• 제목/요약/키워드: Training Samples

검색결과 570건 처리시간 0.023초

UWB 시스템에서 합성곱 신경망을 이용한 거리 추정 (Distance Estimation Using Convolutional Neural Network in UWB Systems)

  • 남경모;정태윤;정성훈;정의림
    • 한국정보통신학회논문지
    • /
    • 제23권10호
    • /
    • pp.1290-1297
    • /
    • 2019
  • 본 논문에서는 ultra-wideband(UWB) 시스템에서 합성곱 신경망(CNN)을 이용한 거리 추정 기법을 제안한다. 제안하는 기법은 UWB 신호를 이용하여 송신기와 수신기 사이의 거리를 추정하기 위하여 수신신호의 크기 샘플로 이루어진 1차원 벡터를 2차원 행렬로 재구성하며, 이 2차원 행렬로부터 합성곱 신경망 회귀를 이용하여 거리를 추정한다. IEEE 802.15.4a 표준의 UWB 실내 가시선 채널모델을 이용하여 수신신호를 생성하여 학습데이터를 만들며 합성곱 신경망 모델을 학습시킨다. 또한 실제 필드 시험을 통해 실내환경에서의 실험 데이터를 이용하여 거리추정 성능을 확인한다. 제안하는 기법은 기존의 문턱값 기반의 거리 추정 기법과의 성능비교도 수행하는데, 결과에 따르면 10m 거리에서 제안기법은 0.6m의 제곱근 평균 자승 에러를 보이는데 기존기법은 1.6m로 훨씬 큰 에러를 보인다.

객체 감지 데이터 셋 기반 인체 자세 인식시스템 연구 (Research on Human Posture Recognition System Based on The Object Detection Dataset)

  • 유암;리라이춘;루징쉬엔;쉬멍;정양권
    • 한국전자통신학회논문지
    • /
    • 제17권1호
    • /
    • pp.111-118
    • /
    • 2022
  • 컴퓨터 비전 연구에서 2차원 인체 자세는 매우 광범위한 연구 방향으로 특히 자세 추적과 행동 인식에서 유의미한 분야다. 인체 자세 표적 획득은 이미지에서 인체 목표를 정확히 찾는 방법을 연구하는 것이 핵심이며 인체 자세 인식은 인공지능(AI)에 적용하는 한편 일상생활에 활용되고 있어서 매우 중요한 연구의의가 있다. 인체 자세 인식 효과의 우수성의 기준은 인식 과정의 성공률과 정확도에 의해 결정된다. 본 연구의 인체 자세 인식에서는 딥러닝 전용 데이터셋인 MS COCO를 기반하여 인체를 17개의 키 포인트로 구분하였다. 다음으로 주요 특징에 대한 세분화 마스크(segmentation mask) 방법을 사용하여 인식률을 개선하였다. 최종적으로 신경망 모델을 설계하고 간단한 단계별 학습부터 효율적인 학습에 이르기까지 많은 수의 표본을 학습시키는 알고리즘을 제안하여 정확도를 향상할 수 있었다.

섬유 드레이프 이미지를 활용한 드레이프 생성 모델 구현에 관한 연구 (A Study on the implementation of the drape generation model using textile drape image)

  • 손재익;김동현;최윤성
    • 스마트미디어저널
    • /
    • 제10권4호
    • /
    • pp.28-34
    • /
    • 2021
  • 드레이프는 의상의 외형을 결정하는 요인 중 하나로 섬유·패션 산업에서 매우 중요한 요소 중 하나이다. 코로나 바이러스의 영향으로 비대면 거래가 활성화되고 있는 시점에서, 드레이프값을 요구하는 업체들이 많아지고 있다. 하지만 중소기업이나 영세 기업의 경우, 드레이프를 측정하는 것에 대한 시간과 비용적 부담을 느껴, 드레이프를 측정하는 데에 어려움을 겪고 있다. 따라서 본 연구는 디지털 물성을 측정하여 생성된 3D 시뮬레이션 이미지를 통해 조건부 적대적 생성 신경망을 이용하여 입력된 소재의 물성값에 대한 드레이프 이미지 생성을 목표로 하였다. 기존 보유한 736개의 디지털 물성값을 통해, 드레이프 이미지를 생성하였으며, 이를 모델 학습에 이용하였다. 이후 생성 모델을 통해 나온 이미지 샘플에 대하여 드레이프 값을 계산하였다. 실제 드레이프 실험 값과 생성 드레이프 값 비교결과, 첨두수의 오차는 0.75개였으며, 드레이프값의 평균 오차는 7.875의 오차를 보임을 확인할 수 있었다.

