• 한국컴퓨터정보학회논문지
• /
• 제24권3호
• /
• pp.19-27
• /
• 2019

This paper proposes a new method using multi-layer overlapped windows to improve the performance of YOLO network which is vulnerable to detect small dense objects. In particular, the proposed method uses the YOLO Network based on the multi-layer overlapped windows to track small dense vehicles that approach from long distances. The method improves the detection performance for location and size of small vehicles. It allows crossing area of two multi-layer overlapped windows to track moving vehicles from a long distance to a short distance. And the YOLO network is optimized so that GPU computation time due to multi-layer overlapped windows should be reduced. The superiority of the proposed algorithm has been proved through various experiments using captured images from road surveillance cameras.

• 전자공학회논문지B
• /
• 제31B권9호
• /
• pp.159-165
• /
• 1994

In this paper, we propose a multi-layer associative neural network structure suitable for hardware implementaion with the function of performance refinement and improved robutst capability. Unlike other methods which reduce network complexity by putting restrictions on synaptic weithts, we are imposing a requirement of hidden layer neurons for the function. The proposed network has synaptic weights obtainted by Hebbian rule between adjacent layer's memory patterns such as Kosko's BAM. This network can be extended to arbitary multi-layer network trainable with Genetic algorithm for getting hidden layer memory patterns starting with initial random binary patterns. Learning is done to minimize newly defined network error. The newly defined error is composed of the errors at input, hidden, and output layers. After learning, we have bidirectional recall process for performance improvement of the network with one-shot recall. Experimental results carried out on pattern recognition problems demonstrate its performace according to the parameter which represets relative significance of the hidden layer error over the sum of input and output layer errors, show that the proposed model has much better performance than that of Kosko's bidirectional associative memory (BAM), and show the performance increment due to the bidirectionality in recall process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권9호
• /
• pp.2213-2231
• /
• 2013

Compressed sensing is a novel technology used in the field of wireless communication and sensor networks for channel estimation, signal detection, data gathering, network monitoring, and other applications. It plays a significant role in highly secure, real-time, well organized, and cost-effective data communication in smart-grid (SG) systems, which consist of multi-tier network standards that make it challenging to synchronize in power management communication. In this paper, we present a multi-layer communication model for SG systems and propose compressed-sensing based data transmission at every layer of the SG system to improve data transmission performance. Our approach is to utilize the compressed-sensing procedure at every layer in a controlled manner. Simulation results demonstrate that the proposed monitoring devices need less transmission power than conventional systems. Additionally, secure, reliable, and real-time data transmission is possible with the compressed-sensing technique.

• 한국컴퓨터정보학회논문지
• /
• 제4권3호
• /
• pp.67-72
• /
• 1999

신경회로망은 학습능력과 근사화 능력으로 말미암아 패턴인식 및 시스템제어분야에서 많이 사용되고 있으며, 입력층. 출력층. 하나 이상의 은닉층으로 구성된 네드워크이다. Elman 신경회로망은 J. Elman에 의해 제안되었으며. recurrent network의 형태로 구성되어 있다. Elman 신경회로망은 기존의 신경회로망에 context층을 새로 추가하여, 은닉층의 출력을 context층의 입력으로 피드백 하는 구조로 되어 있다. 본 논문에서는 새로운 형태의 Elman 신경회로망을 제안한다. 제안한 방식은 Elman 신경회로망을 변형한 형태로. 은닉층 뿐 만 아니라 출력층의 출력도 context층으로 피드백 하는 형태이다. 제안한 방식의 유용성을 확인하기 위해 multi target system에 적용한다. 시뮬레이션 결과는 제안한 방식이 기존의 신경회로망 및 Elman 신경회로망 보다 우수한 방식임을 보여 주고 있다.

