• 전기학회논문지
• /
• 제65권7호
• /
• pp.1263-1269
• /
• 2016

Hearing impaired persons are exposed to the danger since they can't be aware of many dangerous situations like fire alarms, car hones and so on. Therefore they need haptic or visual informations when they meet dangerous situations. In this paper, we design a dangerous sound detection engine for hearing impaired. We consider four dangerous indoor situations such as a boiled sound of kettle, a fire alarm, a door bell and a phone ringing. For outdoor, two dangerous situations such as a car horn and a siren of emergency vehicle are considered. For a test, 6 data sets are collected from those six situations. we extract LPC, LPCC and MFCC as feature vectors from the collected data and compare the vectors for feasibility. Finally we design a matching engine using an artificial neural network and perform classification tests. We perform classification tests for 3 times considering the use outdoors and indoors. The test result shows the feasibility for the dangerous sound detection.

• 한국CDE학회논문집
• /
• 제15권2호
• /
• pp.106-114
• /
• 2010

The swept volume, the region of a moving object, is applied in many fields such as valid paths for motions of tools, visualization in robot paths and interference tests for parts assembling or disjointing. The shape of a swept volume depends on an generators computed with normal vectors of an object and velocity vectors of a motion. Although free-from surfaces are widely used to represent geometric models in CAD, computing the generators for a free-form object is a formidable task. Previous approaches exploit the closed form expressions of generators but limited to planer or quadric faces. In this paper, we propose the algorithm to compute swept volumes generated by free-form objects in screw motions. For the algorithm a tracing method is applied to the computation of generators. It considers curvatures of surfaces of an object to increase the computational accuracy. We implemented our algorithm in the CATIA V.5 environment to test the validity of our algorithm and to generate examples.

• 한국생물공학회:학술대회논문집
• /
• 한국생물공학회 2001년도 추계학술발표대회
• /
• pp.441-443
• /
• 2001

CMP(caseinomacropeptide) is known to be a peptide which controls the gain of body weight and eventually will be used as a new candidate to control obesity problem. In this study, CMP gene was obtained using RT-PCR and ligated to secretion vectors having different kinds of promoters and P.pastoris and S.cerevisiae were transformed with these vectors. Colonies showing high titre of CMP cxpressecl were chosen and fed-batch fermentation is being carried out with these transformant to test economic feasibility

• 경영과학
• /
• 제5권2호
• /
• pp.71-80
• /
• 1988

The object of this thesis is to develop an effective method for Five-in-a-Row. For this purpose, we develop a method that describes a move accurately, and a procedure that choses a move more effectively. In describing a move, we represent each move as eight vectors generated from four directions for both offensive and defensive strategies. Each vector consists of three components, that is, connectivity, agressiveness, and directions of stones in a line. In choosing a move, we introduce a preference order among all vectors by an expert's knowledge. Then, an efficient algorithm is developed to test a cycle in the preference order. Experimental results show that the success rate of this new method is about 90% against Weisenbaum's program known as the prototype of the Five-in-a-Row program.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2002년도 학술대회지
• /
• pp.471-474
• /
• 2002

A new stereoscopic PIV has been constructed using two CCD cameras, stereoscopic photogrammetry, and 3D-PTV principle. The capability of the developed stereoscopic PIV was verified through a test on the Standard Images which are provided on the website of VSJ. The arrangement of the two cameras was based on angular position For the acquisition of 3D velocity vectors, 2D velocity vectors were obtained using the gray-level cross-correlation method from the two camera images and they were matched stereoscopically. The wake of a circular cylinder was measured and turbulent properties were presented.

