• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.178-179
• /
• 2018

Recently, methods of using machine learning in artificial intelligence such as autonomous navigation and speech recognition have been actively studied. Classical image processing methods such as classical boundary detection and pattern recognition have many limitations in order to recognize a specific object or area in a digital image. However, when a machine learning method such as deep-learning is used, Can be obtained. However, basically, a large amount of learning data must be secured for machine learning such as deep-learning. Therefore, it is difficult to apply the machine learning for area classification when the amount of data is very small, such as aerial photographs for environmental analysis. In this study, we apply a transfer-learning technique that can be used when the dataset size of the input image is small and the shape of the input image is not included in the category of the training dataset.

• Journal of The Korean Association of Information Education
• /
• v.26 no.4
• /
• pp.273-284
• /
• 2022

The goal of this paper is to propose the use of machine learning platforms in education to train learners to recognize data biases. Learners can cultivate the ability to recognize when learners deal with AI data and systems when they want to prevent damage caused by data bias. Specifically, this paper presents a method of data bias education using MachineLearningforKids, focusing on the case of AI baseball referee. Learners take the steps of selecting a specific topic, reviewing prior research, inputting biased/unbiased data on a machine learning platform, composing test data, comparing the results of machine learning, and present implications. Learners can learn that AI data bias should be minimized and the impact of data collection and selection on society. This learning method has the significance of promoting the ease of problem-based self-directed learning, the possibility of combining with coding education, and the combination of humanities and social topics with artificial intelligence literacy.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.836-848
• /
• 2019

This paper aims at providing a critical view over the cybernetics theory especially of first generation on which the artificial intelligence heavily depends nowadays. There has been a commonly accepted thought that the conception of artificial intelligence could not has been possible without being influenced by N. Wiener's cybernetic feedback based information system. Despite the founder of contemporary cybernetics' ethical concerns in order to avoid an increasing entropy phenomena(social violence, economic misery, wars) produced through a negative dynamics of the western modernity regarded as the most advanced form of humanism. In this civilizationally changing atmosphere, the newly born cybernetic technology was thus firmly believed as an antidote to these vices deeply rooted in humanism itself. But cybernetics has been turned out to be a self-organizing, self-controlling mechanical system that entails the possibility of telegraphing human brain (which are transformed into patterns) through the uploading of human brain neurons digitalized by the artificial intelligence embedded into computing technology. On this background emerges posthuman (or posthumanism) movement of which concepts have been theorized mainly by its ardent apostles like N. K. Hayles, Neil Bedington, Laurent Alexandre, Donna J. Haraway. The converging of NBIC Technologies leading to the opening of a much more digitalizing society has served as a catalyst to promote the posthuman representations and different narratives especially in the contemporary visual arts as well as in the study of humanities including philosophy and fictional literature. Once Bruno Latour wrote "Modernity is often defined in terms of humanism, either as a way of saluting the birth of 'man' or as a way of announcing his death. But this habit is itself modern, because it remains asymmetrical. It overlooks the simultaneous birth of 'nonhumaniy' - things, or objects, or beasts, - and the equally strange beginning of a crossed-out God, relegated to the sidelines."4) These highly suggestive ideas enable us to better understand what kind of human beings would emerge following the dazzlingly accelerating advancement of artificial intelligence technology. We wonder whether or not this newly born humankind would become essentially Homo Artificialis as a neuronal man stripping off his biological apparatus. However due to this unprecedented situation humans should deal with enormous challenges involving ethical, metaphysical, existential implications on their life.

• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.4
• /
• pp.19-28
• /
• 2016

최근 RFID와 같은 무선 센싱 네트워크 기술과 객체 추적을 위한 센싱 디바이스 및 다양한 컴퓨팅 자원들이 빠르게 발전함에 따라, 기존 웹의 형태는 소셜 웹에서 유비쿼터스 컴퓨팅 웹으로 자연스럽게 진화되고 있다. 유비쿼터스 컴퓨팅 웹에서 사물인터넷(IoT)은 기존의 컴퓨터를 대체할 수 있는데, 이것은 곧 한 사람과 주변 사물들 간에 연결되는 네트워크가 확장되는 것과 동시에 네트워크 안에서 생성되는 데이터의 수가 기하급수적으로 증가되는 것을 의미한다. 따라서 보다 지능적인 IoT 서비스를 위해서는, 수많은 미가공 데이터들 사이에서 사람의 의도와 상황을 실시간으로 정확히 파악할 수 있어야 한다. 이때 사물과의 상호작용을 위한 동작 인식 기술(Gesture recognition)은 집적적인 접촉을 필요로 하지 않기 때문에, 미래의 사람-사물 간 상호작용에 응용될 수 있는 잠재력을 갖고 있다. 한편, 기계학습 분야의 최신 알고리즘들은 다양한 문제에서 사람의 인지능력을 종종 뛰어넘는 성능을 보이고 있는데, 그 중에서도 의사결정나무(Decision Tree)를 기반으로 한 Decision Forest는 분류(Classification)와 회귀(Regression)를 포함한 전 영역에 걸쳐 우월한 성능을 보이고 있다. 따라서 본 논문에서는 지능형 IoT 서비스를 위한 다양한 동작 인식 기술들을 알아보고, 동작 인식을 위한 Decision Forest의 기본 개념과 구현을 위한 학습, 테스팅에 대해 구체적으로 소개한다. 특히 대표적으로 사용되는 3가지 학습방법인 배깅(Bagging), 부스팅(Boosting) 그리고 Random Forest에 대해 소개하고, 이것들이 동작 인식을 위해 어떠한 특징을 갖는지 기존의 연구결과를 토대로 알아보았다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.847-850
• /
• 2008

