• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.842-849
• /
• 2022

With the development of deep learning technology, there are many cases of using DNNs in embedded systems such as unmanned vehicles, drones, and robotics. Typically, in the case of an autonomous driving system, it is crucial to run several DNNs which have high accuracy results and large computation amount at the same time. However, running multiple DNNs simultaneously in an embedded system with relatively low performance increases the time required for the inference. This phenomenon may cause a problem of performing an abnormal function because the operation according to the inference result is not performed in time. To solve this problem, the solution proposed in this paper first reduces the computation by applying the Tucker decomposition to DNN models with big computation amount, and then, make DNN models run in parallel as much as possible in the unit of hidden layer inside the GPU. The experimental result shows that the DNN inference time decreases by up to 75.6% compared to the case before applying the proposed technique.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.368-376
• /
• 2021

With the recent development of deep learning technology, autonomous things technology is attracting attention, and DNNs are widely used in embedded systems such as drones and autonomous vehicles. Embedded systems that can perform large-scale operations and process multiple DNNs for high recognition accuracy without relying on the cloud are being released. DNNs with various levels of priority exist within these systems. DNNs related to the safety-critical applications of autonomous vehicles have the highest priority, and they must be handled first. In this paper, we propose a priority-based scheduling framework for DNNs when multiple DNNs are executed simultaneously. Even if a low-priority DNN is being executed first, a high-priority DNN can preempt it, guaranteeing the fast response characteristics of safety-critical applications of autonomous vehicles. As a result of checking through extensive experiments, the performance improved by up to 76.6% in the actual commercial board.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.39-39
• /
• 2020

Low-flow 하천에서의 최저수위를 나타내는 지표이다. 일반적으로 유황곡선의 갈수량(Q355)를 대표적으로 사용한다. Low-flow는 물 공급 관리 및 계획, 관개용수, 생태계등 다양한 분야에 영향을 미친다. 이러한 Low-flow를 산정하기 위해서는 충분한 기간의 유량자료가 필요하다. 하지만 국토의 70%가 산지지형으로 구성되어 있는 우리나라의 경우 국가하천과 1급하천을 제외한 산지유역은 수위관측소가 부재하거나 결측으로 인해 자료가 충분하지 않아 Low-flow분석에 한계가 있다. 이에 과거에는 미계측지역의 갈수량을 예측하기 위해서 다중회귀분석, ARIMA 모형 등 다양한 기법을 사용하였지만, 최근들어 머신러닝 모형의 수요가 증가하고 있다. 이에 본 연구에서는 새로운 패러다임에 맞는 머신러닝 기법인 DNN기법을 사용하고자 한다. DNN기법은 ANN기법의 단점인 학습과정에서 최적 매개변수값을 찾기 어렵고, 학습시간이 느린 단점을 보완한 방법이다. 따라서 본연구에서는 머신러닝 기법인 DNN기법을 통해 미계측지역에 적용 가능한 지역화 Low-flow indices를 산정하고자 한다. 먼저, Low-flow에 영향을 미치는 인자들을 수집하고 인자들간의 상관분석, 다중공선성 분석을 통해 통계적으로 유의한 변수를 선정하여, 머신러닝 모형에 입력자료를 구축하였다. 또한 기존의 갈수량 예측기법인 다중회귀분석 결과와 비교하여 머신러닝 기법의 효용성을 검토하였다.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.141-144
• /
• 2023

Recently, a joint channel estimation, channel quantization, feedback, and precoding system based on deep-neural network (DNN) was proposed. The corresponding system achieved a joint optimization based on deep learning such that it achieved a higher sum rate than the existing codebook-based precoding systems. However, this DNN-based procoding system is not directly applicable for the environments with many users such that a specific user selection can potentially increase the sum rate of the system. Thus, in this letter, we study an appropriate user selection method suitable for DNN-based precoding.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.430-435
• /
• 2022

In this paper, we consider the non-orthogonal multiple access (NOMA) technique in the heterogeneous network (HetNET) consisting of a single macro base station (BS) and multiple small BSs, where the perfect successive interference cancellation is assumed for the NOMA signals. In this paper, we propose a deep learning-based user association and power allocation scheme to maximize the data rate in the NOMA-based HetNET. In particular, the proposed scheme includes the deep neural network (DNN)-based user association process for load balancing and the DNN-based power allocation process for data-rate maximization. Through the simulation assuming path loss and Rayleigh fading channels between BSs and users, the performance of the proposed scheme is evaluated, and it is compared with the conventional maximum signal-to-interference-plus-noise ratio (Max-SINR) scheme. Through the performance comparison, we show that the proposed scheme provides better sum rate performance than the conventional Max-SINR scheme.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1183-1193
• /
• 2021

