• Journal of Korea Game Society
• /
• v.17 no.4
• /
• pp.101-108
• /
• 2017

This study explores how Artificial Intelligence (AI), which is tremendously developed these days, applies to the game and advances. It analyzes the reality of AI and provides reasonable suggestion in Poker, one of the most popular games. Specifically, this study focuses on Texas Hold'em, the most favored kind in the world among various kinds of Poker games and deals with two AIs, Libratus and DeepStack that have applied to the game. Several news media report the growth of AI, but this study will multi-dimensionally discusses how and why AI works in Poker, the real problems of AI, and suggestions for advancement.

• Smart Media Journal
• /
• v.11 no.7
• /
• pp.94-103
• /
• 2022

Weeds bring disadvantages to crops since they can damage them, and a clean treatment with less pollution and contamination should be developed. Artificial intelligence gives new hope to agriculture to achieve smart farming. This study delivers an automated weeds growth point detection using deep learning. This study proposes a combination of semantic graphics for generating data annotation and U-Net with pre-trained deep learning as a backbone for locating the growth point of the weeds on the given field scene. The dataset was collected from an actual field. We measured the intersection over union, f1-score, precision, and recall to evaluate our method. Moreover, Mobilenet V2 was chosen as the backbone and compared with Resnet 34. The results showed that the proposed method was accurate enough to detect the growth point and handle the brightness variation. The best performance was achieved by Mobilenet V2 as a backbone with IoU 96.81%, precision 97.77%, recall 98.97%, and f1-score 97.30%.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.2
• /
• pp.9-16
• /
• 2024

In this study, we delve into the effects of personalization algorithms on the creation of "filter bubbles," which can isolate individuals intellectually by reinforcing their pre-existing biases, particularly through personalized Google searches. By setting up accounts with distinct ideological learnings-progressive and conservative-and employing deep neural networks to simulate user interactions, we quantitatively confirmed the existence of filter bubbles. Our investigation extends to the deployment of an LSTM model designed to assess political orientation in text, enabling us to bias accounts deliberately and monitor their increasing ideological inclinations. We observed politically biased search results appearing over time in searches through biased accounts. Additionally, the political bias of the accounts continued to increase. These results provide numerical evidence for the existence of filter bubbles and demonstrate that these bubbles exert a greater influence on search results over time. Moreover, we explored potential solutions to mitigate the influence of filter bubbles, proposing methods to promote a more diverse and inclusive information ecosystem. Our findings underscore the significance of filter bubbles in shaping users' access to information and highlight the urgency of addressing this issue to prevent further political polarization and media habit entrenchment. Through this research, we contribute to a broader understanding of the challenges posed by personalized digital environments and offer insights into strategies that can help alleviate the risks of intellectual isolation caused by filter bubbles.

• Membrane Journal
• /
• v.14 no.2
• /
• pp.85-98
• /
• 2004

The situation of technology Predominance and the distribution of core technology were visually mapped thorough the investigation of technical trend during 20 years, which was provided with the analysis of patent information for the artificial skin. Therefore, it was expected that technology mapping by means of multilateral analysis method allowed a good grasp of current technology trend of the artificial skin and the subdivision into nation and a field of research presents the direction of R&D. In the early R&D stage of artificial skin, the preparation technology of filters implantable into the living body including nursing devices, bandages, and dressings or absorbent pads (A6IF-002/10) was on the rise in research field of artificial skin until 1980's. And then the materials technology for coating prostheses (A6l L-027/00)was leading the core technology of artificial skin. Also, Nowadays the fusion technology connected the material technology with the cultivation technology of undifferentiated human or animal cells/tissues including culture media (C l2N-005/00, C 12N-005/06) was highlighted all over the world.

• The Korean Journal of Mycology
• /
• v.36 no.1
• /
• pp.51-57
• /
• 2008

To develop artificial cultivation and improve some problems such as auto-lysis on commercialization of Coprinus comatus that has been known edible and medicinal mushroom, they were conducted for selection of superior strain, suitable culture methods for mycelial growth and fruiting, and morphological characteristics of fruit body. Strain CM 980301 of Coprinus comatus was selected as a superior strain for artificial cultivation. Wheat grain and rice straw full-grown compost media were most effective for preparation of spawn and artificial cultivation of C. comatus, respectively. Spawn running of Coprinus spp. on the rice straw full-grown compost media required to be 15 days from 24 to $28^{\circ}C$. The casing layer incubation before initiation of fruit body formation, required for 13 days at same temperature for spawn running. And then require $10{\sim}11$ days for initiation and $7{\sim}8$ days for development of fruit body from 20 to $24^{\circ}C$. The fruit body of strain CM 980301 was harvested within a week from initiation of primordium formation. The hardness of pileus and stipe that were harvested in optimal stage showed 102 to 169, and 128 to $182\;g/cm^2$, respectively. Yields of srain CM 980301 from the rice straw full-grown compost media was $37.7kg/3.3m^2$. Weight of individual fruit body was 17.9 g in average.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.411-419
• /
• 2019

