• Cartoon and Animation Studies
• /
• s.43
• /
• pp.321-342
• /
• 2016

The "uncanny valley" curve describes the measured results of the negative emotion response which depends on the similarity between the artificially created character and the real human shape. The "uncanny valley" effect that usually appears in the animation character design induces negative response such as fear and hatred feeling, and anxiety, which is not expected by designers. Especially, in the case of the commercial animation which mostly reply on public response, this kind of negative response is directly related to the failure of artificially created character. Accordingly, designers adjust the desirability of the character design by avoiding or utilizing the "uncanny valley" effect, inducing certain character effect that leads to the success in animation work. This manuscript confirmed the "uncanny valley" coefficient of the positive emotion character design which was based on the actual character design and animation analysis. The "uncanny valley" concept was firstly introduced by a medical scientist Ernst Jentsch in 1906. After then, a psychologist Freud applied this concept to psychological phenomenon in 1919 and a Japanese robert expert Professor Masahiro Mori presented the "uncanny valley" theory on the view of the recognition effect. This paper interpreted the "uncanny valley" effect based on these research theory outcomes in two aspects including sensation production and emotion expression. The mickey-mouse character design analysis confirmed the existence basis of the "uncanny valley" effect, which presented how mickey-mouse human shape image imposed the "uncanny valley" effect on audience. The animation work analysis investigated the reason why the produced 3D animation character should not be 100% similar to the real human by comparing the animation baby character produced by Pix company as the experimental subject to the data of the real baby with the same age. Therefore, the examples of avoiding or utilizing the "uncanny valley" effect in animation character design was discussed in detail and the four stages of sensation production and emotional change of audience due to this kind of effect was figured out. This research result can be used as an important reference in deciding the desirability of the animation character.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_1
• /
• pp.847-860
• /
• 2020

The 2-pass DInSAR (Differential Interferometric SAR) processing steps for DEM generation consist of the co-registration of SAR image pair, interferogram generation, phase unwrapping, calculation of DEM errors, and geocoding, etc. It requires complicated steps, and the accuracy of data processing at each step affects the performance of the finally generated DEM. In this study, we developed an improved method for enhancing the performance of the DEM generation method based on the 2-pass DInSAR technique of TanDEM-X bistatic SAR images was developed. The developed DEM generation method is a method that can significantly reduce both the DEM error in the unwrapped phase image and that may occur during geocoding step. The performance analysis of the developed algorithm was performed by comparing the vertical accuracy (Root Mean Square Error, RMSE) between the existing method and the newly proposed method using the ground control point (GCP) generated from GPS survey. The vertical accuracy of the DInSAR-based DEM generated without correction for the unwrapped phase error and geocoding error is 39.617 m. However, the vertical accuracy of the DEM generated through the proposed method is 2.346 m. It was confirmed that the DEM accuracy was improved through the proposed correction method. Through the proposed 2-pass DInSAR-based DEM generation method, the SRTM DEM error observed by DInSAR was compensated for the SRTM 30 m DEM (vertical accuracy 5.567 m) used as a reference. Through this, it was possible to finally create a DEM with improved spatial resolution of about 5 times and vertical accuracy of about 2.4 times. In addition, the spatial resolution of the DEM generated through the proposed method was matched with the SRTM 30 m DEM and the TanDEM-X 90m DEM, and the vertical accuracy was compared. As a result, it was confirmed that the vertical accuracy was improved by about 1.7 and 1.6 times, respectively, and more accurate DEM generation was possible with the proposed method. If the method derived in this study is used to continuously update the DEM for regions with frequent morphological changes, it will be possible to update the DEM effectively in a short time at low cost.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.

