• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1013-1016
• /
• 1993

This paper describes a new type of neuron model, the inputs of which are interfered with one another. It has a high mapping ability with only single unit. The learning speed is considerably improved compared with the conventional linear type neural networks. The proposed neuron model was successfully applied to the prediction problem of chaotic time series signal.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.5
• /
• pp.2623-2627
• /
• 2014

The objective of this study is to experimentally investigate the heat transfer characteristics of 200W woofer speaker unit with the input voice signals such as 500 Hz, 1000 Hz, 2000 Hz, and 3000 Hz. The temperature and heat transfer characteristics of the woofer speaker unit were evaluated with the input signals. As results. the temperature of the voice-coil for woofer speaker unit increased with a decrease of the input signals and the temperature differences between parts of the tested speaker unit increased with the decrease of the input voice signals. In addition, the voice-coil temperature for the input signal of 500 Hz showed 48.4 % lower than that of 3000 Hz during 18000 sec.

• 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.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.11 no.3
• /
• pp.492-498
• /
• 2000

When multi-carriers are applied to the high power amplifier(HPA) having nonlinear characteristics, the HPA output has unwanted IMD signals. The IMD signal is noise in the HPA. The magnitude and phase of the main and IMD signal of HPA output are changed as the input signal power is changed. If we know exactly the magnitude and phase characteristics of the main and IMD signal, we can design a more adequate linearizer and understand the characteristics of transistor. In this paper the magnitude and phase of the main and IMD signal of HPA output are measured and analyzed for variation of the input power.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.7
• /
• pp.1650-1658
• /
• 1998

This paper describes how to remove echoes effectively using speech parameter information provided form speech coder. More specially, the proposed adaptive echo canceller utilizes the excitation signal or linearly predicted error signal instead of output speech signal of vocoder as the input signal for adaptation algorithm. The normalized least mean ssquare(NLMS) algorithm is used for the adaptive echo canceller. The proposed algorithm showed a fast convergece charactersitcis in the sinulatio compared to the conventional method. Specially, the proposed echo canceller utilizing the excitation signal of speech coder showed about four times fast convergence speed over the echo canceller utilizing the output speech signal of the speech coder for the adaptation input.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.723-726
• /
• 2009

In this research, We simulated performances of error reduction algorithm for the speech signal based on the microphone array-based beamforming method in speech recognition system and analyzed its performance. Also, we processed speech signal adopted from microphone array and maximum signal to noise ratio for each channel, and then compared them with signal to noise ratio of speech signal. Speech recognition rate is improved from 54.2% to 61.4% in case 1 and is improved from 41.2% to 50.5% in case 2 of the lower signal to noise ratio. Therefore the average reduction rates are showed 15.7% in case 1.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.5
• /
• pp.435-441
• /
• 2017

Detecting an inter-harmonic accurately is not easy work, because it has small magnitude, and its frequency which can be observed is not an integer multiple of fundamental frequency. In this paper, a new method using filter bank system and adaptive predictor is proposed. Filter bank system decomposes input signal to sub bands. In adaptive predictor, inter-harmonic is detected with decomposed sub band signal as input, and error signal as output. In this scheme, input-output characteristic of adaptive predictor is notch filter, as predicted harmonic is canceled in error signal, so detecting an inter-harmonic can be possible. Magnitude and frequency of detected inter-harmonic is estimated by recursive algorithm. The performances of proposed method are evaluated to sinusoidal signal model synthesized with harmonics and inter-harmonics. And validity of the method is proved as comparing the inter-harmonic detection results to MUSIC and ESPRIT.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.457-461
• /
• 2014

Using $0.18{\mu}m$ CMOS process silicon neuron circuit of the pulse type for modeling biological neurons, were designed in the semiconductor integrated circuit. Neuron circuiSt providing is formed by MOS switch for initializing the input terminal of the capacitor to the input current signal, a pulse signal and an amplifier stage for generating an output voltage signal. Synapse circuit that can convert the current signal output of the input voltage signal, using a bump circuit consisting of NMOS transistors and PMOS few. Configure a chain of neurons for verification of the neuron model that provides synaptic neurons and two are connected in series, were performed SPICE simulation. Result of simulation, it was confirmed the normal operation of the synaptic transmission characteristics of the signal generation of nerve cells.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.890-896
• /
• 2022

In this paper, gimbal camera control through smart gloves was implemented to increase convenience and accessibility to the control of drones used in various fields. Smart gloves identify human gestures and transmit signals through Bluetooth. The received signal is converted into a signal suitable for the drone through a GCS (Gound Control Station). Signals from smart gloves are expressed in a quaternion method to prevent gimbal locks, but for gimbal cameras, conversion is required to use Roll, Pitch, and Yaw methods. The data conversion mission is performed in the GCS. The GCS transmits an input signal to the control board of the drone through Wi-Fi. The control board generates and outputs the transmitted signal in a PWM manner. The output signal is input to the gimbal camera through the SBUS method and controlled. The input signal of the smart glove averaged 0.093 s and up to 0.099 s to output to the gimbal camera, showing that there was no problem in real-time use.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.7 no.1
• /
• pp.79-86
• /
• 2003

A myoelectric signal, under sustained isometric contraction of muscle the modelled as the output of a linear time-varying system whose input is constant number of pulse train. The proposed model considered localized muscle fatigue by metabolic by-products during sustained fatiguing contraction. To characterize muscle fatiguing model of myoelectric signal, We calculated median frequency of generated signal as fatiguing index of muscle during sustained isometric contraction.