• Korean Journal of Cognitive Science
• /
• v.23 no.1
• /
• pp.109-132
• /
• 2012

According to recent embodied cognition approach, understanding of actions is not based on abstract symbolic process but based on mental simulation of sensory-motor information related to those actions. As supporting evidence, motor resonance effect is a facilitation/interference effect of motor response in terms of similarity between observed action and concurrent own action. In the current research, we investigated this effect in the situation to perceive a complex social action perception and how it would be modulated by perspectives of construals of the social action scene. For this purpose, we created three kinds of fighting action scenes of two people in terms of body actions of the subject(ie., hitting, stepping, biting), and described them in two perspectives; active and passive. During the experiment, subjects had to verify the congruency of the picture and the description first, and if they are congruent, they had to do two different actions in terms of color of following cues. In the first experiment, subjects' response time for stepping on a pedal and pressing a button were analyzed for measuring motor resonance effect for the foot movement. In the second experiment, voice response time with a microphone and button pressing time were analyzed for the mouth movement motor resonance effect. Results showed the facilitation of the foot movement(in Exp1), and the mouth movement(in Exp2) only when the action scene was described in active perspective. Our results indicate that the motor resonance effect can be occurred during perception of social actions in the real life situation, but it can be also modulated by the perspective of the mental construal of the action event.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.7
• /
• pp.586-603
• /
• 2004

One of the subtle problems that make noise control difficult for engineers is “the invisibility of noise or sound.” The visual image of noise often helps to determine an appropriate means for noise control. There have been many attempts to fulfill this rather challenging objective. Theoretical or numerical means to visualize the sound field have been attempted and as a result, a great deal of progress has been accomplished, for example in the field of visualization of turbulent noise. However, most of the numerical methods are not quite ready to be applied practically to noise control issues. In the meantime, fast progress has made it possible instrumentally by using multiple microphones and fast signal processing systems, although these systems are not perfect but are useful. The state of the art system is recently available but still has many problematic issues : for example, how we can implement the visualized noise field. The constructed noise or sound picture always consists of bias and random errors, and consequently it is often difficult to determine the origin of the noise and the spatial shape of noise, as highlighted in the title. The first part of this paper introduces a brief history, which is associated with “sound visualization,” from Leonardo da Vinci's famous drawing on vortex street (Fig. 1) to modern acoustic holography and what has been accomplished by a line or surface array. The second part introduces the difficulties and the recent studies. These include de-Dopplerization and do-reverberation methods. The former is essential for visualizing a moving noise source, such as cars or trains. The latter relates to what produces noise in a room or closed space. Another mar issue associated this sound/noise visualization is whether or not Ivecan distinguish mutual dependence of noise in space : for example, we are asked to answer the question, “Can we see two birds singing or one bird with two beaks?"

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1373-1387
• /
• 2021

Forest fire poses a significant threat to the environment and society, affecting carbon cycle and surface energy balance, and resulting in socioeconomic losses. Widely used multi-spectral satellite image-based approaches for burned area detection have a problem in that they do not work under cloudy conditions. Therefore, in this study, Sentinel-1 Synthetic Aperture Radar (SAR) data from Europe Space Agency, which can be collected in all weather conditions, were used to identify forest fire damaged area based on a series of processes including Principal Component Analysis (PCA) and K-means clustering. Four forest fire cases, which occurred in Gangneung·Donghae and Goseong·Sokcho in Gangwon-do of South Korea and two areas in North Korea on April 4, 2019, were examined. The estimated burned areas were evaluated using fire reference data provided by the National Institute of Forest Science (NIFOS) for two forest fire cases in South Korea, and differenced normalized burn ratio (dNBR) for all four cases. The average accuracy using the NIFOS reference data was 86% for the Gangneung·Donghae and Goseong·Sokcho fires. Evaluation using dNBR showed an average accuracy of 84% for all four forest fire cases. It was also confirmed that the stronger the burned intensity, the higher detection the accuracy, and vice versa. Given the advantage of SAR remote sensing, the proposed statistical processing and K-means clustering-based approach can be used to quickly identify forest fire damaged area across the Korean Peninsula, where a cloud cover rate is high and small-scale forest fires frequently occur.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.444-453
• /
• 2003

