• Steel and Composite Structures
• /
• 제29권6호
• /
• pp.703-716
• /
• 2018

Rapid detection of damages in civil engineering structures, in order to assess their possible disorders and as a result produce competent decision making, are crucial to ensure their health and ultimately enhance the level of public safety. In traditional intelligent health monitoring methods, the features are manually extracted depending on prior knowledge and diagnostic expertise. Inspired by the idea of unsupervised feature learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed here for intelligent health monitoring of civil engineering structures. In the first stage, $Nystr{\ddot{o}}m$ method is used for automatic feature extraction from structural vibration signals. In the second stage, Moving Kernel Principal Component Analysis (MKPCA) is employed to classify the health conditions based on the extracted features. In this paper, KPCA has been implemented in a new form as Moving KPCA for effectively segmenting large data and for determining the changes, as data are continuously collected. Numerical results revealed that the proposed health monitoring system has a satisfactory performance for detecting the damage scenarios of a three-story frame aluminum structure. Furthermore, the enhanced version of KPCA methods exhibited a significant improvement in sensitivity, accuracy, and effectiveness over conventional methods.

• 반도체디스플레이기술학회지
• /
• 제18권2호
• /
• pp.1-5
• /
• 2019

As the number of IOT devices is growing rapidly, various 'see-thru connection' techniques have been reported for efficient communication with them. In this paper, we propose a deep learning based IOT device recognition system for interaction with these devices. The overall system consists of a TensorFlow based deep learning server and two Android apps for data collection and recognition purposes. As the basic neural network model, we adopted Google's inception-v3, and modified the output stage to classify 20 types of IOT devices. After creating a data set consisting of 1000 images of 20 categories, we trained our deep learning network using a transfer learning technology. As a result of the experiment, we achieve 94.5% top-1 accuracy and 98.1% top-2 accuracy.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제35권9호
• /
• pp.547-553
• /
• 2008

본 논문에서는 2 단계 서류 레이아웃 분할 방법을 제안한다. 서류 분할의 1 차 단계는 top-down 계열의 영역 추출로서 모폴로지 기반의 거리 함수를 사용하여 주어진 영상 데이타를 사각형 영역들로 분할한다. 거리 사상 함수를 통한 예비 결과는 성능 개선을 위한 2 차 단계의 입력 변수로 작용한다. 서류 분할의 2차 단계로서 기계 학습 이론을 적용한다. 통계 모델을 따르는 RBF 신경망을 선택하였고, 은닉 층의 설계를 위해 코호넨 네트워크의 자기 조직화 성격을 활용한 데이타 군집화 기법을 기반으로 하였다. 본 논문에서는 300개의 영상에서 추출된 영역 데이타를 통해 학습된 신경망이 1차 단계에서 도출된 예비 결과를 개선함을 연구 결과로 제시하였다.

• 한국가정과교육학회지
• /
• 제23권4호
• /
• pp.87-103
• /
• 2011

본 연구의 목적은 중학교 1학년 기술 가정 교과의 '청소년의 성과 친구관계' 단원을 중심으로 동기 유발 전략을 적용한 ARCS 교수 학습 과정안을 개발하고, 적용 및 평가를 통해 교수 학습 과정안을 수정, 보완하여 제시하는 데 있다. 이를 위해 ADDIE 교수설계 모형을 따라 분석, 설계, 개발, 실행, 평가의 다섯 단계를 거쳤다. 분석 단계에서는 관련 선행연구 분석과 설문조사를 통해 ARCS 동기 유발 전략을 추출하고 교육과정 분석을 통해 학습 내용을 선정하였으며, 설계 단계에서는 각 차시별 수업 내용과 수업 목표를 설정하고 구체적인 동기 유발 전략을 계획하였다. 개발단계에서는 8차시 분량의 교수 학습 과정안과 학생활동지, 수업자료 등을 제작하였고, 실행 단계에서 중학교 1학년 학생들을 대상으로 6차시의 내용에 대해 실제 수업을 실행하였다. 평가 단계에서는 수업실행에 참여한 학생들의 동기유발 전략에 대한 의견과, 수업 실행 교사의 수업일지를 중심으로 현장 적용가능성을 고려하여 교수 학습 과정안을 수정, 보완하였다. 본 연구는 ARCS 동기 유발 전략을 적용하여 교수 학습 과정안을 개발하고, 이를 실행함으로써 적용된 동기 유발 전략들이 학생들에게 실제로 흥미를 끌 수 있는지, 학교 현장에서 사용하기에 적절한지 등을 평가하여 교수 학습 과정안을 수정 보안하는 데 초점을 두었다. 실행 결과 수업에 있어서 '흥미'라는 요소에 대한 학생들의 요구가 매우 높은 것으로 나타났다. 앞으로 다양한 학생들의 호기심을 자극할 수 있도록 앞으로 현장에서 효과적으로 사용할 수 있는 다양한 동기 유발 전략들이 새롭게 개발 보완될 필요가 있다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.29-39
• /
• 2022

