• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.26-26
• /
• 2023

General circulation models (GCMs) are widely used in hydrological prediction, however their coarse grids make them unsuitable for regional analysis, therefore a downscaling method is required to utilize them in hydrological assessment. As one of the downscaling methods, convolutional neural network (CNN)-based downscaling has been proposed in recent years. The aim of this study is to generate the process of dynamic downscaling using CNNs by applying GCM output as input and RCM output as label data output. Prediction accuracy is compared between different input datasets, and model structures. Several input datasets with key atmospheric variables such as precipitation, temperature, and humidity were tested with two different formats; one is two-dimensional data and the other one is three-dimensional data. And in the model structure, the hyperparameters were tested to check the effect on model accuracy. The results of the experiments on the input dataset showed that the accuracy was higher for the input dataset without precipitation than with precipitation. The results of the experiments on the model structure showed that substantially increasing the number of convolutions resulted in higher accuracy, however increasing the size of the receptive field did not necessarily lead to higher accuracy. Though further investigation is required for the application, this paper can contribute to the development of efficient downscaling method with CNNs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.720-723
• /
• 2017

돼지 호흡기 질병은 돈사에 막대한 경제적 손실을 초래하는 질병들 중 하나이다. 본 논문에서는 저비용으로도 구축이 가능한 소리 센서 기반의 돼지 호흡기 질병 탐지 시스템을 제안하며, 특히 잡음 환경에서도 강인한 시스템의 구성에 초점을 두었다. 제안하는 시스템은 먼저, 돈사 내의 소리 센서로부터 취득한 돼지 소리를 2차원 회색조 이미지로 변환한다. 이후, 잡음에 강인한 성능을 보이는 Dominant Neighborhood Structure(DNS) 알고리즘을 이용하여 질감정보를 추출한다. 마지막으로, 이미지 분류에서 그 성능이 이미 입증된 딥러닝의 대표적 모델인 Convolutional Neural Network(CNN)에 사용하여 돼지 호흡기 질병을 탐지 및 분류한다. 실제 국내 돈사에서 취득한 돼지 소리를 이용하여 제안하는 시스템의 성능을 실험적으로 검증한 바 96%가 넘는 안정적인 시스템임을 확인하였다.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.4
• /
• pp.184-191
• /
• 2001

This paper proposes a prefilter type velocity compensating control system using modified chaotic neural networks for the trajectory control of robotic manipulator. Since the structure of modified chaotic neural networks(MCNN) and neurons have highly nonlinear dynamic characteristics, MCNN can show the robust characteristics for controlling highly nonlinear dynamics like robotic manipulators. For its application, the trajectory controller of the three-axis robot manipulator is designed by MCNN. The MCNN controller acts as the compensator of the PD controller. Simulation results show that learning error decrease drastically via on-line learning and the performance is excellent. The MCNN controller showed much better control performance and shorter calculation time compared to the RNN controller, Another advantage of the proposed controller could by attached to conventional robot controller without hardware changes.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.398-400
• /
• 2019

Faced with the increasing demand for image recognition on mobile devices, how to run convolutional neural network (CNN) models on mobile devices with limited computing power and limited storage resources encourages people to study efficient model design. In recent years, many effective architectures have been proposed, such as mobilenet_v1, mobilenet_v2 and PeleeNet. However, in the process of feature selection, all these models neglect some information of shallow features, which reduces the capture of shallow feature location and semantics. In this study, we propose an effective framework based on Feature Pyramid Networks to improve the recognition accuracy of deep and shallow images while guaranteeing the recognition speed of PeleeNet structured images. Compared with PeleeNet, the accuracy of structure recognition on CIFA-10 data set increased by 4.0%.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• International journal of advanced smart convergence
• /
• v.8 no.2
• /
• pp.116-125
• /
• 2019

The fire should extinguish as soon as possible because it causes economic loss and loses precious life. In this study, we propose a new atypical fire and smoke detection algorithm using deep learning and color histogram of fire and smoke. First, input frame images obtain from the ONVIF surveillance camera mounted in factory search motion candidate frame by motion detection algorithm and mean square error (MSE). Second deep learning (Faster R-CNN) is used to extract the fire and smoke candidate area of motion frame. Third, we apply a novel algorithm to detect the fire and smoke using color histogram algorithm with local area motion, similarity, and MSE. In this study, we developed a novel fire and smoke detection algorithm applied the local motion and color histogram method. Experimental results show that the surveillance camera with the proposed algorithm showed good fire and smoke detection results with very few false positives.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.247-256
• /
• 2022

Visual tracking of selected target objects is fundamental challenging problems in computer vision. Object tracking localize the region of target object with bounding box in the video. We propose a Siam-FPN based custom fully CNN to solve visual tracking problems by regressing the target area in an end-to-end manner. A method of preserving the feature information flow using a feature map connection structure was applied. In this way, information is preserved and emphasized across the network. To regress object region and to classify object, the region proposal network was connected with the Siamese network. The performance of the tracking algorithm was evaluated using the OTB-100 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.621 in Success Plot and 0.838 in Precision Plot were achieved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.305-318
• /
• 2022

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.55-56
• /
• 2021

최근, 딥러닝 및 인공신경망 기술의 발전으로 비디오 부호화 분야에서도 인공지능을 이용한 요소 기술에 대한 연구가 활발이 진행되고 있다. 본 논문에서는 주변 참조샘플로부터 문맥정보를 이용하여 현재블록을 예측하는 CNN 기반의 화면내 예측 모델을 구현하고, 비디오 부호화의 블록 분할 구조를 반영한 학습 기법에 따른 부호화 성능을 분석한다. 실험결과 HM(HEVC Test Model)에 구현한 문맥적응적 신경망 기반 예측 모델에서 트리 분할 구조를 반영한 학습이 HM16.19 대비 0.35% BD-rate 부호화 성능 향상을 보였다.