• 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 the Korean GEO-environmental Society
• /
• v.15 no.11
• /
• pp.53-59
• /
• 2014

It has been generally recognized that the conventional rockfall protection nets have several problems to actual field application in the aspect of shock absorption, lack of pullout bearing capacities, and net damages. Because of the recognition, authors have tried to develop a new rockfall protection system consisted of shock absorption parts and hexagonal net configuration. In the previous research by the authors, the performance of the newly developed rockfall protection system has been investigated through the laboratory tests and the full-scale testing. In this study, subsequently, numerical analysis program is organized to make a confirmation of the structural stability and performance. For the correct design procedure of the hexagonal net system, it is essential to understand the various mechanical behavior of the entire system. It is also important to be reproduced the systematic characteristics of the system acquired by laboratory and full-scale testing by numerical analysis in order to carry out the numerical experiment to understand various mechanical behavior of the system. As a conclusion, the hexagonal net has better performance in mechanical and physical behavior compared with that of the rectangular net. Furthermore, due to the hexagonal net shows a good performance in aspect of the load distribution, it gives a good alternative in long-term management of the rockfall protection net.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2004.05a
• /
• pp.400-403
• /
• 2004

A non-heat기leafed steel does not need quenching and tempering processes that are called a heat treatment differently from conventional steel. Since the tensile strength of this steel is higher than 900MPa, a conventional forming process should be changed to incremental forming process such as a cross wedge rolling that requires lower load capacity than conventional ones. In this paper, the cold cross wedge rolling (CWR) die has been designed using CAD/CAE In order to produce near-net-shaped component of ball stud of non-heat-treated cold steel. Finite element analyses were applied in order to investigate process parameters of CWR. Results provide that the stretching angle and the forming angie at knifing zone in CWR process is important parameter to be the stable process under the low friction coefficient condition.

• Proceedings of the KIEE Conference
• /
• 2000.07c
• /
• pp.1818-1820
• /
• 2000

Due to recent technology advances, needs for flat panel displays, plasma display panels(PDPs) whose advantages are simple structure, high resolution, wide viewing angle is increasingly expected to be the first flat panel of large screen, walt hanging TVs. But the luminance and luminous efficiency of color PDP is net up to the level of a CRT. So, New electrode shape which is different from the conventional electrode has to propose to improve the luminance and luminous efficiency. In this paper, we suggested new shaped electrodes. In new shaped electrode, the discharge current was reduced compared with conventional type by reducing the unnecessary diffusion loss near the barrier rib. However, the luminance was nearly the same as conventional type. So, the luminous efficiency improved about 35%.

• Transactions of Materials Processing
• /
• v.3 no.3
• /
• pp.359-374
• /
• 1994

Process sequence design in sheet metal forming process by the finite element method is investigated. The forming of sheet metal into a washing machine container is used to demonstrate the design of an improved process sequence which has fewer operations. The design procedure makes extensive use of the finite element method which has simulation capabilities of elastic-plastic modeling. A one-stage process to make an initial blank to the final product is simulated to obtain information on metal flow requirements. Loading simulation for a conventional method is also performed to evaluate the design criteria which are uniform thickness distribution around the finished part and maximum punch load within limit of available press capacity. The newly designed sequence has two forming operations and can achieve net-shape manufacturing, while the conventional process sequence has three forming operations. This specific case conventional process sequence has three forming operations. This specific case can be considered for application of the method and for development of the sequence design methodology in general.

