• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1249-1256
• /
• 2019

In this paper, we propose a new algorithm to remove acoustic feedback and noise in hearing aids. Instead of using the conventional FIR structure, this algorithm is a deep learning algorithm using neural network adaptive prediction filter to improve the feedback and noise reduction performance. The feedback canceller first removes the feedback signal from the microphone signal and then removes the noise using the Wiener filter technique. Noise elimination is to estimate the speech from the speech signal containing noise using the linear prediction model according to the periodicity of the speech signal. In order to ensure stable convergence of two adaptive systems in a loop, coefficient updates of the feedback canceller and noise canceller are separated and converged using the residual error signal generated after the cancellation. In order to verify the performance of the feedback and noise canceller proposed in this study, a simulation program was written and simulated. Experimental results show that the proposed deep learning algorithm improves the signal to feedback ratio(: SFR) of about 10 dB in the feedback canceller and the signal to noise ratio enhancement(: SNRE) of about 3 dB in the noise canceller than the conventional FIR structure.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.19-23
• /
• 2024

Patients with amputations of both hands need prosthetic hands that serve both cosmetic and functional purposes, and research on prosthetic hands using electromyography of remaining muscles is active, but there is still the problem of high cost. In this study, an artificial prosthetic hand was manufactured and its performance was evaluated using low-cost parts and software such as a surface electromyography sensor, machine learning software Edge Impulse, Arduino Nano 33 BLE, and 3D printing. Using signals acquired with surface electromyography sensors and subjected to digital signal processing through Edge Impulse, the flexing movement signals of each finger were transmitted to the fingers of the prosthetic hand model through training to determine the type of finger movement using machine learning. When the digital signal processing conditions were set to a notch filter of 60 Hz, a bandpass filter of 10-300 Hz, and a sampling frequency of 1,000 Hz, the accuracy of machine learning was the highest at 82.1%. The possibility of being confused between each finger flexion movement was highest for the ring finger, with a 44.7% chance of being confused with the movement of the index finger. More research is needed to successfully develop a low-cost prosthetic hand.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.379-384
• /
• 2002

개발적인 측면에서 온라인 게임 환경에서의 NPC(Non Playable Character)들은 환경인식능력, 이동능력, 특수 능력 및 아이템의 소유 배분 등을 원활히 하기 위한 능력들을 소유해야 하며, 게임 환경을 인식, 저장하기 위한 데이터구조와 자신만의 독특한 임무(mission)를 달성하기 위한 계획을 갖고 행위를 해야 한다. 이런 의미에서 NPC는 자신만의 고유한 규칙과 행동 패턴, 그리고 목표(Goal)와 이를 실행하기 위한 계획(plan)을 소유하는 에이전트로 인식되어야 할 것이다. 그러나, 기존 게임의 NPC 제어 구조나 구현 방법은 이러한 요구조건에 부합되지 못한 부분이 많았다. C/C++ 같은 컴퓨터 언어들을 이용한 구현은 NPC의 유연성이나, 행위에 많은 문제점이 있었다. 이들 언어의 switch 문법은 NPC의 몇몇 특정 상태를 묘사하고, 그에 대한 행위를 지정하는 방법으로 사용되었으나, 게임 환경이 복잡해지면서, 더욱더 방대한 코드를 만들어야 했고, 해석하는데 많은 어려움을 주었으며, 동일한 NPC에 다른 행동패턴을 적용시키기도 어려웠다. 또한, 대부분의 제어권을 게임 서버 폭에서 도맡아 함으로써, 서버측에 많은 과부하 요인이 되기도 하였다. 이러한 어려움을 제거하기 위해서 게임 스크립트를 사용하기도 하였지만, 그 또한 단순 반복적인 패턴에 사용되거나, 캐릭터의 속성적인 측면만을 기술 할 수 있을 뿐이었다 이러한 어려움을 해소하기 위해서는 NPC들의 작업에 필요한 지식의 계층적 분화를 해야 하고, 현재 상황과 목표 변화에 적합한 반응을 표현할 수 있는 스크립트의 개발이 필수 적이라 할 수 있다 또한 스크립트의 실행도 게임 서버 측이 아닌 클라이언트 측에서 수행됨으로써, 서버에 걸리는 많은 부하를 줄일 수 있어야 할 것이다. 본 논문에서는, 대표적인 반응형 에이전트 시스템인 UMPRS/JAM을 이용하여, 에이전트 기반의 게임 캐릭터 구현 방법론에 대해 알아본다.퓨터 부품조립을 사용해서 Template-based reasoning 예를 보인다 본 방법론은 검색노력을 줄이고, 검색에 있어 Feasibility와 Admissibility를 보장한다.매김할 수 있는 중요한 계기가 될 것이다.재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity of computation. Adaptive transversal filter with proposed data recycling buffer algorithm could efficiently reject ISI of channel and increase speed of convergence in avoidance burden of computational complexity in reality when it was experimented having