On today, human is going to develop machine by using mutual communication to machine. Including vision - based HCI(Human Computer Interaction), the technique which to recognize finger and to track finger is important in HCI systems, in HCI systems. In order to divide finger, this paper uses more effectively dividing the technique using subtraction which is separation of background and foreground, as well as to divide finger from limited background and cluttered background. In order to divide finger, the finger is recognized to make "Template-Matching" by identified fingertip images. And, identified gestures be compared the tracked gesture after tracking recognized finger. In this paper, after obtaining interest area, not only using subtraction image and template-matching but to perform template-matching in the area. So, emphasis is placed on decreasing perform speed and reaction speed, and we propose technique which is more effectively recognizing gestures.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.1173-1178
• /
• 2007

The robot for narrow space is used in searching, investigating or cleaning. Up to now variety of researches on in-pipe robots have been introduced. However it is still hard to overcome vertical or curved passage. In most cases of narrow space robots are able to travel just aimed diameter which was selected when those are developed. Also, a large percentage of robots are not able to detect the configuration of pipe or circumstance. In this paper we present a robot called PAROYSⅡ for narrow space with vertical and curved passage. This proposed robot is not affected at all to variance of pipes, vertical or horizontal passages, curved pipes, projecting parts and parallel planes. In addition to that, it will perceive the internal configuration of pipe and terrain, which will be not only available to control navigating scheme by itself, but also mappable about the passage which the robot traveled. Core points in the design and structure are introduced and preliminary verification is given.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.15 no.6
• /
• pp.95-100
• /
• 2016

We suggest and simulate an optical filter that a red wavelength range cannot transmit to protect the psychological stress that originates from the cognition of red color in emergency medical technicians. When a nanohole hexagonal array is fabricated on gold film using Anodic Aluminum Oxide (AAO), the blocked wavelength can be tuned by the hole diameter and film thickness. The characteristic of the transmittance for normal incident white light is simulated with Finite Element Method (FEM) in the MATLAB platform. Although the transmittance of the overall wavelength is reduced by 50% by the gold film, the transmittance of the red wavelength range is decreased by over 87%.

• Journal of Drive and Control
• /
• v.17 no.3
• /
• pp.9-14
• /
• 2020

A special purpose machine with two manipulators and quadruped crawler system is being developed to work at disaster sites where it is intended to quickly respond in the initial stages after the event. In this study, a terrain recognition module is developed so that the above special purpose machine can quickly obtain ground information to help choose its path while recognizing objects in its way, this is intended to enhance the remote driver's limited situational awareness. Terrain recognition modules were developed for two tasks (real-time path guidance, precision terrain measurements). The real-time path guidance analyzes terrain and obstacles while moving, while the precision terrain measurement feature provides more accurate terrain information by precisely measuring the ground in front of the vehicle while stationary. In this study, an air-cooled sensor protection module was developed so that the terrain recognition module can continue its vital tasks in the event of exposure to foreign substances, including scattered dust, mist and rainfall, as well as high temperatures.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.2
• /
• pp.29-34
• /
• 2019

This paper presents a new method for construction of a static obstacle map. A static obstacle is important since it is utilized to path planning and decision. Several established approaches generate static obstacle map by grid method and counting algorithm. However, these approaches are occasionally ineffective since the density of LiDAR layer is low. Our approach solved this problem by applying probability theory. First, we converted all LiDAR point to Gaussian distribution to considers an uncertainty of LiDAR point. This Gaussian distribution represents likelihood of obstacle. Second, we modeled dynamic transition of a static obstacle map by adopting the Hidden Markov Model. Due to the dynamic characteristics of the vehicle in relation to the conditions of the next stage only, a more accurate map of the obstacles can be obtained using the Hidden Markov Model. Experimental data obtained from test driving demonstrates that our approach is suitable for mapping static obstacles. In addition, this result shows that our algorithm has an advantage in estimating not only static obstacles but also dynamic characteristics of moving target such as driving vehicles.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.535-540
• /
• 2022

Out of Vocabulary(OOV) 문제는 인공신경망 기계번역(Neural Machine Translation, NMT)에서 빈번히 제기되어 왔다. 이를 해결하기 위해, 기존에는 단어를 효율적인 압축할 수 있는 Byte Pair Encoding(BPE)[1]이 대표적으로 이용되었다. 하지만 BPE는 빈도수를 기반으로 토큰화가 진행되는 결정론적 특성을 취하고 있기에, 다양한 문장에 관한 일반화된 분절 능력을 함양하기 어렵다. 이를 극복하기 위해 최근 서브 워드를 정규화하는 방법(Subword Regularization)이 제안되었다. 서브 워드 정규화는 동일한 단어 안에서 발생할 수 있는 다양한 분절 경우의 수를 고려하도록 설계되어 다수의 실험에서 우수한 성능을 보였다. 그러나 분류 작업, 특히 한국어를 대상으로 한 분류에 있어서 서브 워드 정규화를 적용한 사례는 아직까지 확인된 바가 없다. 이를 위해 본 논문에서는 서브 워드 정규화를 대표하는 두 가지 방법인 유니그램 기반 서브 워드 정규화[2]와 BPE-Dropout[3]을 이용해 한국어 분류 문제에 대한 서브 워드 정규화의 효과성을 제안한다. NMT 뿐만 아니라 분류 문제 역시 단어의 구성성 및 그 의미를 파악하는 것은 각 문장이 속하는 클래스를 결정하는데 유의미한 기여를 한다. 더불어 서브 워드 정규화는 한국어의 문장 구성 요소에 관해 폭넓은 인지능력을 함양할 수 있다. 해당 방법은 본고에서 진행한 한국어 분류 과제 실험에서 기존 BPE 대비 최대 4.7% 높은 성능을 거두었다.