• Smart Structures and Systems
• /
• 제19권4호
• /
• pp.341-350
• /
• 2017

Based on the super elastic properties of the shape memory alloy (SMA) and the inverse piezoelectric effect of piezoelectric (PZT) ceramics, a kind of hybrid semi-active control device was designed and made, its mechanical properties test was done under different frequency and different voltage. The local search ability of genetic algorithm is poor, which would fall into the defect of prematurity easily. A kind of adaptive immune memory cloning algorithm(AIMCA) was proposed based on the simulation of clone selection and immune memory process. It can adjust the mutation probability and clone scale adaptively through the way of introducing memory cell and antibody incentive degrees. And performance indicator based on the modal controllable degree was taken as antigen-antibody affinity function, the optimization analysis of damper layout in a space truss structure was done. The structural seismic response was analyzed by applying the neural network prediction model and T-S fuzzy logic. Results show that SMA and PZT friction composite damper has a good energy dissipation capacity and stable performance, the bigger voltage, the better energy dissipation ability. Compared with genetic algorithm, the adaptive immune memory clone algorithm overcomes the problem of prematurity effectively. Besides, it has stronger global searching ability, better population diversity and faster convergence speed, makes the damper has a better arrangement position in structural dampers optimization leading to the better damping effect.

• 전자공학회논문지C
• /
• 제36C권6호
• /
• pp.44-51
• /
• 1999

HMM-Net은 은닉 마르코프 모델(HMM)의 계산과정을 신경망 구조로 구현한 것으로, HMM이 갖고 있는 시계열 모델링 능력과 신경망이 갖고 있는 우수한 변별력을 결합한 것이다. HMM-Net 분류기를 학습하는 방법으로는 HMM의 학습에 이용되는 最尤法(ML)과 신경망 학습의 最小二乘誤差法(MMSE)를 적용할 수 있다. 이들 중 ML이 MMSE보다 안정된 학습을 보장하는 반면 초기 학습조건을 적절하게 설정하였을 경우에는 MMSE가 ML보다 우수하다고 알려져 있다[3]. 따라서 이 논문에서는 먼저 ML을 이용하여 초기학습을 수행한 다음 보다 학습성능이 우수한 MMSE로 바꾸어 최적 또는 준최적으로 학습하는 하이브리드 학습법(ML/MMSE)을 제안한다. 실험용 시계열 패턴으로 /0/부터 /9/까지의 고립 숫자음을 이용하여 실험한 결과, 제안한 방법이 학습특성 및 인식률면에서 ML이나 MMSE만을 이용하는 기존의 방법보다 우수하였음을 확인하였다.

• Imaging Science in Dentistry
• /
• 제53권4호
• /
• pp.271-281
• /
• 2023

Purpose: The objective of this scoping review was to investigate the applicability and performance of various convolutional neural network (CNN) models in tooth numbering on panoramic radiographs, achieved through classification, detection, and segmentation tasks. Materials and Methods: An online search was performed of the PubMed, Science Direct, and Scopus databases. Based on the selection process, 12 studies were included in this review. Results: Eleven studies utilized a CNN model for detection tasks, 5 for classification tasks, and 3 for segmentation tasks in the context of tooth numbering on panoramic radiographs. Most of these studies revealed high performance of various CNN models in automating tooth numbering. However, several studies also highlighted limitations of CNNs, such as the presence of false positives and false negatives in identifying decayed teeth, teeth with crown prosthetics, teeth adjacent to edentulous areas, dental implants, root remnants, wisdom teeth, and root canal-treated teeth. These limitations can be overcome by ensuring both the quality and quantity of datasets, as well as optimizing the CNN architecture. Conclusion: CNNs have demonstrated high performance in automated tooth numbering on panoramic radiographs. Future development of CNN-based models for this purpose should also consider different stages of dentition, such as the primary and mixed dentition stages, as well as the presence of various tooth conditions. Ultimately, an optimized CNN architecture can serve as the foundation for an automated tooth numbering system and for further artificial intelligence research on panoramic radiographs for a variety of purposes.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2021년도 제63차 동계학술대회논문집 29권1호
• /
• pp.221-223
• /
• 2021

