• The Journal of Korea Robotics Society
• /
• v.18 no.4
• /
• pp.463-471
• /
• 2023

This paper proposes a method to estimate the level of interest shown by visitors towards a specific target, a guide robot, in spaces where a large number of visitors, such as exhibition halls and museums, can show interest in a specific subject. To accomplish this, we apply deep learning-based behavior recognition and object tracking techniques for multiple visitors, and based on this, we derive the behavior analysis and interest level of visitors. To implement this research, a personalized dataset tailored to the characteristics of exhibition hall and museum environments was created, and a deep learning model was constructed based on this. Four scenarios that visitors can exhibit were classified, and through this, prediction and experimental values were obtained, thus completing the validation for the interest estimation method proposed in this paper.

• BMB Reports
• /
• v.53 no.4
• /
• pp.173-180
• /
• 2020

Galectin-3 is a carbohydrate-binding protein and regulates diverse functions, including cell proliferation and differentiation, mRNA splicing, apoptosis induction, immune surveillance and inflammation, cell adhesion, angiogenesis, and cancer-cell metastasis. Galectin-3 is also recommended as a diagnostic or prognostic biomarker of various diseases, including heart disease, kidney disease, and cancer. Galectin-3 exists as a cytosol, is secreted in extracellular spaces on cells, and is also detected in nuclei. It has been found that galectin-3 has different functions in cellular localization: (i) Extracellular galectin-3 mediates cell attachment and detachment. (ii) cytosolic galectin-3 regulates cell survival by blocking the intrinsic apoptotic pathway, and (iii) nuclear galectin-3 supports the ability of the transcriptional factor for target gene expression. In this review, we focused on the role of galectin-3 on translocation from cytosol to nucleus, because it happens in a way independent of carbohydrate recognition and accelerates cancer progression. We also suggested here that intracellular galecin-3 could be a potent therapeutic target in cancer therapy.

• Plant Journal
• /
• v.16 no.4
• /
• pp.33-39
• /
• 2020

For several decades, productivity in construction industry has been regressed and it is inevitable to improve productivity for major EPC players. One of challenges to achieve this goal is automatically extracting information from imaged drawings. Although computer vision technique has been advanced rapidly, it is still a problem to detect pipe lines in a drawing. Earlier works for line detection have problems that detected line elements be broken into small pieces and accuracy of detection is not enough for engineers. Thus, we adopted Contour and Hough Transform algorithm and reinforced these to improve detection results. First, Contour algorithm is used with Ramer Douglas Peucker algorithm(RDP). Weakness of contour algorithm is that some blank spaces are occasionally found in the middle of lines and RDP covers them around 17%. Second, HEC Hough Transform algorithm, we propose on this paper, is improved version of Hough Transform. It adopted iteration of Hough Transform and merged detected lines by conventional Hough Transform based on Euclidean Distance. As a result, performance of Our proposed method improved by 30% than previous.

• Korean Journal of Artificial Intelligence
• /
• v.9 no.2
• /
• pp.29-34
• /
• 2021

In this paper, for efficient parking control, in an Arduino environment, an intelligent parking control prototype was implemented to provide parking control and parking guidance information using HC-SR2O4 and RC522. The main elements of intelligent parking control are vehicle recognition sensors, parking control facilities, and integrated operating software. Whether the vehicle is parked on the parking surface may be confirmed through sensor or intelligent camera image analysis. Parking control equipment products include parking guidance and parking available display devices, vehicle number recognition cameras, and intelligent parking assistance systems. This paper applies and implements ultrasonic sensors and RFID concepts based on Arduino, recognizes registered vehicles, and displays empty spaces. When a vehicle enters a parking space to handle this function, the automatic parking management system distinguishes the registered vehicle from the external vehicle through the RC522 sensor. In addition, after checking whether the parking slot is empty, the HC-SR204 sensor is displayed through the LED so that the driver can visually check it. RFID is designed to check the parking status of the server in real time and provide the driver with optimal route service to the parking slot.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.190-195
• /
• 2007

As Ubiquitous era comes, it became necessary to construct environment which can provide more useful information to human in the spaces where people live like homes or offices. On this account, network of the peripheral devices of Ubiquitous should constitute efficiently. For it, this paper researched human pattern by classified motion recognition using sensors module data. (This data processing by Neural network and fuzzy algorithm.) This pattern classification can help control home network system communication. I suggest the system which can control home network system more easily through patterned movement, and control Ubiquitous environment by grasp human's movement and condition.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.6
• /
• pp.1834-1843
• /
• 2000

