• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.1
• /
• pp.92-98
• /
• 2019

In this paper, we propose a deep learning system based on morphological neural network(MNN). The deep learning layers are morphological operation layer, pooling layer, ReLU layer, and the fully connected layer. The operations used in morphological layer are erosion, dilation, and edge detection, etc. Unlike CNN, the number of hidden layers and kernels applied to each layer is limited in MNN. Because of the reduction of processing time and utility of VLSI chip design, it is possible to apply MNN to various mobile embedded systems. MNN performs the edge and shape detection operations with a limited number of kernels. Through experiments using database images, it is confirmed that MNN can be used as a deep learning system and its performance.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.496-499
• /
• 1999

This paper describes a medular neural network(MNN) for a vision system which tracks a given object using a sequence of images from a camera unit. The MNN is used to precisely recognize the given robot endeffector and to minize the processing time. Since the robot endeffector can be viewed in many different shapes in 3-D space, a MNN structure, which contains a set of feedforwared neural networks, co be more attractive in recognizing the given object. Each single neural network learns the endeffector with a cluster of training patterns. The training patterns for a neural network share the similar charateristics so that they can be easily trained. The trained MNN is less sensitive to noise and it shows the better performance in recognizing the endeffector. The recognition rate of MNN is enhanced by 14% over the single neural network. A vision system with the MNN can precisely recognize the endeffector and place it at the center of a display for a remote operator.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.186-191
• /
• 2003

Skills in tracing of the MR divide into following, approaching, avoiding and warning and so on. It is difficult to have all these skills learned as neural network. To make this up for, skills consisted of each module, and Mobile Robot was controlled by the output of module adequate for the situation. A mobile Robot was equipped multi-ultrasonic sensor and a USB Camera, which can be in place of human sense, and the measured environment information data is learned through Modular Neural Network. MNN consisted of optimal combination of activation function in the Expert Network and its structure seemed to improve learning time and errors. The Gating Network(GN) used to control output values of the MNN by switching for angle and speed of the robot. In the paper, EN of Modular Neural network was designed optimal combination. Traveling with a real MR was performed repeatedly to verity the usefulness of the MNN which was proposed in this paper. The robot was properly controlled and driven by the result value and the experimental is rewarded with good fruits.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.415-418
• /
• 2002

MR의 자율주행 기능에는 추종, 접근, 충돌회피, 경고 등의 여러 기능이 있다. 이 기능들을하나의 Neural Network로 학습시키는 것은 어려운 일이다. 이것을 보안하고자 기능들을 각각의 Module로 구성하여 상황에 맞게 학습된 Module의 출력 값으로 MR을 제어하였다 로봇은 인간의 감각을 대신할 수 있는 다중 초음파 센서와 PC 카메라를 장착하고 있으며, 이곳에서 측정된 환경정보 데이터들은 Modular Neural Network을 통해 학습이 이루어진다 MNN에서의 출력값은 Gating Network(GN)에서 로봇의 진행 방향과 속도를 스위칭 출력함으로서 MR을 제어하는데 사용된다. MNN 내 EN의 활성화 함수 최적결합을 통해 효과적인 MNN을 구성하였다. 본 논문에서는 Modular Neural Network의 Expert Network(EN)을 최적설계 하였고, 제안한 MNN의 검증을 위해 실시간으로 MR에 구현하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5C
• /
• pp.618-626
• /
• 2004

In this paper, we describe a robot endeffector recognition system based on a Modular Neural Networks (MNN). The proposed recognition system can be used for vision system which track a given object using a sequence of images from a camera unit. The main objective to achieve with the designed MNN is to precisely recognize the given robot endeffector and to minimize the processing time. Since the robot endeffector can be viewed in many different shapes in 3- D space, a MNN structure, which contains a set of feedforwared neural networks, can be more attractive in recognizing the given object. Each single neural network learns the endeffector with a cluster of training patterns. The training MNN patterns for a neural network share the similar characteristics so that they can be easily trained. The trained UM is les s sensitive to noise and it shows the better performance in recognizing the endeffector. The recognition rate of MNN is enhanced by 14％ over the single neural network. A vision system with the MNN can precisely recognize the endeffector and place it at the center of a display for a remote operator.

