• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1025-1030
• /
• 2019

This paper describes SON(: Self Organization Network) technology in LTE networks. The SON is a unique feature of LTE compared to previous cellular systems such as UMTS and GSM, and it is a tool that effectively derives the best performance in the time-varying wireless radio environment. Also, the SON has the ability for the operator to automate the setting of the network, allowing for centralized planning and reducing the need for manual work. The SON is largely divided into three categories: Self-Configuration, Self-Optimization, and Self-Healing. Each large categories has a detailed description of technology, and the technologies in each categories are gathered to complete the technology called the SON. In this paper, we focus on MRO which is one of the Self-Optimization technique in each of the three categories.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.837-852
• /
• 2021

Recurrent neural network (RNN) architectures have been used for language modeling (LM) tasks that require learning long-range word or character sequences. However, the RNN architecture is still suffered from unstable gradients on long-range sequences. To address the issue of long-range sequences, an attention mechanism has been used, showing state-of-the-art (SOTA) performance in all LM tasks. A differentiable neural computer (DNC) is a deep learning architecture using an attention mechanism. The DNC architecture is a neural network augmented with a content-addressable external memory. However, in the write operation, some information unrelated to the input word remains in memory. Moreover, DNCs have been found to perform poorly with low numbers of weight parameters. Therefore, we propose a robust memory deallocation method using a limited retention vector. The limited retention vector determines whether the network increases or decreases its usage of information in external memory according to a threshold. We experimentally evaluate the robustness of a DNC implementing the proposed approach according to the size of the controller and external memory on the enwik8 LM task. When we decreased the number of weight parameters by 32.47%, the proposed DNC showed a low bits-per-character (BPC) degradation of 4.30%, demonstrating the effectiveness of our approach in language modeling tasks.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.2 s.314
• /
• pp.24-31
• /
• 2007

This paper presents self tuning PI(STPI) controller of IPMSM drive using neural network. In general, PI controller in computer numerically controlled machine process fixed gain. They may perform well under some operating conditions, but not all. To increase the robustness of fixed gain PI controller, STPI controller proposes a new method based neural network. STPI controller is developed to minimize overshoot, rise time and settling time following sudden parameter changes such as speed, load torque and inertia. Also, this paper is proposed speed control of IPMSM using neural network and estimation of speed using artificial neural network(ANN) controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The results on a speed controller of IPMSM are presented to show the effectiveness of the proposed gain tuner. And this controller is better than the fixed gains one in terms of robustness, even under great variations of operating conditions and load disturbance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.2
• /
• pp.215-221
• /
• 2016

Data failure in wireless communications considerably affects the reconstruction quality of transmitted data. Traditionally, fascinating trials have been conducted to overcome the data failure intensifying reliable reconstruction of a media. But, none of these efforts neither effective, computationally inexpensive nor simply configurable to reduce the problems of transmitting media or images. In practice, it is necessary to maintain the quality of transmitted image without sacrificing any data, content, or information. So, to deal with dynamic events such as sensor node participation and departure, during transmission, an efficient scheme is important. For this reason, a new robust scheme has been presented in this paper to minimize the limitation of traditional wireless networking. This scheme uses Software-Defined Image Sensor Network (SD-ISN) to ensure scalability and dependability of the sensor network of handling data losses. Finally, a comparison of our proposed SD-ISN with conventional wireless networking has been presented in simulation to test the robustness and effectiveness of our proposed SD-ISN approach.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.228-228
• /
• 2023

국지적 지역에 내리는 강한 강도의 강우는 많은 인명 및 재산 피해를 발생시킨다. 이러한 피해를 예방하기 위해 도시 침수 예측에 관한 연구가 오랜 기간 수행되어 왔으며, 최근에는 다양한 신경망(neural network) 모델이 활발히 이용되고 있다. 강우 지속 기간이나 강도는 일정하지 않고, 공간적 특징 또한 도시마다 다르므로 안정적인 침수 예측을 위한 신경망 모델은 강건성(robustness)을 지녀야 한다. 강건한 신경망 모델이란 적대적 공격(adversarial attack)을 방어할 수 있는 능력을 갖춘 모델을 일컫는다. 따라서 본 연구에서는, 도시 침수 예측을 위한 시공간 신경망(spatio-temporal neural network) 모델의 강건성 제고를 위한 방법론을 제안한다. 먼저 적대적 공격의 유형과 방어 방법을 분류하고, 시공간 신경망 모델의 학습 데이터 특성 및 모델 구조구성 조건 등을 활용하여 최적의 강건성 제고 방안을 도출하였다. 해당 모델은 집중호우로 인해 나타날 다양한 관망에서의 침수 피해를 각각 예측하고 피해를 예방하기 위해 활용될 수 있다.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.166-175
• /
• 2020

