• The Journal of the Acoustical Society of Korea
• /
• v.18 no.4
• /
• pp.47-52
• /
• 1999

In this paper, we proposed a new approach to weight each feature parameter by considering the dispersion of feature parameters and its degree of contribution to recognition rate. We determined the total distribution factor that is proportional to recognition rate of each feature parameter and the dispersion factor according to the dispersion of each feature parameter. Then. we determined state-dependent weighting using the total distribution factor and dispersion factor. To verify the validity of the proposed approach, recognition experiments were performed using the PLU(Phoneme-Like Unit)-based HMM. Experimental results showed the improvement of 7.7% at the recognition rate using the proposed method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.6
• /
• pp.17-24
• /
• 1994

This paper is a study on Korean word recognition and suggest the method that stabilizes the state-transition in the HMM by applying the `inertia' to the feature vector sequences. In order to reduce the quantized distortion considering probability distribution of input vectors, we used SOFM, an unsupervised learning method, as a vector quantizer, By applying inertia to the feature vector sequences, the overlapping of probability distributions for the response path of each word on the self organizing feature map can be reduced and the state-transition in the Hmm can be Stabilized. In order to evaluate the performance of the method, we carried out experiments for 50 DDD area names. The results showed that applying inertia to the feature vector sequence improved the recognition rate by 7.4% and can make more HMMs available without reducing the recognition rate for the SOFM having the fixed number of neuron.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.832-854
• /
• 2019

Action recognition has been studied in computer vision field for years. We present an effective approach to recognize actions using a dimension reduction method, which is applied as a crucial step to reduce the dimensionality of feature descriptors after extracting features. We propose to use sparse matrix and randomized kd-tree to modify it and then propose modified Local Fisher Discriminant Analysis (mLFDA) method which greatly reduces the required memory and accelerate the standard Local Fisher Discriminant Analysis. For feature encoding, we propose a useful encoding method called mix encoding which combines Fisher vector encoding and locality-constrained linear coding to get the final video representations. In order to add more meaningful features to the process of action recognition, the convolutional neural network is utilized and combined with mix encoding to produce the deep network feature. Experimental results show that our algorithm is a competitive method on KTH dataset, HMDB51 dataset and UCF101 dataset when combining all these methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.150-155
• /
• 2004

In this paper, an emotion recognition method using speech signal is presented. Six basic human emotions including happiness, sadness, anger, surprise, fear and dislike are investigated. The proposed recognizer have each codebook constructed by using the wavelet transform for the emotional state. Here, we first verify the emotional state at each filterbank and then the final recognition is obtained from a multi-decision method scheme. The database consists of 360 emotional utterances from twenty person who talk a sentence three times for six emotional states. The proposed method showed more 5% improvement of the recognition rate than previous works.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.372-377
• /
• 2006

In this paper, we propose sensibility recognition model that recognize user's sensibility using brain waves. Method to acquire quantitative data of brain waves including priority living body data or sensitivity data to recognize user's sensitivity need and pattern recognition techniques to examine closely present user's sensitivity state through next acquired brain waves becomes problem that is important. In this paper, we used pattern recognition techniques to use Multi Layer Perceptron (MLP) that is pattern recognition techniques that recognize user's sensibility state through brain waves. We measures several subject's emotion brain waves in specification space for an experiment of sensibility recognition model's which propose in this paper and we made a emotion DB by the meaning data that made of concentration or stability by the brain waves measured. The model recognizes new user's sensibility by the user's brain waves after study by sensibility recognition model which propose in this paper to emotion DB. Finally, we estimates the performance of sensibility recognition model which used brain waves as that measure the change of recognition rate by the number of subjects and a number of hidden nodes.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.528-538
• /
• 2003

A SCCRS (Speech and Character Combined Recognition System) is developed for working on mobile devices such as PDA (Personal Digital Assistants). In SCCRS, the feature extraction is separately carried out for speech and for hand-written character, but the recognition is performed in a common engine. The recognition engine employs essentially CHMM (Continuous Hidden Markov Model), which consists of variable parameter topology in order to minimize the number of model parameters and to reduce recognition time. For generating contort independent variable parameter model, we propose the SSMS(Successive State and Mixture Splitting), which gives appropriate numbers of mixture and of states through splitting in mixture domain and in time domain. The recognition results show that the proposed SSMS method can reduce the total number of GOPDD (Gaussian Output Probability Density Distribution) up to 40.0% compared to the conventional method with fixed parameter model, at the same recognition performance in speech recognition system.