• Korean Journal of Applied Biomechanics
• /
• v.15 no.2
• /
• pp.11-20
• /
• 2005

This study has a purpose on contributing to apprehend safe and right way to stop to the inline skate beginners and to the instructors who teaches line skating on the basis for the result of the kinematical analysis on Heel brake stop movement of the inline skate, focusing on the displacement on COG, angle displacement of ankle joint, angle displacement of knee joint, angle displacement of hip joint, using a 3D image method by DLT. To achieve this goal, we analysed the kinematical factor of the 3 well-trained inline skating instructors and obtained the following results. 1. During the movement of heel-brake stop, when strong power was given to a stable and balanced stop and the lower limbs, if the physical centroid is lowered the stability increases, and if it is placed high from the base surface, as the stability decreases compared to the case of low physical centroid, we should make a stop by placing a physical centroid in the base surface and lowering the hight of physical centroid. 2. To make a stable and balanced stop and to provide a strong power to the lower limbs, it is advisable to make a stop by decreasing an angle displacement of ankle joint during a "down" movement. In case of the left ankle joint, in all events and phases the dorsiflexion angle showed a decrease. Nevertheless, in the case of the right ankle joint, the dorsiflexion angle shows an increase after a slight decrease. The dorsiflexion angle displacement of ankle joint can be diminished because of the brake pad of the rear axis frame of the right side inline skate by raising a toe, but cannot be more decreased if certain degree of an angle is made by a brake pad touching a ground surface. To provide a power to a brake pad, it is recommended to place a power by lowering a posture making the dorsiflexion angle of the left ankle joint relatively smaller than that of the right ankle. 3. To make a stable and balanced stop and to add a power to a brake pad, the power must be given to the lower limbs in lowering the hight of physical centroid. For this, it is recommended to make a down movement by decreasing the flexion angle of a knee joint and it is necessary to make a down movement by a regular decrease of the angle displacement of knee joint rather than a swift down movement in every event and phase. 4. The right angle displacement of hip joint is made by lowering vertically the hight of physical centroid as leaning slightly forward. If too narrow angle displacement of hip joint is made by leaning forward too much, the balance is lost during the stop by placing the center in front. To make a stable and balance stop and to place a strong power to the lower limbs, it is recommendable to make a narrow angle by lower the hip joint angle. However, excessive leaning of the upper body to make the angle too narrow, can cause an instable stop and loss of physical centroid. After this study, it is considered to assist the kinematical understanding during the heel brake stop movement of the inline skate, and, to present basic data in learning a method of stable and balanced stop for the inline skating beginners or for the inline skate instructors in the present situation of the complete absence of the study in inline skating.

• The Korean Journal of Nuclear Medicine
• /
• v.33 no.3
• /
• pp.316-326
• /
• 1999

Purpose: We evaluated the feasibility of extracting pure left ventricular blood pool and myocardial time-activity curves (TACs) and of generating factor images from human dynamic N-13 ammonia PET using factor analysis. The myocardial blood flow (MBF) estimates obtained with factor analysis were compared with those obtained with the user drawn region-of-interest (ROI) method. Materials and Methods: Stress and rest N-13 ammonia cardiac PET imaging was acquired for 23 min in 5 patients with coronary artery disease using GE Advance tomograph. Factor analysis generated physiological TACs and factor images using the normalized TACs from each dixel. Four steps were involved in this algorithm: (a) data preprocessing; (b) principal component analysis; (c) oblique rotation with positivity constraints; (d) factor image computation. Area under curves and MBF estimated using the two compartment N-13 ammonia model were used to validate the accuracy of the factor analysis generated physiological TACs. The MBF estimated by factor analysis was compared to the values estimated by using the ROI method. Results: MBF values obtained by factor analysis were linearly correlated with MBF obtained by the ROI method (slope = 0.84, r = 0.91), Left ventricular blood pool TACs obtained by the two methods agreed well (Area under curve ratio: 1.02 ($0{\sim}1min$), 0.98 ($0{\sim}2min$), 0.86 ($1{\sim}2min$)). Conclusion: The results of this study demonstrates that MBF can be measured accurately and noninvasively with dynamic N-13 ammonia PET imaging and factor analysis. This method is simple and accurate, and can measure MBF without blood sampling, ROI definition or spillover correction.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.387-397
• /
• 2023