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.535-542
• /
• 2002

최근 IT 산업이 급성장하면서 화상 회의, 게임, 채팅 등에서의 아바타(avatar) 제어를 위한 자연스러운 인터페이스 기술이 요구되고 있다. 본 논문에서는 동적 윤곽선 모델(active contour models; snakes)을 이용하여 복잡한 배경이 있는 컬러 CCD 카메라 영상에서 얼굴과 눈, 입, 눈썹, 코 등의 얼굴 요소에 대해 윤곽선을 추출하거나 위치를 파악하는 방법을 제안한다. 일반적으로 스네이크 알고리즘은 잡음에 민감하고 초기 모델을 어떻게 설정하는가에 따라 추출 성능이 크게 좌우되기 때문에 주로 단순한 배경의 영상에서 정면 얼굴의 추출에 사용되어왔다 본 연구에서는 이러한 단점을 파악하기 위해, 먼저 YIQ 색상 모델의 I 성분을 이용한 색상 정보와 차 영상 정보를 사용하여 얼굴의 최소 포함 사각형(minimum enclosing rectangle; MER)을 찾고, 이 얼굴 영역 내에서 기하학적인 위치 정보와 에지 정보를 이용하여 눈, 입, 눈썹, 코의 MER을 설정한다. 그런 다음, 각 요소의 MER 내에서 1차 미분과 2차 미분에 근거한 내부 에너지와 에지에 기반한 영상 에너지를 이용한 스네이크 알고리즘을 적용한다. 이때, 에지 영상에서 얼굴 주변의 복잡한 잡음을 제거하기 위하여 색상 정보 영상과 차 영상에 각각 모폴로지(morphology)의 팽창(dilation) 연산을 적용하고 이들의 AND 결합 영상에 팽창 연산을 다시 적용한 이진 영상을 필터로 사용한다. 총 7명으로부터 양 눈이 보이는 정면 유사 방향의 영상을 20장씩 취득하여 총 140장에 대해 실험한 결과, MER의 오차율은 얼굴, 눈, 입에 대해 각각 6.2%, 11.2%, 9.4%로 나타났다. 또한, 스네이크의 초기 제어점을 얼굴은 44개, 눈은 16개, 입은 24개로 지정하여 MER추출에 성공한 영상에 대해 스네이크 알고리즘을 수행한 결과, 추출된 영역의 오차율은 각각 2.2%, 2.6%, 2.5%로 나타났다.해서 Template-based reasoning 예를 보인다 본 방법론은 검색노력을 줄이고, 검색에 있어 Feasibility와 Admissibility를 보장한다.매김할 수 있는 중요한 계기가 될 것이다.재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity of computation. Adaptive transversal filter with proposed data recycling buffer algorithm could efficiently reject ISI of channel and increase speed of convergence in avoidance burden of computational complexity in reality when it was experimented having the same condition of

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.12
• /
• pp.27-36
• /
• 2019

The demand for a low dispersion lens with a small refractive index and a high refractive index is increasing, and accordingly, there is an increasing need for a releasable protective film with high heat resistance and abrasion resistance. On the other hand, the optical industry has not yet established a clear standard for the manufacturing process and quality standards for mold-releasing protective films used in aspheric glass lens molding. Optical lens manufacturers treat this technology as proprietary information. In this study, an experiment was conducted regarding the optimization of ion etching, magnetron, and arc current at each source and filter part, and bias voltage in FCVA (filtered cathode vacuum arc)-based Ta-C thin film coatings. This study found that compared to iridium-rhenium alloy thin film sputtering products, the coating conditions were improved by approximately 50%, 20%, and 40% in terms of thickness, hardness, and adhesive strength of the film, respectively. The thin-film coating process proposed in this study is expected to contribute significantly to the development and utilization of glass lenses, which will help enhance the minimum mechanical properties and quality of the mold-release thin film layer required for glass mold surface forming technology.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.4
• /
• pp.97-112
• /
• 2013

The quality of the data is the most basic prerequisite for effective use of data. Problems and the resulting loss due to error data has emerged using case studies and a number of, to a national, quality certification system of the data has been enforced, you must manage to generate data study on the method for selecting the point of view of an organization's data CTQ is a very unsatisfactory state of affairs. Selected CTQ main data is subject to quality control in the organization, to develop criteria for CTQ data side of the business and IT so that it can be managed in a systematic manner, the proposed model, to filter the data accordingly presented in detail how to manage enterprise-wide CTQ data that can be quantified Te. By utilizing SPSS, factor analyzes, for which I used the AHP method for quantification. In particular, we present a framework of management measures along the maturity of the data in the organization due to the enforcement of authentic quality certification system of DB, utilizing the CTQ-DSMM model readily applicable to practice.