• Journal of Microbiology and Biotechnology
• /
• v.31 no.1
• /
• pp.163-170
• /
• 2021

Enzyme replacement therapy for lysosomal storage diseases usually requires recombinant enzymes containing mannose-6-phosphate (M6P) glycans for cellular uptake and lysosomal targeting. For the first time, a strategy is established here for the in vitro mannosyl-phosphorylation of high-mannose type N-glycans that utilizes a recombinant Mnn14 protein derived from Saccharomyces cerevisiae. Among a series of N-terminal- or C-terminal-deleted recombinant Mnn14 proteins expressed in Pichia pastoris, rMnn1477-935 with deletion of N-terminal 76 amino acids spanning the transmembrane domain (46 amino acids) and part of the stem region (30 amino acids), showed the highest level of mannosyl-phosphorylation activity. The optimum reaction conditions for rMnn1477-935 were determined through enzyme assays with a high-mannose type N-glycan (Man8GlcNAc2) as a substrate. In addition, rMnn1477-935 was shown to mannosyl-phosphorylate high-mannose type N-glycans (Man7-9GlcNAc2) on recombinant human lysosomal alpha-glucosidase (rhGAA) with remarkably high efficiency. Moreover, the majority of the resulting mannosyl-phosphorylated glycans were bis-form which can be converted to bis-phosphorylated M6P glycans having a superior lysosomal targeting capability. An in vitro N-glycan mannosyl-phosphorylation reaction using rMnn1477-935 will provide a flexible and straightforward method to increase the M6P glycan content for the generation of "Biobetter" therapeutic enzymes.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.1
• /
• pp.57-61
• /
• 2013

A hybrid genetic algorithm based learning method for the morphological neural networks (MNN) is proposed. The morphological neural networks are based on max-plus algebra, therefore, it is difficult to optimize the coefficients of MNN by the learning method with derivative operations. In order to solve the difficulty, a hybrid genetic algorithm based learning method to optimize the coefficients of MNN is used. Through the image compression/reconstruction experiment using test images extracted from standard image database(SIDBA), it is confirmed that the quality of the reconstructed images obtained by the proposed method is better than that obtained by the conventional neural networks.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.201-204
• /
• 1998

This paper presents a new construction method of candidate controllers using Multi-modal Neural Network(MNN). To improve a control performance of multiple controller, we construct, candidate controllers which consist of MNN. MNN can learn more complicated function than multilayer neural network. MNN consists of preprocessing module and neural network module. The preprocessing module transforms input signals into spectra which are used as input of the following neural network module. We apply the proposed method to multiple control system which controls the cart-pole balancing system and show the effectiveness of the proposed method.

• Journal of Korea Water Resources Association
• /
• v.34 no.6
• /
• pp.701-711
• /
• 2001

Forecasting of water quality variation is not an easy process due to the complicated nature of various water quality factors and their interrelationships. The objective of this study is to test the applicability of neural network models to the forecasting of the water quality at Gongju station in Geum River. This is done by forecasting monthly water qualities such as DO, BOD, and TN, and comparing with those obtained by ARIMA model. The neural network models of this study use BP(Back Propagation) algorithm for training. In order to improve the performance of the training, the models are tested in three different styles ; MANN model which uses the Moment-Adaptive learning rate method, LMNN model which uses the Levenberg-Marquardt method, and MNN model which separates the hidden layers for judgement factors from the hidden layers for water quality data. the results show that the forecasted water qualities are reasonably close to the observed data. And the MNN model shows the best results among the three models tested

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.4
• /
• pp.658-667
• /
• 2009

NEMO (Network Mobility) introduces the concept of mobile router in order to supply users with group mobility over wireless and mobile networks. This paper investigates the advantages and disadvantages of NEMO in terms of the overhead of group mobility management. This paper proposes the additional requirements to enhance NEMO performance. Moreover, we analyze the main communication paths, CN-HA, HA-MR, and MR-MNN, in the real NEMO testbed.