• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• 한국정보처리학회논문지
• /
• 제1권4호
• /
• pp.452-460
• /
• 1994

정보의 다양화와 고도화에 따라 지도정보 시스템 구축에 대한 요구가 급격히 대두 되고 있다. 본 논문에서는 생체 시각신경계(Opitcal Neural Field)의 처리과정에서 시 각영역의 특징추출 기구인 수용영역 즉, RF(Receptive Field) 모델을 이용하여 지도도 형의 도로정보를 추출하는 방법을 제안한다. 지형도에는 각종화상 정보가 다양하게 중 첩 포함되어 있는데 대한 복잡한 정보의 분리추출과 계층화 및 데이터베이스화등 시각 적으로 더욱 명백한 처리과정이 필요하다. 본 기법의 특징은 일반적인 처리과정에서 사용한 평행선 추출수법과 윤곽선 추출방법과는 달리 새로운 접근에 의한 특징추출방 법으로 국소적인 처리에서 얻어진 도로정보를 대국적인 처리로 통합 추출하는 것으 로서 실제 국립 지리원에서 발생한 1/25000 지도에 적용하여 가능성을 확인할 수 있었다.

• Journal of Ecology and Environment
• /
• 제33권4호
• /
• pp.307-315
• /
• 2010

Males of the field cricket Teleogryllus emma produce calling songs that are attractive to receptive females. The calling songs of T. emma consist of two components, the long chirp that is composed of up to 12 single pulses, followed by a variable number of short chirps. Based on the analysis of coefficient of variation (CV), temporal characters of the long chirp were less variable than those of the short chirps in male calling songs. To test for phonotactic selectivity of females, we conducted a single-stimulus playback experiment in which five stimuli (standard, long chirp only, long chirp augmented, short chirps only, and short chirps augmented) were used. The standard stimulus included both long and short chirps whose characteristics were derived from the calling songs of field populations. Results of the playback experiment showed that female crickets oriented more frequently toward the stimuli that included the long chirp (standard, long chirp only, and long chirp augmented stimuli) than toward the stimuli lacking the long chirp (short chirps only and short chirps augmented stimuli), indicating that the long chirp in the calling songs was required to elicit positive phonotaxis in the female crickets. The result of CV analysis of the male calling songs and the findings of the female phonotaxis experiment suggested that the long chirp of calling songs may play a role in species recognition in T. emma.

• 전기학회논문지
• /
• 제60권12호
• /
• pp.2352-2360
• /
• 2011

In this paper, we introduce a comprehensive design methodology of Radial Basis Function Neural Networks (RBFNN) that is based on mechanism of clustering and optimization algorithm. We can divide some clusters based on similarity of input dataset by using clustering algorithm. As a result, the number of clusters is equal to the number of nodes in the hidden layer. Moreover, the centers of each cluster are used into the centers of each receptive field in the hidden layer. In this study, we have applied Fuzzy-C Means(FCM) and K-Means(KM) clustering algorithm, respectively and compared between them. The weight connections of model are expanded into the type of polynomial functions such as linear and quadratic. In this reason, the output of model consists of relation between input and output. In order to get the optimal structure and better performance, Particle Swarm Optimization(PSO) is used. We can obtain optimized parameters such as both the number of clusters and the polynomial order of weights connection through structural optimization as well as the widths of receptive fields through parametric optimization. To evaluate the performance of proposed model, NXT equipment offered by National Instrument(NI) is exploited. The situation awareness system-related intelligent model was built up by the experimental dataset of distance information measured between object and diverse sensor such as sound sensor, light sensor, and ultrasonic sensor of NXT equipment.

