• Journal of Technology Innovation
• /
• v.29 no.4
• /
• pp.161-196
• /
• 2021

This study presents a new methodology for developing AI-based products. It identifies the distinctive attributes of AI innovation that are different from existing methods, and presents a product design process and methodology reflecting these attributes. This study emphasizes that AI product development should be oriented toward an ambidexterity approach. This study proposes a design process and specific development method for AI-based products that including steps such as technology push oriented idea generation with morphological approach, market pull oriented consumer requirements analysis, product design refinement, etc. In order to verify the practical applicability of this methodology, an AI-based car infotainment system development strategy is derived as a case study. 13 innovative ideas were generated by the morphological approach and expert review based on technological possibility, and a total of 6 quality requirements were derived as new product development strategies through the analysis of consumer requirements by combining Kano and TOPSIS. The methodology proposed in this research paper can be usefully utilized for companies to pioneer new markets through AI-based products or to expand the market by upgrading existing products or services.

• Journal of Platform Technology
• /
• v.11 no.3
• /
• pp.24-31
• /
• 2023

Recently, interest in UAM (Urban Air Mobility, UAM), which can take off and land vertically in the operation of urban air transportation systems, has been increasing. Therefore, various start-up companies are developing related technologies as eco-friendly future transportation with advanced technology. However, studies on ways to increase safety in the operation of UAM are still insignificant. In particular, efforts are more urgent to improve the safety of risks generated in the process of attempting to land in the city center by UAM equipped with autonomous driving. Accordingly, this study proposes a plan to safely land by avoiding dangerous region that interfere when autonomous UAM attempts to land in the city center. To this end, first, the latitude and longitude coordinate values of dangerous objects observed by the sense of the UAM are calculated. Based on this, we proposed to convert the coordinates of the distorted planar image from the 3D image to latitude and longitude and then use the calculated latitude and longitude to compare the pre-learned feature descriptor with the HOG (Histogram of Oriented Gradients, HOG) feature descriptor to extract the dangerous Region. Although the dangerous region could not be completely extracted, generally satisfactory results were obtained. Accordingly, the proposed research method reduces the enormous cost of selecting a take-off and landing site for UAM equipped with autonomous driving technology and contribute to basic measures to reduce risk increase safety when attempting to land in complex environments such as urban areas.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.657-662
• /
• 2003

A mechanical system controlled by human operator, such as master-slave system, includes human dynamics in the whole system and such a system is called a human-machine system. In the system, operator's skill is required considerably in order to realize a meaningful operation. In this paper, a new concept and design strategy of compensator that improves the operativity of human-machine system are proposed. The compensator is called "collaborater "that is named after "collaborator" who works together with people. We mean not to design the automatic controller but the compensator that works together with a machine so that human feels the fulfillment in the operation. Our aim is to realize cooperation of people and a machine on a higher level.

• Proceedings of the Korean Society of Organic Agriculture Conference
• /
• 2001.10a
• /
• pp.248-265
• /
• 2001

Recently, agriculture in Korea is seriously depressed by economic globalization and trade liberalization because of low competitive power. Organic farming, which is favorable for small scale agriculture, is expected to be one of alternatives to boost agricultural activities in Korea. Organic agriculture requires systemic developments of new technologies considering the complex biological interaction within the system in connection with high quality and safety standard. The National Institute of Agricultural Science & Technology(NIAST) has been worked on the series of organic farming technologies, including bio-pesticides, pheromone, natural enemies as well as the testings of materials used in organic farming. NIAST will concentrate on the technological development for compromising to the conflict between commodity-oriented and ecological harmony. Research on systemic land and water use, management of plant nutrition, pest and disease control, post-harvest would also be important targets. Integrated efforts among researchers, professors, administrators, farmers, private sectors, and extension workers are substantial for fast technology development and its dissemination. Development and use of these technologies will homely enlighten the Korean organic farming although it may require quite a time and endeavor.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.6
• /
• pp.81-89
• /
• 2008

