• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• 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.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.4
• /
• pp.452-460
• /
• 1994

Maps are one of the most complicated types of drawings. Drawing recognition technology is not yet sophisticated enough for automated map reading To automatically extract a road map directly from more complicated topographical maps, a very complicated algorithm is needed, since the image generally involves such complicated patterns as symbols, characters, residential sections, rivers, railroads, etc. This paper describes a new feature extraction method based on the human optical neural field. We apply this method to extract complete set of road segments from topographical maps. The proposed method successfully extract road segments from various areas.

• Journal of Ecology and Environment
• /
• v.33 no.4
• /
• 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.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.12
• /
• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.12-18
• /
• 2011

In this paper, we proposed Interval Type-2 polynomial Radial Basis Function Neural Networks. In the receptive filed of hidden layer, Interval Type-2 fuzzy set is used. The characteristic of Interval Type-2 fuzzy set has Footprint Of Uncertainly(FOU), which denotes a certain level of robustness in the presence of un-known information when compared with the type-1 fuzzy set. In order to improve the performance of proposed model, we used the linear polynomial function as connection weight of network. The parameters such as center values of receptive field, constant deviation, and connection weight between hidden layer and output layer are optimized by Conjugate Gradient Method(CGM) and Space Search Evolutionary Algorithm(SSEA). The proposed model is applied to gas furnace dataset and its result are compared with those reported in the previous studies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.109-118
• /
• 2016

Language intervention through cooking activity programs is designed to provide an efficient teaching method and improved educational environment in the field of teaching. This program addresses the effects of this program on the language development of three three-year-old infants (M;2, F;1) in the Center in Seoul. A cooking topic suitable for the age of this group was selected. The language Intervention was conducted for 50 minutes per week for a total of 25 times, and made use of vocabulary, verbs and nouns related to cooking which were evenly distributed. In this study, the Peabody Picture Vocabulary Test-Revised (PPVT-R), receptive language age (RLA) and expressive language age (ELA), and Preschool Receptive-Expressive Language Scale (PRES) were used to analyze the collected data. After the study, the cooking activity was accomplished with normal development outcomes appearing in the ability of vocabulary, receptive language, expressive language, and integrated language. There is now a solid evidence base supporting the efficacy of cooking activity in producing positive outcomes in the language development of language delayed infants. Consequently, cooking can induce their active participation and interest and extend their language abilities through various experiences.

• Restorative Dentistry and Endodontics
• /
• v.16 no.2
• /
• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.33-42
• /
• 2022

In this paper, we proposed a deep learning model based on multi-scale dilated convolution feature fusion for the segmentation of black ice region in road image to send black ice warning to drivers in real time. In the proposed multi-scale dilated convolution feature fusion network, different dilated ratio convolutions are connected in parallel in the encoder blocks, and different dilated ratios are used in different resolution feature maps, and multi-layer feature information are fused together. The multi-scale dilated convolution feature fusion improves the performance by diversifying and expending the receptive field of the network and by preserving detailed space information and enhancing the effectiveness of diated convolutions. The performance of the proposed network model was gradually improved with the increase of the number of dilated convolution branch. The mIoU value of the proposed method is 96.46%, which was higher than the existing networks such as U-Net, FCN, PSPNet, ENet, LinkNet. The parameter was 1,858K, which was 6 times smaller than the existing LinkNet model. From the experimental results of Jetson Nano, the FPS of the proposed method was 3.63, which can realize segmentation of black ice field in real time.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• 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
• /
• v.28 no.2
• /
• 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.