• 한국지능시스템학회논문지
• /
• 제21권1호
• /
• pp.12-18
• /
• 2011

본 논문에서는 RBF 뉴럴 네트워크에서 은닉층 활성함수에 Interval type-2 퍼지개념을 적용한 새로운 RBF 뉴럴 네트워크를 설계하였다. 퍼지 시스템 분야에서 불확실한 정보에 대한 Type-1 퍼지집합의 성능을 보안하고자 Type-2 퍼지집합이 제안되었으며, 멤버쉽함수 안에 다시 멤버쉽함수를 생성함으로써 불확실한 정보를 좀 더 효과적으로 다루고자 하였다. 따라서 본 논문에서는 RBF 뉴럴 네트워크의 은닉층 활성함수에 type-2 퍼지집합의 개념을 적용하여 불확실한 정보에 대한 모델 성능을 개선하고자 하였다. 나아가 연결가중치를 상수항이 아닌 1차식으로 구성된 다항식을 사용하여 최종출력을 입력-출력의 관계식으로 표현하였다. 연결가중치는 기존의 경사하강법(Gradient Descent Method; GDM) 대신 conjugate gradient method(CGM)을 사용하여 파라미터를 동조하고, 은닉층의 활성함수는 공간탐색 진화 알고리즘(Space Search Evolutionary Algorithm; SSEA)을 이용하여 가우시안 함수의 중심점 및 분포상수를 동조하여 모델의 성능을 개선시킨다. 제안된 모델의 성능을 평가하기 위해 가스로 시계열 데이터를 사용하였으며, 결과를 기존 모델과 비교하였다.

• 한국산학기술학회논문지
• /
• 제17권10호
• /
• pp.109-118
• /
• 2016

본 연구는 요리활동을 통한 언어중재가 언어발달지연을 보이는 유아의 언어능력 향상에 대해 알아보고 현장에서의 효율적인 교수학습 및 환경구성을 마련하는데 연구의 목적을 두고 있다. 연구대상은 서울시에 위치한 E아동발달센터에 재원 중인 만3세 유아 3명(남아 2명, 여아 1명)을 대상으로 각 연령 별 발달을 고려한 주제를 각각 선정하여 요리활동을 통한 언어중재를 실행하였다. 언어중재는 1주에 1회 50분씩 총 25회에 거쳐 실시하였고, 어휘는 요리동사 및 명사가 골고루 분포되도록 하였다. 자료 분석은 그림 어휘력검사(PPVT-R), 취학 전 아동의 수용언어(RLA) 및 표현언어(ELA) 발달 검사(PRES)를 사전 사후 검사를 실시하였고, 결과를 요약하면 다음과 같다. 요리활동을 통한 언어중재를 언어발달지연을 보이는 유아에게 실시한 결과 어휘력, 수용언어, 표현언어, 통합언어 모두 정상언어발달수준에 도달하였음을 알 수 있었다. 이러한 결과는 요리활동을 통한 언어중재가 언어발달지연을 보이는 만3세 유아들에게 긍정적인 영향을 주는 활동임을 시사하고 있다. 따라서 요리활동은 유아의 능동적인 참여와 흥미를 유발 시킬 수 있으며, 다양한 경험을 통해 언어능력을 신장 시킬 수 있다고 본다.

• Restorative Dentistry and Endodontics
• /
• 제16권2호
• /
• pp.85-98
• /
• 1991

The aim of this study was to investigate the effect of low - power laser used in the medical field for various purposes to suppress pain responses evoked by noxious electrical or mechanical stimuli. After both inferior alveolar nerves and the left anterior digastric muscle of cats under general anesthesia were exposed, a recording electrode for the jaw opening reflex was inserted into the anterior digastric muscle. The right inferior alveolar nerve was dissected under a surgical microscope until the response of the functional single nerve could be evoked by the electrical stimulation of the dental pulp or oral mucosa. The electrical stimulus was applied with a rectangular pulse of 10 ms duration for measuring the threshold intensity of a single nerve fiber in the inferior alveolar nerve which responds to stimulation of dental pulp and oral mucosa. Then a pulse of 1 ms duration was applied for determination of conduction velocity. A noxious mechanical stimulus to the oral mucosa was applied by clamping the receptive field with an arterial clamp. The Ga-As diodide laser(wave length, 904 nm ; frequency, 1,000 Hz) was irradiated to the prepared tooth cavity, inferior alveolar nerve and oral mucosa as a pulse wave of 2 mW for 6 minutes. This was followed by a continuous wave of 15 mW for 3 minutes. The action potential of the nerve and EMG of the digastric muscle evoked by the noxious electrical stimulus and nerve response to noxious mechanical stimulus were compared at intervals of before, immediately after, and at 5, 10, 20, 40, 60 minutes after laser irradiation. The results were as follows: The conduction velocity of the intrapulpal $A{\delta}$- nerve fiber recorded from the inferior alveolar nerve before irradiation had a mean value of $6.68{\pm}2.07m/sec$. The laser irradiation did not affect the conduction velocity of the AS - nerve fiber and did not change the threshold intensity or amplitude of the action potential either. The EMG of the digastric muscle evoked by noxious electrical stimulation to the tooth was not changed by the laser irradiation, whether in latency, threshold intensity or amplitude. The laser irradiated to the receptive field of the oral mucosa which was subjected to noxious stimuli did not affect the amplitude of the action potential or the frequency either.

