• ETRI Journal
• /
• v.22 no.3
• /
• pp.10-18
• /
• 2000

Although an n-th order cross-entropy (nCE) error function resolves the incorrect saturation problem of conventional error backpropagation (EBP) algorithm, performance of multilayer perceptrons (MLPs) trained using the nCE function depends heavily on the order of nCE. In this paper, we propose an adaptive learning rate to markedly reduce the sensitivity of MLP performance to the order of nCE. Additionally, we propose to limit error signal values at out-put nodes for stable learning with the adaptive learning rate. Through simulations of handwritten digit recognition and isolated-word recognition tasks, it was verified that the proposed method successfully reduced the performance dependency of MLPs on the nCE order while maintaining advantages of the nCE function.

• International Journal of Contents
• /
• v.7 no.3
• /
• pp.1-5
• /
• 2011

It has been an interesting challenge to find a good classifier for imbalanced data, since it is pervasive but a difficult problem to solve. However, classifiers developed with the assumption of well-balanced class distributions show poor classification performance for the imbalanced data. Among many approaches to the imbalanced data problems, the algorithmic level approach is attractive because it can be applied to the other approaches such as data level or ensemble approaches. Especially, the error back-propagation algorithm using the target node method, which can change the amount of weight-updating with regards to the target node of each class, attains good performances in the imbalanced data problems. In this paper, we analyze the relationship between two optimal outputs of neural network classifier trained with the target node method. Also, the optimal relationship is compared with those of the other error function methods such as mean-squared error and the n-th order extension of cross-entropy error. The analyses are verified through simulations on a thyroid data set.

• Journal of Broadcast Engineering
• /
• v.7 no.4
• /
• pp.291-299
• /
• 2002

This paper proposes an efficient motion compensation algorithm for video sequences with brightness variations. In the proposed algorithm, the brightness variation parameters are estimated and local motions are compensated. To detect the frame with large brightness variations. we employ the frame classification based on the cross entropy between histograms of two successive frames, which can reduce the computational redundancy. Simulation results show that the proposed method yields a higher peak signal to noise ratio (PSNR) than the conventional methods, with a low computational load, when the video scene contains large brightness changes.

• Review of KIISC
• /
• v.30 no.4
• /
• pp.69-76
• /
• 2020

본 연구에서는 신재생에너지의 큰 비중을 차지하고 있는 풍력발전의 ICT 환경을 조사하고 최신해킹사례를 분석하여, 예상되는 보안위협을 도출하였다. 이 중 가장 영향도가 높은 보안위협요소로 CSRF(Cross-Site Request Forgery) 공격을 선정하고 공격을 방어할 수 있는 인증강화모델을 제안하였다. 우선, 풍력발전 관련한 국제표준화 동향 및 대형제작사 구현실태를 살펴보고 CSRF 공격 예방을 위한 선행연구를 조사하였다. 선행연구의 이점을 접목하고 약점을 강화하여 재인증, CAPTCHA, OTP(One Time Password)와 같은 인증방식을 주요명령수행 구간에 임의로 표출시켜 인증시점의 불확실성(Entropy)을 높여 공격자가 쉽게 예측하지 못하도록 하였다. 명령수행과정의 일관성(고정성)이 매회 변화되므로 고정화된 형태의 CSRF 공격을 예방할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1101-1104
• /
• 2019

키넥트는 RGBD 카메라로 인체의 뼈대와 관절을 3D 공간에서 스켈레톤 데이터수집을 가능하게 해주었다. 스켈레톤 데이터를 활용한 행동 분류는 RNN, CNN 등 다양한 인공 신경망으로 접근하고 있다. 본 연구는 키넥트를 이용해서 Skeleton Joints를 수집하고, DNN 기반 스켈레톤 모델링 학습으로 행동을 분류한다. Skeleton Joints Processing 과정은 키넥트의 Depth Map 기반의 Skeleton Tracker로 25가지 Skeleton Joints 좌표를 얻고, 학습을 위한 전처리 과정으로 각 좌표를 상대좌표로 변경하고 데이터 수를 제한하며, Joint가 트래킹 되지 않은 부분에 대한 예외 처리를 수행한다. 스켈레톤 모델링 학습 과정에선 3계층의 DNN 신경망을 구축하고, softmax_cross_entropy 함수로 Skeleton Joints를 집는 모션, 내려놓는 모션, 팔짱 낀 모션, 얼굴을 가까이 가져가는 모션 해서 4가지 행동으로 분류한다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.66-72
• /
• 2023

Little attention appears to have been paid to the relevance of learning a good representation function in solving long tail tasks. Therefore, we propose a new loss function to ensure a good representation is learnt while learning to classify. We call this loss function Triplet Class-Wise Difficulty-Based (TriCDB-CE) Loss. It is a combination of the Triplet Loss and Class-wise Difficulty-Based Cross-Entropy (CDB-CE) Loss. We prove its effectiveness empirically by performing experiments on three benchmark datasets. We find improvement in accuracy after comparing with some baseline methods. For instance, in the CIFAR-10-LT, 7 percentage points (pp) increase relative to the CDB-CE Loss was recorded. There is more room for improvement on Places-LT.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.73-74
• /
• 2021

코로나로 인해 X-ray, CT, MRI와 같은 의료영상 분야에서 딥러닝을 많이 접목시키고 있다. 간단히 접할 수 있는 X-ray 영상으로 코로나 진단을 위해 CNN, R-CNN 등과 같은 영상 딥러닝 분야에서 많은 연구가 진행되고 있다. 의료영상 기반 딥러닝 학습은 바이오마커를 정확히 찾아내고, 최소한의 손실률과 높은 정확도를 필요로한다, 따라서 본 논문에서는 높은 정확도를 위한 학습 모델을 선정하고 실험을 진행하였다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.93-97
• /
• 2020

본 연구는 딥 러닝 기반 의존 구문 분석에서, 학습에 적용하는 손실 함수에 따른 성능을 평가하였다. Pointer Network를 이용한 Left-To-Right 모델을 총 세 가지의 손실 함수(Maximize Golden Probability, Cross Entropy, Local Hinge)를 이용하여 학습시켰다. 그 결과 LH 손실 함수로 학습한 모델이 선행 연구와 같이 MGP 손실 함수로 학습한 것에 비해 UAS/LAS가 각각 0.86%p/0.87%p 상승하였으며, 특히 의존 거리가 먼 경우에 대하여 분석 성능이 크게 향상됨을 확인하였다. 딥러닝 의존 구문 분석기를 구현할 때 학습모델과 입력 표상뿐만 아니라 손실 함수 역시 중요하게 고려되어야 함을 보였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.594-596
• /
• 2021

Future healthcare systems will heavily rely on ill-labeled data due to scarcity of the experts who are trained enough to label the data. Considering the contamination of the dataset, it is not desirable to make the neural network being overconfident to the dataset, but rather giving them some margins for the prediction is preferable. In this paper, we propose a novel epoch-wise decaying label-smoothing function to alleviate the model over-confidency, and it outperforms the neural network trained with conventional cross entropy by 6.0%.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.526-537
• /
• 2024

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.