• 한국정보기술학회 영문논문지
• /
• 제10권2호
• /
• pp.139-151
• /
• 2020

Entity name recognition is a part of information extraction that extracts entity names from documents and classifies the types of extracted entity names. Entity name recognition technologies are widely used in natural language processing, such as information retrieval, machine translation, and query response systems. Various deep learning-based models exist to improve entity name recognition performance, but studies that compared and analyzed these models on Korean data are insufficient. In this paper, we compare and analyze the performance of CRF, LSTM-CRF, BiLSTM-CRF, and BERT, which are actively used to identify entity names using Korean data. Also, we compare and evaluate whether embedding models, which are variously used in recent natural language processing tasks, can affect the entity name recognition model's performance improvement. As a result of experiments on patent data and Korean corpus, it was confirmed that the BiLSTM-CRF using FastText method showed the highest performance.

• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• pp.803-811
• /
• 2020

This paper proposes an image classification algorithm that transforms the number of convolution layers in the residual block of ResNet, CNN's representative method. The proposed method modified the structure of 34/50 layer of ResNet structure. First, we analyzed the performance of small and many convolution layers for the structure consisting of only shortcut and 3 × 3 convolution layers for 34 and 50 layers. And then the performance was analyzed in the case of small and many cases of convolutional layers for the bottleneck structure of 50 layers. By applying the results, the best classification method in the residual block was applied to construct a 34-layer simple structure and a 50-layer bottleneck image classification model. To evaluate the performance of the proposed image classification model, the results were analyzed by applying to the cifar10 dataset. The proposed 34-layer simple structure and 50-layer bottleneck showed improved performance over the ResNet-110 and Densnet-40 models.

• 한국융합학회논문지
• /
• 제11권10호
• /
• pp.219-224
• /
• 2020

입상재료를 균일하게 혼합하기 위한 입자 교반기는 다양한 산업 분야에서 널리 활용되는 기계 장치로써 응용 분야와 혼합 조건에 따라 다양한 형태로 개발되어 사용되고 있다. 하지만 대부분 산업용 교반기의 구동 자유도는 2 자유도 이하로써 혼합재료의 기계적 특성 및 교반기의 구조를 제외한 운전 조건 측면에서 최적 교반을 위한 인자의 선택범위는 넓지 않다. 운전 조건의 선택 범위를 확대하기 위해 본 논문에서는 다관절 로봇과 입자용 드럼 믹서를 융합한 다자유도 로봇 교반기를 제안하였고 가상 작동 환경에서 교반 성능을 평가하였다. 입자 유동 해석 기법인 이산요소법을 이용하여 다자유도 로봇 믹서의 성능 예측 시뮬레이션을 수행하였고 제안된 장치 설계안이 기존 교반기보다 개선된 혼합 성능을 발휘할 수 있다는 것을 확인하였다.

• Current Photovoltaic Research
• /
• 제8권2호
• /
• pp.50-53
• /
• 2020

GaN based photoelectrode has shown good potential owing to its better chemical stability and tunable bandgap with materials such as InN and AlN. Tunable bandgap allows GaN to make the maximum utilization of solar spectrum, which could improve photoelectrode performance. However, the problems about low photoelectrode performance and photo-corrosion still remain. In this study, we attempt to investigate the photoelectrochemical (PEC) properties of phosphor application to InGaN photoelectrode. Experimental result shows YAG:Ce³⁺ and beta-SiALON phosphor result in the highest photoelectrode performance of InGaN.

• 한국전자거래학회지
• /
• 제19권1호
• /
• pp.79-93
• /
• 2014

미래 신 성장동력이며 융합산업의 핵심 도메인인 IT 산업은 타 산업과의 융합을 통하여 국가 발전의 기반이 되는 산업이지만, IT 고급인력의 부족 현상은 지방과 수도권에 한정되지 않고 지속되고 있다. 그러나, 그간의 연구들은 포괄적인 인력양성에 대한 연구가 주를 이루고 있으며, 사업수행 지역의 특성화를 이룰 수 있는 인력양성 정책에 대한 성과분석에 대한 연구들은 미흡한 실정이다. 이에 따라, 지역의 IT 고급 인력을 양성하여 IT 융합을 기반으로 지역산업을 활성화하고 이를 통하여 지역을 발전시키기 위한 제도적 개선방안에 대한 필요성이 나타나고 있다. 따라서 본 연구에서는 지역의 IT 인력양성 활성화를 위하여 지역 기반 인력양성사업의 IT 분야 성과분석을 통하여 제도개선방안을 설계하고자 한다.