In this paper, we propose a modular neural network based classification method for handwritten numerals utilizing rotated and translated images of an input image. The whole numeral pattern space is divided into smaller spaces which overlap each other and form multiple clusters. On these multiple clusters, multiple multilayer perceptrons (MLP) neural networks, specialized in those clusters, are constructed. Thus, each MLP acts as an expert network on the corresponding cluster. An MLP is also used as a gating network functioning as a mediator among the multiple MLPs. In the learning phase, an input numeral image is dithered by tow geometric operations of translation and rotation so that new numeral images similar to original one are generated. In the recognition phase, we utilize not only input numeral image, but also nearly generated images through the rotation and the translation of the original image. Thus, multiple output values for those generated images were combined to make class decision by various combination methods. The experimental results confirm the validity of the proposed method.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.26 no.1
• /
• pp.20-29
• /
• 2017

Motion synchronization between developed real and virtual robots for object recognition and target tracking is introduced. ASUS's XTION PRO Live is implemented as a sensor and configured to recognize walls and obstacles, and perceive objects. In order to create virtual reality, Unity 3D is adopted to be associated with the real robot, and the virtual object is controlled by using an input device. A Bluetooth serial communication module is used for wireless communication between the PC and the real robot. The motion information of a virtual object controlled by the user is sent to the robot. Then, the robot moves in the same way as the virtual object according to the motion information. Through motion synchronization, two scenarios, which map the real space and current object information with virtual objects and space, were demonstrated, yielding good agreement between the two spaces.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.6
• /
• pp.93-103
• /
• 2018

In the past, the rooftop was a place where a water tank was to be installed, and a space of secretion and concealment such as a warehouse exposed in the air. It was because it was judged to hinder the beauty of a city as a whole without having any functional value per se. However, the roof portion is increasingly being utilized for a space such as a cafe, a pub, and a lounge as the rooftop is highly recognized as a place for leisure activities other than an idle space in modern times. Nonetheless, there are no detailed ordinances and criteria corresponding to such circumstances. For example, in case of the rooftop space, the building code applied to the rooftop space is a legal system when the rooftop was an idle space in the past though people have now accessed more increasingly to the rooftop than in the past. This study investigated the definition on the rooftop space evolved in accordance with the change of the rooftop space and the related legal system in Korea, and conducted a survey for the purpose of performing the field investigation for the analysis of physical status in 117 spaces that form the rooftop space in the rooftop of small-scale commercial facilities with 2 stories through 4 stories in Korea and analyze the recognition of users and analyzing the recognition of users. We analyzed the problems in the rooftop space through analysis of derived data, and suggested improvement plans.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1759-1772
• /
• 2023

Chinese named entity recognition (NER) is a challenging work that seeks to find, recognize and classify various types of information elements in unstructured text. Due to the Chinese text has no natural boundary like the spaces in the English text, Chinese named entity identification is much more difficult. At present, most deep learning based NER models are developed using a bidirectional long short-term memory network (BiLSTM), yet the performance still has some space to improve. To further improve their performance in Chinese NER tasks, we propose a new NER model, IDCNN-BiLSTM-Highway, which is a combination of the BiLSTM, the iterated dilated convolutional neural network (IDCNN) and the highway network. In our model, IDCNN is used to achieve multiscale context aggregation from a long sequence of words. Highway network is used to effectively connect different layers of networks, allowing information to pass through network layers smoothly without attenuation. Finally, the global optimum tag result is obtained by introducing conditional random field (CRF). The experimental results show that compared with other popular deep learning-based NER models, our model shows superior performance on two Chinese NER data sets: Resume and Yidu-S4k, The F1-scores are 94.98 and 77.59, respectively.

• Korean Institute of Interior Design Journal
• /
• no.5
• /
• pp.30-36
• /
• 1995

Light plays an important role in making a continuity of space and in determining the distinctive expression and char-acter of a space. Particularly, the introduction of natural light derives from our esthetic needs, as well as from the fundamental biologi-cal necessities of human beings. And also, adaptation to time and space is the vital factor of human survival and prosperity. Our visual recognition of light is usually formed not only by practical illumination but by analogy, expection and expe-rienced of lighting itself. As the forecase of natural light is (almost) impossible be-cause of variables such as changing weather, reflection rate of light and the patterns of shade, in designing the introduc-tion of daylight, there should be follow-ed careful considera-tion of the adaptation to such variety and the impet-us of light. The research was conducted to mane a contribution to cre-ate more rich and beautiful interior spaces by studying the characteristic of light which is one of the important factors of interior space design, and by inquiring the way to intro-duce light and its effect through the practical examples of Alvar Aalto, Le Corbusier and Louis I. Kahn.