• Journal of Semiconductor Engineering
• /
• 제2권2호
• /
• pp.130-135
• /
• 2021

Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.

• Journal of Multimedia Information System
• /
• 제9권3호
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• 방송공학회논문지
• /
• 제28권1호
• /
• pp.141-144
• /
• 2023

최근에 심층신경망(DNN)을 활용하여 채널 추정, 채널 양자화, 피드백, 프리코딩 과정을 통합하여 모델링하는 연구가 진행되었다. 해당연구는 기존에 이론적으로 어렵던 통합 최적화를 deep learning (DL)을 기반으로 수행하여 기존의 실제 codebook을 활용하는 프리코딩기법에 비해 높은 잠재력이 있음을 보였다. 하지만 기존의 기법은 랜덤하게 정해진 소수의 사용자만을 대상으로하며, 기존의 기법과 다르게 스케줄링이 포함된 환경에는 적응이 어렵다. 따라서 본 연구에서는 심층신경망기반의 프리코딩기법이 활용가능한 스케줄링 방식을 연구하여 기존의 결과와 비교한다.

• 한국멀티미디어학회논문지
• /
• 제23권3호
• /
• pp.402-411
• /
• 2020

Power line noise in electrocardiogram signals makes it difficult to diagnose cardiovascular disease. ECG signals without power line noise are needed to increase the accuracy of diagnosis. In this paper, it is proposed DNN(Deep Neural Network) model to remove the power line noise in ECG. The proposed model is learned with noisy ECG, and clean ECG. Performance of the proposed model were performed in various environments(varying amplitude, frequency change, real-time amplitude change). The evaluation used signal-to-noise ratio and root mean square error (RMSE). The difference in evaluation metrics between the noisy ECG signals and the de-noising ECG signals can demonstrate effectiveness as the de-noising model. The proposed DNN model learning result was a decrease in RMSE 0.0224dB and a increase in signal-to-noise ratio 1.048dB. The results performed in various environments showed a decrease in RMSE 1.7672dB and a increase in signal-to-noise ratio 15.1879dB in amplitude changes, a decrease in RMSE 0.0823dB and a increase in signal-to-noise ratio 4.9287dB in frequency changes. Finally, in real-time amplitude changes, RMSE was decreased 0.3886dB and signal-to-noise ratio was increased 11.4536dB. Thus, it was shown that the proposed DNN model can de-noise power line noise in ECG.

• 한국통신학회논문지
• /
• 제41권8호
• /
• pp.958-964
• /
• 2016

본 논문에서는 여러 개의 이원 support vector machine (binary SVM)을 사용하여 세 개 이상의 클래스를 분류하는 multi-class SVM과 유사하게 다중의 판별 deep neural network (DNN) 모델을 사용하는 i-벡터 기반의 언어 인식 시스템을 제안한다. 제안하는 시스템은 NIST 2015 i-vector Machine Learning Challenge 데이터베이스에 포함된 i-벡터들을 이용하여 학습 및 테스트 되었으며, 오픈 세트에서 기존의 cosine distance, multi-class SVM 및 단일 neural network (NN) 기반의 언어 인식 시스템에 비하여 높은 성능을 보임이 확인되었다.

• 지질공학
• /
• 제31권1호
• /
• pp.31-42
• /
• 2021

도로비탈면관리시스템(Cut-Slope Management System, CSMS)은 전국 일반국도 비탈면에 대해 기초·정밀 조사를 바탕으로 데이터베이스를 구축해왔다. 그런데 이러한 데이터는 사람에 의해 기록되기 때문에 데이터 누락 및 오기입 문제가 발생할 수밖에 없다. 본 연구에서는 데이터의 불완전성 문제를 극복하기 위해 여러 머신러닝 기반의 예측모델들을 개발하고 이를 이용한 데이터 품질 강화 가능성을 검토하고자 하였다. 우선 다 범주 문자형 데이터를 수치화하는 과정을 수행하였고, 선정된 데이터 항목들에 대해 다항 로지스틱 회귀분석(Multinomial Logistic Regression)과 심층신경망(Deep-Neural-Network) 기반의 예측모델들을 개발하였다. 그 결과, 심층신경망 모델들의 정확도가 월등히 높은 것으로 나타났다. 향후 개발된 모델들을 활용하여 누락 및 오기입 데이터의 보완이 가능할 것으로 기대된다.