• Journal of Electrical Engineering and Technology
• /
• 제9권1호
• /
• pp.170-177
• /
• 2014

This paper presents a new method of classification of the induction machine faults using Time Frequency Representation, Particle Swarm Optimization and artificial neural network. The essence of the feature extraction is to project from faulty machine to a low size signal time-frequency representation (TFR), which is deliberately designed for maximizing the separability between classes, a distinct TFR is designed for each class. The feature vectors size is optimized using Particle Swarm Optimization method (PSO). The classifier is designed using an artificial neural network. This method allows an accurate classification independently of load level. The introduction of the PSO in the classification procedure has given good results using the reduced size of the feature vectors obtained by the optimization process. These results are validated on a 5.5-kW induction motor test bench.

• 전자공학회논문지B
• /
• 제30B권6호
• /
• pp.35-48
• /
• 1993

In this paper, a hierarchical motion vector estimation algorithm using pyramidal structure is proposed. Using a smaller measurement window at each level of a pyramid than that of the conventional scheme, the proposed algorithm, based on the TSS(three step search), reduces the computational complexity greatly with its performance comparable to that of the TSS. By increasing the number of cnadidate motion vectors which are to be used as the initial search points for motion vector estimation at the next level, the performance improves further. Then the computational complexity of the proposed hierarchical algorithm depends on the number of candidate motion vectors, with its PSNR (peak signal to noise ratio) ranging between those of the TSS and the full search method. The simulation results with two different block sizes and various test sequences are given and its hardware implementation is also sketched.

• 음성과학
• /
• 제7권4호
• /
• pp.11-26
• /
• 2000

In this paper, we propose the HMM with the MIN module. Because initial and re-estimated variance vectors are important elements for performance in HMM recognition systems, we propose a method which compensates for the mismatched statistical feature of training and test data. The MIN module function is a differentiable function similar to the sigmoid function. Unlike a continuous density function, it does not include variance vectors of the data set. The proposed hybrid HMM/MIN module is a unified network in which the observation probability in the HMM is replaced by the MIN module neural network. The parameters in the unified network are re-estimated by the gradient descent method for the Maximum Likelihood (ML) criterion. In estimating parameters, the variance vector is not estimated because there is no variance element in the MIN module function. The experiment was performed to compare the performance of the proposed HMM and the conventional HMM. The experiment measured an isolated number for speaker independent recognition.

• 한국산학기술학회논문지
• /
• 제5권4호
• /
• pp.279-281
• /
• 2004

100%천연향을 이용하여 제작, 개발된 해충기피제의 기피력을 테스트하였다. 해충기피제를 착용한 그룹과 착용하지 않은 그룹으로 구분하여 실험실에서 사육한 모기와 서해안에 위치한 몽산포 해수욕장, 동해안에 위치한 낙산 및 설악 해수욕장과 천안에 있는 태조산에서 해충에 대한 기피력을 측정하였으며, 각 그룹별로 5명씩 5회에 걸쳐 각 회당 1시간동안에 흡혈개체로부터 물린 갯수를 확인하여 이들의 평균값을 계산하였다. 그 결과, 실험실에서는 91%,몽산포 해수욕장에서는 78%, 낙산 및 설악 해수욕장에서는 93%, 태조산에서는 90%의 기피력을 보여주었으며, 이는 상당히 탁월한 기피효과를 나타내었다.

• 전자공학회논문지C
• /
• 제35C권12호
• /
• pp.49-58
• /
• 1998

본 논문에서는 무고정 부분 스캔 테스트 방법을 위한 새로운 스캔 선택 알고리즘에 대하여 논한다. 무고정 부분 스캔 테스트 방법은 모든 플립-플롭을 스캔하지 않는다는 점을 제외하면 완전 스캔과 동일한 테스트 방법이다. 이 테스트 방법은 테스트 벡터를 입력, 인가, 혹은 적용 등, 어느 때에도 스캔, 비스캔 중 어느 플립-플롭의 데이터 값도 고정하지 않는다. 제안된 스캔 선택 알고리즘은 무고정 부분 스캔 테스트 방법에서 완전 스캔 고장 검출율을 거의 유지하면서 많은 플립-플롭을 스캔하지 않게 한다.