• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1403-1413
• /
• 2021

In this paper, we investigate automated data validation techniques for artificial intelligence training, and also disclose open-source frameworks, such as Google's TensorFlow Data Validation (TFDV), that support automated data validation in the AI model development process. We also introduce an experimental study using public data sets to demonstrate the effectiveness of the open-source data validation framework. In particular, we presents experimental results of the data validation functions for schema testing and discuss the limitations of the current open-source frameworks for semantic data. Last, we introduce the latest studies for the semantic data validation using machine learning techniques.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.371-374
• /
• 1995

The real-time holographic interferometer with a digital high-speed camera is applied to the visualization of transient temperature field. Collimated and diffused laser beams are used to the object beam according to the shape and transmittance of the phase object. Also, ESPI(Electronic Speckle Speckle Pattern Interferometer) technique is used to the visualization and quantitatie measurement of slow-varying temperature field. The experimental results obtained form these two techniques are discussed.

• Journal of Power Electronics
• /
• 제3권2호
• /
• pp.69-80
• /
• 2003

Computer aided engineering (CAE) is a systematic approach to develop a better product/application with maximum possible options and minimum transition time. This paper presents a comprehensive feasibility analysis of various CAE techniques for evaluation and optimization of power electronic converters and systems. Different CAE methods for analysis, design, and performance improvement are classified. In addition, their advantages compared to the conventional workbench experimental methods are explained in detail and through examples.

• 대한약학회:학술대회논문집
• /
• 대한약학회 2002년도 Proceedings of the Convention of the Pharmaceutical Society of Korea Vol.2
• /
• pp.88-89
• /
• 2002

Traditionally, kinetics of brain influx of drugs has been evaluated by a number of experimental techniques. Brain uptake index and in situ brain perfusion study have been used for the determination of the kinetics; However, these methods generally focus on the accuracy of the uptake rate into the brain rather than the speed of the determination. In addition, application of radiolabelled substrates (e.g., $_{14}$C-labelled sucrose) further impedes the wide spread acceptance of these techniques for the application of high throughput screening system. (omitted)

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.685-688
• /
• 1998

Measurement of optical flow is a core problem of matching through the analysis of image sequences. In this paper, horn's and anandan's techniques are analyzed to derive a better technique for matching. Experimental results show that Horn's technique has low accuracy in measuring the velocity of optical flow while anandan's technique has poor performaance for diverging images. Based upon this observation, a new technique for the measurement of optical flow is proposed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1232-1235
• /
• 2002

An experiment on the automatic population measurement of brown Mealy Bugs is first reported in this article. Several image processing techniques are employed along with mapping function and neural network. Though brown Mealy Bugs are difficult to detect because of their camouflage, the experimental results showed that approximately 74% of them were correctly detected.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 컴퓨터소사이어티 추계학술대회논문집
• /
• pp.99-102
• /
• 2003

In this paper we propose an adaptive learning method for HMM classifiers by using splitting and merging techniques to overcome the problem of the conventional teaming, where one HMM classifier per class has been trained, individually. The experimental results demonstrate a possibility that the proposed mechanism could be applied for applications of having multiple clusters in a class.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2002년도 전력전자학술대회 논문집
• /
• pp.730-733
• /
• 2002

In this paper, implementation of active noise barriers using active noise control techniques is presented. Multi-channel FX-LMS algorithms and Leaky LMS algorithms are used for adaptive filters to attenuate noise which is propagated from the outside of experimental enclosures. Experiments have done to show the effectivene a proposed active noise barriers.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1991년도 추계종합학술발표회논문집
• /
• pp.220-224
• /
• 1991

Uninterruptible Power Supply(UPS) Systems are widely used in a varietyof fields as highly reliable power sources. This paper describes the operation and performance of an UPS using sinusoidal Pulse Width Modulation (PWM)techniques. A newly developed UPS adopted switching element -power TR, power MOSFET, IGBT- is introduced. Experimental results showed that sinusoidal PWM techniques have good features for UPS systems.

• 대한전기학회논문지
• /
• 제41권3호
• /
• pp.219-226
• /
• 1992

In this study, Kalman filtering theory is applied to the estimation of symmetrical components from fault voltage and current signal when it comes to faults with the power system. An algorithm for estimating fault location accurately and quickly by calculating the symmetrical components from the extracted fundamental voltage phasor and current phasor is presented. Also, to confirm the validity of digital distance relaying techniques using Kalman filtering, the experimental results obtained by using the digital simulation of power system is shown.