본 논문에서는 손동작 데이터에서 추출한 데이터를 다변수 시계열 데이터 분류를 자동으로 찾는 NAS 모델에 적용하여 손동작 인식 모델을 찾는 방법을 제안한다. NAS를 통해 모델을 구하는 과정은 프로그래머의 시간과 노력을 절감시켜준다. 손동작 인식을 위해 DHG-14/28 데이터셋과 SHREC'17 Track 데이터셋에 논문에서 제안한 방법을 적용하여 손동작 인식 정확도가 기존의 모델보다 높은 손동작 인식률을 얻음을 실험을 통하여 확인하였다. 실험에서 DHG-14/28 데이터셋의 손동작 인식 정확도는 96.38%, 96.63%, SHREC'17 Track 데이터셋의 정확도는 96.88%, 96.57%를 얻었다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2023년도 제35회 한글 및 한국어 정보처리 학술대회
• /
• pp.125-130
• /
• 2023

최근 심층 신경망을 활용한 한국어 자연어 처리에 대한 관심이 높아지고 있지만, 한국어 자연어 처리에 적합한 신경망 구조 탐색에 대한 연구는 이뤄지지 않았다. 본 논문에서는 문서 분류 정확도를 보상으로 하는 강화 학습 알고리즘을 이용하여 장단기 기억 신경망으로 한국어 문서 분류에 적합한 심층 신경망 구조를 탐색하였으며, 탐색을 위해 사전 학습한 한국어 임베딩 성능과 탐색한 신경망 구조를 분석하였다. 탐색을 통해 찾아낸 신경망 구조는 기존 한국어 자연어 처리 모델에 대해 4 가지 한국어 문서 분류 과제로 비교하였을 때 일반적으로 성능이 우수하고 모델의 크기가 작아 효율적이었다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권6호
• /
• pp.264-273
• /
• 2006

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) by means of consecutive optimization and also discuss its comprehensive design methodology involving mechanisms of genetic optimization. The network is based on a structurally as well as parametrically optimized fuzzy polynomial neurons (FPNs) conducted with the aid of information granulation and genetic algorithms. In structurally identification of FPN, the design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics and addresses specific aspects of parametric optimization. In addition, the fuzzy rules used in the networks exploit the notion of information granules defined over system's variables and formed through the process of information granulation. That is, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. This granulation is realized with the aid of the hard c-menas clustering method (HCM). For the parametric identification, we obtained the effective model that the axes of MFs are identified by GA to reflect characteristic of given data. Especially, the genetically dynamic search method is introduced in the identification of parameter. It helps lead to rapidly optimal convergence over a limited region or a boundary condition. To evaluate the performance of the proposed model, the model is experimented with using two time series data(gas furnace process, nonlinear system data, and NOx process data).

• 한국산업융합학회 논문집
• /
• 제26권1호
• /
• pp.113-119
• /
• 2023

In this paper, we propose an optimization of a pose estimation deep learning model for recognition of abnormal behavior in unmanned stores using radio frequencies. The radio frequency use millimeter wave in the 30 GHz to 300 GHz band. Due to the short wavelength and strong straightness, it is a frequency with less grayness and less interference due to radio absorption on the object. A millimeter wave radar is used to solve the problem of personal information infringement that may occur in conventional CCTV image-based pose estimation. Deep learning-based pose estimation models generally use convolution neural networks. The convolution neural network is a combination of convolution layers and pooling layers of different types, and there are many cases of convolution filter size, number, and convolution operations, and more cases of combining components. Therefore, it is difficult to find the structure and components of the optimal posture estimation model for input data. Compared with conventional millimeter wave-based posture estimation studies, it is possible to explore the structure and components of the optimal posture estimation model for input data using genetic algorithms, and the performance of optimizing the proposed posture estimation model is excellent. Data are collected for actual unmanned stores, and point cloud data and three-dimensional keypoint information of Kinect Azure are collected using millimeter wave radar for collapse and property damage occurring in unmanned stores. As a result of the experiment, it was confirmed that the error was moored compared to the conventional posture estimation model.