Nowadays we are not able to consider and imagine anything without taking into account what is called Artificial Intelligence. Even broadcasting media technologies could not be thought of outside this newly emerging technology of A.I.. Since the last part of 20th century, this technology seemingly is accelerating it's development thanks to an unbelievably enormous computational capacity of data information treatments. In conjunction with the firmly established worldwide platform companies like GAFA(Google, Amazon, Facebook, Apple), the key cutting edge technologies dubbed NBIC(Nanotech, Biotech, Information Technology, Cognitive science) converge to change the map of the current civilization by affecting the human relationship with the world and hence modifying what is essential in humans. Under the sign of the converging technologies, the relatively recently coined concepts such as 'trans(post)humanism' are emerging in the academic sphere in the North American and Major European regions. Even though the so-called trans(post)human movements are prevailing in the major technological spots, we have to say that these terms do not yet reach an unanimous acceptation among many experts coming from diverse fields. Indeed trans(post)humanism as a sort of obscure term has been a largely controversial trend. Because there have been many different opinions depending on scientific, philosophical, medical, engineering scholars like Peter Sloterdijk, K. N. Hayles, Neil Badington, Raymond Kurzweil, Hans Moravec, Laurent Alexandre, Gilbert Hottois just to name a few. However, considering the highly dazzling development of artificial intelligence technology basically functioning in conjunction with the cybernetic communication system firstly conceived by Nobert Wiener, MIT mathematician, we can not avoid questioning what A. I. signifies and how it will affect the current media communication environment.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.30 no.1
• /
• pp.25-32
• /
• 2003

S. mutans is the most important causative bacteria of dental caries among the oral bacteria. S. salivarius is a normal inhabitant in the human oral cavity. Nine strains of S. salivarius in this study were isolated from the oral cavities of children and identified, and their effect on S. mutans and S. oralis was studied. 1. The mean weight of produced artificial plaque on the wires in the beaker was 204.9 mg in the culture of S. mutans only, whereas being reduced to 1.9 mg through 20.6mg in the combined culture of S. mutans and each S. salivarius isolate (p<0.05). The viable cell didn't show the difference between them after culturing. 2. When S. mutans was cultured in the media containing culture supernatant of each S. salivarius isolate in M17 broth, the mean weight of produced artificial plaque was 117.1 mg on the wires, whereas being 47.7 mg in the media containing culture supernatant of each S. salivarius isolate in M17 broth containing 5% sucrose. 3. The polymer produced by S. salivarius isolates was on the thin layer chromatography. 4. Inulin and levan didn't inhibit the formation of artificial plaque by S. mutans in the beaker test. These results suggested that fructan-producing S. salivarius isolates inhibited the formation of artificial plaque by S. mutans.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.654-664
• /
• 2022

Immersive content overcomes spatial limitations through convergence with extended reality, artificial intelligence, and photogrammetry technology along with interest due to the COVID-19 pandemic, presenting a new paradigm in the content market such as entertainment, media, performances, and exhibitions. However, it can be seen that in order for realistic content to have sustained public interest, it is necessary to study storytelling method that can increase immersion in content rather than technological freshness. Therefore, in this study, we propose a immersive content storytelling method using artificial intelligence and photogrammetry technology. The proposed storytelling method is to create a content story through interaction between interactive virtual beings and participants. In this way, participation can increase content immersion. This study is expected to help content creators in the accelerating immersive content market with a storytelling methodology through virtual existence that utilizes artificial intelligence technology proposed to content creators to help in efficient content creation. In addition, I think that it will contribute to the establishment of a immersive content production pipeline using artificial intelligence and photogrammetry technology in content production.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.10 no.3
• /
• pp.1-7
• /
• 2007

For waste water treatment, artificial wetland was constructed in 1998. The size of artificial wetland is 20m${\times}$200m, with sand and gravel as media and Phragmites japonica was implanted. The removal rate of BOD, TN, and TP were 86%, 33% and 25% from June 2004 to November 2005 respectively, while those were 88%, 38% and 55% in 1999. Organic materials and nitrogen compounds are still effectively removed, after 6 years of construction, but the removal efficiency of phosphorus compounds is reduced. So for sustaining of artificial wetland as waste water treatment system, the removal efficiency of phosphorus compounds must be elevated.

• Journal of the Korean Society of Radiology
• /
• v.10 no.8
• /
• pp.637-643
• /
• 2016

Due to the popularity of artificial intelligent, medical image processing using artificial neural network is increasingly attracting the attention of academic and industry researches. Deep learning with a convolutional neural network has been proved to very effective representation of images. However, the training process requires high performance H/W platform. Thus, the realtime learning of a large number of high dimensional samples within low-power devices is a challenging problem. In this paper, we attempt to establish this possibility by presenting a realtime neural network method on Raspberry pi using online sequential extreme learning machine. Our experiments on high-dimensional dataset show that the proposed method records an almost real-time execution.