자연어 처리 기반 멀티 소스 이벤트 로그의 보안 심각도 다중 클래스 분류 (A Multiclass Classification of the Security Severity Level of Multi-Source Event Log Based on Natural Language Processing)

  • 서양진
    • 정보보호학회논문지
    • /
    • 제32권5호
    • /
    • pp.1009-1017
    • /
    • 2022
  • 로그 데이터는 정보 시스템의 주요 동작과 상태를 이해하고 판단하는 근거로 사용되어 왔으며, 여러 보안 분야 응용에서도 중요한 입력 데이터로 사용된다. 로그 데이터로부터 필요한 정보를 얻어 이를 근거로 의사 결정을 하고, 적절한 대응 방안을 취하는 것은 시스템을 보호하고 안정적으로 운영하는 데 있어 필수적인 요소이지만, 로그의 종류와 양이 폭발적으로 증가함에 따라 기존 도구들로는 효과적이고 효율적인 대응이 쉽지 않은 상황이다. 이에 본 연구에서는 자연어 처리 기반의 머신 러닝을 이용해 멀티 소스 이벤트 로그의 보안 심각도를 여러 단계로 분류하는 방법을 제안하였으며, 472,972건의 훈련 및 테스트 샘플을 이용하여 실험을 수행한 결과 99.59%의 정확도를 달성하였다.

2D-MELPP: A two dimensional matrix exponential based extension of locality preserving projections for dimensional reduction

  • Xiong, Zixun;Wan, Minghua;Xue, Rui;Yang, Guowei
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제16권9호
    • /
    • pp.2991-3007
    • /
    • 2022
  • Two dimensional locality preserving projections (2D-LPP) is an improved algorithm of 2D image to solve the small sample size (SSS) problems which locality preserving projections (LPP) meets. It's able to find the low dimension manifold mapping that not only preserves local information but also detects manifold embedded in original data spaces. However, 2D-LPP is simple and elegant. So, inspired by the comparison experiments between two dimensional linear discriminant analysis (2D-LDA) and linear discriminant analysis (LDA) which indicated that matrix based methods don't always perform better even when training samples are limited, we surmise 2D-LPP may meet the same limitation as 2D-LDA and propose a novel matrix exponential method to enhance the performance of 2D-LPP. 2D-MELPP is equivalent to employing distance diffusion mapping to transform original images into a new space, and margins between labels are broadened, which is beneficial for solving classification problems. Nonetheless, the computational time complexity of 2D-MELPP is extremely high. In this paper, we replace some of matrix multiplications with multiple multiplications to save the memory cost and provide an efficient way for solving 2D-MELPP. We test it on public databases: random 3D data set, ORL, AR face database and Polyu Palmprint database and compare it with other 2D methods like 2D-LDA, 2D-LPP and 1D methods like LPP and exponential locality preserving projections (ELPP), finding it outperforms than others in recognition accuracy. We also compare different dimensions of projection vector and record the cost time on the ORL, AR face database and Polyu Palmprint database. The experiment results above proves that our advanced algorithm has a better performance on 3 independent public databases.

Structural health monitoring response reconstruction based on UAGAN under structural condition variations with few-shot learning

  • Jun, Li;Zhengyan, He;Gao, Fan
    • Smart Structures and Systems
    • /
    • 제30권6호
    • /
    • pp.687-701
    • /
    • 2022
  • Inevitable response loss under complex operational conditions significantly affects the integrity and quality of measured data, leading the structural health monitoring (SHM) ineffective. To remedy the impact of data loss, a common way is to transfer the recorded response of available measure point to where the data loss occurred by establishing the response mapping from measured data. However, the current research has yet addressed the structural condition changes afterward and response mapping learning from a small sample. So, this paper proposes a novel data driven structural response reconstruction method based on a sophisticated designed generating adversarial network (UAGAN). Advanced deep learning techniques including U-shaped dense blocks, self-attention and a customized loss function are specialized and embedded in UAGAN to improve the universal and representative features extraction and generalized responses mapping establishment. In numerical validation, UAGAN efficiently and accurately captures the distinguished features of structural response from only 40 training samples of the intact structure. Besides, the established response mapping is universal, which effectively reconstructs responses of the structure suffered up to 10% random stiffness reduction or structural damage. In the experimental validation, UAGAN is trained with ambient response and applied to reconstruct response measured under earthquake. The reconstruction losses of response in the time and frequency domains reached 16% and 17%, that is better than the previous research, demonstrating the leading performance of the sophisticated designed network. In addition, the identified modal parameters from reconstructed and the corresponding true responses are highly consistent indicates that the proposed UAGAN is very potential to be applied to practical civil engineering.

뷰티관광 활성화를 위한 교육과정 개선 방안 연구: IPA를 중심으로 (The Study on the Improvement of Curriculum for the Development of Beauty Tourism: Focusing on IPA)

  • 황영아;엄문연
    • 디지털융복합연구
    • /
    • 제20권5호
    • /
    • pp.233-238
    • /
    • 2022
  • 본 연구는 뷰티관광 교육과정의 중요도-만족도의 차이를 분석하여 뷰티관광 활성화를 위한 교육과정의 개선을 목적으로 한다. 뷰티관광산업 종사자를 대상으로 온·오프라인 설문조사를 실시하였으며 208개의 유효표본을 활용하여 IPA분석을 실시하였다. 분석결과, 모든 교육내용에 대한 중요도와 만족도는 차이가 있는 것으로 나타났다. 또한 개선이 필요한 교육내용은 없는 것으로 나타났으며 지속 및 유지가 필요한 교육과정은 현장실습, 전공실무, 서비스 및 매너, 고객상담, 고객관리, 마케팅, 대인관계 등으로 나타났다. 우선순위가 낮은 교육내용은 외국어, 다문화 이해, 관광학, 뷰티경영 등으로 나타났으며 과잉 노력을 지양이 필요한 교육내용은 전공 이론인 것으로 나타났다. 연구 결과를 바탕으로 뷰티관광 활성화를 위한 교육과정 개선 방향을 제시하였다.

