• Proceedings of the KIEE Conference
• /
• 1999.07a
• /
• pp.244-246
• /
• 1999

This paper deals with the design and fabrication of a novel superconducting power supply system, and characteristics have been analyzed through experiments. Superconducting power supply consists of rotating and static parts, and superconducting magnet. In this experiment, the current pumping characteristics have been analyzed with superconducting sheets placed in parallel within the static part of the machine. In addition, in order to observe the rotating flux distribution in the superconducting sheet, several hall-sensors were placed in it. With the flux distribution acquired, the effect of the flux on the superconducting sheet during the process of current pumping have been analyzed. Also, general operational characteristics of the superconducting power supply system have been investigated on the basis of the current and voltage data, and magnetic field values acquired through the experiments.

• International journal of advanced smart convergence
• /
• v.10 no.2
• /
• pp.79-85
• /
• 2021

Speech recognition technology refers to a technology in which a computer interprets the speech language spoken by a person and converts the contents into text data. This technology has recently been combined with artificial intelligence and has been used in various fields such as smartphones, set-top boxes, and smart TVs. Examples include Google Assistant, Google Home, Samsung's Bixby, Apple's Siri and SK's NUGU. Google and Daum Kakao offer free open APIs for speech recognition technologies. This paper selects three APIs that are free to use by ordinary users, and compares each recognition rate according to the three types. First, the recognition rate of "numbers" and secondly, the recognition rate of "Ga Na Da Hangul" are conducted, and finally, the experiment is conducted with the complete sentence that the author uses the most. All experiments use real voice as input through a computer microphone. Through the three experiments and results, we hope that the general public will be able to identify differences in recognition rates according to the applications currently available, helping to select APIs suitable for specific application purposes.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.43-54
• /
• 2022

Simultaneous translation is online decoding to translates with only subsentence. The goal of simultaneous translation research is to improve translation performance against delay. For this reason, most studies find trade-off performance between delays. We studied the experiments of the fixed policy-based simultaneous translation in Korean. Our experiments suggest that Korean tokenization causes many fragments, resulting in delay compared to other languages. We suggest follow-up studies such as n-gram tokenization to solve the problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.301-304
• /
• 1999

In this paper, we proposed the new method of extracting the position and the length of the input-line by using only two parameters ($\theta$, $\rho$) from the HT(Hough Transform) data. The computer simulations and the optical experiments by using the HT CGH(Computer Generated Hologram) filter is perfermed. The results are very similar to those of the computer simulation results.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.21 no.47
• /
• pp.233-241
• /
• 1998

With the increasing complexity of man-made systems, computer simulation has become a widely used tool for the design and analysis of complex system. When computer simulation is used for the purpose of system design, the analysts want to develop strategies to achieve some pre-defined target condition for an output of interest while simultaneously minimizing its variance. The goal of this research is to develop and demonstrate a new method for the design of robust systems with multiple responses using the fuzzy satisfaction function and computer simulation experiments.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1014-1017
• /
• 2009

The analytical expression for quality function is found including the dependence on disparity. The problem is considered in the projective coordinates for which the forward and backward transformation matrices are found. The formation of side observer regions is considered. The probability of the pseudo stereo effect is also estimated. Testing patterns are improved in order to provide higher accuracy of measurements. This is confirmed in experiments.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.11-12
• /
• 2023

GPGPU 환경에서의 ML 모델이 다양한 분야에 지속적으로 활용되면서, 이미지 분할(image segmentation) 연구가 활발하다. multi-GPU 환경에서 성능 최적화를 위하여 병렬화 기법들이 활용되고 있다. 본 연구에서는 multi-GPU 환경에서 U-Net 모델의 전체 수행 시간을 단축하기 위해 convolution 연산을 최적화하는 기법을 적용하는 실험을 진행하였고 shared memory, data parallelism 를 적용하여 82% 성능 향상을 보여주었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.958-961
• /
• 2008

본 논문은 옥내측위 결과에 지도정합 방법을 적용하는 실험 결과를 소개한다. 사용한 지도정합 방법은 측위 결과로 얻은 측정 궤적에 칼만필터를 적용하여 매끄러운 칼만필터궤적을 얻은 다음, 칼만필터궤적과 이산크레쉐거리가 가장 가까운 보행자 통로로 정합한다. 사용한 지도정합 방법의 효율성을 보이는 실험 결과도 소개한다.

• Journal of Radiation Protection and Research
• /
• v.22 no.4
• /
• pp.289-298
• /
• 1997

Time-consuming experiments have been required in the development of neutron moisture gauge to induce a relation between the water content in soil and the neutron counts. Applying a monte carlo computer code to simulate the experiments of neutron moisture gauging may contribute to reduce time and efforts for experiments and produce a calibration equation which is more applicable to soil in general. In this study MCNP4A, a monte carlo computer code, was employed to simulate soil experiments and the simulated results were compared with experimental ones. The comparative study showed that MCNP4A is applicable to simulate the experiments and calibration equation can be obtained through simulations. Effects of dry density changes were also studied.