• 제목/요약/키워드: Auto Augmentation

검색결과 25건 처리시간 0.025초

변분 오토인코더와 비교사 데이터 증강을 이용한 음성인식기 준지도 학습 (Semi-supervised learning of speech recognizers based on variational autoencoder and unsupervised data augmentation)

  • 조현호;강병옥;권오욱
    • 한국음향학회지
    • /
    • 제40권6호
    • /
    • pp.578-586
    • /
    • 2021
  • 종단간 음성인식기의 성능향상을 위한 변분 오토인코더(Variational AutoEncoder, VAE) 및 비교사 데이터 증강(Unsupervised Data Augmentation, UDA) 기반의 준지도 학습 방법을 제안한다. 제안된 방법에서는 먼저 원래의 음성데이터를 이용하여 VAE 기반 증강모델과 베이스라인 종단간 음성인식기를 학습한다. 그 다음, 학습된 증강모델로부터 증강된 데이터를 이용하여 베이스라인 종단간 음성인식기를 다시 학습한다. 마지막으로, 학습된 증강모델 및 종단간 음성인식기를 비교사 데이터 증강 기반의 준지도 학습 방법으로 다시 학습한다. 컴퓨터 모의실험 결과, 증강모델은 기존의 종단간 음성인식기의 단어오류율(Word Error Rate, WER)을 개선하였으며, 비교사 데이터 증강학습방법과 결합함으로써 성능을 더욱 개선하였다.

자가골 블럭 이식을 이용한 수평골 증강술시 이식골의 치유 (THE HISTOLOGIC STUDY OF BONE HEALING AFTER HORIZONTAL RIDGE AUGMENTATION USING AUTO BLOCK BONE GRAFT)

  • 오재권;최병준;이백수
    • Maxillofacial Plastic and Reconstructive Surgery
    • /
    • 제31권3호
    • /
    • pp.207-215
    • /
    • 2009
  • Purpose: The aim of the present study is to evaluate the long term bone healing after horizontal ridge augmentation using auto block bone graft for implant installation timing. Materials and Methods: Five Beagle dogs(which were 14 months old and weighted approximately 10kg). In surgery 1(extraction & bone defect), premolars(P2, P3,P4) were extracted and the buccal bone plate was removed to create a horizontally defected ridge. After three months healing, in surgery 2(ridge augmentation). Auto block bone grafts from the mandibular ramus were used in filling the bone defects were fixed with stabilizing screws. The following fluorochrome labels were given intravenously to the beagle dogs: oxytetracycline 1week after the surgery, alizarin red 4 weeks after the surgery, calcein blue 8 weeks after the surgery. The tissue samples were obtained from the sacrificed dogs of 1, 4, 8, 12, 16 weeks after the surgery. Non-decalcified sections were prepared by resin embedding and microsection to find thickness of $10{\mu}m$ for the histologic examination and analysis. Results: 1. We could achieve the successful reconstruction of the horizontal bone defect by auto block bone graft. The grafted bone block remained stable morohologically after 16 weeks of the surgery. 2. In the histologic view. We observed osteoid tissue from the sample $4^{th}$ week sample and active capillary reconstruction in the grafted bone from the $12^{th}$ week sample. Healing procedures of auto bone grafts were compared to that of the host bone. 3. Bone mineralization could be detected from the $8^{th}$ week sample. 4. Fluorochrome labeling showed active bony changes and formation at the interface of the host bone and the block graft mainly. Bony activation in the grafted bone could be seen from the $4^{th}$ week samples. Conclusions: Active bone formation and remodeling between the grafted bone and host bone can be seen through the revascularization. After the perfect adhesion to host bone, Timing of successful implant installation can be detected through the ideal ridge formation by horizontal ridge augmentation.

