• 대한의용생체공학회:의공학회지
• /
• 제44권4호
• /
• pp.293-301
• /
• 2023

Scoliosis is a three-dimensional deformation of the spine that is a deformity induced by physical or disease-related causes as the spine is rotated abnormally. Early detection has a significant influence on the possibility of nonsurgical treatment. To train a deep learning model with preprocessed images and to evaluate the results with and without data augmentation to enable the diagnosis of scoliosis based only on a chest X-ray image. The preprocessed images in which only the spine, rib contours, and some hard tissues were left from the original chest image, were used for learning along with the original images, and three CNN(Convolutional Neural Networks) models (VGG16, ResNet152, and EfficientNet) were selected to proceed with training. The results obtained by training with the preprocessed images showed a superior accuracy to those obtained by training with the original image. When the scoliosis image was added through data augmentation, the accuracy was further improved, ultimately achieving a classification accuracy of 93.56% with the ResNet152 model using test data. Through supplementation with future research, the method proposed herein is expected to allow the early diagnosis of scoliosis as well as cost reduction by reducing the burden of additional radiographic imaging for disease detection.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.417-424
• /
• 2009

For a construction project to progress smoothly, effective cost estimation is vital, particularly in the conceptual and schematic design stages. In these early phases, despite the fact that initial estimates are highly sensitive to changes in project scope, owners require accurate forecasts which reflect their supplying information. Thus, cost estimators need effective estimation strategies. Practically, parametric cost estimates are the most commonly used method in these initial phases, which utilizes historical cost data (Karshenas 1984, Kirkham 2007). Hence, compilation of historical data regarding appropriate cost variance governing parameters is a prime requirement. However, precedent practice of data mining (data preprocessing) for denoising internal errors or abnormal values is needed before compilation. As an effort to deal with this issue, this research proposed a statistical methodology for data preprocessing and verified that data preprocessing has a positive impact on the enhancement of estimate accuracy and stability. Moreover, Statistically Preprocessed data Based Parametric (SPBP) cost models are developed based on multiple regression equations and verified their effectiveness compared with conventional cost models.

• 정보교육학회논문지
• /
• 제15권1호
• /
• pp.147-154
• /
• 2011

본 연구에서는 가속도 센서의 각 축의 값들을 이용해 숫자나 특정 입력 값을 기기에 전달할 수 있는 제스처 인식을 위한 센서 값들의 효율적인 사전 보정 알고리즘과 분류 알고리즘에 대해서 제안한다. 실험결과 보정 전과 보정 후의 X축과 Z축의 에러율을 통하여 전처리 된 데이터가 생성됨을 알 수 있었다. 또한 전처리 된 데이터에 적용할 정규화와 분류 알고리즘으로 구현한 인식기가 높은 인식률을 보여주었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2485-2489
• /
• 2005

This paper introduces a new preprocessing scheme to replace original data of gray scale images with particular ordered data so that performance of lossless compression can be improved more efficiently. As a kind of preprocessing technique to maximize performance of entropy encoder, the proposed method converts the input image data into more compressible form. Before encoding a stream of the input image, the proposed preprocessor counts co-occurrence frequencies for neighboring pixel pairs. Then, it replaces each pair of adjacent gray values with particular ordered numbers based on the investigated co-occurrence frequencies. When compressing ordered image using entropy encoder, we can expect to raise compression rate more highly because of enhanced statistical feature of the input image. In this paper, we show that lossless compression rate increased by up to 37.85% when comparing results from compressing preprocessed and non-preprocessed image data using entropy encoder such as Huffman, Arithmetic encoder.

