• 대한전자공학회논문지SD
• /
• 제41권3호
• /
• pp.71-82
• /
• 2004

생태계의 군집 특성을 네트워크 환경에 적용하여 급변하는 환경에 대한 자가 적응 및 생존 특성을 부여하는 연구가 최근 많은 주목을 받고 있다. 그 중 AntNet은 개미를 모델링한 모바일 에이젼트를 사용하여 최적의 네트워크 경로를 선택하는 적응적 라우팅 알고리즘이다. 본 논문에서는 SoC 시스템에 적용 가능한 AntNet 기반 하드웨어 구조를 제안한다. 제안된 구조는 기존 알고리즘 수준의 AntNet을 하드웨어 레벨로 근사화 하여 설계되었으며, 기존 AntNet과 가상 네트워크 구조에서의 비교를 통하여 그 타당성을 검증하였다. 그리고 RTL 수준의 설계 및 합성 결과를 통하여 제안된 하드웨어 구조가 AntNet 기반 라우팅 구현에 효과적임을 확인할 수 있었다.

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1415-1421
• /
• 2015

This paper presents a new algorithm called Quantum-behaved Electromagnetism-like Mechanism Algorithm which is used to solve economic load dispatch of power system. Electromagnetism-like mechanism algorithm simulates attraction and repulsion mechanism for particles in the electromagnetic field. Every solution is a charged particle, and it move to optimum solution according to certain criteria. Quantum-behaved electromagnetism-like mechanism algorithm merges quantum computing theory with electromagnetism-like mechanism algorithm. Superposition characteristic of quantum methodology can make a single particle present several states, and the characteristic potentially increases population diversity. Probability representation of quantum methodology is to make particle state be presented according to a certain probability. And the quantum rotation gates are used to realize update operation of particles. The algorithm is tested for 13-generator system and 40-generator system, which validates it can effectively solve economic load dispatch problem. Through performance comparison, it is obvious the solution is superior to other optimization algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2277-2298
• /
• 2019

Adaptive learning in e-learning has garnered researchers' interest. In it, learning resources could be recommended automatically to achieve a personalized learning experience. There are various ways to realize it. One of the realistic ways is adaptive learning path recommendation, in which learning resources are provided according to learners' requirements. This paper summarizes existing works and proposes an innovative approach. Firstly, a learner-centred concept map is created using graph theory based on the features of the learners and concepts. Then, the approach generates a linear concept sequence from the concept map using the proposed traversal algorithm. Finally, Learning Objects (LOs), which are the smallest concrete units that make up a learning path, are organized based on the concept sequences. In order to realize this step, we model it as a multi-objective combinatorial optimization problem, and an improved immune algorithm (IIA) is proposed to solve it. In the experimental stage, a series of simulated experiments are conducted on nine datasets with different levels of complexity. The results show that the proposed algorithm increases the computational efficiency and effectiveness. Moreover, an empirical study is carried out to validate the proposed approach from a pedagogical view. Compared with a self-selection based approach and the other evolutionary algorithm based approaches, the proposed approach produces better outcomes in terms of learners' homework, final exam grades and satisfaction.

• 조명전기설비학회논문지
• /
• 제26권8호
• /
• pp.56-64
• /
• 2012

This paper proposes a novel maximum power point tracking (MPPT) control algorithm considering radiation to improve efficiency of PV system. The proposed algorithm is composed perturb and observe (PO) method and constant voltage (CV) method. PO method is simple to realize and CV method is possible to tracking MPP with low radiation. Response characteristics of proposed algorithm are compared to conventional MPPT algorithm such as PO method, IC method and CV method with radiation variation. This paper proves the validity of proposed algorithm through the analysis results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.173-178
• /
• 1998

The strategy presented in this paper is based on modifying the past patterens and adjusting the content of the driving patterns by a new algorithm. Learning happens during the driving procedure of a mobile vehicle. The purpose of this paper is to solve the problem how to realize the hardware neurocomputer by back propagation (BP) neural network learning on-line.

• Journal of Information Processing Systems
• /
• 제19권2호
• /
• pp.232-239
• /
• 2023

Aiming at the poor compression quality of traditional image compression coding (ICC) algorithm, a multi-description ICC algorithm based on depth learning is put forward in this study. In this study, first an image compression algorithm was designed based on multi-description coding theory. Image compression samples were collected, and the measurement matrix was calculated. Then, it processed the multi-description ICC sample set by using the convolutional self-coding neural system in depth learning. Compressing the wavelet coefficients after coding and synthesizing the multi-description image band sparse matrix obtained the multi-description ICC sequence. Averaging the multi-description image coding data in accordance with the effective single point's position could finally realize the compression coding of multi-description images. According to experimental results, the designed algorithm consumes less time for image compression, and exhibits better image compression quality and better image reconstruction effect.

• ETRI Journal
• /
• 제36권4호
• /
• pp.591-598
• /
• 2014

This paper proposes a new min-sum algorithm for low-density parity-check decoding. In this paper, we first define the negative and positive effects of the received signal-to-noise ratio (SNR) in the min-sum decoding algorithm. To improve the performance of error correction by considering the negative and positive effects of the received SNR, the proposed algorithm applies adaptive scaling factors not only to extrinsic information but also to a received log-likelihood ratio. We also propose a combined variable and check node architecture to realize the proposed algorithm with low complexity. The simulation results show that the proposed algorithm achieves up to 0.4 dB coding gain with low complexity compared to existing min-sum-based algorithms.

• 전자공학회논문지B
• /
• 제33B권2호
• /
• pp.178-186
• /
• 1996

This paper proposes a new design technique that can be used for BSB (brain-state-in-a-box) neural networks to realize autoassociative memories. The proposed method is based on the parametrization of solution space and optimization using genetic algorithm. The applicability of the established technique is demonstrated by means of a simulation example, which illustrates its strengths.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.1045-1048
• /
• 1999

In this paper, we report on a set of new algorithms to realize a nonlinear compressed-domain video/audio editor that overcomes various realization problems. For efficiency, the underlying algorithm, which uses a central data structure in the form of doubled linked lists, performs soft edits of cut and paste (which, in turn, involves soft implementations of frame type conversion) and addresses problems relating to video/audio synchronization and random access, and decoder buffer control.

• 한국통신학회논문지
• /
• 제21권1호
• /
• pp.144-154
• /
• 1996

Proposed numerous algorithms for the policing function have mainly focused on their performances. Besides their performance evaluation, however, the VLSI-implementation of these algorithms is worth consideration as well. Although, no algorithms for the policing function have been standardized up to now, ITU-T I.371 suggests two examples of algorithms, the Virtual Scheduling Algorithm (VSA) and the Continuous State Leaky Bucket algorithm. In this paper, we suggest the architecture of a policing device implementing the VSA among various algorithms for the peak cell rate policing and discuss some issues on the implementation. We also present how to select the policing modes of the two devices used to realize various policing schemes and show the experimental results obtained under four different peak cell rate values to confirm that the device performs the policing function satisfactorily. We exploit the priority encoder to run the algorithm in parallel instead of sequentially, which reduces the operation time to a great extent.