• Journal of the Korean Wood Science and Technology
• /
• v.45 no.6
• /
• pp.797-808
• /
• 2017

Automatic wood species identification systems have enabled fast and accurate identification of wood species outside of specialized laboratories with well-trained experts on wood species identification. Conventional automatic wood species identification systems consist of two major parts: a feature extractor and a classifier. Feature extractors require hand-engineering to obtain optimal features to quantify the content of an image. A Convolutional Neural Network (CNN), which is one of the Deep Learning methods, trained for wood species can extract intrinsic feature representations and classify them correctly. It usually outperforms classifiers built on top of extracted features with a hand-tuning process. We developed an automatic wood species identification system utilizing CNN models such as LeNet, MiniVGGNet, and their variants. A smartphone camera was used for obtaining macroscopic images of rough sawn surfaces from cross sections of woods. Five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch) were under classification by the CNN models. The highest and most stable CNN model was LeNet3 that is two additional layers added to the original LeNet architecture. The accuracy of species identification by LeNet3 architecture for the five Korean softwood species was 99.3%. The result showed the automatic wood species identification system is sufficiently fast and accurate as well as small to be deployed to a mobile device such as a smartphone.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.1 s.31
• /
• pp.3-10
• /
• 2005

This study attempts to measure effectively three dimensional deformation in road slopes using digital close-range photographs. After the still video images were acquired respectively on the same multi-station geometric configuration in two epoches, photo-triangulation was rallied out respectively by conventional standard bundle adjustment and free-net bundle adjustment and the computed results were compared with those of geodetic method by total station. Three dimensional coordinates and deformation amounts were able to be derived with the RMSE of sub-millimeter and the relative accuracy of $1/30,000{\sim}1/35,000$. It was shown that free-net bundle adjustment is about 13% higher than standard bundle adjustment in the accuracy of photo-triangulation. It was ascertained that the free-net technique is able to promote fast and accurate deformation surveying without the necessity of geodetic control survey in complicated industrial sites.

• Journal of KIISE:Software and Applications
• /
• v.28 no.10
• /
• pp.773-784
• /
• 2001

Since documents on the Web are naturally partitioned into may document database, the efficient information retrieval process requires identifying the document database that are most likely to provide relevant documents to the query and then querying the identified document database. We propose a neural net agent approach to such an efficient information retrieval. First, we present a neural net agent that learns about underlying document database using the relevance feedbacks obtained from many retrieval experiences. For a given query, the neural net agent, which is sufficiently trained on the basis of the BPN learning mechanism, discovers the document database associated with the relevant documents and retrieves those documents effectively. In the experiment, we introduce a neural net agent based information retrieval system and evaluate its performance by comparing experimental results to those of the conventional well-known approaches.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.23 no.1
• /
• pp.49-62
• /
• 2018

Net community production (NCP), defined as the difference between net primary production and respiration of heterotrophs, has been used as a measure of oceanic biological carbon pump. This paper summarizes the theoretical background and experimental methods for the estimation of NCP based on $O_2/Ar$ measurements ($O_2/Ar-NCP$). The high frequency measurements of $O_2/Ar-NCP$ (<1 min) is a significant enhancement over the conventional measures of biological pump, such as new production and export production. This paper also introduces some of important works as to the comparison between $O_2/Ar-NCP$ and other measures of biological pump, the distributions of $O_2/Ar-NCP$ in the oceans, and the correlation of $O_2/Ar-NCP$ with various oceanic parameters, including community structures.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.3
• /
• pp.99-103
• /
• 2021

Recently, convolutional neural networks (CNNs) have been widely utilized due to their outstanding performance in various computer vision fields. However, due to their computational-intensive and high memory requirements, it is difficult to deploy CNNs on hardware platforms that have limited resources, such as mobile devices and IoT devices. To address these limitations, a neural network compression research is underway to reduce the size of neural networks while maintaining their performance. This paper proposes a CNN compression technique that dynamically adjusts the thresholds of pruning, one of the neural network compression techniques. Unlike the conventional pruning that experimentally or heuristically sets the thresholds that determine the weights to be pruned, the proposed technique can dynamically find the optimal thresholds that prevent accuracy degradation and output the light-weight neural network in less time. To validate the performance of the proposed technique, the LeNet was trained using the MNIST dataset and the light-weight LeNet could be automatically obtained 1.3 to 3 times faster without loss of accuracy.