• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.167-179
• /
• 2002

In this paper, we propose a new acoustic model for characterizing segmental features and an algorithm based upon a general framework of hidden Markov models (HMMs) in order to compensate the weakness of HMM assumptions. The segmental features are represented as a trajectory of observed vector sequences by a polynomial regression function because the single frame feature cannot represent the temporal dynamics of speech signals effectively. To apply the segmental features to pattern classification, we adopted segmental HMM(SHMM) which is known as the effective method to represent the trend of speech signals. SHMM separates observation probability of the given state into extra- and intra-segmental variations that show the long-term and short-term variabilities, respectively. To consider the segmental characteristics in acoustic model, we present segmental-feature HMM(SFHMM) by modifying the SHMM. The SFHMM therefore represents the external- and internal-variation as the observation probability of the trajectory in a given state and trajectory estimation error for the given segment, respectively. We conducted several experiments on the TIMIT database to establish the effectiveness of the proposed method and the characteristics of the segmental features. From the experimental results, we conclude that the proposed method is valuable, if its number of parameters is greater than that of conventional HMM, in the flexible and informative feature representation and the performance improvement.

• Korean Journal of Plant Resources
• /
• v.30 no.5
• /
• pp.571-577
• /
• 2017

Abscisic acid (ABA) is an important phytohormone involved in abiotic stress tolerance in plants. The group A bZIP transcription factors play important roles in the ABA signaling pathway in Arabidopsis but little is known about their functions in rice. In our current study, we have isolated and characterized a group A bZIP transcription factor in rice, OsABF3 (Oryza sativa ABA responsive element binding factor 3). We examined the expression patterns of OsABF3 in various tissues and time course analysis after abiotic stress treatments such as drought, salinity, cold, oxidative stress, and ABA in rice. Subcellular localization analysis in maize protoplasts using a GFP fusion vector further indicated that OsABF3 is a nuclear protein. Moreover, in a yeast one-hybrid experiment, OsABF3 was shown to bind to ABA responsive elements (ABREs) and its N-terminal region found to be necessary to transactivate a downstream reporter. A homozygous T-DNA insertional mutant of OsABF3 is more sensitive to salinity, drought, and oxidative stress compared with wild type plants ＆ OsABF3OX plants. In addition, this Osabf3 mutant showed a significantly decreased sensitivity to high levels of ABA at germination and post-germination. Collectively, our present results indicate that OsABF3 functions as a transcriptional regulator that modulates the expression of abiotic stress-responsive genes through an ABA-dependent pathway.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.9 no.2
• /
• pp.171-182
• /
• 2007

For minimizing the effect on the focus of civil traffic and environment conditions related to the excavation at the traffic jamming points, an underground station tunnel was planned with 35.5 m in length and bigger area than $200\;m^2$ in sedimentary rock mass. It faced the case that the overburden was just under 13 m. Not based on a pattern design but on the case histories of similar projects and arching effect, the design of large section tunnel under shallow overburden was investigated on three design subjects which are shape effect on the section area, application method of support pressure, and supporting and tunnel safety. According to the mechanical effect from section shape, a basic design and a preliminary design was obtained, and then supporting method of large section was planned by the supporting of NATM and a pipe roof method for subsidence prevention and mechanical stability. From the comparative study between both designs, it was found that the basic design was suitable and acceptable for the steel alignment of tunnel lining, safety and the design parameter restricted by the limit considered as partition of the excavation facilities. Through the analysis result of preliminary design showing the mechanical stability without stress concentration in tunnel arch level, it also was induced that shape effect of the large section area and yielding load obtained from deformation zone in the surrounding rock mass of tunnel have to be considered as major topics for the further development of design technique on the large section tunnel.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.1-6
• /
• 2003

This paper analyses the performance of either the minimum variance distortionless response (MVDR) or the recursive least square (RLS) beamformer structured on the systolic array. Provided that the snapshot vector including the desired user's signal and the interferences with the noise is received at the array antenna. In order to improve the quality of received signal, MVDR or RLS algorithm can be utilized to update the beamformer weights recursively. Furthermore to increase the channel capacity, by the usage of the above schemes, the effect of the spatial filtering can be obtained which constructively combining multipath components corresponding to the desired user whereas the multiple access interferences (MAI) is nulled out on spatial domain. This paper introduces the MVDR and RLS beamformer structured on systolic array conducting the spatial filtering, and its performance under the multipath fading channel in the presence of multiple access interferences will be analyzed. To show the superior spatial filtering performances of the proposed scheme employing the systolic way structured beamformer, the computer simulations are carried out. And the validity of practical deployment of the proposed scheme will be confirmed throughout showing the BER behaviors and the beampatterns.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.35-44
• /
• 2000

In this paper, we propose a new trajectory model for characterizing segmental features and their interaction based upon a general framework of hidden Markov models. Each segment, a sequence of vectors, is represented by a trajectory of observed sequences. This trajectory is obtained by applying a new design matrix which includes transitional information on contiguous frames, and is characterized as a polynomial regression function. To apply the trajectory to the segmental HMM, the frame features are replaced with the trajectory of a given segment. We also propose the likelihood of a given segment and the estimation of trajectory parameters. The obervation probability of a given segment is represented as the relation between the segment likelihood and the estimation error of the trajectories. The estimation error of a trajectory is considered as the weight of the likelihood of a given segment in a state. This weight represents the probability of how well the corresponding trajectory characterize the segment. The proposed model can be regarded as a generalization of a conventional HMM and a parametric trajectory model. The experimental results are reported on the TIMIT corpus and performance is show to improve significantly over that of the conventional HMM.

• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.135-140
• /
• 2012

The mirror neuron system in the cerebrum, which are handled by visual information-based imitative learning. When we observe the observer's range of mirror neuron system, we can assume intention of performance through progress of neural activation as specific range, in include of partially hidden range. It is goal of our paper that imitative learning is applied to 3D vision-based intelligent system. We have experiment as stereo camera-based restoration about acquired 3D image our previous research Using Optical flow, unscented Kalman filter. At this point, 3D input image is sequential continuous image as including of partially hidden range. We used Hidden Markov Model to perform the intention recognition about performance as result of restoration-based hidden range. The dynamic inference function about sequential input data have compatible properties such as hand gesture recognition include of hidden range. In this paper, for proposed intention recognition, we already had a simulation about object outline and feature extraction in the previous research, we generated temporal continuous feature vector about feature extraction and when we apply to Hidden Markov Model, make a result of simulation about hand gesture classification according to intention pattern. We got the result of hand gesture classification as value of posterior probability, and proved the accuracy outstandingness through the result.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.187-193
• /
• 2015

The ICT healing platform sets a couple of goals including preventing chronic diseases and sending out early disease warnings based on personal information such as bio-signals and life habits. The 2-step open system(TOS) had a relay designed between the healing platform and the storage of personal health data. It also took into account a publish/subscribe(pub/sub) service based on large-scale connections to transmit(monitor) the data processing process in real time. In the early design of TOS pub/sub, however, the same buffers were allocated regardless of connection idling and type of message in order to encode connection messages into a deflate algorithm. Proposed in this study, the dynamic buffer allocation was performed as follows: the message transmission type of each connection was first put to queuing; each queue was extracted for its feature, computed, and converted into vector through tf-idf, then being entered into a k-means cluster and forming a cluster; connections categorized under a certain cluster would re-allocate the resources according to the resource table of the cluster; the centroid of each cluster would select a queuing pattern to represent the cluster in advance and present it as a resource reference table(encoding efficiency by the buffer sizes); and the proposed design would perform trade-off between the calculation resources and the network bandwidth for cluster and feature calculations to efficiently allocate the encoding buffer resources of TOS to the network connections, thus contributing to the increased tps(number of real-time data processing and monitoring connections per unit hour) of TOS.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.27-36
• /
• 2004

Detection and recognition of human faces in images can be considered as an important aspect for applications that involve interaction between human and computer. In this paper, we propose a face recognition method using eigenfaces and fuzzy neural networks. The Principal Components Analysis (PCA) is one of the most successful technique that have been used to recognize faces in images. In this technique the eigenvectors (eigenfaces) and eigenvalues of an image is extracted from a covariance matrix which is constructed form image database. Face recognition is Performed by projecting an unknown image into the subspace spanned by the eigenfaces and by comparing its position in the face space with the positions of known indivisuals. Based on this technique, we propose a new algorithm for face recognition consisting of 5 steps including preprocessing, eigenfaces generation, design of fuzzy membership function, training of neural network, and recognition. First, each face image in the face database is preprocessed and eigenfaces are created. Fuzzy membership degrees are assigned to 135 eigenface weights, and these membership degrees are then inputted to a neural network to be trained. After training, the output value of the neural network is intupreted as the degree of face closeness to each face in the training database.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.55-62
• /
• 2005

In this paper, we propose the face recognition system using HNMA(Hippocampal Neuron Modeling Algorithm) which can remodel the cerebral cortex and hippocampal neuron as a principle of a man's brain in engineering, then it can learn the feature-vector of the face images very fast and construct the optimized feature each image. The system is composed of two parts. One is feature-extraction and the other is teaming and recognition. In the feature extraction part, it can construct good-classified features applying PCA(Principal Component Analysis) and LDA(Linear Discriminants Analysis) in order. In the learning part, it cm table the features of the image data which are inputted according to the order of hippocampal neuron structure to reaction-pattern according to the adjustment of a good impression in the dentate gyrus region and remove the noise through the associate memory in the CA3 region. In the CA1 region receiving the information of the CA3, it can make long-term memory learned by neuron. Experiments confirm the each recognition rate, that are face changes, pose changes and low quality image. The experimental results show that we can compare a feature extraction and learning method proposed in this paper of any other methods, and we can confirm that the proposed method is superior to existing methods.