• 산업기술연구
• /
• 제16권
• /
• pp.197-205
• /
• 1996

In this paper, we propose a new neural architecture. We synthesize the architecture from a combination of structures known as MRCCN (Multi-resolution Radial-basis Competitive and Cooperative Network) and BPN (Backpropagation Network). The proposed neural network is able to improve the learning speed of MRCCN and the mapping capability of BPN. The ability and effectiveness of identifying a ninlinear dynamic system using the proposed architecture will be demonstrated by computer simulation.

• 한국통신학회논문지
• /
• 제26권10A호
• /
• pp.1717-1726
• /
• 2001

본 논문에서는 CORBA(Common Object Request Architecture)기반의 TINA(Telecommunications Information Networking Architecture) 분산체계에서 통신망 하부 장비들이 SNMP(Simple Network Management Protocol) 혹은 TMN(Telecommunications Management Network) 체계로 혼재되어 관리되는 네트워크의 NE(Network Element)들을 효율적으로 통합 관리할 수 있는 Generic Interface Adaptor(GIA)를 제안하고 이를 설계 및 구현하였다. GIA는 message mapping, protocol conversion 및 DBMS를 이용한 Object Abstract Translation(OAT)을 통해서 각 관리체계에 맞도록 관리정보를 변환시키며, 이를 통해 TINA EML(Element Management Layer) component와 SNMP NE agent 간의 상호연동을 가능하게 한다.

• 한국음향학회지
• /
• 제41권1호
• /
• pp.30-37
• /
• 2022

본 논문은 주파수 영역에서 심층 신경망 기반 음성 향상 모델 학습을 위하여 학습 대상과 네트워크 구조에 따라 두 가지 관점에서 성능을 비교 평가한다. 이때, 학습 대상으로는 스펙트럼 매핑과 Time-Frequency(T-F) 마스킹 기법을 사용하였고 네트워크 구조는 실수 네트워크와 복소 네트워크를 사용하였다. 음성 향상 모델의 성능은 데이터 셋 규모에 따라 Perceptual Evaluation of Speech Quality(PESQ)와 Short-Time Objective Intelligibility(STOI) 두 가지 객관적 평가지표를 통해 평가하였다. 실험 결과, 네트워크의 종류와 데이터 셋 종류에 따라 적정한 훈련 데이터의 크기가 다르다는 것을 확인하였다. 또한, 데이터의 크기와 학습 대상에 따라 복소 네트워크보다 실수 네트워크가 비교적 높은 성능을 보이기 때문에 총 파라미터의 수를 고려한다면 경우에 따라 실수 네트워크를 사용하는 것이 보다 현실적인 해결책일 수 있다는 것을 확인하였다.

• 한국측량학회지
• /
• 제29권4호
• /
• pp.429-438
• /
• 2011

LiDAR technology is a combination of laser ranging, satellite positioning technology and digital image technology for study and determination with high accuracy of the true earth surface features in 3 D. Laser scanning data is typically a points cloud on the ground, including coordinates, altitude and intensity of laser from the object on the ground to the sensor (Wehr & Lohr, 1999). Data from laser scanning can produce products such as digital elevation model (DEM), digital surface model (DSM) and the intensity data. In Vietnam, the LiDAR technology has been applied since 2005. However, the application of LiDAR in Vietnam is mostly for topological mapping and DEM establishment using point cloud 3D coordinate. In this study, another application of LiDAR data are present. The study use the intensity image combine with some other data sets (elevation data, Panchromatic image, RGB image) in Bacgiang City to perform land cover classification using neural network method. The results show that it is possible to obtain land cover classes from LiDAR data. However, the highest accurate classification can be obtained using LiDAR data with other data set and the neural network classification is more appropriate approach to conventional method such as maximum likelyhood classification.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.710-712
• /
• 2006

The aim of this study was to analyze limestone deposits potential using an artificial neural network and a Geographic Information System (GIS) environment to identify areas that have not been subjected to the same degree of exploration. For this, a variety of spatial geological data were compiled, evaluated and integrated to produce a map of potential deposits in the Gangreung area, Korea. A spatial database considering deposit, topographic, geologic, geophysical and geochemical data was constructed for the study area using a GIS. The factors relating to 44 limestone deposits were the geological data, geochemical data and geophysical data. These factors were used with an artificial neural network to analyze mineral potential. Each factor’s weight was determined by the back-propagation training method. Training area was applied to analyze and verify the effect of training. Then the mineral deposit potential indices were calculated using the trained back-propagation weights, and potential map was constructed from GIS data. The mineral potential map was then verified by comparison with the known mineral deposit areas. The verification result gave accuracy of 87.31% for training area.