변이형 오토인코더를 이용한 탄도미사일 궤적 증강기법 개발 (Development of Augmentation Method of Ballistic Missile Trajectory using Variational Autoencoder)

  • 이동규;홍동욱
    • 시스템엔지니어링학술지
    • /
    • 제19권2호
    • /
    • pp.145-156
    • /
    • 2023
  • Trajectory of ballistic missile is defined by inherent flight dynamics, which decided range and maneuvering characteristics. It is crucial to predict range and maneuvering characteristics of ballistic missile in KAMD (Korea Air and Missile Defense) to minimize damage due to ballistic missile attacks, Nowadays, needs for applying AI(Artificial Intelligence) technologies are increasing due to rapid developments of DNN(Deep Neural Networks) technologies. To apply these DNN technologies amount of data are required for superviesed learning, but trajectory data of ballistic missiles is limited because of security issues. Trajectory data could be considered as multivariate time series including many variables. And augmentation in time series data is a developing area of research. In this paper, we tried to augment trajectory data of ballistic missiles using recently developed methods. We used TimeVAE(Time Variational AutoEncoder) method and TimeGAN(Time Generative Adversarial Networks) to synthesize missile trajectory data. We also compare the results of two methods and analyse for future works.

지적재조사사업의 효율화를 위한 신 기술 적용 방안 (Application of the New Technology for an Efficient Cadastral Re-survey Project)

  • 홍성언
    • 한국산학기술학회논문지
    • /
    • 제14권12호
    • /
    • pp.6196-6203
    • /
    • 2013
  • 본 연구에서는 "지적재조사에 관한 특별법"에서 규정하고 있는 지적측량 기술들의 고찰과 함께 현재 새롭게 대두되고 있는 관련 측량 방법들을 분석해 보았다. 그리고 분석된 내용을 기초로 향후 지적재조사사업에 효율적인 적용 방안을 제시해 보고자 하였다. 분석된 새로운 기술은 GNSS, GPS RTK, Network RTK, GPS Augmentation System 그리고 모바일 및 자동시준 TS이었다. 분석결과 GPS/GLONASS/Galileo 시스템을 통합수신 할 수 있는 수신 기술을 개발한다면 위치결정의 정확도 향상은 물론 안정적인 데이터의 취득이 가능할 것으로 판단된다. Network RTK 기술은 장기적으로는 GPS Augmentation System을 이용한다면 위성정보의 수신 제약요소를 해결할 수 있을 것으로 판단된다. 끝으로 모바일 및 자동시준 TS기술은 인원소요를 줄일 수 있으나 초기화의 문제가 극복되어야 적용이 가능할 것으로 판단되었다.

Clinical application of auto-tooth bone graft material

  • Park, Sung-Min;Um, In-Woong;Kim, Young-Kyun;Kim, Kyung-Wook
    • Journal of the Korean Association of Oral and Maxillofacial Surgeons
    • /
    • 제38권1호
    • /
    • pp.2-8
    • /
    • 2012
  • Introduction: Auto-tooth bone graft material consists of 55% inorganic hydroxyapatite (HA) and 45% organic substances. Inorganic HA possesses properties of bone in terms of the combining and dissociating of calcium and phosphate. The organic substances include bone morphogenetic protein and proteins which have osteoinduction capacity, as well as the type I collagen identical to that found in alveolar bone. Auto-tooth bone graft material is useful as it supports excellent bone regeneration capacity and minimizes the possibility of foreign body reaction,genetic diseases and disease transmission. Materials and Methods: Implant placement combined with osteoinductive regeneration,preservation of extraction socket, maxillary sinus augmentation, and ridge augmentation using block type,powder type, and block+powder type autobone graft materialwere performed for 250 patients with alveolar bone defect and who visited the Department of Oral and Maxillofacial Surgery, College of Dentistry, Dankook University from September 2009 to August 2011. Results: Clinical assessment: Among the 250 patients of auto-tooth bone graft, clinical assessment was performed for 133 cases of implant placement. The average initial stabilization of placed implants was 74 implant stability quotient (ISQ). Radiological assessment: The average loss of crestal bone in the mandible as measured 6 months on the average after the application of prosthesis load was 0.29 mm, ranging from 0 mm to 3.0 mm. Histological assessment: In the histological assessment, formation of new bone, densified lamellated bone, trabecular bones, osteoblast, and planting fixtures were investigated. Conclusion: Based on these results, we concluded that auto-tooth bone graft material should be researched further as a good bone graft material with osteoconduction and osteoinduction capacities to replace autogenous bone, which has many limitations.