• Journal of Positioning, Navigation, and Timing
• /
• 제10권4호
• /
• pp.243-251
• /
• 2021

Real-Time Kinematic (RTK) is a phase-based differential GNSS technique and uses additional observations from permanent reference stations to mitigate or eliminate effects like atmospheric delays or satellite clocks and orbit errors. In particular, as the position accuracy required in the fields of autonomous vehicles and drones is gradually increasing, the demand for RTK-based precise navigation that can provide cm-level position is increasing. Recently, with the rapid growth of the open-source software market, the use of open-source software for building navigation system of unmanned vehicles, which is difficult to mount an expensive GNSS receivers, is gradually increasing. RTKLIB is an open-source software package that can perform RTK positioning and is widely used for research and education purposes. However, since the performance and stability of RTK algorithm of RTKLIB is inevitably inferior to that of commercial GNSS receivers, users need to verify whether RTKLIB can satisfy the navigation performance requirements of unmanned vehicles. Therefore, in this paper, the performance evaluation of the RTK positioning algorithm of RTKLIB was performed using GNSS observation data acquired in a dynamic environment. Therefore, in this paper, the RTK positioning performance of RTKLIB was evaluated using GNSS observation data acquired in a dynamic environment. Our results show that the current RTK algorithm of RTKLIB is not suitable for precise navigation of unmanned vehicles.

• 한국산업융합학회 논문집
• /
• 제25권6_2호
• /
• pp.1017-1027
• /
• 2022

Development of social overhead capital (SOC) requires huge national finance, and performance issues such as cost-efficiency, safety, and environment have been constantly raised. However, currently each construction client has limited access to its own projects' performance without analytic methodology for industry-level comparisons and benchmarking for improvement. To overcome this problem, this study proposes a comprehensive performance analysis framework for post-evaluation of large-scale construction projects. To this end, this study performed a case study of advanced countries (the U.S., the U.K. and Japan) and consultation with related experts to develop a tailored performance analysis framework for the Post- Construction Evaluation and Management system in Korea. The developed framework covers three categories (project performance, project efficiency, and ripple effect), nine areas (cost, schedule, change, safety, quality, demand, benefit-cost ratio, civil complaint, and defect), and 31 detailed metrics. Using industry-level project performance database and statistical techniques, the proposed framework can be used not only to diagnose excellent and unsatisfactory performance areas for completed construction projects, but also to provide reference data for future similar projects. This study can contribute to the improvement of clients' performance management practices and effectiveness of construction projects.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권1호
• /
• pp.44-57
• /
• 2016

Rectification is used as a preprocessing to reduce the computation complexity of disparity estimation. However, rectification also requires a complex computation. To minimize the computing complexity, rectification using a lookup-table (R-LUT) has been introduced. However, since, the R-LUT consumes large amount of memory, rectification with compressed LUT (R-CLUT) has been introduced. However, the more we reduce the memory consumption, the more we need decoding overhead. Therefore, we need to attain an acceptable trade-off between the size of LUT and decoding overhead. In this paper, we present such a trade-off by adaptively combining simple coding methods, such as differential coding, modified run-length coding (MRLE), and Huffman coding. Differential coding is applied to transform coordinate data into a differential form in order to further improve the coding efficiency along with Huffman coding for better stability and MRLE for better performance. Our experimental results verified that our coding scheme yields high performance with maintaining robustness. Our method showed about ranging from 1 % to 16 % lower average inverse of compression ratio than the existing methods. Moreover, we maintained low latency with tolerable hardware overhead for real-time implementation.

• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• 전기전자학회논문지
• /
• 제24권4호
• /
• pp.1069-1073
• /
• 2020

본 논문에서는 폐어구의 체계적 관리를 위해 개발 중인 어구 자동식별 모니터링 시스템의 신뢰성을 확인코자 서해어업관리단의 어업지도선에 승선하여 해상에서 시제품의 기능별 동작확인과 통신 시험을 진행하였다. 또한 수집 데이터를 분석하여 어구 자동식별 모니터링 시스템에서 활용되는 LoRa통신망에 대한 해상에서의 신뢰성을 확인하고 시스템의 안정성을 검토하고자 하였다.