• Journal of Welding and Joining
• /
• 제17권5호
• /
• pp.40-46
• /
• 1999

The sensors employed in the robotic are welding system must detect the changes in weld characteristics and produce the output that is in some way related to the change being detected. Such adaptive systems, which synchronise the robot arm and eyes using a primitive brain will form the basis for the development of robotic GMA(Gas Metal Arc) welding which increasingly higher levels of artificial intelligence. The objective of this paper is to realize the mapping characteristics of bead height through learning. After learning, the neural estimation can estimate the bead height desired from the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) are chosen from an estimation error analysis. A series of bead of bead-on-plate GMA welding experiments was carried out in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the bead height with reasonable accuracy and guarantee the uniform weld quality.

• ETRI Journal
• /
• 제31권2호
• /
• pp.111-120
• /
• 2009

Network-on-chip (NoC) architecture provides a highper-formance communication infrastructure for system-on-chip designs. Circuit-switched networks guarantee transmission latency and throughput; hence, they are suitable for NoC architecture with real-time traffic. In this paper, we propose an efficient integrated scheme which automatically maps application tasks onto NoC tiles, establishes communication circuits, and allocates a proper bandwidth for each circuit. Simulation results show that the average waiting times of packets in a switch in $6{\times}6$6, $8{\times}8$, and $10{\times}10$ mesh NoC networks are 0.59, 0.62, and 0.61, respectively. The latency of circuits is significantly decreased. Furthermore, the buffer of a switch in NoC only needs to accommodate the data of one time slot. The cost of the switch in the circuit-switched network can be reduced using our scheme. Our design provides an effective solution for a critical step in NoC design.

• 센서학회지
• /
• 제30권1호
• /
• pp.20-24
• /
• 2021

The electrocardiogram (ECG) is one of the most extensively employed signals used to diagnose and predict cardiovascular diseases (CVDs). In recent years, several deep learning (DL) models have been proposed to improve detection accuracy. Among these, deep neural networks (DNNs) are the most popular, wherein the features are extracted automatically. Despite the increment in classification accuracy, DL models require exorbitant computational resources and power. This causes the mapping of DNNs to be slow; in addition, the mapping is challenging for a wearable device. Embedded systems have constrained power and memory resources. Therefore full-precision DNNs are not easily deployable on devices. To make the neural network faster and more power-efficient, spiking neural networks (SNNs) have been introduced for fewer operations and less complex hardware resources. However, the conventional SNN has low accuracy and high computational cost. Therefore, this paper proposes a new binarized SNN which modifies the synaptic weights of SNN constraining it to be binary (+1 and -1). In the simulation results, this paper compares the DL models and SNNs and evaluates which model is optimal for ECG classification. Although there is a slight compromise in accuracy, the latter proves to be energy-efficient.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2002년도 추계공동학술대회
• /
• pp.350-362
• /
• 2002

높은 가용성, 확장성, 시스템 성능의 요구를 만족시키기 위해 SAN(Storage Area Network)이 등장했다. SAN을 보다 효과적으로 활용할 수 있도록, 대부분의 SAN 운영체제들은 SAN에 부착된 물리적 저장장치들을 가상적으로 하나의 커다란 볼륨으로 보이게 하는 저장장치 가상화 개념을 지원한다. 저장장치 가상화의 핵심적인 역할을 하는 것이 바로 논리볼륨 관리자이다. 논리볼륨 관리자는 논리 주소를 물리 주소로 매핑 시킴으로서 저장장치 가상화를 실현한다. 이 논문에서는 논리볼륨 관리자를 위한 효율적이고 유연한 매핑 기법을 설계하고 구현한다. 이 논문의 매핑 기법은 특정 시점의 볼륨이미지를 유지할 수 있는 스냅 샷과 시스템을 정지시키지 않고 SAN에 디스크를 추가 또는 삭제할 수 있는 온라인 재구성 기능을 지원한다.

• 디지털산업정보학회논문지
• /
• 제18권2호
• /
• pp.17-26
• /
• 2022

In this paper, we propose a novel method of performing convolutional operations on a 2-D Processing Element(PE) array. The conventional method [1] of mapping the convolutional operation using the 2-D PE array lacks flexibility and provides low utilization of PEs. However, by mapping a convolutional operation from a 2-D PE array to a 1-D PE array, the proposed method can increase the number and utilization of active PEs. Consequently, the throughput of the proposed Deep Convolutional Neural Network(DCNN) accelerator can be increased significantly. Furthermore, the power consumption for the transmission of weights between PEs can be saved. Based on the simulation results, the performance of the proposed method provides approximately 4.55%, 13.7%, and 2.27% throughput gains for each of the convolutional layers of AlexNet, VGG16, and ResNet50 using the DCNN accelerator with a (weights size) x (output data size) 2-D PE array compared to the conventional method. Additionally the proposed method provides approximately 63.21%, 52.46%, and 39.23% power savings.