A standardized method to study immune responses using porcine whole blood

  • Sameer-ul-Salam Mattoo;Ram Prasad Aganja;Seung-Chai Kim;Chang-Gi Jeong;Salik Nazki;Amina Khatun;Won-Il Kim;Sang-Myeong Lee
    • Journal of Veterinary Science
    • /
    • 제24권1호
    • /
    • pp.11.1-11.14
    • /
    • 2023
  • Background: Peripheral blood mononuclear cells (PBMCs) are commonly used to assess in vitro immune responses. However, PBMC isolation is a time-consuming procedure, introduces technical variability, and requires a relatively large volume of blood. By contrast, whole blood assay (WBA) is faster, cheaper, maintains more physiological conditions, and requires less sample volume, laboratory training, and equipment. Objectives: Herein, this study aimed to develop a porcine WBA for in vitro evaluation of immune responses. Methods: Heparinized whole blood (WB) was diluted (non-diluted, 1/2, 1/8, and 1/16) in RPMI-1640 media, followed by phorbol myristate acetate and ionomycin. After 24 h, cells were stained for interferon (IFN)-γ secreting T-cells followed by flow cytometry, and the supernatant was analyzed for tumor necrosis factor (TNF)-α. In addition, diluted WB was stimulated by lipopolysaccharide (LPS) and polyinosinic:polycytidylic acid (poly I:C), reference strain KCTC3557 (RS), field isolate (FI), of heat-killed (HK) Streptococcus suis, and porcine reproductive and respiratory syndrome virus (PRRSV). Results: The frequency of IFN-γ+CD3+ T-cells and concentration of TNF-α in the supernatant of WB increased with increasing dilution factor and were optimal at 1/8. WB TNF-α and interleukin (IL)-10 cytokine levels increased significantly following stimulation with LPS or poly I:C. Further, FI and RS induced IL-10 production in WB. Additionally, PRRSV strains increased the frequency of IFN-γ+ CD4-CD8+ cells, and IFN-γ was non-significantly induced in the supernatant of re-stimulated samples. Conclusions: We propose that the WBA is a rapid, reliable, and simple method to evaluate immune responses and WB should be diluted to trigger immune cells.

감각통합중재에 대한 인식도 및 취업선호도에 대한 교육프로그램의 효과 및 필요성 연구 : 작업치료전공 대학생을 중심으로 (A Study on the Effects and Needs of Educational Programs on Awareness and Preference for Sensory Integration Intervention : Focusing on college students in the department of occupational therapy)

  • 김시은;장철
    • 대한통합의학회지
    • /
    • 제11권1호
    • /
    • pp.113-120
    • /
    • 2023
  • Purpose : This study aims to investigate occupational therapy students' perceptions of sensory integration therapy and the effect of an educational program on these perceptions and future preferences. Methods : The participants were 200 occupational therapy students in Busan and Gyeongsangnam-do. A primary survey was first conducted to shed light on students' perceptions of sensory integration therapy, followed by an education program on sensory integration provided through an online video. After this training on sensory integration therapy, an additional survey assessed the their preferred employment routes and intention to take educational courses on clinical sensory integration therapy in the future. A secondary survey was then conducted, using the same form as the primary survey, to identify changes in the students' perceptions of and preferences for sensory integration therapy. A frequency analysis using descriptive statistics was employed to identify the participants' general characteristics, employment-related preferences, and intention to take courses on sensory integration, and a paired samples t-test was used for a comparative analysis of the students' perceptions before and after the education program. Results : In terms of the students' perceptions of sensory integration therapy, the variables of efficiency, facilitation, and expertise showed statistically significant differences before and after the educational program, which resulted in a positive change in their overall perceptions of the therapy after the program. In relation to their preferred employment routes after the program, 100 students (50 %) answered the "field of adults," and 100 (50 %) students answered the "field of children." Conclusion : The findings of this study demonstrated that sensory integration education positively influences occupational therapy students' preferences for and perceptions of sensory integration therapy. Additional research is recommended to organize a more systematic education program and investigate employees in organizations related to children with disabilities.

Metaheuristic models for the prediction of bearing capacity of pile foundation

  • Kumar, Manish;Biswas, Rahul;Kumar, Divesh Ranjan;T., Pradeep;Samui, Pijush
    • Geomechanics and Engineering
    • /
    • 제31권2호
    • /
    • pp.129-147
    • /
    • 2022
  • The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R2 = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R2 = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.