• 한국컴퓨터정보학회논문지
• /
• 제27권2호
• /
• pp.33-42
• /
• 2022

본 논문에서는 운전자한테 실시간으로 블랙 아이스 경고를 보내기 위해서 도로 영상에서 블랙 아이스 영역 분할을 위한 다중 척도 팽창 컨볼루션 특징 융합에 기반한 딥러닝 모델을 제안한다. 제안한 다중척도 팽창 컨볼루션 특징 융합 네트워크는 인코더 블록에 서로 다른 팽창 비율 컨볼루션을 병렬로 추가하고, 서로 다른 해상도 특징 맵에서 서로 다른 팽창 비율을 설정하고, 다중 단계 특징 정보가 함께 융합된다. 다중 척도 팽창 컨볼루션 특징 융합은 수용 영역을 확장함과 동시에 공간의 세부 정보를 잘 보존하고 팽창 컨볼루션의 효과성을 높임으로써 기존 모델보다 성능을 향상시킨다. 실험 결과를 통해 본 논문 제안한 네트워크 모델은 병렬 평창 컨볼루션 수가 증가함에 따라 성능이 향상되는 것을 알 수 있었다. 제안한 방법의 mIoU 값은 96.46%로 U-Net, FCN, PSPNet, ENet, LinkNet 등 기존 네트워크보다 높았다. 그리고 파라미터는 1,858K개로, 기존 LinkNet모델보다 6배로 축소하였다. Jetson Nano에서 실험 결과 보면, 제안한 방법의 FPS는 3.63로 실시간으로 블랙 아이스 영역을 실시간으로 분할 할 수 있었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.273-276
• /
• 2002

Pulse-Coupled Neural Network (PCNN), which can explain the synchronous burst of neurons in a cat visual cortex, is a fundamental model for the biomimetic vision. The PCNN is a kind of pulse coded neural network models. In order to get deep understanding of the visual information Processing, it is important to simulate the visual system through such biologically plausible neural network model. In this paper, we construct the motion detection model based on the PCNN with the receptive field models of neurons in the lateral geniculate nucleus and the primary visual cortex. Then it is shown that this motion detection model can detect the movements and the direction of motion effectively.

• The Korean Journal of Physiology
• /
• 제28권2호
• /
• pp.123-132
• /
• 1994

The present study was undertaken to elucidate the desensitization of cutaneous receptors and the conduction block of the afferent nerves induced by direct application of allyl isotheocyanate (mustard oil) to the receptive field (RF) or onto the afferent nerve, respectively. Dorsal horn cell responses to mechanical stimulations of RF were completely suppressed when mustard oil was applied to either the afferent nerve or the whole area of RF. C-fiber responses of dorsal horn cells were more susceptive to mustard oil than A-fiber activities. This was confirmed by the experiment in which the compound action potentials recorded from rat tibial nerve before and after topical application of mustard oil were compared. The higher the concentration of mustard oil and the longer the application time, the more powerful desensitization or conduction block was induced. From the results of the present study, it is suggested that the desensitization of the afferent fiber and sensory receptors induced by mustard oil results mainly from the conduction block of C-fiber in the primary afferent nerve.