• 한국정보통신학회논문지
• /
• 제22권12호
• /
• pp.1596-1603
• /
• 2018

화재에 대한 신속한 예측과 경고는 인명 및 재산피해를 최소화시킬 수 있는 필수적인 요소이다. 일반적으로 화재가 발생하면 연기와 화염이 함께 발생하기 때문에 화재 감지 시스템은 연기와 화염을 모두 감지할 필요가 있다. 그러나 대부분의 화재 감지 시스템은 화염 혹은 연기만 감지하며, 화재 감지를 위한 전처리 작업을 추가함에 따라 처리 속도가 느려지는 단점이 있다. 본 연구에서는 다중 레이블 분류(Multi-labeled Classification)를 지원하는 CNN 모델을 구성해서 화염과 연기를 동시에 예측하고, CNN의 특징을 기반으로 클래스에 대한 위치를 시각화하는 Grad-CAM을 이용해서 실시간으로 화재 상태를 모니터링 할 수 있는 화재 감지 시스템을 구현하였다. 또한, 13개의 화재 동영상을 사용해서 테스트한 결과, 화염과 연기에 대해 각각 98.73%와 95.77%의 정확도를 보였다.

• 대한치과교정학회지
• /
• 제51권2호
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1310-1319
• /
• 2016

Face detection is the first step in a wide range of face applications. However, detecting faces in the wild is still a challenging task due to the wide range of variations in pose, scale, and occlusions. Recently, many deep learning methods have been proposed for face detection. However, further improvements are required in the wild. Another important issue to be considered in the face detection is the computational complexity. Current state-of-the-art deep learning methods require a large number of patches to deal with varying scales and the arbitrary image sizes, which result in an increased computational complexity. To reduce the complexity while achieving better detection accuracy, we propose a fully convolutional network-based face detection that can take arbitrarily-sized input and produce feature maps (heat maps) corresponding to the input image size. To deal with the various face scales, a multi-scale network architecture that utilizes the facial components when learning the feature maps is proposed. On top of it, we design multi-task learning technique to improve detection performance. Extensive experiments have been conducted on the FDDB dataset. The experimental results show that the proposed method outperforms state-of-the-art methods with the accuracy of 82.33% at 517 false alarms, while improving computational efficiency significantly.

• 한국정보통신학회논문지
• /
• 제26권10호
• /
• pp.1551-1558
• /
• 2022

본 논문에서는 FEC (Fog/Edge Computing) 환경에서 다중 분기구조의 부분 오프로딩을 위해 모바일 장치와 에지서버로 구성된 2계층 협력 컴퓨팅 시스템을 제안한다. 제안 시스템은 다중 분기구조에 대한 재구성 선형화 기법을 적용하여 응용 서비스 처리를 분할하는 알고리즘과 모바일 장치와 에지 서버 간의 부분 오프로딩을 통한 최적의 협업 알고리즘을 포함한다. 또한 계산 오프로딩 및 CNN 계층 스케줄링을 지연시간 최소화 문제로 공식화하고 시뮬레이션을 통해 제안 시스템의 효과를 분석한다. 실험 결과 제안 알고리즘은 DAG 및 체인 토폴로지 모두에 적합하고 다양한 네트워크 조건에 잘 적응할 수 있으며, 로컬이나 에지 전용 실행과 비교하여 효율적인 작업 처리 전략 및 처리시간을 제공한다. 또한 제안 시스템은 모바일 장치에서의 응용 서비스 최적 실행을 위한 모델의 경량화 및 에지 리소스 워크로드의 효율적 분배 관련 연구에 적용 가능하다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1610-1629
• /
• 2021

Failures frequently occurred in manufacturing machines due to complex and changeable manufacturing environments, increasing the downtime and maintenance costs. This manuscript develops a novel deep learning-based method named Multi-Domain Convolutional Neural Network (MDCNN) to deal with this challenging task with vibration signals. The proposed MDCNN consists of time-domain, frequency-domain, and statistical-domain feature channels. The Time-domain channel is to model the hidden patterns of signals in the time domain. The frequency-domain channel uses Discrete Wavelet Transformation (DWT) to obtain the rich feature representations of signals in the frequency domain. The statistic-domain channel contains six statistical variables, which is to reflect the signals' macro statistical-domain features, respectively. Firstly, in the proposed MDCNN, time-domain and frequency-domain channels are processed by CNN individually with various filters. Secondly, the CNN extracted features from time, and frequency domains are merged as time-frequency features. Lastly, time-frequency domain features are fused with six statistical variables as the comprehensive features for identifying the fault. Thereby, the proposed method could make full use of those three domain-features for fault diagnosis while keeping high distinguishability due to CNN's utilization. The authors designed massive experiments with 10-folder cross-validation technology to validate the proposed method's effectiveness on the CWRU bearing data set. The experimental results are calculated by ten-time averaged accuracy. They have confirmed that the proposed MDCNN could intelligently, accurately, and timely detect the fault under the complex manufacturing environments, whose accuracy is nearly 100%.