Crack detection plays an important role in the maintenance and protection of steel box girder of bridges. However, since the cracks only occupy an extremely small region of the high-resolution images captured from actual conditions, the existing methods cannot deal with this kind of image effectively. To solve this problem, this paper proposed a novel three-stage method based on deep learning technology and morphology operations. The training set and test set used in this paper are composed of 360 images (4928 × 3264 pixels) in steel girder box. The first stage of the proposed model converted high-resolution images into sub-images by using patch-based method and located the region of cracks by CBAM ResNet-50 model. The Recall reaches 0.95 on the test set. The second stage of our method uses the Attention U-Net model to get the accurate geometric edges of cracks based on results in the first stage. The IoU of the segmentation model implemented in this stage attains 0.48. In the third stage of the model, we remove the wrong-predicted isolated points in the predicted results through dilate operation and outlier elimination algorithm. The IoU of test set ascends to 0.70 after this stage. Ablation experiments are conducted to optimize the parameters and further promote the accuracy of the proposed method. The result shows that: (1) the best patch size of sub-images is 1024 × 1024. (2) the CBAM ResNet-50 and the Attention U-Net achieved the best results in the first and the second stage, respectively. (3) Pre-training the model of the first two stages can improve the IoU by 2.9%. In general, our method is of great significance for crack detection.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.73-82
• /
• 2022

Early detection continues to be the mainstay of breast cancer control as well as the improvement of its treatment. Even so, the absence of cancer symptoms at the onset has early detection quite challenging. Therefore, various researchers continue to focus on cancer as a topic of health to try and make improvements from the perspectives of diagnosis, prevention, and treatment. This research's chief goal is development of a system with deep learning for classification of the breast cancer as non-malignant and malignant using mammogram images. The following two distinct approaches: the first one with the utilization of patches of the Region of Interest (ROI), and the second one with the utilization of the overall images is used. The proposed system is composed of the following two distinct stages: the pre-processing stage and the Convolution Neural Network (CNN) building stage. Of late, the use of meta-heuristic optimization algorithms has accomplished a lot of progress in resolving these problems. Teaching-Learning Based Optimization algorithm (TIBO) meta-heuristic was originally employed for resolving problems of continuous optimization. This work has offered the proposals of novel methods for training the Residual Network (ResNet) as well as the CNN based on the TLBO and the Genetic Algorithm (GA). The classification of breast cancer can be enhanced with direct application of the hybrid TLBO- GA. For this hybrid algorithm, the TLBO, i.e., a core component, will combine the following three distinct operators of the GA: coding, crossover, and mutation. In the TLBO, there is a representation of the optimization solutions as students. On the other hand, the hybrid TLBO-GA will have further division of the students as follows: the top students, the ordinary students, and the poor students. The experiments demonstrated that the proposed hybrid TLBO-GA is more effective than TLBO and GA.

• ETRI Journal
• /
• 제44권6호
• /
• pp.915-924
• /
• 2022

In this paper, we present a two-stage scalable channel estimator (TSCE), a deep learning (DL)-based scalable, and robust channel estimator for wireless cellular networks, which is made up of two DL networks to efficiently support different resource allocation sizes and reference signal configurations. Both networks use the transformer, one of cutting-edge neural network architecture, as a backbone for accurate estimation. For computation-efficient global feature extractions, we propose using window and window averaging-based self-attentions. Our results show that TSCE learns wireless propagation channels correctly and outperforms both traditional estimators and baseline DL-based estimators. Additionally, scalability and robustness evaluations are performed, revealing that TSCE is more robust in various environments than the baseline DL-based estimators.

• 대한전기학회논문지
• /
• 제40권4호
• /
• pp.374-381
• /
• 1991

As a diagnostic image of hospitl, the utilization of digital image is steadily increasing. Image coding is indispensable for storing and compressing an enormous amount of diagnostic images economically and effectively. In this paper adaptive two stage vector quantization based on Kohonen's neural network for the compression of cardioangiography among typical angiography of radiographic image sequences is presented and the performance of the coding scheme is compare and gone over. In an attempt to exploit the known characteristics of changes in cardioangiography, relatively large blocks of image are quantized in the first stage and in the next stage the bloks subdivided by the threshold of quantization error are vector quantized employing the neural network of frequency sensitive competitive learning. The scheme is employed because the change produced in cardioangiography is due to such two types of motion as a heart itself and body motion, and a contrast dye material injected. Computer simulation shows that the good reproduction of images can be obtained at a bit rate of 0.78 bits/pixel.

• Journal of information and communication convergence engineering
• /
• 제5권1호
• /
• pp.50-53
• /
• 2007

This paper presents face features detection and a new physiological neuro-fuzzy learning method by using two-dimensional variances based on variation of gray level and by learning for a statistical distribution of the detected face features. This paper reports a method to learn by not using partial face image but using global face image. Face detection process of this method is performed by describing differences of variance change between edge region and stationary region by gray-scale variation of global face having featured regions including nose, mouse, and couple of eyes. To process the learning stage, we use the input layer obtained by statistical distribution of the featured regions for performing the new physiological neuro-fuzzy algorithm.

• Nuclear Engineering and Technology
• /
• 제55권1호
• /
• pp.285-294
• /
• 2023

Autonomous radiation source detection has long been studied for radiation emergencies. Compared to conventional data-driven or path planning methods, deep reinforcement learning shows a strong capacity in source detection while still lacking the generalized ability to the geometry in unknown environments. In this work, the detection task is decomposed into two subtasks: exploration and localization. A hierarchical control policy (HC) is proposed to perform the subtasks at different stages. The low-level controller learns how to execute the individual subtasks by deep reinforcement learning, and the high-level controller determines which subtasks should be executed at the current stage. In experimental tests under different geometrical conditions, HC achieves the best performance among the autonomous decision policies. The robustness and generalized ability of the hierarchy have been demonstrated.