• Journal of Platform Technology
• /
• 제11권3호
• /
• pp.12-23
• /
• 2023

2020 년대 K-Pop 시장은 보이그룹보다 걸그룹이, 3 세대보다 4 세대가 전반에서 주목받았다. 해당 논문은 걸그룹의 세대가 바뀌기 시작했는지 알아보고자 가사 군집화에 대한 방법과 결과를 제시한다. 2013 년부터 2022 년까지 발표된 47 개 그룹의 1469 곡에 대한 메타정보를 수집하여 가사 정보와 가사 외 메타정보로 분류하여 각각 수치화했다. 가사 정보는 선행연구를 기반으로 단어역문서 빈도 벡터화를 적용한 뒤 상위 벡터 값만 선정하는 전처리를 하였다. 가사 외 메타정보는 가사 정보만 사용했을 때의 편향성을 줄이고 더 좋은 군집화 결과를 보여주기 위해 One-Hot Encoding 으로 전처리하여 적용했다. 전처리된 데이터에 대한 군집화 성능은 Spherical K-Means 의 Silhouette Coefficient, Calinski-Harabasz Score 가 Hierarchical Clustering 에 비해 각각 129%, 45% 더 높았다. 본 연구는 한국 대중가요 발전사와 걸그룹 가사 분석 및 군집화 연구에 기여할 수 있을 것으로 기대된다.

• 제어로봇시스템학회논문지
• /
• 제8권7호
• /
• pp.589-598
• /
• 2002

The color measuring/matching expert system is implemented with a new color measuring method that combines intelligent algorithms with image processing techniques. Color measuring part of the proposed system preprocesses the scanned original color input images to eliminate their distorted components by means of the image histogram technique of image pixels, and then extracts RGB(Red, Green, Blue)data among color information from preprocessed color input images. If the extracted RGB color data does not exist on the matching recipe databases, we can measure the colors for the user who want to implement the model that can search the rules for the color mixing information, using the intelligent modeling techniques such as fuzzy inference system and adaptive neuro-fuzzy inference system. Color matching part can easily choose images close to the original color for the user by comparing information of preprocessed color real input images with data-based measuring recipe information of the expert, from the viewpoint of the delta Eformula used in practical process.

• 한국식품영양과학회지
• /
• 제42권10호
• /
• pp.1690-1700
• /
• 2013

본 연구에서 사용한 전처리 나물류 중 고사리 경우 $13^{\circ}C$에서 B. cereus 영양세포 및 포자가, $8^{\circ}C$에서 S. aureus는 성장하지 않았다. 전처리 나물류 및 구근류에서 B. cereus 영양세포 및 포자의 성장특성을 비교한 결과, 도라지와 취나물에서 LT, SGR 및 MPD는 B. cereus 영양세포와 포자사이에 유의적인 차이를 보이지 않았다. 반면 우엉은 $13^{\circ}C$에 저장한 경우 B. cereus 영양세포와 포자의 유도기는 유의적인 차이를 보였으며 고사리의 경우, 17, 24, $35^{\circ}C$ 온도에서 B. cereus 포자의 유도기는 영양세포의 유도기 값보다 2배 연장된 것으로 유의적인 차이를 나타내었다(P<0.05). $24^{\circ}C$와 $35^{\circ}C$의 상온에서는 모든 나물류 및 구근류에서 B. cereus 포자 유도기는 영양세포의 유도기보다 연장되었고, SGR 값은 포자가 빠른 것으로 나타났다. 한편, $13^{\circ}C$와 $17^{\circ}C$에서는 B. cereus 영양세포와 포자의 유도기가 고온에 비하여 연장되어 B. cereus 영양세포와 포자의 성장을 억제하기 위해서는 $13^{\circ}C$ 이하의 온도 관리가 중요하다. 또한 B. cereus와 S. aureus 영양세포의 성장특성 비교 결과, $13^{\circ}C$ 이하에서는 B. cereus 성장이 관찰되지 않았으나 S. aureus는 $8^{\circ}C$에서도 성장하였다. 전반적으로 $13^{\circ}C$에서 모든 나물류 및 구근류는 B. cereus의 유도기가 S. aureus 의 유도기보다 3배 이상 연장되었다. 전처리 나물류 및 구근류에서 개발된 설사형 B. cereus 영양세포 및 포자 성장예측모델을 구토형 B. cereus 영양세포 및 포자의 실험값으로 검증한 결과, 도라지와 고사리의 LT 모델과 고사리의 SGR 모델을 제외한 모든 모델에서 Bf 값이 허용범위(0.07~1.15)에 속하여 설사형 B. cereus 영양세포, 포자 성장모델이 구토형 B. cereus 영양세포, 포자의 성장을 예측하는데 적합한 것으로 나타났다. 또한 전처리 나물류 및 구근류에서 $8{\sim}35^{\circ}C$ 사이에 개발된 S. aureus의 성장예측 모델을 실험에 사용하지 않은 온도(18, $30^{\circ}C$)로 적합성을 검증한 결과, 도라지의 SGR 모델을 제외한 모든 모델에서 Bf와 Af 값이 가장 이상적인 1에 가까운 값으로 나타나 실험값과 예측값 사이의 일치성을 보였다. 본 연구 결과 개발된 전처리 나물류 및 구근류의 성장예측 모델은 병원성 미생물의 증식을 억제하는 기준과 규격 설정 시 활용 가능할 것이며, 전처리 나물류의 HACCP 공정의 CCP(critical control point) 및 CL(critical limit)을 설정하는데 유용한 자료로 활용될 수 있을 것으로 사료된다.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권1호
• /
• pp.73-77
• /
• 2021