• 방송공학회논문지
• /
• 제23권3호
• /
• pp.351-360
• /
• 2018

인간 감정 인식은 컴퓨터 비전 및 인공 지능 영역에서 지속적인 관심을 받는 연구 주제이다. 본 논문에서는 wild 환경에서 이미지, 얼굴 특징점 및 음성신호로 구성된 multi-modal 신호를 기반으로 여러 신경망을 통해 인간의 감정을 분류하는 방법을 제안한다. 제안 방법은 다음과 같은 특징을 갖는다. 첫째, multi task learning과 비디오의 시공간 특성을 이용한 준 감독 학습을 사용함으로써 영상 기반 네트워크의 학습 성능을 크게 향상시켰다. 둘째, 얼굴의 1 차원 랜드 마크 정보를 2 차원 영상으로 변환하는 모델을 새로 제안하였고, 이를 바탕으로 한 CNN-LSTM 네트워크를 제안하여 감정 인식을 향상시켰다. 셋째, 특정 감정에 오디오 신호가 매우 효과적이라는 관측을 기반으로 특정 감정에 robust한 오디오 심층 학습 메커니즘을 제안한다. 마지막으로 소위 적응적 감정 융합 (emotion adaptive fusion)을 적용하여 여러 네트워크의 시너지 효과를 극대화한다. 제안 네트워크는 기존의 지도 학습과 반 지도학습 네트워크를 적절히 융합하여 감정 분류 성능을 향상시켰다. EmotiW2017 대회에서 주어진 테스트 셋에 대한 5번째 시도에서, 제안 방법은 57.12 %의 분류 정확도를 달성하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.192-198
• /
• 2024

This paper investigates the application of multi-agent deep reinforcement learning in the fighting game Samurai Shodown using Proximal Policy Optimization (PPO) and Advantage Actor-Critic (A2C) algorithms. Initially, agents are trained separately for 200,000 timesteps using Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) with LSTM networks. PPO demonstrates superior performance early on with stable policy updates, while A2C shows better adaptation and higher rewards over extended training periods, culminating in A2C outperforming PPO after 1,000,000 timesteps. These findings highlight PPO's effectiveness for short-term training and A2C's advantages in long-term learning scenarios, emphasizing the importance of algorithm selection based on training duration and task complexity. The code can be found in this link https://github.com/Lexer04/Samurai-Shodown-with-Reinforcement-Learning-PPO.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• 융합보안논문지
• /
• 제22권2호
• /
• pp.21-26
• /
• 2022

마스크 착용은 COVID-19 감염을 예방하기 위한 효과적인 방안이다. 적외선 열화상 기반의 온도 측정과 신원 인식 시스템이 기업에서 널리 사용되고 있는 상황에서 마스크 감지를 위한 연구는 필수적이다. 최근 비전분야에 소개된 MTCNN은 객체 인스턴스 세분화를위한 개념적으로 간단하고 유연하며 일반적인 프레임 워크를 제시한다. 본 논문에서는 열적외선 카메라로부터 획득한 열감지영상에서 발열체인 인스턴스에 대해 발열부위의 세그멘테이션을 생성하는 동시에 이미지 내의 오브젝트 발열부분을 효율적으로 탐색하는 알고리즘을 제안한다. MTCNN(Multi-task Cascaded Convolutional Networks) 기법은 바운딩 박스 인식을 위해 기존 브랜치와 병렬로 객체 마스크를 예측하기 위한 브랜치를 추가한 알고리즘이다. MTCNN은 다른 작업으로 일반화하기 용이하다. 본 논문에서는 MTCNN기반 적외선 열영상 검출알고리즘을 제안하여 RGB영상에서 구별할 수 없는 마스크 착용 여부를 탐지하였다.