Low flow affects various fields such as river water supply management and planning, and irrigation water. A sufficient period of flow data is required to calculate the Flow Duration Curve. However, in order to calculate the Flow Duration Curve, it is essential to secure flow data for more than 30 years. However, in the case of rivers below the national river unit, there is no long-term flow data or there are observed data missing for a certain period in the middle, so there is a limit to calculating the Flow Duration Curve for each river. In the past, statistical-based methods such as Multiple Regression Analysis and ARIMA models were used to predict sulfur in the unmeasured watershed, but recently, the demand for machine learning and deep learning models is increasing. Therefore, in this study, we present the DNN technique, which is a machine learning technique that fits the latest paradigm. The DNN technique is a method that compensates for the shortcomings of the ANN technique, such as difficult to find optimal parameter values in the learning process and slow learning time. Therefore, in this study, the Flow Duration Curve applicable to the unmeasured watershed is calculated using the DNN model. First, the factors affecting the Flow Duration Curve were collected and statistically significant variables were selected through multicollinearity analysis between the factors, and input data were built into the machine learning model. The effectiveness of machine learning techniques was reviewed through statistical verification.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.361-368
• /
• 2018

As autonomous driving research is rapidly developing, pedestrian detection study is also successfully investigated. However, most of the study utilizes color image datasets and those are relatively easy to detect the pedestrian. In case of color images, the scene should be exposed by enough light in order to capture the pedestrian and it is not easy for the conventional methods to detect the pedestrian if it is the other case. Therefore, in this paper, we propose deep neural network (DNN)-based multi-spectrum pedestrian detection method using color and thermal images. Based on single-shot multibox detector (SSD), we propose fusion network structures which simultaneously employ color and thermal images. In the experiment, we used KAIST dataset. We showed that proposed SSD-H (SSD-Halfway fusion) technique shows 18.18% lower miss rate compared to the KAIST pedestrian detection baseline. In addition, the proposed method shows at least 2.1% lower miss rate compared to the conventional halfway fusion method.

• Journal of Advanced Navigation Technology
• /
• v.23 no.6
• /
• pp.561-569
• /
• 2019

Solar photovoltaic can provide electrical energy with only radiation, and its use is expanding rapidly as a new energy source. This study predicts the short and long-term PV power generation using actual converter output data of photovoltaic system. The prediction algorithm uses multiple linear regression, support vector machine (SVM), and deep learning such as deep neural network (DNN) and long short-term memory (LSTM). In addition, three models are used according to the input and output structure of the weather element. Long-term forecasts are made monthly, seasonally and annually, and short-term forecasts are made for 7 days. As a result, the deep learning network is better in prediction accuracy than multiple linear regression and SVM. In addition, LSTM, which is a better model for time series prediction than DNN, is somewhat superior in terms of prediction accuracy. The experiment results according to the input and output structure appear Model 2 has less error than Model 1, and Model 3 has less error than Model 2.

• Smart Media Journal
• /
• v.7 no.1
• /
• pp.16-23
• /
• 2018

In this paper, we used the Deep Neural Network (DNN) to predict the number of daily spectators of Gwangju - KIA Champions Field in order to provide marketing data for the team and related businesses and for managing the inventories of the facilities in the stadium. In this study, the DNN model, which is based on an artificial neural network (ANN), was used, and four kinds of DNN model were designed along with dropout and batch normalization model to prevent overfitting. Each of four models consists of 10 DNNs, and we added extra models with ensemble model. Each model was evaluated by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The learning data from the model randomly selected 80% of the collected data from 2008 to 2017, and the other 20% were used as test data. With the result of 100 data selection, model configuration, and learning and prediction, we concluded that the predictive power of the DNN model with ensemble model is the best, and RMSE and MAPE are 15.17% and 14.34% higher, correspondingly, than the prediction value of the multiple linear regression model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.3
• /
• pp.252-262
• /
• 2020

In Remote Sensing, a machine learning based SVM model is typically utilized for land cover classification. And study using neural network models is also being carried out continuously. But study using high-resolution imagery of KOMPSAT is insufficient. Therefore, the purpose of this study is to assess the accuracy of land cover classification by neural network models using high-resolution KOMPSAT-3 satellite imagery. After acquiring satellite imagery of coastal areas near Gyeongju City, training data were produced. And land cover was classified with the SVM, ANN and DNN models for the three items of water, vegetation and land. Then, the accuracy of the classification results was quantitatively assessed through error matrix: the result using DNN model showed the best with 92.0% accuracy. It is necessary to supplement the training data through future multi-temporal satellite imagery, and to carry out classifications for various items.