• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.4
• /
• pp.610-625
• /
• 2020

This study suggests an alternative breast-prosthesis-making process for female breast cancer patients. From June 2018 to July 2018, we conducted a study using nine females between the ages 40-50 who never had breast cancer. We recorded the reported subjective sensations and objective physiological responses to different types of artificial breast materials: Trulife silicon breast prostheses (TS) and hand-made silk breast prostheses (HS). Considering the materials used in TS and HS individually, we studied the subjective sensation with regards to how each material functioned in a photo (VP), movement (VM) and the visual tactility (VT) sense. The results showed that comparing VP and VT led to more significant differences than those comparing VM and VT. In addition, there was a significant difference in terms of tactile sensation when comparing TS and HS with respect to subjective responses to texture. Subjects reported that HS felt more comfortable and gave a better cooling sensation. However, the measured objective physiological responses indicated that skin temperature was higher with HS than TS when touched. This research contributes to scholarship around alternative and new materials to build breast prostheses for women with breast cancer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2470-2491
• /
• 2018

Web-scale open information extraction (Open IE) plays an important role in NLP tasks like acquiring common-sense knowledge, learning selectional preferences and automatic text understanding. A large number of Open IE approaches have been proposed in the last decade, and the majority of these approaches are based on supervised learning or dependency parsing. In this paper, we present a novel method for web scale open information extraction, which employs cosine distance based on Google word vector as the confidence score of the extraction. The proposed method is a purely unsupervised learning algorithm without requiring any hand-labeled training data or dependency parse features. We also present the mathematically rigorous proof for the new method with Bayes Inference and Artificial Neural Network theory. It turns out that the proposed algorithm is equivalent to Maximum Likelihood Estimation of the joint probability distribution over the elements of the candidate extraction. The proof itself also theoretically suggests a typical usage of word vector for other NLP tasks. Experiments show that the distance-based method leads to further improvements over the newly presented Open IE systems on three benchmark datasets, in terms of effectiveness and efficiency.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.965-976
• /
• 2020

We present in this work a segmentation method of E. coli bacterial images generated via phase contrast microscopy using a deep learning based hybrid feature generation. Unlike conventional machine learning methods that use the hand-crafted features, we adopt the denoising autoencoder in order to generate a precise and accurate representation of the pixels. We first construct a hybrid vector that combines original image, difference of Gaussians and image gradients. The created hybrid features are then given to a deep autoencoder that learns the pixels' internal dependencies and the cells' shape and boundary information. The latent representations learned by the autoencoder are used as the inputs of a softmax classification layer and the direct outputs from the classifier represent the coarse segmentation mask. Finally, the classifier's outputs are used as prior information for a graph partitioning based fine segmentation. We demonstrate that the proposed hybrid vector representation manages to preserve the global shape and boundary information of the cells, allowing to retrieve the majority of the cellular patterns without the need of any post-processing.

• New & Renewable Energy
• /
• v.16 no.1
• /
• pp.15-24
• /
• 2020

For mechanical load testing of wind turbines, capture matrix is constructed for various range of wind speeds according to the international standard IEC 61400-13. The conventional method wastes considerable amount of data by its invalid data policy -segment data into 10 minutes then remove invalid ones. Previously, we have suggested an alternative way to save the total amount of data to build a capture matrix, but the efficient selection of data has been still under question. The paper introduces optimization algorithms to construct capture matrix with less data. Heuristic algorithm (simple stacking and lowest frequency first), population method (particle swarm optimization) and Q-Learning accompanied with epsilon-greedy exploration are compared. All algorithms show better performance than the conventional way, where the distribution of enhancement was quite diverse. Among the algorithms, the best performance was achieved by heuristic method (lowest frequency first), and similarly by particle swarm optimization: Approximately 28% of data reduction in average and more than 40% in maximum. On the other hand, unexpectedly, the worst performance was achieved by Q-Learning, which was a promising candidate at the beginning. This study is helpful for not only wind turbine evaluation particularly the viewpoint of cost, but also understanding nature of wind speed data.

• The Korean Journal of Ecology
• /
• v.16 no.3
• /
• pp.305-316
• /
• 1993

Stands profiles, yearly changes in growth of annual rings, age and diameter structure, and spatial distribution pattern of individuals in the Pinus densiflora stands around the Yeocheon industrial complex were investigated. Growth of annual ring in Pinus densiflora, which survived when vegetation of this area was damaged by air pollutants, was suppressed for about 10 years since 1974 when factories in this area began to operate, but since then such suppressed growth tended to be recovered. It was supposed that the suppresed growth was originated from air pollution and that improvement of growth since the suppressed period was due to the release from competition with them by death of neighbouring trees and the resuction of the amount of air pollutants. Physiognomy of Pinus densiflora stands showed mosaic pattern composed of different patches. Spatial distribution pattern of individuals an stand profiles were similar to those of Pinus densiflora stands regenerated after natural and artificial disturbances. In an age distribution diagram, age of Pinus densiflora population ranged from 1 to 33 years, Among these individuals were recrited corresponded to the suppresed period of growth of annual ring in Pinus densiflora survived when the vegetation was damaged by air pollution. On the other hand, from the result of analysis of frequency distribution diagram of diameter, it was postulated that even if whis Pinus densiflora community can be maintained as it is for the time being, it might be changed to Quercus community with the lapse of time.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.1
• /
• pp.35-40
• /
• 2001

