• Journal of Biomedical Engineering Research
• /
• 제32권1호
• /
• pp.55-60
• /
• 2011

Although sound intensity is considered as one of important factors in auditory processing, its neural mechanism in auditory neurons with limited dynamic range of firing rates is still unclear. In this study, we examined the effect of sound intensity adaptation on the change of glucose metabolism in a rat brain using [F-18] micro positron emission tomography (PET) neuroimaging technique. In the experiment, broadband white noise sound was given for 30 minutes after the [F-18]FDG injection in order to explore the functional adaptation of rat brain into the sound intensity levels. Nine rats were scanned with four different sound intensity levels: 40 dB, 60 dB, 80 dB, 100 dB sound pressure level (SPL) for four weeks. When glucose uptake during the adaptation of a high intensity sound level (100 dB SPL) was compared with that during adaptation to a low intensity level (40 dB SPL) in the experiment, the former induced a greater uptake at bilateral cochlear nucleus, superior olivary complexes and inferior colliculi in the auditory pathway. Expectedly, the metabolic activity in those areas linearly increased as the sound intensity level increased. In contrast, significant decrease interestingly occurred in the bilateral auditory cortices: The activities of auditory cortex proportionally decreased with higher sound intensities. It may reflect that the auditory cortex actively down-regulates neural activities when the sound gets louder.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.531-531
• /
• 2000

The challenge is to control unstable nonlinear dynamic systems using only sparse feedback from the environment concerning its performance. The design of such controllers can be achieved by evolving neural networks. An evolutionary approach to train neural networks in realtime is proposed. Evolutionary strategies adapt the weights of neural networks and the threshold values of neuron's synapses. The proposed method has been successfully implemented for pole balancing problem.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• 제30A권4호
• /
• pp.37-43
• /
• 1993

As an approach to develope the intelligent control scheme, this paper will propose an adaptive neural-fuzzy control scheme. The proposed neural-fuzzy control system, which consists of the Fuzzy-Neural Controller(FNC) and Model Neural Network(MNN), has two important characteristics of adaptation and learning. The error back propagation algorithm has been adopted as a learning technique.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1998년도 하계학술대회 논문집 G
• /
• pp.2265-2267
• /
• 1998

This paper deals with study of Fast Speaker Adaptation Type Speech Recognition, and to analyze speech signal efficiently in time domain and time-frequency domain, utilizes SCONN[1] with Speech Signal Process suffices for Fast Speaker Adaptation Type Speech Recognition, and examined Speech Recognition to investigate adaptation of system, which has speech data input after speaker dependent recognition test.

• Journal of Korea Multimedia Society
• /
• 제20권8호
• /
• pp.1208-1215
• /
• 2017

Recently, people's attention and worries about fine particulate matter have been increasing. Due to the construction and maintenance costs, there are insufficient air quality monitoring stations. As a result, people have limited information about the concentration of fine particulate matter, depending on the location. Studies have been undertaken to estimate the fine particle concentrations in areas without a measurement station. Yet there are limitations in that the estimate cannot take account of other factors that affect the concentration of fine particle. In order to solve these problems, we propose a framework for estimating the concentration of fine particulate matter of a specific area using meteorological data and traffic data. Since there are more grids without a monitor station than grids with a monitor station, we used a domain adversarial neural network based on the domain adaptation method. The features extracted from meteorological data and traffic data are learned in the network, and the air quality index of the corresponding area is then predicted by the generated model. Experimental results demonstrate that the proposed method performs better as the number of source data increases than the method using conditional random fields.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.2785-2799
• /
• 2020

We propose a novel speaker adaptation method using acoustic model clustering. The similarity of different speakers is defined by the cosine distance between their i-vectors (intermediate vectors), and various efficient clustering algorithms are applied to obtain a number of speaker subsets with different characteristics. The speaker-independent model is then retrained with the training data of the individual speaker subsets grouped by the clustering results, and an unknown speech is recognized by the retrained model of the closest cluster. The proposed method is applied to a large-scale speech recognition system implemented by a hybrid hidden Markov model and deep neural network framework. An experiment was conducted to evaluate the word error rates using Resource Management database. When the proposed speaker adaptation method using i-vector based clustering was applied, the performance, as compared to that of the conventional speaker-independent speech recognition model, was improved relatively by as much as 12.2% for the conventional fully neural network, and by as much as 10.5% for the bidirectional long short-term memory.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• 제32B권5호
• /
• pp.765-776
• /
• 1995

This paper describes a speaker adaptation method to improve the recognition performance of MLP(multiLayer Perceptron) based HMM(Hidden Markov Model) speech recognizer. In this method, we use lst-order linear transformation network to fit data of a new speaker to the MLP. Transformation parameters are adjusted by back-propagating classification error to the transformation network while leaving the MLP classifier fixed. The recognition system is based on semicontinuous HMM's which use the MLP as a fuzzy vector quantizer. The experimental results show that rapid speaker adaptation resulting in high recognition performance can be accomplished by this method. Namely, for supervised adaptation, the error rate is signifecantly reduced from 9.2% for the baseline system to 5.6% after speaker adaptation. And for unsupervised adaptation, the error rate is reduced to 5.1%, without any information from new speakers.

• BMB Reports
• /
• 제50권3호
• /
• pp.109-110
• /
• 2017

The nature of encoded information in neural circuits is determined by neuronal firing patterns and frequencies. This paper discusses the molecular identity and cellular mechanisms of spike-frequency adaptation in the central nervous system (CNS). Spike-frequency adaptation in thalamocortical (TC) and CA1 hippocampal neurons is mediated by the $Ca^{2+}$-activated $Cl^-$ channel (CACC) anoctamin-2 (ANO2). Knockdown of ANO2 in these neurons results in increased number of spikes, in conjunction with significantly reduced spike-frequency adaptation. No study has so far demonstrated that CACCs mediate afterhyperpolarization currents, which result in the modulation of neuronal spike patterns in the CNS. Our study therefore proposes a novel role for ANO2 in spike-frequency adaptation and transmission of information in the brain.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1994년도 추계학술대회 논문집 학회본부
• /
• pp.326-328
• /
• 1994

A modified Kohonen's simple Competitive Learning(SCL) algorithm which has binary reinforcement function and a constant adaptation gain is proposed. In contrast to the time-varing adaptation gain of the original Kohonen's SCL algorithm, the proposed algorithm uses a constant adaptation gain, and adds a binary reinforcement function in order to compensate for the lowered learning ability of SCL due to the constant adaptation gain. Since the proposed algorithm does not have the complicated multiplication, it's digital hardware implementation is much easier than one of the original SCL.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• 제39권12호
• /
• pp.1306-1316
• /
• 1990

A controller using a multilayer neural network is proposed to the dynamic control of a PUMA 560 robot arm. This controller is developed based on an error back-propagation (BP) neural network. Since the neural network can model an arbitrary nonlinear mapping, it is used as a commanded feedforward torque generator. A Proportional Derivative (PD) feedback controller is used in parallel with the feedforward neural network to train the system. The neural network was trained by the current state of the manipulator as well as the PD feedback error torque. No a priori knowledge on system dynamics is needed and this information is rather implicitly stored in the interconnection weights of the neural network. In another experiment, the neural network was trained with the current, past and future positions only without any use of velocity sensors. Form this thim window of position values, BP network implicitly filters out the velocity and acceleration components for each joint. Computer simulation demonstrates such powerful characteristics of the neurocontroller as adaptation to changing environments, robustness to sensor noise, and continuous performance improvement with self-learning.