• 대한원격탐사학회지
• /
• 제37권5_1호
• /
• pp.1149-1161
• /
• 2021

컴퓨터 비전 기술이 위성영상에 적용되면서, 최근 들어 딥러닝 영상인식을 이용한 구름 탐지가 관심을 끌고 있다. 본연구에서는 SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset과 영상자료증대 기법을 활용하여 U-Net 구름탐지 모델링을 수행하고, 10폴드 교차검증을 통해 객관적인 정확도 평가를 수행하였다. 512×512 화소로 구성된 1800장의 학습자료에 대한 암맹평가 결과, Accuracy 0.821, Precision 0.847, Recall 0.821, F1-score 0.831, IoU (Intersection over Union) 0.723의 비교적 높은 정확도를 나타냈다. 그러나 구름그림자 중 14.5%, 구름 중 19.7% 정도가 땅으로 잘못 예측되기도 했는데, 이는 학습자료의 양과 질을 보다 더 향상시킴으로써 개선 가능할 것으로 보인다. 또한 최근 각광받고 있는 DeepLab V3+ 모델이나 NAS(Neural Architecture Search) 최적화 기법을 통해 차세대중형위성 1, 2, 4호 등의 구름탐지에 활용 가능할 것으로 기대한다.

• 한국컴퓨터정보학회논문지
• /
• 제25권5호
• /
• pp.11-18
• /
• 2020

본 연구는 컨베이어 시스템에서 딥러닝을 이용한 배출구 막힘 판단 기술에 대하여 제안한다. 제안 방법은 산업 현장의 CCTV에서 수집한 영상을 이용하여 배출구 막힘 판단을 위한 다양한 CNN 모델들을 학습시키고, 성능이 가장 좋은 모델을 사용하여 실제 공정에 적용하는 것을 목적으로 한다. CNN 모델로는 잘 알려진 VGGNet, ResNet, DenseNet, 그리고 NASNet을 사용하였으며, 모델 학습과 성능 테스트를 위하여 CCTV에서 수집한 18,000장의 영상을 이용하였다. 다양한 모델에 대한 실험 결과, VGGNet은 99.89%의 정확도와 29.05ms의 처리 시간으로 가장 좋은 성능을 보였으며, 이로부터 배출구 막힘 판단 문제에 VGGNet이 가장 적합함을 확인하였다.

• Steel and Composite Structures
• /
• 제51권4호
• /
• pp.441-456
• /
• 2024

This paper aims to develop Machine Learning (ML) algorithms to predict the buckling resistance of cold-formed steel (CFS) channels with restrained flanges, widely used in typical CFS sheathed wall panels, and provide practical design tools for engineers. The effects of cross-sectional restraints were first evaluated on the elastic buckling behaviour of CFS channels subjected to pure axial compressive load or bending moment. Feedforward multi-layer Artificial Neural Networks (ANNs) were then trained on different datasets comprising CFS channels with various dimensions and properties, plate thicknesses, and restraining conditions on one or two flanges, while the elastic distortional buckling resistance of the elements were determined according to the Finite Strip Method (FSM). To develop less biased networks and ensure that every observation from the original dataset has the chance of appearing in the training and test set, a K-fold cross-validation technique was implemented. In addition, the hyperparameters of the ANNs were tuned using a grid search technique to provide ANNs with optimum performances. The results demonstrated that the trained ANNs were able to predict the elastic distortional buckling resistance of CFS flange-restrained elements with an average accuracy of 99% in terms of coefficient of determination. The developed models were then used to propose a simple ANN-based design formula for the prediction of the elastic distortional buckling stress of CFS flange-restrained elements. Finally, the proposed formula was further evaluated on a separate set of unseen data to ensure its accuracy for practical applications.