Plant height is a growth parameter that provides visible insights into the plant's growth status and has a high correlation with yield, so it is widely used in crop breeding and cultivation research. Investigation of the growth characteristics of crops such as plant height has generally been conducted directly by humans using a ruler, but with the recent development of sensing and image analysis technology, research is being attempted to digitally convert growth measurement technology to efficiently investigate crop growth. In this study, the canopy height of rice grown at various nitrogen fertilization levels was measured using a laser scanner capable of precise measurement over a wide range, and a comparative analysis was performed with the actual plant height. As a result of comparing the point cloud data collected with a laser scanner and the actual plant height, it was confirmed that the estimated plant height measured based on the average height of the top 1% points showed the highest correlation with the actual plant height (R² = 0.93, RMSE = 2.73). Based on this, a linear regression equation was derived and used to convert the canopy height measured with a laser scanner to the actual plant height. The rice growth curve drawn by combining the actual and estimated plant height collected by various nitrogen fertilization conditions and growth period shows that the laser scanner-based canopy height measurement technology can be effectively utilized for assessing the plant height and growth of rice. In the future, 3D images derived from laser scanners are expected to be applicable to crop biomass estimation, plant shape analysis, etc., and can be used as a technology for digital conversion of conventional crop growth assessment methods.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4
• /
• pp.35-41
• /
• 2001

This paper describes Linear Discriminant Analysis and common vector extraction for speech recognition. Voice signal contains psychological and physiological properties of the speaker as well as dialect differences, acoustical environment effects, and phase differences. For these reasons, the same word spelled out by different speakers can be very different heard. This property of speech signal make it very difficult to extract common properties in the same speech class (word or phoneme). Linear algebra method like BT (Karhunen-Loeve Transformation) is generally used for common properties extraction In the speech signals, but common vector extraction which is suggested by M. Bilginer et at. is used in this paper. The method of M. Bilginer et al. extracts the optimized common vector from the speech signals used for training. And it has 100％ recognition accuracy in the trained data which is used for common vector extraction. In spite of these characteristics, the method has some drawback-we cannot use numbers of speech signal for training and the discriminant information among common vectors is not defined. This paper suggests advanced method which can reduce error rate by maximizing the discriminant information among common vectors. And novel method to normalize the size of common vector also added. The result shows improved performance of algorithm and better recognition accuracy of 2％ than conventional method.

• Journal of Global Scholars of Marketing Science
• /
• v.18 no.2
• /
• pp.19-45
• /
• 2008