오토인코더 기반 수치형 학습데이터의 자동 증강 기법 (Automatic Augmentation Technique of an Autoencoder-based Numerical Training Data)

  • 정주은;김한준;전종훈
    • 한국인터넷방송통신학회논문지
    • /
    • 제22권5호
    • /
    • pp.75-86
    • /
    • 2022
  • 본 연구는 딥러닝 기반 변분 오토인코더(Variational Autoencoder)를 활용하여 수치형 학습데이터 내 클래스 불균형 문제를 해결하고, 학습데이터를 증강하여 학습모델의 성능을 향상시키고자 한다. 우리는 주어진 테이블 데이터에 대하여 인위적으로 레코드 개수를 늘리기 위해 'D-VAE'을 제안한다. 제안 기법은 최적의 데이터 증강을 지원하기 위해 우선 이산화와 특징선택을 수반한 전처리 과정을 수행한다. 이산화 과정에서 k-means 클러스터링을 적용하여 그룹화한 후, 주어진 데이터가 원-핫 인코딩(one-hot encoding) 기법으로 원-핫 벡터(one-hot vector)로 변환한다. 이후, 특징 선택 기법 중 RFECV 기법을 활용하여 예측에 도움이 되는 변수를 가려내고, 이에 대해서만 변분 오토인코더를 활용하여 새로운 학습데이터를 생성한다. 제안 기법의 성능을 검증하기 위해 4가지 유형의 실험 데이터를 활용하여 데이터 증강 비율별로 그 유효성을 입증한다.

Clinical evaluation of ridge augmentation using autogenous tooth bone graft material: case series study

  • Lee, Ji-Young;Kim, Young-Kyun;Yi, Yang-Jin;Choi, Joon-Ho
    • Journal of the Korean Association of Oral and Maxillofacial Surgeons
    • /
    • 제39권4호
    • /
    • pp.156-160
    • /
    • 2013
  • Objectives: Interest in bone graft material has increased with regard to restoration in cases of bone defect around the implant. Autogenous tooth bone graft material was developed and commercialized in 2008. In this study, we evaluated the results of vertical and horizontal ridge augmentation with autogenous tooth bone graft material. Materials and Methods: This study targeted patients who had vertical or horizontal ridge augmentation using AutoBT from March 2009 to April 2010. We evaluated the age and gender of the subject patients, implant stability, adjunctive surgery, additional bone graft material and barrier membrane, post-operative complication, implant survival rate, and crestal bone loss. Results: We performed vertical and horizontal ridge augmentation using powder- or block-type autogenous tooth bone graft material, and implant placement was performed on nine patients (male: 7, female: 2). The average age of patients was $49.88{\pm}12.98$ years, and the post-operative follow-up period was $35{\pm}5.31$ months. Post-operative complications included wound dehiscence (one case), hematoma (one case), and implant osseointegration failure (one case; survival rate: 96%); however, there were no complications related to bone graft material, such as infection. Average marginal bone loss after one-year loading was $0.12{\pm}0.19$ mm. Therefore, excellent clinical results can be said to have been obtained. Conclusion: Excellent clinical results can be said to have been obtained with vertical and horizontal ridge augmentation using autogenous tooth bone graft material.

