• 인지과학
• /
• 제2권2호
• /
• pp.205-220
• /
• 1990

물질적으로 존재하는 모든 실체는 질료인과 형상인을 갖춘 개별 물체로 실재하면서 어떤 기능을 할 \ 수도 있고,동력인과 기능인을 갖춘 비물체적 양상으로 실재하면서 기능망(functional network)으로서 형상을 가질 수도 있다.기능망은 신경망,신경기능망,심리기능망 등 차원을 다르게 하면서 상하로 연관된 계층으 이루고 있으며 심리기능망 안에서도 비언어적 기능망,언어적 기능망이 구별되어 차원적 언어기능을 가능하게 하는 것으로 볼수 있다.이러한 기능망의 실재성은 신경과학과 인공지능학의 발전에 따라 확인, 수정,보완될 수 있을 것이다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 춘계학술대회
• /
• pp.419-421
• /
• 2018

Cloud vehicular networks are a promising paradigm to improve vehicular through distributing computation tasks between remote clouds and local vehicular terminals. Software-Defined Network(SDN) can bring advantages to Intelligent Transportation System(ITS) through its ability to provide flexibility and programmability through a logically centralized controlled cluster that has a full comprehension of view of the network. However, as the SDN paradigm is currently studied in vehicular ad hoc networks(VANETs), adapting it to work on cloud-based vehicular network requires some changes to address particular computation features such as task computation of applications of cloud-based vehicular networks. There has been initial work on briging SDN concepts to vehicular networks to reduce the latency by using the fog computing technology, but most of these studies do not directly tackle the issue of task computation. This paper proposes a Software-Defined Cloud-based vehicular Network called SDCVN framework. In this framework, we study the effectiveness of task computation of applications of cloud-based vehicular networks with vehicular cloud and roadside edge cloud. Considering the edge cloud service migration due to the vehicle mobility, we present an efficient roadside cloud based controller entity scheme where the tasks are adaptively computed through vehicular cloud mode or roadside computing predictive trajectory decision mode. Simulation results show that our proposal demonstrates a stable and low route setup time in case of installing the forwarding rules of the routing applications because the source node needs to contact the controller once to setup the route.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 춘계학술대회
• /
• pp.238-240
• /
• 2018

Cloud vehicular networks are a promising paradigm to improve vehicular through distributing computation tasks between remote clouds and local vehicular terminals. Software-Defined Network(SDN) can bring advantages to Intelligent Transportation System(ITS) through its ability to provide flexibility and programmability through a logically centralized controlled cluster that has a full comprehension of view of the network. However, as the SDN paradigm is currently studied in vehicular ad hoc networks(VANETs), adapting it to work on cloud-based vehicular network requires some changes to address particular computation features such as task computation of applications of cloud-based vehicular networks. There has been initial work on briging SDN concepts to vehicular networks to reduce the latency by using the fog computing technology, but most of these studies do not directly tackle the issue of task computation. This paper proposes a Software-Defined Cloud-based vehicular Network called SDCVN framework. In this framework, we study the effectiveness of task computation of applications of cloud-based vehicular networks with vehicular cloud and roadside edge cloud. Considering the edge cloud service migration due to the vehicle mobility, we present an efficient roadside cloud based controller entity scheme where the tasks are adaptively computed through vehicular cloud mode or roadside computing predictive trajectory decision mode. Simulation results show that our proposal demonstrates a stable and low route setup time in case of installing the forwarding rules of the routing applications because the source node needs to contact the controller once to setup the route.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1989년도 하계종합학술대회 논문집
• /
• pp.679-684
• /
• 1989

In this paper, we describe the PTP notion of robot manipulators by neural networks. The PTP motion requires the inverse kinematic redline and the joint trajectory generation algorithm. We use the multi-layered Perceptron neural networks and the Error Back Propagation(EBP) learning rule for inverse kinematic problems. Varying the number of hidden layers and the neurons of each hidden layer, we investigate the performance of the neural networks. Increasing the number of learning sweeps, we also discuss the performance of the neural networks. We propose a method for solving the inverse kinematic problems by adding the error compensation neural networks(ECNN). And, we implement the neural networks proposed by Grossberg et al. for automatic trajectory generation and discuss the problems in detail. Applying the neural networks to the current trajectory generation problems, we can refute the computation time for trajectory generation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.4618-4639
• /
• 2018

One of the most innovative paradigms for the next-generation of wireless cellular networks is the cloud-radio access networks (C-RANs). In C-RANs, base station functions are distributed between the remote radio heads (RHHs) and base band unit (BBU) pool, and a communication link is defined between them which is referred as the fronthaul. This leveraging link is expected to reduce the CAPEX (capital expenditure) and OPEX (operating expense) of envisioned cellular architectures as well as improves the spectral and energy efficiencies, provides the high scalability, and efficient mobility management capabilities. The fronthaul link carries the baseband signals between the RRHs and BBU pool using the digital radio over fiber (RoF) based common public radio interface (CPRI). CPRI based optical links imposed stringent synchronization, latency and throughput requirements on the fronthaul. As a result, fronthaul becomes a hinder in commercial deployments of C-RANs and is seen as one of a major bottleneck for backbone networks. The optimization of fronthaul is still a challenging issue and requires further exploration at industrial and academic levels. This paper comprehensively summarized the current challenges and requirements of fronthaul networks, and discusses the recently proposed system architectures, virtualization techniques, key transport technologies and compression schemes to carry the time-sensitive traffic in fronthaul networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권3호
• /
• pp.1249-1272
• /
• 2016