• Journal of Arbitration Studies
• /
• v.27 no.1
• /
• pp.131-160
• /
• 2017

When any investment dispute arises, the investor has to exhaust the local remedies available in the host state, and according to the agreement between the parties, the investor is filed to the ICSID arbitral tribunal to seek arbitral awards. At this time, if the arbitral tribunal decides that the investment agreement has been violated, it normally demands the host state to provide financial compensations to the investor for economic loss. According to the rules of the investment agreement, the host state is supposed to fulfill the arbitral awards voluntarily. If it is unwilling to provide financial compensations according to the arbitral awards, however, the investor may ask the domestic court of the host state for the recognition and enforcement of arbitral awards. In addition, if the host state is unwilling to fulfill arbitral awards on account of state immunity, the investor may ask his own country (state of nationality) for diplomatic protection and urge it to demand the fulfillment of arbitral awards. Effectiveness for pecuniary damages, a means to solve problems arising in the enforcement of investment arbitral awards, is found to be rather ineffective. For such cases, this study suggests an alternative to demand either a restitution of property or a corrections of violated measures subject to arbitral awards.

• Journal of Internet of Things and Convergence
• /
• v.10 no.3
• /
• pp.57-64
• /
• 2024

In this paper, we propose a Line-of-Sight (LoS)/Non-Line-of-Sight (NLoS) identification- based Human Activity Recognition (HAR) system using Channel State Information (CSI) to improve the accuracy of HAR, which dynamically changes depending on the reception environment. to consider the reception environment of HAR system, the proposed system includes three operational phases: Preprocessing phase, Classification phase, and Activity recognition phase. In the preprocessing phase, amplitude is extracted from CSI raw data, and noise in the extracted amplitude is removed. In the Classification phase, the reception environment is categorized into LoS and NLoS. Then, based on the categorized reception environment, the HAR model is determined based on the result of the reception environment categorization. Finally, in the activity recognition phase, human actions are classified into sitting, walking, standing, and absent using the determined HAR model. To demonstrate the superiority of the proposed system, an experimental implementation was performed and the accuracy of the proposed system was compared with that of the existing HAR system. The results showed that the proposed system achieved 16.25% higher accuracy than the existing system.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1992.06a
• /
• pp.61-65
• /
• 1992

This paper presents a study on Neural Networks for Phoneme Recognition and performs phoneme recognition using TDNN(Time Delay Neural Network). Also, this paper proposes new training algorithm for speech recognition using neural nets that proper to large scale TDNN. Because phoneme recognition is indispensable for continuous speech recognition, this paper uses TDNN to get accurate recognition result of phoneme. And this paper proposes new training algorithm that can converge TDNN to optimal state regardless of the number of phoneme to be recognized. The result of recognition on three phoneme classes shows recognition rate of 9.1%. And this paper proves that proposed algorithm is a efficient method for high performance and reducing convergence time.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.77-80
• /
• 2000

In this paper, the speaker-recognition process based on both DTW and discrete HMM was performed using the method to evaluate state-dependent parameter weighting from training data so as the personal audio-characteristics are to be well reflected. In the suggested method below, we found the optimal state sequence using the Viterbi algorithm. The optimal path could be evaluated after comparing the sequence of base pattern which already have, with that of the other patterns. After that the frame of which the pattern was matched with the base pattern in the same state are to be found so that the reference pattern can be gained by weighting on the numbers of matched frames.