University Research Centers specialized in defense technology(DURCs) were designed to develop fundamental knowledge and to acquire core technologies related to defense development by conducting creative and interdisciplinary research. The centers also have a function of fostering scientists and practitioners possessing defense-oriented cross-disciplinary knowledges. Since the outset of the DURC in 1994, Sixteen DURCs have been funded and eleven DURCs are now in operation. The purpose of this paper is to analyse the operational status and the performance of DURCs and to suggest ideas on improving the effectiveness of the DURC program by comparing with the Korea Excellent Research Center program and the U.S. National Science Foundation(NSF) Engineering Research Center(ERC) program.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.235-238
• /
• 1997

The Graphical User Interface (GUI) software is developed for 0.3 Tesla Permanent Magnet Resonance Imaging (MRI) system and the state of art of designing GUI system is discussed in this paper. The Object-Oriented concepts are applied for designing GUI software utilizing Interbase ODBC Database layer. Also, Multimedia concepts such as voice, sound and music are integrated in GUI system to enhance the efficiency of MRI operation.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.147-150
• /
• 2018

목적 지향 대화 시스템은 자연어 이해, 대화 관리자, 자연어 생성과 같은 세분화 모델들의 결합으로 이루어져있어 하위 모델에 대한 오류 전파에 취약하다. 이러한 문제점을 해결하기 위해 자연어 이해 모델과 대화 관리자를 하나의 네트워크로 구성하고 오류에 강건한 심층 Q 네트워크를 제안한다. 본 논문에서는 대화의 전체 흐름을 파악 할 수 있는 순환 신경망인 LSTM에 심층 Q 네트워크 적용한 심층 순환 Q 네트워크 기반 목적 지향 대화 시스템을 제안한다. 실험 결과, 제안한 심층 순환 Q 네트워크는 LSTM, 심층 Q 네트워크보다 각각 정밀도 1.0%p, 6.7%p 높은 성능을 보였다.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.1021-1028
• /
• 2013

Automatic facial expression recognition is a widely studied problem in computer vision and human-robot interaction. There has been a range of studies for representing facial descriptors for facial expression recognition. Some prominent descriptors were presented in the first facial expression recognition and analysis challenge (FERA2011). In that competition, the Local Gabor Binary Pattern Histogram Sequence descriptor showed the most powerful description capability. In this paper, we introduce hybrid facial representations for facial expression recognition, which have more powerful description capability with lower dimensionality. Our descriptors consist of a block-based descriptor and a pixel-based descriptor. The block-based descriptor represents the micro-orientation and micro-geometric structure information. The pixel-based descriptor represents texture information. We validate our descriptors on two public databases, and the results show that our descriptors perform well with a relatively low dimensionality.

• Convergence Security Journal
• /
• v.16 no.7
• /
• pp.93-100
• /
• 2016

Important evidence or clue in general crime as well as crime relevant to computer has been discovered in digital devices including computer with advance of information technology and turning into a information-oriented society. A leakage of industrial technology and confidential business information is related to digital devices such as computer, smart phone, USB, etc. This paper deal with a current state and comparison analysis of digital forensic technology for developing way of forensic field, so we seek for method of preventing information leakage.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3534-3549
• /
• 2020

The traditional method of smoke image recognition has low accuracy. For this reason, we proposed an algorithm based on the good group of IMFOA which is GMFOA to optimize the parameters of SVM. Firstly, we divide the motion region by combining the three-frame difference algorithm and the ViBe algorithm. Then, we divide it into several parts and extract the histogram of oriented gradient and volume local binary patterns of each part. Finally, we use the GMFOA to optimize the parameters of SVM and multiple kernel learning algorithms to Classify smoke images. The experimental results show that the classification ability of our method is better than other methods, and it can better adapt to the complex environmental conditions.