Recently, application fields for processing and using digital image contents in various forms and types are rapidly increasing. Since image content is high value-added content, the intellectual property rights of this content must be protected in order to activate the production and use of the digital image content. In this paper, we propose a deep learning based watermark embedding and extraction network. The proposed method is to maximize the robustness of the watermark against malicious/non-malicious attacks while preserving the invisibility of the host image. This network consists of a preprocessing network that changes the watermark to have the same resolution as the host image, a watermark embedding network that embeds watermark data while maintaining the resolution of the host image by three-dimensionally concatenating the changed host image and the watermark information, and a watermark extraction network that reduces the resolution and extracts watermarks. This network verifies the invisibility and robustness of the proposed method by experimenting with various pixel value change attacks and geometric attacks against various watermark data and host images with various resolutions, and shows that this method is universal and practical.

• The KIPS Transactions:PartC
• /
• v.12C no.6 s.102
• /
• pp.891-900
• /
• 2005

This paper studies network recovery methods for WDM optical mesh networks, concentrating on improving spare resource utilization. The resource efficiency can be obtained by sharing spare resources needed for network recovery. To improve the sharability of spare resources in WDM networks, methods to share backup paths us well as spare capacity should be studied. The proposed method in this paper uses multiple ring-covers and this method provides fast and simple recovery operation by exploiting the characteristics of logical ring topology, and also provides efficient resource utilization by using multiple distributed backup paths to improve the sharability of overall spare resources in the networks. This method can provide layered reliability to network service by enabling hierarchical robustness against multiple failures. The performance results show that the proposed method provide improved resource efficiency for single failure and enhanced robustness for multiple failures.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.7
• /
• pp.65-73
• /
• 2006

This paper presents speed control of IPMSM drive using neural network(NN) PI controller. In general, PI controller in computer numerically controlled machine process fixed gain. They may perform well under some operating conditions, but not all. To increase the robustness of fixed gain PI controller, NNPI controller proposes a new method based neural network. NNPI controller is developed to minimize overshoot rise time and settling time following sudden parameter changes such as speed, load torque and inertia. Also, this paper is proposed speed control of IPMSM using neural network and estimation of speed using artificial neural network(ANN) controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The results on a speed controller of IPMSM are presented to show the effectiveness of the proposed gain tuner. And this controller is better than the fixed gains one in terms of robustness, even under great variations of operating conditions and load disturbance.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.12
• /
• pp.1306-1316
• /
• 1990

A controller using a multilayer neural network is proposed to the dynamic control of a PUMA 560 robot arm. This controller is developed based on an error back-propagation (BP) neural network. Since the neural network can model an arbitrary nonlinear mapping, it is used as a commanded feedforward torque generator. A Proportional Derivative (PD) feedback controller is used in parallel with the feedforward neural network to train the system. The neural network was trained by the current state of the manipulator as well as the PD feedback error torque. No a priori knowledge on system dynamics is needed and this information is rather implicitly stored in the interconnection weights of the neural network. In another experiment, the neural network was trained with the current, past and future positions only without any use of velocity sensors. Form this thim window of position values, BP network implicitly filters out the velocity and acceleration components for each joint. Computer simulation demonstrates such powerful characteristics of the neurocontroller as adaptation to changing environments, robustness to sensor noise, and continuous performance improvement with self-learning.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.71.2-71
• /
• 2001

This paper deals with nonlinear system modelling using neural network and genetic algorithm. Application of neural network to control and identification is actively studied because of their approximating ability of nonlinear function. It is important to design the neural network with optimal structure for minimum error and fast response time. Genetic algorithm is getting more popular nowadays because of their simplicity and robustness. In this paper, We optimize neural network structure using genetic algorithm. The genetic algorithm uses binary coding for neural network structure and search for optimal neural network structure of minimum error and response time. Through extensive simulation, Optimal neural network structure is shown to be effective for ...