequences. In this case, a peptide of the same sequence could be included in both the target and the decoy databases or multiple entries of a same peptide could exist in the decoy database. These phenomena make the protein identification problem complicated. Thus, it is important to minimize the number of such redundant peptides for accurate protein identification. In this regard, we examined two popular methods for decoy database generation: 'pseudo-shuffling' and 'pseudo-reversing'. We experimented with target databases of varying sizes and investigated the effect of the maximum number of missed cleavage sites allowed in a peptide (MC), which is one of the parameters for target and decoy database generation. In our experiments, the level of redundancy in decoy databases was proportional to the target database size and the value of MC, due to the increase in the number of short peptides (7 to 10 AA). Moreover, 'pseudo-reversing' always generated decoy databases with lower levels of redundancy compared to 'pseudo-shuffling'.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.433-439
• /
• 1998

In this paper, we present an approach to the structure identification based on the input space partition methods and to the parameter identification by hybrid learning method in neuro-fuzzy system. The structure identification can automatically estimate the number of membership function and fuzzy rule using grid partition, tree partition, scatter partition from numerical input-output data. And then the parameter identification is carried out by the hybrid learning scheme using back-propagation and least squares estimate. Finally, we sill show its usefulness for neuro-fuzzy modeling to truck backer-upper control.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.426-428
• /
• 2012

In order to identify proteins that are present in biological samples, these samples are separated and analyzed under the sequential procedure as follows: protein purification and digestion, peptide fragmentation by tandem mass spectrometry (MS/MS) which breaks peptides into fragments, peptide identification, and protein identification. One of the widely used methods for protein identification is based on probabilistic approaches such as ProteinProphet and BaysPro. However, they do not consider the difference in peptide identification probabilities according to their length. Here, we propose a probabilistic graphical model-based approach to protein identification from MS/MS data considering peptide identification probabilities, number of sibling peptides, and peptide length. We compared our approach with ProteinProphet using a yeast MS/MS dataset. As a result, our model identified 27 more proteins than ProteinProphet at 1% of FDR (false discovery rate), confirming the importance of peptide length information in protein identification.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.333-342
• /
• 2005

This paper proposes a method, which recognizes student's identification card by using image processing and recognition technology and can manage student information on the web. The presented scheme sets up an average brightness as a threshold, based on the brightest Pixel and the least bright one for the source image of the ID card. It is converting to binary image, applies a horizontal histogram, and extracts student number through its location. And, it removes the noise of the student number region by the mode smoothing with 3$\times$3 mask. After removing noise from the student number region, each number is extracted using vertical histogram and normalized. Using the enhanced ART1 algorithm recognized the extracted student number region. In this study, we propose the enhanced ART1 algorithm different from the conventional ART1 algorithm by the dynamical establishment of the vigilance parameter. which shows a tolerance limit of unbalance between voluntary and stored patterns for clustering. The Experiment results showed that the recognition rate of the proposed ART1 algorithm was improved much more than that of the conventional ART1 algorithm. So, we develop an educational matters administration system by using the proposed recognition method of the student's identification card.

• Journal of information and communication convergence engineering
• /
• v.7 no.2
• /
• pp.164-169
• /
• 2009

An RFID system consists of radio frequency tags attached to objects that need to be identified and one or more electromagnetic readers. Unlike the traditional bar code system, the great benefit of RFID technology is that it allows information to be read without requiring contact between the tag and the reader. For this contact-less feature, RFID technology in the near future will become an attractive alternative to bar code in many application fields. In almost all the 13.56MHz RFID systems, FSA (Framed Slot ALOHA) algorithm is used for identifying multiple tags in the reader's identification range. In FSA algorithm, the tag identification time and system efficiency depend mainly on the number of tags and frame size. In this paper, we propose a tag number estimation scheme and a dynamic frame size allocation scheme based on the estimated number of tags.

• Journal of Sensor Science and Technology
• /
• v.25 no.6
• /
• pp.431-434
• /
• 2016

Currently, the radial basis function network (RBFN) and various other neural networks are employed to classify gases using chemical sensors arrays, and their performance is steadily improving. In particular, the identification performance of the RBFN algorithm is being improved by optimizing parameters such as the center, width, and weight, and improved algorithms such as the radial basis function network-stochastic gradient (RBFN-SG) and radial basis function network-normalized stochastic gradient (RBFN-NSG) have been announced. In this study, we optimized the number of centers, which is one of the parameters of the RBFN-NSG algorithm, and observed the change in the identification performance. For the experiment, repeated measurement data of 8 samples were used, and the elbow method was applied to determine the optimal number of centers for each sample of input data. The experiment was carried out in two cases(the only one center per sample and the optimal number of centers obtained by elbow method), and the experimental results were compared using the mean square error (MSE). From the results of the experiments, we observed that the case having an optimal number of centers, obtained using the elbow method, showed a better identification performance than that without any optimization.

• 대한상한금궤의학회지
• /
• v.13 no.1
• /
• pp.145-153
• /
• 2021

Objective : This study aimed to report the improvement of a patient with anorexia by treatment with Jinmu-tang (Hyunmu-tang) based on the disease pattern identification diagnostic system (DPIDS) of the Shanghanlun provisions. Methods : We evaluated the progress of symptoms, patient compliance, and presence of side effects after the patient was administered Jinmu-tang. The clinical response was estimated according to the number of meals a day, the size of meals, the number of complaints of abdominal pain in a week, and a Likert scale. Results : According to the DPIDS, the patient was diagnosed according to provision 316 with soyinbing. After administration of Jinmu-tang for 45 days, the number of meals a day and the size of meals increased, the number of complaints of abdominal pain in a week decreased, and the Likert scale score decreased from 3 to 0. Conclusions : This case report suggests that the word "腹痛" (abdominal pain) in the 316th Shanghanlun provision indicates anxiety about abdominal pain, which affected anorexia in this case.