A Deep Learning Approach for Classification of Cloud Image Patches on Small Datasets

  • Phung, Van Hiep;Rhee, Eun Joo
    • Journal of information and communication convergence engineering
    • /
    • 제16권3호
    • /
    • pp.173-178
    • /
    • 2018
  • Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

진구성 아킬레스 건 파열에 대한 단일 절개 술식을 통한 건이전술 및 재건술 (Reconstruction of Neglected Achilles Tendon Rupture with Flexor Hallucis Longus Augmentation Using One Incision Technique)

  • 박광환;김범수;이진우
    • 대한족부족관절학회지
    • /
    • 제13권1호
    • /
    • pp.23-27
    • /
    • 2009
  • Purpose: The purpose of this study was to evaluate the clinical outcome of neglected Achilles tendon rupture treated with reconstruction and augmentation with flexor hallucis longus (FHL) tendon using one incision technique. Materials and Methods: Between July 2006 and March 2008, eleven patients with neglected Achilles tendon rupture received surgical treatment. Through one incision technique, augmentation with auto FHL tendon transfer was performed using a Bio-Interference screw (Arthrex, Naples, FL) and followed by V-Y advancement (5 cases) or gastronemius fascial turn-down flap procedure (6 cases). After mean follow up of 20.7 months (range, 11.8-33.3 weeks), clinical outcomes were evaluated with Visual Analogue Scale (VAS), American Orthopedic Foot and Ankle Society (AOFAS) score, 10 repetitive double heel raise test, 10 repetitive single heel raise test and subjective satisfaction. Results: The length of the gap after debridement was $5.4{\pm}2.0$ cm. The VAS improved from $4.1{\pm}0.9$ to $1.5{\pm}0.8$ at last follow up (p<0.05). The AOFAS score increased from $38.9{\pm}12.2$ to $91.5{\pm}8.9$ at last follow up (p<0.05). Eight patients were satisfied with excellent results and three were satisfied with good results. All patients were able to perform 10 repetitive double heel raise and nine out of eleven patients were able to perform 10 repetitive single heel raise at last follow up. There were no complications including deep infection or re-rupture. Conclusion: Augmentation with FHL tendon transfer and reconstruction with V-Y advancement or turn-down flap through one incision technique appeared to be effective and safe. This technique is recommendable for the treatment of neglected Achilles tendon rupture.

  • PDF

Breast Auto-Augmentation: A Versatile Method of Breast Rehabilitation-A Retrospective Series of 107 Procedures

  • Kirwan, Laurence;Wazir, Umar;Mokbel, Kefah
    • Archives of Plastic Surgery
    • /
    • 제42권4호
    • /
    • pp.438-445
    • /
    • 2015
  • Background Breast auto-augmentation (BAA) using an inferior pedicle dermoglandular flap aims to redistribute the breast tissue in order to increase the fullness in the upper pole and enhance the central projection of the breast at the time of mastopexy in women who want to avoid implants. The procedure achieves mastopexy and an increase in breast volume. Methods Between 2003 and 2014, 107 BAA procedures were performed in 53 patients (51 bilateral, 2 unilateral and 3 reoperations) with primary or secondary ptosis of the breast associated with loss of fullness in the upper pole (n=45) or undergoing explantation combined with capsulectomy (n=8). Six patients (11.3%) had prior mastopexy and 2 (3.7%) patients had prior reduction mammoplasty. The mean patients' age was 41 years (range, 19-66 years). All patients had preoperative and postoperative photographs and careful preoperative markings. Follow-up ranged from 6 months to 9 years (mean, 6.6 months). Results The range of elevation of the nipple was from 6 to 12 cm (mean, 8 cm). The wounds healed completely with no complications in 50 (94.3%) patients. Three patients had complications including 2 (3.7%) hematomas and 1 (1.9%) partial necrosis of the nipple-areola complex. Three (5.7%) patients were dissatisfied with the level of mastopexy achieved underwent a further procedure. No patient complained of scar hypertrophy. Conclusions BAA is a versatile technique for women with small breasts associated with primary or secondary ptosis. It is also an effective technique for the salvage of breasts after capsulectomy and explantation.