• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2001년도 기술교육위원회 창립총회 및 학술대회 의료기기전시회
• /
• pp.23-27
• /
• 2001

Making the safety situation from the various work system is very important in the industrial fields. The proposed neural network technique is the real titre computation method based theory of inter-node diffusion for searching the safety distances from the sudden appearance-objests during the work driving. The main steps of the distance computation using the theory of stereo vision like the eyes of man is following steps. One is the processing for finding the corresponding points of stereo images and the other is the interpolation processing of full image data from nonlinear image data of obejects. All of them request much memory space and titre. Therefore the most reliable neural-network algorithm is drived for real time recognition of obejects, which is composed of a dynamic programming algorithm based on sequence matching techniques. And the real time reconstruction of nonlinear image information is processed through several simulations. I-D LIPN hardware has been composed, and the real time reconstruction is verified through the various experiments.

• 정보보호학회논문지
• /
• 제22권5호
• /
• pp.999-1007
• /
• 2012

공개키 기반 암호화 상에서의 다중 곱셈 연산은 높은 복잡도로 인해 성능 개선을 위해서는 우선적으로 고려되어야 한다. 특히 임베디드 장비는 기존의 환경과는 달리 한정적인 계산 능력과 저장 공간으로 인해 높은 복잡도를 나타내는 공개키 기반의 암호화를 수행하기에는 부적합한 특성을 가진다. 이를 극복하기 위해 다중 곱셈 연산을 빠르게 연산하고 적은 저장공간을 요구하는 기법이 활발히 연구되고 있다. 본 논문에서는 자원 한정적인 센서 네트워크 상에서의 효율적인 공개키 기반 암호화 구현을 위한 다중 곱셈기의 최신 연구 동향을 살펴본다. 이는 앞으로의 센서 네트워크상에서의 공개키 기반 암호화 구현을 위한 참고자료로서 활용이 가능하다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1996년도 추계학술대회 논문
• /
• pp.133-137
• /
• 1996

This paper presents a new approach to the design of neural control system using digital signal processors in order to improve the precision and robustness. Robotic manipulators have bevome increasingly important in the field of flexible automation. High speed and high-precision trajectory tracking arre indispensable capabilities for their versatile application. the need to meet demanding control requirement in increasingly complex dynamical control systems under sygnificant uncertainties leads toward design of implementing real time neural control to provide an enhanced motion control for robotic manipulators. In this control scheme the ntworks intrduced are neural nets with dynamic neurouns whose dynamics are distributed over all the network nodes. The nets are trained by the distributed dynamic are distributed over all the network nodes. The nets are trained by the distributed dynamic back propagation algorithm. The proposed neural network control scheme is simple in structure fast in computation and suitable for implementation of real-time control, Performance of the neural controller is illustrated by simulation and experimental results for a SCAEA robot.

• 로봇학회논문지
• /
• 제18권1호
• /
• pp.88-92
• /
• 2023

Lithium-ion batteries are actively used in various industrial sites such as field robots, drones, and electric vehicles due to their high energy efficiency, light weight, long life span, and low self-discharge rate. When using a lithium-ion battery in a field, it is important to accurately estimate the SoC (State of Charge) of batteries to prevent damage. In recent years, SoC estimation using data-based artificial neural networks has been in the spotlight, but it has been difficult to deploy in the embedded board environment at the actual site because the computation is heavy and complex. To solve this problem, neural network lightening technologies such as network pruning have recently attracted attention. When pruning a neural network, the performance varies depending on which layer and how much pruning is performed. In this paper, we introduce an optimized pruning technique by improving the existing pruning method, and perform a comparative experiment to analyze the results.

• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• 한국국방경영분석학회지
• /
• 제25권2호
• /
• pp.73-83
• /
• 1999

In this paper, we consider the shortest path network problem with fixed charges. A turn penalty algorithm for the shortest path problem with fixed charges or turn penalties is presented, which is using the next node comparison method. The algorithm described here is designed to determine the shortest route in the shortest path network problem including turn penalties. Additionally, the way to simplify the computation for the shortest path problem with turn penalties was pursued.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2007년도 추계학술대회 논문집
• /
• pp.506-507
• /
• 2007

Lateral Information Propagation Neural Networks (LIPN) is proposed for on-line interpolation. The proposed neural network technique is the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Through several simulation experiments, real time reconstruction of the nonlinear image information is processed.

• 한국정보통신학회논문지
• /
• 제22권1호
• /
• pp.1-8
• /
• 2018

최근 합성곱 신경망은 컴퓨터 비전에 관련된 여러 분야에서 높은 성능을 보여 주고 있으나 합성곱 신경망이 요구하는 많은 연산양은 임베디드 환경에 도입되는 것을 어렵게 하고 있다. 이를 해결하기 위해 ASIC이나 FPGA를 통한 합성곱 신경망의 구현에 많은 관심이 모이고 있고, 이러한 구현을 위해서는 효율적인 고정 소수점 표현이 필요하다. 고정 소수점 표현은 ASIC이나 FPGA에서의 구현에 적합하나 합성곱 신경망의 성능이 저하될 수 있는 문제가 있다. 이 논문에서는 합성곱 계층과 배치(batch) 정규화 계층에 대해 고정 소수점 표현을 분리해서, ResNet-50 합성곱 신경망의 합성곱 계층을 표현하기 위해 필요한 비트 수를 16비트에서 10비트로 줄일 수 있게 하였다. 연산이 집중되는 합성곱 계층이 더 간단하게 표현되므로 합성곱 신경망 구현이 전체적으로 더 효율적으로 될 것이다.

• 융합보안논문지
• /
• 제13권6호
• /
• pp.77-82
• /
• 2013

최근 네트워크 사용자의 가치 변화와 이용 패턴을 살펴보면, 단순 웹 정보, 단방향 정보습득의 일방적인 데이터 전달에서, 멀티미디어 활용의 증가, 보안 및 개인화의 요구 증대, 자유로운 이동성에 대한 욕구 증가 등의 변화가 생기고 있다. 이러한 욕구의 변화로 인해 개별적으로 제공되는 각각의 서비스는 점차 융합화된 형태의 통합 서비스로 발전하고, 네트워크 또한 각각의 서비스를 위한 개별 망에서 이용자의 다양한 통합 욕구를 실현시켜 주는 지능형 통합망의 형태로 발전할 것으로 전망되며, 관련한 기술의 핵심이 되는 통신망 제어기술 또한 급속히 발전하고 있다. 본 논문에서는 자원의 효율적 사용은 물론 다중 도메인 (multi-domain)환경에서 다계층 (multi-layer)간의 정보 전달을 최소화하고, 최적의 경로선택을 할 수 있는 방법을 제안하였다. 기존의 경로선택에서 각각의 계층에 대한 정보를 이용하여 경로를 선택한 것에 비하여 다계층 구조상에서 다 계층의 정보를 활용하여 경로선택에 대한 다각화를 통한 최적의 경로선택이 수행되도록 제안하였다.