Recently, a great interest of bio-technology(BT) is concentrated and the image analysis technique for electrophoresis gels is highly requested to analyze genetic information or to look for some new bio-activation materials. For this purpose, the location and quantity of each band in a lane should be measured. In most of existing techniques, the approach of peak searching in a profile of a lane is used. But this peak is improper as the representative of a band, because its location does not correspond to that of the brightest pixel or the center of gravity. Also, it is improper to measure band quantity in most of these approaches because various enhancement processes are commonly applied to original images to extract peaks easily. In this paper, we adopt an approach to measure accumulated brightness as a band quantity in each band region, which Is extracted by not using any process of changing relative brightness, and the gravity center of the region is calculated as a band location. Actually, we first extract lanes with an entropy-based threshold calculated on a gel-image histogram. And then, three other methods are proposed and applied to extract bands. In the MER method, peaks and valleys are searched on a vertical search line by which each lane is bisected. And the minimum enclosing rectangle of each band is set between successive two valleys. On the other hand, in the RG-1 method, each band is extracted by using region growing with a peak as a seed, separating overlapped neighbor bands. In the RG-2 method, peaks and valleys are searched on two vertical lines by which each lane is trisected, and the left and right peaks nay be paired up if they seem to belong to the same band, and then each band region is grown up with a peak or both peaks if exist. To compare above three methods, we have measured the location and amount of bands. As a result, the average errors in band location of MER, RG-1, and RG-2 were 6%, 3%, and 1%, respectively, when the lane length is normalized to a unit value. And the average errors in band amount were 8%, 5%, and 2%, respectively, when the sum of band amount is normalized to a unit value. In conclusion, RG-2 was shown to be more reliable in the accuracy of measuring the location and amount of bands.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.54 no.2
• /
• pp.203-209
• /
• 2009

Yield monitoring is one of a precision agriculture technology that is used most widely. It is spatial variability analysis of yield information that should be attained with yield monitoring system development. This experiment was conducted to evaluate spatial variability of yield and grain moisture content in rice paddy field, and their relationships to rice productivity. It is necessary to minimize sampling interval for accurate yield map making or to control cutting width of rice combine. Considering small rice plots such as $0.2{\sim}0.4$ ha, optimum size of sampling plot was below 15 m more than 5 m in with and length. In variable rate treatment field, average yield was similar, but yield variation was reduced than conventional field. Gap of yield by another plot in same field was bigger than half of average yield than yield variation was significantly big. Therefore yield measuring flow sensor must be able to measure at least 300 kg/10a more than 1000 kg/10a. Variation of moisture content in same field was not big and spatial dependance did not appear greatly. But, variation between different field is appeared difference according to weather circumstance before harvesting. Change of spatial dependence of yield was not big, because of field variation of moisture content is not big.

• International Commerce and Information Review
• /
• v.13 no.3
• /
• pp.169-201
• /
• 2011

There was a new wave in grocery business with development of information and technology, thus a movement from traditional stores to online stores, In order to expand the scale of traditional supermarket and to satisfy the customers' needs, they provide offline and online services simultaneously. This paper is based on the previous studies which had been researched in developed countries from late 1990s to early 2000s and the purpose of this study is to introduce the idea and operation system of e-Grocery business. Moreover, we suggest the alternatives on delivery service methods in order to satisfy the customers' needs through analyzing the current condition of e-Grocers in Korea. According to the result of this study, Korean e-Grocers offer only attended home delivery services. In our opinion, Korean supermarkets have to take hybrid model which Tesco.com is using. There are some alternatives to increase the profits of Korean e-Grocers and to provide better services to their customers as follows: As an alternatives for delivery services, picking service is the easiest and cheapest way to apply for supermarkets. This is very useful for working women and also it is possible to order by smartphone recently. They can order the goods to the closest local supermarkets from working place, and then they pick them up on the way home from working off. In order to improve the quality of delivery services, to use the reception box will be the way to provide better services to the customers. The reception box is a way to protect the quality of goods such as fresh-cut product, which require the freshness through the temperature adjustment, and also to keep the safety of ordered goods through locking system Through this system, supermarkets are able to use attended or unattended services under the customers' satisfaction. However, using the reception box is expensive, so shared reception box will be an alternative. As an alternative for development of e-Grocery business, the advertisement for e-Grocery business has to be supported in order to attract potential customers in e-Grocery business. Furthermore, the main concerns of e-Grocery business such as the sanitation and safety of goods, and convenience must be guaranteed in order to keep the loyal customers and to attract new customers.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.191-203
• /
• 2022

