• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.1120-1128
• /
• 1999

The model-based object recognition is defined as a graph matching process between model images and an input image. In this paper, a graph matching problem is modeled as a n optimization problems and a genetic algorithm is proposed to solve the problems. For this work, fitness function, data structured and genetic operators are developed The simulation results are shown that the proposed genetic algorithm can match feature points between model image and input image for recognition of partially occluded two-dimensional objects. The performance fo the proposed technique is compare with that of a neural network technique.

• Journal of the Speleological Society of Korea
• /
• no.80
• /
• pp.21-24
• /
• 2007

The need for high-frequency decoupling capacitors to supply the transient current requirements to high-speed devices is ubiquitous in current microelectronics applications. Even though materials and their processes have already been developed in terms of their performances, low manufacturing cost cannot be overemphasized in current microelectronics industry. For this reason, we revisited low cost ceramic filled polymer integrated capacitor. Experiments were performed according to the design of experiment (DOE). The best recipe that has the optimized ratio of material composite was obtained using by response optimizer in Minitab. And also, high-frequency measurements were performed to get frequency dependent data using network analyzer.

• Electronics and Telecommunications Trends
• /
• v.35 no.5
• /
• pp.14-29
• /
• 2020

The 6G mobile communication system will become a backbone infrastructure around 2030 for the future digital world by providing distinctive services such as five-sense holograms, ultra-high reliability/low-latency, ultra-high-precision positioning, ultra-massive connectivity, and gigabit-per-second data rate for aerial and maritime terminals. The recent remarkable advances in machine learning (ML) technology have recognized its efficiency in wireless networking fields such as resource management and cell-configuration optimization. Further innovation in ML is expected to play an important role in solving new problems arising from 6G network management and service delivery. In contrast, an approach to apply ML to a physical-layer (PHY) target tackles the basic problems in radio links, such as overcoming signal distortion and interference. This paper reviews the methodologies of ML-based PHY, relevant industrial trends, and candiate technologies, including future research directions and standardization impacts.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.406-410
• /
• 2007

성대마이크는 디바이스의 특성상 환경 잡음을 최소화하는 장점이 있다. 그러나 고주파정보의 손실과 부분적인 포먼트 정보의 손실 때문에, 성대마이크를 이용한 명령어 인식기는 표준마이크를 이용한 명령어 인식기보다 낮은 성능을 보인다. 본 논문은 한국어 음운자질의 특성을 적용한 특징추출 알고리즘과 최적화된 인식모델을 이용하여 높은 성능을 갖는 명령어 인식시스템을 제안한다. 성대 울림 특성이 한국어 내의 분포 분석하여 성대 울림 정보만으로 명령어 인식기 개발이 가능함을 보이고 음성인식에 높은 성능을 보이는 Time Delay Neural Network(TDNN)[1]을 성대신호 명령어 인식에 최적화한 구조를 제안한다. 실험을 통해 찾은 최적 TDNN 구조를 성대신호에 적용한 했을 때 약 87%의 높은 성능을 보였다.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2006.05b
• /
• pp.621-624
• /
• 2006

This paper presents a novel optimum technique for optimum mix-proportion using database-based prediction model of material properties for an object function or a constraint condition. The proposed technique provides high reliability of results introducing effective region model, which assesses whether the prediction model is effective or not, in optimization process. In order to validate the proposed technique, a genetic algorithm was adopted as a optimum technique, and an artificial neural network was adopted as a prediction model for material properties and as a model for assessing effective region. The mix-proportion obtained from the proposed technique is more reasonable than that obtained from a general optimum technique.

• Journal of information and communication convergence engineering
• /
• v.8 no.5
• /
• pp.479-483
• /
• 2010

The rapid progress of the Internet and network is affecting the engineering design environment as well as business that use Web technologies to enhance their competitive edge. In product development, experts and organization who take part in the design process are often geographically dispersed. Furthermore, different divisions and business often have heterogeneous CAD/CAE systems and methods for expressing product data, and addressing this heterogeneity creates additional costs and increases development time. Managing distributed CAD, CAE and other related systems in an organic and holistic manner from the initial stages of product development is imperative to ensure successful collaboration in the design process. Therefore, this study suggests a Web-based MDO framework to support interfacing and collective use of design and analysis tools.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2161-2163
• /
• 2004

This paper focuses on congestion control for ATM network with uncertain time-variant delays. The time-variant delays can be distinguished into two distinct components. The first one that is represented by time-variant queueing delays in the intermediate switches is occurred in the return paths of RM cells. The next one is a forward path delay. It is solved by the VBR Model which quantifies the data propagation from the sources to the switch. Robust $H_{\infty}$ control is studied for solving congestion problem with norm-bounded time-varying uncertain parameters. The suitable robust $H_{\infty}$ controller is obtained from the solution of a convex optimization problem including terms of LMIs.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.5
• /
• pp.61-71
• /
• 1998

Genetic Algorithm(GA) is a method of approaching optimization problems by modeling and simulating the biological evolution. GA needs large time-consuming, so ti had better do on a parallel computer architecture. Our proposed system has a VLSI-oriented interconnection network, which is constructed from a viewpoint of fractal geometry, so that self-similarity is considered in its configuration. The approach to Parallel Genetic Algorithm(PGA) on our proposed system is explained, and then, we construct the classifier system such that the set of samples is classified into weveral classes based on the features of each sample. In the process of designing the classifier system, We have applied PGA to the Traveling Salesman Problem and classified the sample set in the Euclidean space into several categories with a measure of the distance.

• Proceedings of the IEEK Conference
• /
• 2000.11b
• /
• pp.116-119
• /
• 2000

The Process of Inner Product has been widely used in a DSP. But it is difficult to implement by a dedicated hardware because it needs many computation steps for multiplication and addition. To reduce these steps, it is essential to design efficient hardware architecture. This paper proposes the design method of adder-based distributed arithmetic for implementation of DCT module and the automatic design of summation-network which is a core block in the proposed design method. Finally, it shows that the proposed design method is more efficient than a ROM-based distributed arithmetic which is the typical design method.

• 한국전산유체공학회:학술대회논문집
• /
• 2010.05a
• /
• pp.127-128
• /
• 2010

As P-new-city is planned and constructed, district eating utilizing an existing near-by power plant's waste heat is considered as an economic and environment friendly way of providing heating to the new city. Many pipeline diameters and pumping station location and capacity were assumed, investigated and optimized, to satisfy the customers' heat demand considering common district heating pipe-network design and construction practice, and also and construction, pumping station land price and construction and the pumping energy cost during lifetime of DH systems.