• Journal of the Institute of Convergence Signal Processing
• /
• v.25 no.2
• /
• pp.58-66
• /
• 2024

Robotics is a convergence technology with significant ripple effects across various industries, including manufacturing and services. Its importance has been increasingly underscored by advancements in artificial intelligence. As a crucial industry for addressing the challenges posed by a declining and aging production workforce and for enhancing manufacturing competitiveness, the training of robotics experts is now critically important. This paper examines the case of the Robot Job Innovation Center in Gumi City and proposes a strategy for training robotics experts and specialists in robot/AI-based signal processing. A core curriculum was carefully selected and implemented in actual educational settings, with key components necessary for developing a comprehensive educational framework detailed. The convergence of AI-based data signal processing and robotics represents a significant technological advancement poised to impact a wide array of industries. By proposing the comprehensive educational framework outlined in this paper, it is anticipated that related organizations will be able to effectively utilize these foundational elements to train experts in the field.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.810-816
• /
• 2011

The existing underwater acoustic communications modem is developing based on commercial products, so it is possible on functionality and performance of underwater acoustic communications modem implementation. But the production of development system is required to single platform system implementation at the system's size and cost. So this paper designs and implements the signal processing module as an important role to single hardware platform production of underwater acoustic communication modem by using TigerSHARC DSP processor.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.2 s.314
• /
• pp.137-143
• /
• 2007

The P-ECLMS algorithm adapted the existing Post-Processing method occurs the distortion of the near-end signal at the double-talk situation. To solve this problem, we propose the SP-ECLMS algorithm which makes the Post-Processing coefficient differently at the case of the single-talk and the double-talk. When the correlation level is not output less than 30%, the proposed algorithm output the original signal to prevent the signal's distortion.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.282-285
• /
• 2005

This paper discusses the interactive system for smart home environments. In order to realize this, the main emphasis of the paper lies on the description of the multiple signal processing on the basis of the technologies such as fingerprint recognition, video signal processing, speech recognition and synthesis. For essential modules of the interactive system, we adopted the motion detector based on the changes of brightness in pixels as well as the fingerprint identification for adapting home environments to the inhabitants. In addition, the real-time speech recognizer based on the HM-Net(Hidden Markov Network) and the speech synthesis were incorporated into the overall system for interaction between user and system. In experimental evaluation, the results showed that the proposed system was easy to use because the system was able to give special services for specific users in smart home environments, even though the performance of the speech recognizer was not better than the simulation results owing to the noisy environments.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1990.10a
• /
• pp.101-104
• /
• 1990

• The Journal of the Korea Contents Association
• /
• v.4 no.2
• /
• pp.1-6
• /
• 2004

This paper proposes on the acoustic signal processing blocking method of Internet pornographicl sites by calculating correlation values between prototype acoustic signals and input acoustic signals. Pre-existing blocking methods mainly focused on directory-based bled(fin and pornographic related words-based blocking. But these methods are not completely blocked the Internet harmful pornographicl sites by several situations. For this, this paper proposes the content-based blocking method which composes of the image-based blocking and the acoustic-based blocking. This paper, mainly, deals with the acoustic -based blocking method. Finally, the effectiveness of this system is demonstrated by several experiments.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.3
• /
• pp.143-148
• /
• 2007

The many studies have been proceeding to express accurately the feature of a sudden signal and a uncertain system in the image processing field. It is well know that Fourier Transform is widely used for frequency analysis of any signal. However, The frequency transform domain is not used for expressing the sudden signal change and non-stationary signal at the time-axis by this method. This paper describes of image analysis by discrete wavelet transform. Wavelet modulus maxima on transformed plane gives the Lipschitz exponent expression, which is useful to examine the characteristics of signal or the edge of an image. It is possible to reconstruct the original image only using the few maxima points. The fractal analysis is applied as an examples. The visualized image of oil flow on a ship model is analyzed. The fractal variable is obtained by the maxima analysis and the good results on the exprement is obtained by the visualized image analysis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.11
• /
• pp.3121-3129
• /
• 2009

Conventional marine radar systems utilize pulse radar which is capable of high-power transmissions and is effective for remote detection purposes. A pulse radar is most commonly used on medium or large vessels due to its expensive installation and maintenance costs. I propose the use of a Frequency Modulated Continuous Wave (FMCW) radar system operated at low-power and high-resolution instead of the conventional pulse-radar based system. The transmitted and received signals of the FMCW radar system were theoretically analyzed and radar signal processing design and simulation experiments were performed to detect the range and speed. Intermediate Frequency (IF) signal mixed with virtual transmit and receive signals were generated to perform FMCW radar signal processing simulations where the IF signal underwent noise reduction through a lowpass filter. The maximum frequency was derived through the sample interval of the FFT size instead of using A/D converter. This maximum frequency was used to get the frequency range and frequency speed which were in turn used to calculate the range and speed. The virtual beat frequency generated using MATLAB is utilized to analyze the beat frequency used in the actual FMCW radar system signal processing. The differences in the range and speed of the beat frequency signals are processed and analyzed.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1995.06a
• /
• pp.235-238
• /
• 1995

극점에서 비균일 표본화된 음성 신호는 크기열과 간격열의 이중구조로 표현되어, 균일 표본화된 신호에 근거한 기존의 신호처리 방법을 그대로 적용할 수 없다. 본 논문에서는 비균일 표본화된 음성 신호에서 에너지, 크기, 영교차율, 함수의 관계를 직접 유도하고, 특징을 살펴보아 비규닝ㄹ 펴본화된 음성신호에서도 균일 표본화된 신호에 해당하는 에너지, 크기, 영교차율과 같은 전처리과정 파라미터의추정이 가능함을 확인한다.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.6
• /
• pp.62-67
• /
• 1995

In this paper, the features extraction of reflected ultrasonic signals from various type of defects existing in Al metal has been studied by digital signal processing. Since the reflected signals from various type of the defects are ambiguous in features distinction from effects of noise, Wiener filtering using AR (auto-regressive) technique and least-absolute-values norm method has been used in features extraction and comparison of signals. In this experiment, three types of the defect in aluminum specimen have been considered: a flat cut, an angular cut, a circular hole. And the reflected signal have been measured by pulse-echo methods. In the result of digital signal processing of the reflected signal, it has been found that the features extraction method have been effective for classification of the reflected signals from various defects.