In this paper, we developed a system that intelligently identifies skin image data from big data collected from social media Instagram and extracts standardized skin sample data for skin condition diagnosis and management. The system proposed in this paper consists of big data collection and analysis stage, skin image analysis stage, training data preparation stage, artificial neural network training stage, and skin image identification stage. In the big data collection and analysis stage, big data is collected from Instagram and image information for skin condition diagnosis and management is stored as an analysis result. In the skin image analysis stage, the evaluation and analysis results of the skin image are obtained using a traditional image processing technique. In the training data preparation stage, the training data were prepared by extracting the skin sample data from the skin image analysis result. And in the artificial neural network training stage, an artificial neural network AnnSampleSkin that intelligently predicts the skin image type using this training data was built up, and the model was completed through training. In the skin image identification step, skin samples are extracted from images collected from social media, and the image type prediction results of the trained artificial neural network AnnSampleSkin are integrated to intelligently identify the final skin image type. The skin image identification method proposed in this paper shows explain high skin image identification accuracy of about 92% or more, and can provide standardized skin sample image big data. The extracted skin sample set is expected to be used as standardized skin image data that is very efficient and useful for diagnosing and managing skin conditions.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• Horticultural Science & Technology
• /
• v.34 no.5
• /
• pp.665-676
• /
• 2016

As high temperature during citrus growing season has caused a serious problems including inferior coloration in production of mandarins in Korea, we were to investigate the expression pattern of several genes related with coloration during the ripening in high temperature condition of citrus fruits. The expression of genes related with sugar metabolism, cell wall degradation, and flavonoid synthesis in high temperature conditions was investigated in fruits of 'Haryejosaeng' (Citrus unshiu) and 'Shiranuhi' mandarin (C. reticulata). While the expression of beta-amylase (BMY), phenylalanine ammonia-lyase (PAL), chalcone synthase (CHS), and flavanone 3-hydroxylase (F3H) was differently induced, expression of polygalacturonase (PG) decreased dependently on temperature conditions. In 'Haryejosaeng' mandarin, while the expression of genes related to the skin coloration, such as CHS and F3H genes increased at $25^{\circ}C$, the expression of PAL and stilbene synthase (STS) genes were induced at $30-35^{\circ}C$ in all ripening stages. In 'Shiranuhi' mandarin, the expression of the BMY gene decreased at early time point in all temperature condition and then increased at $30-35^{\circ}C$ than at $25^{\circ}C$ in the ripening stage 2 to 3 of fruits. F3H and STS genes also showed the tendency to decrease at $30-35^{\circ}C$. Although the expression levels of genes in ripening stage 1 and stage 2 of fruits showed similar patterns in both 'Haryejosaeng' and 'Shiranuhi', the expression levels of genes were down-regulated in late ripening stage of 'Shiranuhi' fruits compared to 'Haryejosaeng'. In general, the mRNA levels of seven tested genes were higher in 'Haryejosaeng' than in 'Shiranuhi' mandarin, and expression of genes by high temperature was regulated sensitively in 'Haryejosaeng' compared to 'Shiranuhi' mandarin. Further investigations of expression of various genes based on transcriptome analysis in early ripening stage can provide valuable information about the responses to climatic changes in ripening citrus fruits.