In this paper, we propose a symmetric key establishment scheme for wireless sensor networks which tries to minimize the resource usage while satisfying the security requirements. This is accomplished by taking advantage of the communication pattern of wireless sensor networks and adopting heterogeneous wireless sensor networks. By considering the unique communication pattern of wireless sensor networks due to the nature of information gathering from the physical world, the number of keys to be established is minimized and, consequently, the overhead spent for establishing keys decreases. With heterogeneous wireless sensor networks, we can build a hybrid scheme where a small number of powerful nodes do more works than a large number of resource-constrained nodes to provide enhanced security service such as broadcast authentication and reduce the burden of resource-limited nodes. In addition, an on-demand key establishment scheme is introduced to support extra communications and optimize the resource usage. Our performance analysis shows that the proposed scheme is very efficient and highly scalable in terms of storage, communication and computation overhead. Furthermore, our proposed scheme not only satisfies the security requirements but also provides resilience to several attacks.

• Computers and Concrete
• /
• 제25권5호
• /
• pp.401-409
• /
• 2020

Artificial neural networks are used as a useful tool in distinct fields of civil engineering these days. In order to control long-term quality of Self-Compacting Semi-Lightweight Concrete (SCSLC), the 90 days compressive strength is considered as a key issue in this paper. In fact, combined artificial neural networks are used to predict the compressive strength of SCSLC at 28 and 90 days. These networks are able to re-establish non-linear and complex relationships straightforwardly. In this study, two types of neural networks, including Radial Basis and Multilayer Perceptron, were used. Four groups of concrete mix designs also were made with two water to cement ratios (W/C) of 0.35 and 0.4, as well as 10% of cement weight was replaced with silica fume in half of the mixes, and different amounts of superplasticizer were used. With the help of rheology test and compressive strength results at 7 and 14 days as inputs, the neural networks were used to estimate the 28 and 90 days compressive strengths of above-mentioned mixes. It was necessary to add the 14 days compressive strength in the input layer to gain acceptable results for 90 days compressive strength. Then proper neural networks were prepared for each mix, following which four existing networks were combined, and the combinatorial neural network model properly predicted the compressive strength of different mix designs.

• 한국통신학회논문지
• /
• 제41권12호
• /
• pp.1721-1735
• /
• 2016

Power-efficient base station (BS) operation is one of the important issues in future green cellular networks. Previously well-known BS operation schemes, the cell zooming scheme and the cell wilting and blossoming scheme, require tight cooperation between cells in cellular networks. With the previous schemes, the non-cooperative BSs of a serving cell and neighboring cells could cause coverage holes between the cells, thereby seriously degrading the quality of service as well as the power saving efficiency of the cellular networks. In this paper, we propose a novel power-efficient BS operation scheme for green downlink heterogeneous cellular networks, in which the networks virtually adjust the coverage of a serving macrocell (SM) and neighboring macrocells (NMs) without adjusting the transmission power of the BSs when the SM is lightly loaded, and the networks turn off the BS of the SM when none of active users are associated with the SM. Simulation results show that our proposed scheme significantly improves the power saving efficiency without degrading the quality of service (e.g., system throughput) of a downlink heterogeneous LTE network and outperforms the previous schemes in terms of system throughput and power saving efficiency. In particular, with the proposed scheme, macrocells are able to operate independently without the cooperation of a SM and NMs for green heterogeneous cellular networks.

• Journal of Communications and Networks
• /
• 제9권4호
• /
• pp.419-427
• /
• 2007

In wavelength-division-multiplexing(WDM) networks a link failure may cause the failure of several high-bit-rate optical channels, thereby leading to large data loss. Recently, various protection and restoration mechanisms have been proposed to efficiently deal with this problem in mesh networks. Among them, dedicated path protection(DPP) is a promising candidate because of its ultra-fast restoration time and robustness. In this work we investigate the issue of planning and optimization of WDM networks with DPP. Integer linear programming(ILP), in particular, is one of the most common exact method to solve the design optimization problem for protected WDM networks. Traditional ILP formalizations to solve this problem rely on the classical flow or route formulation approaches, but both these approaches suffer from a excessively high computational burden. In this paper, we present a variable-aggregation method that has the ability of significantly reducing the complexity of the traditional flow formulation. We compare also the computational burden of flow formulation with variable aggregation both with the classical flow and route formulations. The comparison is carried out by applying the three alternative methods to the optimization of two case-study networks.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.327-332
• /
• 2005

We investigatea new fuzzy-neural networks-Hybrid Fuzzy set based polynomial Neural Networks (HFSPNN). These networks consist of genetically optimized multi-layer with two kinds of heterogeneous neurons thatare fuzzy set based polynomial neurons (FSPNs) and polynomial neurons (PNs). We have developed a comprehensive design methodology to determine the optimal structure of networks dynamically. The augmented genetically optimized HFSPNN (namely gHFSPNN) results in a structurally optimized structure and comes with a higher level of flexibility in comparison to the one we encounter in the conventional HFPNN. The GA-based design procedure being applied at each layer of gHFSPNN leads to the selection leads to the selection of preferred nodes (FSPNs or PNs) available within the HFSPNN. In the sequel, the structural optimization is realized via GAs, whereas the ensuing detailed parametric optimization is carried out in the setting of a standard least square method-based learning. The performance of the gHFSPNN is quantified through experimentation where we use a number of modeling benchmarks synthetic and experimental data already experimented with in fuzzy or neurofuzzy modeling.