This study is to empirically examine the primary dimensions of visual merchandising (VMD) of internet shopping mall, namely store design, merchandise, and merchandising cues, to be a attractive virtual store to the shoppers. The authors reviewed the literature related to the major components of VMD from the perspective of the AIDA model, which has been mainly applied to the offline store settings. The major purposes of the study are as follows; first, tries to derive the variables related with the components of visual merchandising through reviewing the existing literatures, establish the hypotheses, and test it empirically. Second, examines the relationships between the components of VMD and the attitude toward the VMD, however, putting more emphasis on finding out the component structure of the VMD. VMD needs to be examined with the perspective that an online shopping mall is a virtual self-service or clerkless store, which could reduce the number of employees, help the shoppers search, evaluate and purchase for themselves, and to be explored in terms of the in-store persuasion processes of customers. This study reviewed the literatures related to store design, merchandise, and merchandising cues which might be relevant to the store, product, and promotion respectively. VMD is a total communication tool, and AIDA model could explain the in-store consumer behavior of online shopping. Store design has to do with triggering a consumer attention to the online mall, merchandise with a product related interest, and merchandising cues with promotions such as recommendation and links that induce the desire to pruchase. These three steps might be seen as the processes for purchase actions. The theoretical rationale for the relationship between VMD and AIDA could be found in Tyagi(2005) that the three steps of consumer-oriented merchandising are a store, a product assortment, and placement, in Omar(1999) that three types of interior display are a architectural design display, commodity display, and point-of-sales(POS) display, and in Davies and Ward(2005) that the retail store interior image is related to an atmosphere, merchandise, and in-store promotion. Lee et al(2000) suggested as the web merchandising components a merchandising cues, a shopping metaphor which is an assistant tool for search, a store design, a layout(web design), and a product assortment. The store design which includes differentiation, simplicity and navigation is supposed to be related to the attention to the virtual store. Second, the merchandise dimensions comprising product assortments, visual information and product reputation have to do with the interest in the product offerings. Finally, the merchandising cues that refer to merchandiser(MD)'s recommendation of products and providing the hyperlinks to relevant goods for the shopper is concerned with attempt to induce the desire to purchase. The questionnaire survey was carried out to collect the data about the consumers who would shop at internet shopping malls frequently. To select the subject malls, the mall ranking data announced by a mall rating agency was used to differentiate the most popular and least popular five mall each. The subjects was instructed to answer the questions after navigating the designated mall for five minutes. The 300 questionnaire was distributed to the consumers, 166 samples were used in the final analysis. The empirical testing focused on identifying and confirming the dimensionality of VMD and its subdimensions using a structural equation modeling method. The confirmatory factor analysis for the endogeneous and exogeneous variables was carried out in four parts. The second-order factor analysis was done for a store design, a merchandise, and a merchandising cues, and first-order confirmatory factor analysis for the attitude toward the VMD. The model test results shows that the chi-square value of structural equation is 144.39(d.f 49), significant at 0.01 level which means the proposed model was rejected. But, judging from the ratio of chi-square value vs. degree of freedom, the ratio was 2.94 which smaller than an acceptable level of 3.0, RMR is 0.087 which is higher than a generally acceptable level of 0.08. GFI and AGFI is turned out to be 0.90 and 0.84 respectively. Both NFI and NNFI is 0.94, and CFI 0.95. The major test results are as follows; first, the second-order factor analysis and structural equational modeling reveals that the differentiation, simplicity and ease of identifying current status of the transaction are confirmed to be subdimensions of store design and to be a significant predictors of the dependent variable. This result implies that when designing an online shopping mall, it is necessary to differentiate visually from other malls to improve the effectiveness of the communications of store design. That is, the differentiated store design raise the contrast stimulus to sensory organs to promote the memory of the store and to have a favorable attitude toward the VMD of a store. The results that navigation which means the easiness of identifying current status of shopping affects the attitude to VMD could be interpreted that the navigating processes via the hyperlinks which is characteristics of an internet shopping is a complex and cognitive process and shoppers are likely to lack the sense of overall structure of the store. Consequently, shoppers are likely to be alost amid shopping not knowing where to go. The orientation tool enhance the accessibility of information to raise the perceptive power about the store environment.(Titus & Everett 1995) Second, the primary dimension of merchandise and its subdimensions was confirmed to be unidimensional respectively, have a construct validity, and nomological validity which the VMD dimensions supposed to have a positive correlation with the dependent variable. The subdimensions of product assortment, brand fame and information provision proved to have a positive effect on the attitude toward the VMD. It could be interpreted that the more plentiful the product and brand assortment of the mall is, the more likely the shoppers to favor it. Brand fame and information provision as well affect the VMD attitude, which means that the more famous the brand, the more likely the shoppers would trust and feel familiar with the mall, and the plentifully and visually presented information could have the shopper have a favorable attitude toward the store VMD. Third, it turned out to be that merchandising cue of product recommendation and hyperlinks affect the VMD attitude. This could be interpreted that recommended products could reduce the uncertainty related with the purchase decision, and the hyperlinks to relevant products would help the shopper save the cognitive effort exerted into the information search and gathering, which could lead to a favorable attitude to the VMD. This study tried to sheds some new light on the VMD of online store by reviewing the variables mentioned to be relevant with offline VMD in the existing literatures, and tried to link the VMD components from the perspective of AIDA model. The effect size of the VMD dimensions on the attitude was in the order of the merchandise, the store design and the merchandising cues.It is said that an internet has an unlimited place for display, however, the virtual store is not unlimited since the consumer has a limited amount of cognitive ability to process the external information and internal memory. Particularly, the shoppers are likely to face some difficulties in decision making on account of too many alternative and information overloads. Therefore, the internet shopping mall manager should take into consideration the cost of information search on the part of the consumer, to establish the optimal product placements and search routes. An efficient store composition would be possible by reducing the psychological burdens and cognitive efforts exerted to information search and alternatives evaluation. The store image is in most part determined by the product category and its brand it deals in. The results of this study support this proposition that the merchandise is most important to the VMD attitude than other components, the manager is required to take a strategic approach to VMD. The internet users are getting more accustomed and more knowledgeable about the internet media and more likely to accept the internet as a shopping channel as the period of time during which they use the internet to shop become longer. The web merchandiser should be aware that the product introduction using a moving pictures and a bulletin board become more important in order to present the interactive product information visually and communicate with customers more actively, therefore leading to making the quantity and quality of product information more rich.