• International journal of advanced smart convergence
• /
• v.4 no.1
• /
• pp.45-53
• /
• 2015

This paper is proposed mathematical load modelling based on system identification approach of energy consumption of residential air conditioning. Due to air conditioning is one of the significant equipment which consumes high energy and cause the peak load of power system especially in the summer time. The demand response is one of the solutions to decrease the load consumption and cutting peak load to avoid the reservation of power supply from power plant. In order to operate this solution, mathematical modelling of air conditioning which explains the behaviour is essential tool. The four type of linear model is selected for explanation the behaviour of this system. In order to obtain model, the experimental setup are performed by collecting input and output data every minute of 9,385 BTU/h air-conditioning split type with $25^{\circ}C$ thermostat setting of one sample house. The input data are composed of solar radiation ($W/m^2$) and ambient temperature ($^{\circ}C$). The output data are power and energy consumption of air conditioning. Both data are divided into two groups follow as training data and validation data for getting the exact model. The model is also verified with the other similar type of air condition by feed solar radiation and ambient temperature input data and compare the output energy consumption data. The best model in term of accuracy and model order is output error model with 70.78% accuracy and $17^{th}$ order. The model order reduction technique is used to reduce order of model to seven order for less complexity, then Kalman filtering technique is applied for remove white Gaussian noise for improve accuracy of model to be 72.66%. The obtained model can be also used for electrical load forecasting and designs the optimal size of renewable energy such photovoltaic system for supply the air conditioning.

• Journal of Digital Convergence
• /
• v.16 no.9
• /
• pp.399-404
• /
• 2018

The purpose of this study is to raise the drinking rate of Arisu, the tap water in Seoul, and to propose new solution for continuous water quality management and raising awareness. The research scope was limited to point-of-use water treatment system, and based on the this contents I proceed this study how this will help to increase direct drinking rate of Arisu. Through research, Korea has provided users with the ability to filter contaminated tap water simply as water to be rinsed through water purification. Therefore, it was predicted that it would be difficult to improve tap water as drinking water. With this study, I expect that the strength of point-of-use system and the reliability of tap water quality will be raised and hope various product will be developed to improve the perception as drinking water and I also expect that this can be applied to whole country even further in the scope of Seoul city.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.12
• /
• pp.2353-2362
• /
• 2015

In this paper, we employ the single channel full duplex radio for wireless local area network (WLAN) systems, and design digital interference cancellers using adaptive signal processing. When the full duplex scheme is used for WLAN systems with multiple transmit and receive antennas, some interference is caused through the feedback of transmit signals from multiple antennas. To remove the feedback interference, we derive the least mean square (LMS), normalized LMS (NLMS), and recursive least squares (RLS) algorithms based on adaptive signal processing techniques. In addition, we analyze the theoretical convergence of the proposed LMS and RLS methods. The channel capacity of full duplex radios increases by two times than that of half duplex radios, when the packet error rate (PER) performances for the two systems are identical. Through numerical simulations in WLAN systems, it is shown that the full duplex method with the proposed interference cancellers has a similar PER performance with the conventional half duplex transmission scheme.

• Journal of Ecology and Environment
• /
• v.41 no.11
• /
• pp.318-327
• /
• 2017

Background: A typical sewage treatment plant is designed for organic and nutrient removal from municipal sewage water and not targeted to eliminate micropollutants such as pesticides, pharmaceuticals, and nano-sized metals which become a big concern for sustainable human and ecological system and are mainly discharged from sewage treatment plant. Therefore, despite contaminant removal by wastewater treatment processes, there are still remaining environmental risks by untreated pollutants in STP (sewage treatment plant) effluents. This study performed aquatic toxicity tests of raw wastewater and treated effluents in two sewage treatment plants to evaluate toxicity reduction by wastewater treatment process and analyze concentration of contaminants to reveal potential toxic factors in STP effluents. Methods: Water samples were collected from each treatment steps of two STPs, and acute and chronic toxicity tests were conducted following USEPA (United States Environmental Protection Agency) and OECD (Organization for Economic Cooperation and Development) guidelines. Endpoints were immobility for mortality and reproduction effect for estrogenicity. Results: Acute $EC_{50}s$ (median effective concentration) of influents for Seungki (SK) and Jungnang (JN) STPs are $54.13{\pm}32.64%$ and $30.38{\pm}24.96%$, respectively, and reduced to $96.49{\pm}7.84%$ and 100%. Acute toxicity reduction was clearly correlated with SS (suspended solids) concentration because of filter feeding characteristics of test organisms. Chronic toxicity tests revealed that lethal effect was reduced and low concentration of influents showed higher number of neonates. However, toxicity reduction was not related to nutrient removal. Fecundity effect positively increased in treated wastewater compared to that in raw wastewater, and no significant differences were observed compared to the control group in JN final effluent implying potential effects of estrogenic compounds in the STP effluents. Conclusions: Conventional wastewater treatment process reduced some organics and nutritional compounds from wastewater, and it results in toxicity reduction in lethal effect and positive reproductive effect but not showing correlation. Unknown estrogenic compounds could be a reason causing the increase of brood size. This study suggests that pharmaceutical residues and nanoparticles in STP effluents are one of the major micropollutants and underline as one of estrogenic effect factors.