• 한국군사과학기술학회지
• /
• 제4권2호
• /
• pp.189-201
• /
• 2001

For a design of multi-layer armor, the extensive full scale or sub-scale penetration test data are required. In generally, the collection of penetration data is in need of time-consuming and expensive processes. However, the application of numerical or analytical method is very limited due to poor understanding about penetration mechanics. In this paper, we have developed a neural network analyzer which can be used as a design tool for a new armor. Calculation results show that the developed neural network analyzer can predict relatively exact penetration depth of a new armor through the effective analysis of the pre-existing penetration database.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.250-253
• /
• 1998

This paper presents a multi-modal neural network composed of a preprocessing module and a multi-layer neural network module in order to enhance the nonlinear characteristics of neural network. The former module is based on spectral method using Chebyschev polynomials and transforms input data into spectra. The latter module identifies the system using the spectra generated by the preprocessing module. The omnibus numerical experiments show that the method is applicable to many a nonlinear dynamic system in the real world, and that preprocessing using Chebyschev polynomials reduces the number of neurons required for the multi-layer neural network.

• 한국컴퓨터정보학회논문지
• /
• 제6권4호
• /
• pp.68-73
• /
• 2001

MPLS(Multi protocol Label Switching)는 Network Traffic 흐름의 속도를 높이고 관리하기 쉽게 하기 위한 표준 기술이다. MPLS는 정해진 Pack 열에 특정 경로를 설정하는 것에 관여하고, 각 Pack 내에는 라벨이 있어 Router 입장에서는 그 Pack을 전달할 노드의 주소를 확인하여 소요시간을 절약한다. MPLS는 IP, ATM및 프레임 릴레이 Network protocol 등과 같이 작동한다. MPLS는 Network OSI 참조모델과 함께 3Layer가 아닌 Switching을 하는 2Layer에서 대부분의 Pack이 전달되게 한다. MPLS는 Traffic을 빠르게 움직이게 하며, QoS를 위한 Network관리를 쉽게 한다. 이런 이유에 MPLS 기술은 더 많고 특정한 Traffic을 전송하기 시작한 Network로 채택될 유망한 기술로 기대되고 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.40-45
• /
• 2004

This work presents a boundary estimation approach in electrical impedance imaging for binary-mixture fields based on a parallel structured multi-layer neural network. The interfacial boundaries are expressed with the truncated Fourier series and the unknown Fourier coefficients are estimated with the parallel structure of multi-layer neural network. Results from numerical experiments shows that the proposed approach is insensitive to the measurement noise and has a strong possibility in the visualization of binary mixtures for a real time monitoring.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1565-1568
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with multi-layer neural network. The structure of modular neural network in researched by Jacobs and Jordan is selected in this paper. Modular network consists of several expert networks and a gating network which is composed of single-layer neural network or multi-layer neural network. We propose modular network structure using recurrent neural network, since the state of the whole network at a particular time depends on an aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• 한국지능시스템학회논문지
• /
• 제14권7호
• /
• pp.847-851
• /
• 2004

Bishop과 Nabnck에 의해 소개된 기존치 혼합 밀도 네트워크(Mixture Density Network)에서는 조건부 확률밀도 함수의 매개변수들(parameters)이 하나의 MLP(multi-layer perceptron)의 출력 벡터로 주어진다. 최근에는 변형된 혼합 밀도 네트워크(Modified Mixture Density Network)라고 하는 이름으로 조건부 확률밀도 함수의 선분포(priors), 조건부 평균(conditional means), 그리고 공분산(covariances) 등이 각각 독립적인 MLP의 출력벡터로 주어지는 경우를 다룬 연구가 보고된 바 있다. 본 논문에서는 조건부 평균이 입력에 관해 선형인 경우를 위한 버전에 대한 이론과 매트랩 프로그램 개발을 다룬다. 본 논문에서는 우선 일반적인 혼합 밀도 네트워크에 대해 간단히 설명하고, 혼합 밀도 네트워크의 출력인 다층 퍼셉트론의 매개변수를 각각 다른 다층 퍼셉트론에서 학습시키는 변형된 혼합 밀도 네트워크를 설명한 후, 각각 다른 다층 퍼셉트론을 통해 매개변수를 얻는 것은 동일하나 평균값은 선형함수를 통해 얻는 혼합 밀도 네트워크 버전을 소개한다. 그리고, 모의실험을 통하여 이러한 혼합 밀도 네트워크의 적용가능성에 대해 알아본다.