• 한국정보전자통신기술학회논문지
• /
• 제16권3호
• /
• pp.123-129
• /
• 2023

응시점을 통해 어떤 것을 보고 있는지 알 수 있다면 많은 정보를 얻을 수 있다. 응시 추적 기술의 발달로 응시점에 대한 정보는 다양한 응시 추적 기기에서 제공해주는 소프트웨어를 통해 얻을 수 있다. 하지만 실제 응시 깊이와 같은 정확한 정보를 추정하기란 어렵다. 응시 추적 기기를 통해 만약 실제 응시 깊이로 보정할 수 있다면 시뮬레이션, 디지털 트윈, VR 등 다양한 분야에서 현실적이고 정확한 신뢰성 있는 결과를 도출하는 것이 가능해질 것이다. 따라서 본 논문에서는 응시 추적 기기와 소프트웨어를 통해 원시 응시 깊이를 획득하고 보정하는 실험을 진행한다. 실험은 Deep Neural Network(DNN) 모델을 설계한 후 소프트웨어에서 제공하는 응시 깊이 값을 300mm에서 10,000mm까지 지정한 거리별로 획득한다. 획득한 데이터는 설계한 DNN 모델을 통해 학습을 진행하여 실제 응시 깊이와 대응하도록 보정하였다. 보정한 모델을 통해 실험을 진행한 결과, 300mm에서 10,000mm까지 지정한 거리별 297mm, 904mm, 1,485mm, 2,005mm, 3,011mm, 4,021mm, 4,972mm, 6,027mm, 7,026mm, 8,043mm, 9,021mm, 10,076mm로 실제와 비슷한 응시 깊이 값을 획득할 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제45권3호
• /
• pp.128-137
• /
• 2024

It is necessary to develop a pulsatile Extracorporeal Membrane Oxygenator (p-ECMO) with counter-pulsation control(CPC), which ejects blood during the diastolic phase of the heart rather than the systolic phase, due to the known issues with conventional ECMO causing fatal complications such as ventricular dilation and pulmonary edema. A promising method to simultaneously detect the pulsations of the heart and p-ECMO is to analyze blood pressure waveforms using deep neural network technology(DNN). However, the accurate detection of cardiac rhythms by DNNs is challenging due to various noises such as pulsations from p-ECMO, reflected waves in the vessels, and other dynamic noises. This study aims to evaluate the accuracy of DNNs developed for CPC in p-ECMO, using human-like blood pressure waveforms reproduced in an in-vitro experiment. Especially, an experimental setup that reproduces reflected waves commonly observed in actual patients was developed, and the impact of these waves on DNN judgments was assessed using a multiple DNN (m-DNN) that provides accurate determinations along with a separate index for heartbeat recognition ability. In the experimental setup inducing reflected waves, it was observed that the shape of the blood pressure waveform became increasingly complex, which coincided with an increase in harmonic components, as evident from the Fast Fourier Transform results of the blood pressure wave. It was observed that the recognition score (RS) of DNNs decreased in blood pressure waveforms with significant harmonic components, separate from the frequency components caused by the heart and p-ECMO. This study demonstrated that each DNN trained on blood pressure waveforms without reflected waves showed low RS when faced with waveforms containing reflected waves. However, the accuracy of the final results from the m-DNN remained high even in the presence of reflected waves.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권4호
• /
• pp.26-32
• /
• 2020

There are many airline customer evaluation data, but they are insufficient in terms of predicting customer satisfaction in practice. In particular, they are generally insufficient in case of verification of data value and development of a customer satisfaction prediction model based on customer evaluation data. In this paper, airline customer satisfaction analysis is conducted through an experiment of correlation analysis between customer evaluation data provided by Google's Kaggle. The difference in accuracy varied according to the three types, which are the overall variables, the top 4 and top 8 variables with the highest correlation. To build an airline customer satisfaction prediction model, they are applied to three classification algorithms of Random Forest, SVM, DNN and conduct a classification experiment. They are divided into training data and verification data by 7:3. As a result, the DNN model showed the lowest accuracy at 86.4%, while the SVM model at 89% and the Random Forest model at 95.7% showed the highest accuracy and performance.

• 인터넷정보학회논문지
• /
• 제19권3호
• /
• pp.43-48
• /
• 2018

본 논문은 DNN(Deep Neural Network)와 슈퍼픽셀을 이용한 실내 공간 인식 알고리즘을 제안한다. 영상으로부터 실내 공간 인식을 위해 우선 영상 분할을 위한 세그멘테이션 프로세스가 필요하다. 이를 위해 본 논문에서는 적당한 크기로 나눌 수 있는 슈퍼 픽셀 알고리즘을 이용해 세그멘테이션을 수행한다. 각 세그먼트를 인식하기 위해 세그먼트마다 제안하는 방법을 이용하여 특징을 추출한다. 추출된 특징들을 DNN을 이용하여 학습하고, 학습으로부터 추출된 DNN모델을 이용하여 각 세그먼트를 인식한다. 실험 결과를 통해 제안하는 방법과 기존의 알고리즘과의 성능 비교 분석을 한다.