• 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)
• /
• 제7권4호
• /
• pp.800-818
• /
• 2013

Supporting video streaming over multi-hop wireless networks is particularly challenging due to the time-varying and error-prone characteristics of the wireless channel. In this paper, we propose a joint optimization scheme for video streaming over multi-hop wireless networks. Our coding scheme, called Joint Source/Network Coding (JSNC), combines source coding and network coding to maximize the video quality under the limited wireless resources and coding constraints. JSNC segments the streaming data into generations at the source node and exploits the intra-session coding on both the source and the intermediate nodes. The size of the generation and the level of redundancy influence the streaming performance significantly and need to be determined carefully. We formulate the problem as an optimization problem with the objective of minimizing the end-to-end distortion by jointly considering the generation size and the coding redundancy. The simulation results demonstrate that, with the appropriate generation size and coding redundancy, the JSNC scheme can achieve an optimal performance for video streaming over multi-hop wireless networks.

• 한국통신학회논문지
• /
• 제39C권7호
• /
• pp.566-572
• /
• 2014

본 논문에서는 다중 선박으로 구성된 해양 네트워크에서 선박 간 통신 거리를 확장하면서 전송률을 향상시키는 양방향 다중-홉 릴레이 기법을 제안한다. 제안 기법은 두 단계 디지털 네트워크 부호화를 기반으로 각 선박의 데이터 전송 순서와 네트워크 부호화 순서를 알맞게 설계하여 데이터 교환에 필요한 시간 슬롯 수를 줄인다. 모의실험 결과 제안하는 양방향 다중 홉 릴레이 기법은 기존 기법의 전송률을 약 5/3배 향상시킴을 볼 수 있다.

• 한국항공운항학회:학술대회논문집
• /
• 한국항공운항학회 2016년도 춘계학술대회
• /
• pp.269-275
• /
• 2016

This paper considers the arrival, airport and departure capacity as a whole, through which, the network effect between airports is fully emphasized, the flight action is coordinated, and the flight demand pattern is reasonably assigned. The optimization problem of flight queues in multi-airport is studied in detail; the mathematical model of multi-airport opening non-real time flow management in terminal area is established, and related problems such as the parameters, the simplification and the solving of the model are discussed in detail to some extent. Appropriate decision making variables are taken to make the multi-airport network system linear 0-1 integer programming model, thus, the solving of the model is available and the central flow management is realized. The heuristic implicit enumeration presented in this paper can effectively solve this kind of problems. Through the simulation of some airports network system, we not only validate the algorithm presented in this paper, but also give a deep analysis of the results, which would produce reference for later practicable use. The simulation proves that this algorithm offers a good way to settle the problem of multi-airport flight queue optimization in air traffic management automation system in terminal area.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5013-5034
• /
• 2019

In the Peer-to-Peer (P2P) streaming systems, peers randomly form a network overlay to share video resources with a data scheduling scheme. A data scheduling scheme can have a great impact on system performance, which should achieve two optimal objectives at the same time ideally. The two optimization objectives are to improve the perceived video quality and maximize the network throughput, respectively. Maximizing network throughput means improving the utilization of peer's upload bandwidth. However, maximizing network throughput will result in a reduction in the perceived video quality, and vice versa. Therefore, to achieve the above two objects simultaneously, we proposed a new data scheduling scheme based on multi-objective particle swarm optimization data scheduling scheme, called MOPSO-DS scheme. To design the MOPSO-DS scheme, we first formulated the data scheduling optimization problem as a multi-objective optimization problem. Then, a multi-objective particle swarm optimization algorithm is proposed by encoding the neighbors of peers as the position vector of the particles. Through extensive simulations, we demonstrated the MOPSO-DS scheme could improve the system performance effectively.

• Asia pacific journal of information systems
• /
• 제30권4호
• /
• pp.808-831
• /
• 2020

The business world has been undergoing a digital transformation. The adoption of multi-sided digital platform across the world has sped up this transformation. Multi-sided digital platforms create value by mediating interactions and transactions of distinct groups of users. A platform and its stakeholders need to be considered as a business ecosystem. Elements or components in the ecosystem exchange values and together form a network of exchange values. The objective of this paper is to construct a framework for crafting and observing digital business ecosystems. The foundation theories used to construct the framework are transaction cost economy (TCE), multi-sided markets, and value network. This paper uses Go-Jek, a growing ride-hailing platform from Indonesia, as a case to discuss how the framework works in mapping Go-Jek's digital business ecosystem, and then explain its expansion strategy. This paper has both theoretical and managerial contributions. It provides a formal definition of digital business ecosystems as a network of exchange values. The framework does not only help studies the existing business ecosystems but also can be used to craft a new business ecosystem. It can also be used to study value exchanges within the ecosystem, assessing or crafting ecosystem expansion strategies.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2010년도 추계학술발표논문집 1부
• /
• pp.344-348
• /
• 2010

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2010년도 추계학술발표논문집 1부
• /
• pp.332-336
• /
• 2010

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.

• 산업기술연구
• /
• 제16권
• /
• pp.197-205
• /
• 1996

In this paper, we propose a new neural architecture. We synthesize the architecture from a combination of structures known as MRCCN (Multi-resolution Radial-basis Competitive and Cooperative Network) and BPN (Backpropagation Network). The proposed neural network is able to improve the learning speed of MRCCN and the mapping capability of BPN. The ability and effectiveness of identifying a ninlinear dynamic system using the proposed architecture will be demonstrated by computer simulation.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2009년도 춘계학술발표논문집
• /
• pp.454-457
• /
• 2009

The intent of this paper is to describe a neural network structure called multi dynamic neural network(MDNN), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the MDNN, are described. Computer simulations are demonstrate the effectiveness of the proposed learning using the MDNN.