As the big data analysis technologies has been developed worldwide, the importance of asset management for electric power facilities based data analysis is increasing. It is essential to secure quality of data that will determine the performance of the RISK evaluation algorithm for asset management. To improve reliability of asset management, asset data must be preprocessed. In particular, the process of cleaning dirty data is required, and it is also urgent to develop an algorithm to reduce time and improve accuracy for data treatment. In this paper, the result of the development of an automatic cleaning algorithm specialized in overhead transmission asset data is presented. A data cleaning algorithm was developed to enable data clean by analyzing quality and overall pattern of raw data.

• 대한간호학회지
• /
• 제49권6호
• /
• pp.736-747
• /
• 2019

Purpose: This study aimed to explore public opinion on workplace bullying in the nursing field, by analyzing the keywords and topics of online news comments. Methods: This was a text-mining study that collected, processed, and analyzed text data. A total of 89,951 comments on 650 online news articles, reported between January 1, 2013 and July 31, 2018, were collected via web crawling. The collected unstructured text data were preprocessed and keyword analysis and topic modeling were performed using R programming. Results: The 10 most important keywords were "work" (37121.7), "hospital" (25286.0), "patients" (24600.8), "woman" (24015.6), "physician" (20840.6), "trouble" (18539.4), "time" (17896.3), "money" (16379.9), "new nurses" (14056.8), and "salary" (13084.1). The 22,572 preprocessed key words were categorized into four topics: "poor working environment", "culture among women", "unfair oppression", and "society-level solutions". Conclusion: Public interest in workplace bullying among nurses has continued to increase. The public agreed that negative work environment and nursing shortage could cause workplace bullying. They also considered nurse bullying as a problem that should be resolved at a societal level. It is necessary to conduct further research through gender discrimination perspectives on nurse workplace bullying and the social value of nursing work.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.27-30
• /
• 2003

In this paper a new approach of digitalized ‘Takbon’ is introduced. By image signal processing, the letters which were written on stones can be deciphered. Epigraphic letter is detected by digital image device, digital camera. The two dimensional digital image is preprocessed because of sensor noise and detective turbulence. Color image is transformed into grey level. The letter image is analyzed in time/frequency domain. By the resultant analysis data decisive functions are calculated. Signal Processing techniques, such as scaling, clipping, digital negative, high/low filter, morphology and so on, provide algorithms that can extract letter from stones.