The physiological role of brain neuropeptide Y (NPY) in the central regulation of grass intake in sheep was investigated through a continuous intracerebroventricular (ICV) infusion of NPY at a dose of $5{\mu}g/0.2ml/hr$ for 98.5 hours from day 1 to day 5. Sheep (n=5) were fed for 2 hours once a day, and water and 0.5 M NaCl solution were given ad libitum. Feed intake during ICV NPY infusion increased significantly compared to that during ICV artificial cerebrospinal fluid (CSF) infusion. Water and NaCl intake during ICV NPY infusion remained unchanged. Mean arterial blood pressure (MAP) and plasma osmolality during ICV NPY infusion were not significantly different from those during ICV CSF infusion. On the other hand, plasma glucose concentration during ICV NPY infusion increased significantly compared to that during ICV CSF infusion. The results suggest that brain NPY acts as a hunger factor in brain mechanisms controlling feeding to increase grass intake in sheep.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1251-1258
• /
• 2019

Intelligent tutoring system enables users to effectively learn by utilizing various artificial intelligence techniques. For instance, it can recommend a proper curriculum or learning method to individual users based on their learning history. To do this effectively, user's characteristics need to be analyzed and classified based on various aspects such as interest, learning ability, and personality. Even though data labeled by the characteristics are required for more accurate classification, it is not easy to acquire enough amount of labeled data due to the labeling cost. On the other hand, unlabeled data should not need labeling process to make a large number of unlabeled data be collected and utilized. In this paper, we propose a semi-supervised learning method based on feedback variational auto-encoder(FVAE), which uses both labeled data and unlabeled data. FVAE is a variation of variational auto-encoder(VAE), where a multi-layer perceptron is added for giving feedback. Using unlabeled data, we train FVAE and fetch the encoder of FVAE. And then, we extract features from labeled data by using the encoder and train classifiers with the extracted features. In the experiments, we proved that FVAE-based semi-supervised learning was superior to VAE-based method in terms with accuracy and F1 score.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.4
• /
• pp.371-376
• /
• 2007

This paper presents an emotion recognition and its expression system of an intelligent robot like a home robot or a service robot. Emotion recognition method in the robot is used by a facial image. We use a motion and a position of many facial features. apply a tracking algorithm to recognize a moving user in the mobile robot and eliminate a skin color of a hand and a background without a facial region by using the facial region detecting algorithm in objecting user image. After normalizer operations are the image enlarge or reduction by distance of the detecting facial region and the image revolution transformation by an angel of a face, the mobile robot can object the facial image of a fixing size. And materialize a multi feature selection algorithm to enable robot to recognize an emotion of user. In this paper, used a multi layer perceptron of Artificial Neural Network(ANN) as a pattern recognition art, and a Back Propagation(BP) algorithm as a learning algorithm. Emotion of user that robot recognized is expressed as a graphic LCD. At this time, change two coordinates as the number of times of emotion expressed in ANN, and change a parameter of facial elements(eyes, eyebrows, mouth) as the change of two coordinates. By materializing the system, expressed the complex emotion of human as the avatar of LCD.

• Carbon letters
• /
• v.25
• /
• pp.78-83
• /
• 2018

Pyrolyzed fuel oil (PFO) and coal tar was blended in the feedstock to produce pitch via thermal reaction. The blended feedstock and produced pitch were characterized to investigate the effect of the blending ratio. In the feedstock analysis, coal tar exhibited a distinct distribution in its boiling point related to the number of aromatic rings and showed higher Conradson carbon residue and aromaticity values of 26.6% and 0.67%, respectively, compared with PFO. The pitch yield changed with the blending ratio, while the softening point of the produced pitch was determined by the PFO ratio in the blends. On the other hand, the carbon yield increased with increasing coal tar ratio in the blends. This phenomenon indicated that the formation of aliphatic bridges in PFO may occur during the thermal reaction, resulting in an increased softening point. In addition, it was confirmed that the molecular weight distribution of the produced pitch was associated with the predominant feedstock in the blend.

• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.4
• /
• pp.1-7
• /
• 2017

Clipart is artificial visual contents that are created using various tools such as Illustrator to highlight some information. Here, the style of the clipart plays a critical role in determining how it looks. However, previous studies on clipart are focused only on the object recognition [16], segmentation, and retrieval of clipart images using hand-craft image features. Recently, some clipart classification researches based on the style similarity using CNN have been proposed, however, they have used different CNN-models and experimented with different benchmark dataset so that it is very hard to compare their performances. This paper presents an experimental analysis of the clipart classification based on the style similarity with two well-known CNN-models (Inception Resnet V2 [13] and VGG-16 [14] and transfers learning with the same benchmark dataset (Microsoft Style Dataset 3.6K). From this experiment, we find out that the accuracy of Inception Resnet V2 is better than VGG for clipart style classification because of its deep nature and convolution map with various sizes in parallel. We also find out that the end-to-end training can improve the accuracy more than 20% in both CNN models.