• 한국문헌정보학회지
• /
• 제40권2호
• /
• pp.333-355
• /
• 2006

이 연구에서는 지적 구조 분석을 위해서 계량서지적 자료를 시각적으로 표현하는 다양한 네트워크 형성 방식에 대해서 사례와 함께 각각의 특성을 살펴보았다. 기준값 절단 방식, 최근접이웃 그래프, 최소비용 신장트리, 패스파인더 네트워크의 네 가지 네트워크 형성 방식 중에서 전체 구조와 세부 구조의 표현 능력이 모두 뛰어난 패스파인더 네트워크 알고리즘이 최근 가장 활발히 응용되고 있다. 최근접이웃 그래프는 아직까지 계량서지적 분석에 응용된 사례는 없으나 간단한 알고리즘과 클러스터링 능력 등과 같은 지적 구조 규명에 도움이 될 수 있는 몇 가지 장점을 갖추고 있는 것으로 확인되었다. 다차원척도나 군집분석과 달리 네트워크를 이용한 시각화에서는 입력자료의 전처리에 따라서 생성된 지적 구조의 차이가 큰 것으로 나타났다. 이 연구에서 고찰한 여러 네트워크 형성 방식을 적절히 활용함으로써 국내의 지적 구조 규명 연구를 활성화할 수 있을 것이라 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권5호
• /
• pp.527-547
• /
• 2009

Moving object management is widely used in traffic, logistic and data mining applications in ubiquitous environments. It is required to analyze spatio-temporal data and trajectories for moving object management. In this paper, we proposed a novel index structure for spatio-temporal aggregation of trajectory in a constrained network, named aCN-RB-tree. It manages aggregation values of trajectories using a constraint network-based index and it also supports direction of trajectory. An aCN-RB-tree consists of an aR-tree in its center and an extended B-tree. In this structure, an aR-tree is similar to a Min/Max R-tree, which stores the child nodes' max aggregation value in the parent node. Also, the proposed index structure is based on a constrained network structure such as a FNR-tree, so that it can decrease the dead space of index nodes. Each leaf node of an aR-tree has an extended B-tree which can store timestamp-based aggregation values. As it considers the direction of trajectory, the extended B-tree has a structure with direction. So this kind of aCN-RB-tree index can support efficient search for trajectory and traffic zone. The aCN-RB-tree can find a moving object trajectory in a given time interval efficiently. It can support traffic management systems and mining systems in ubiquitous environments.

• Food Science and Biotechnology
• /
• 제15권1호
• /
• pp.77-81
• /
• 2006

The dextransucrase activity of microorganisms which were identified as contributing to the fermentation of jeungpyeon made with yeast was measured. The dextran generated during fermentation was quantified and the viscosity changes were measured. The mechanism of network structure formation was clarified by observing the inside of the network structure over the fermentation periods ranging from 1 to 7 hr using scanning electron microscopy (SEM). The pH of jeungpyeon batter decreased significantly as the fermentation proceeded, whereas the viscosity increased. The identified lactic acid bacteria (LAB) were Leuconostoc mesenteroides subsp. mesenteroides, Pediococcus pentosaceus, Tetragenococcus halophilus, and Leuconostoc mesenteroides subsp. dextranicum. The yeast was identified as Saccharomyces cerevisiae A/Tor. Pretorien. The dextransucrase extracted from those microorganisms showed high activity. On the other hand, the amount of dextran generated from the batter increased significantly beyond 2 hr of fermentation, and the viscosity increment showed a similar trend. The SEM photos showed that the most homogeneous fine network structure was observed in the batter fermented for 2 hr. Therefore, we assumed that the dextran that was generated by microorganisms during fermentation interacted with the components of the batter to increase the stability of the network structure.

• 전자공학회논문지S
• /
• 제35S권4호
• /
• pp.67-75
• /
• 1998

In general, Evoluationary Algorithm(EAs) are refered to as methods of population-based optimization. And EAs are considered as very efficient methods of optimal sytem design because they can provice much opportunity for obtaining the global optimal solution. This paper presents a co-evolution scheme of artifical neural networks, which has two different, still cooperatively working, populations, called as a host popuation and a parasite population, respectively. Using the conventional generatic algorithm the host population is evolved in the given environment, and the parastie population composed of schemata is evolved to find useful schema for the host population. the structure of artificial neural network is a diagonal recurrent neural netork which has self-feedback loops only in its hidden nodes. To find optimal neural networks we should take into account the structure of the neural network as well as the adaptive parameters, weight of neurons. So we use the genetic algorithm that searches the structure of the neural network by the co-evolution mechanism, and for the weights learning we adopted the evolutionary stategies. As a results of co-evolution we will find the optimal structure of the neural network in a short time with a small population. The validity and effectiveness of the proposed method are inspected by applying it to the stabilization and position control of the invered-pendulum system. And we will show that the result of co-evolution is better than that of the conventioal genetic algorithm.

• 융합보안논문지
• /
• 제21권2호
• /
• pp.47-56
• /
• 2021

그래프 시각화 이론에 근간을 둔 네트워크 토폴로지 시각화는 복잡한 네트워크의 전체 구조와 노드간의 상호작용을 보다 이해하기 쉽게 만든다. 네트워크 토폴로지를 시각화하는 도구는 과거부터 많이 개발되었지만, 일정 수준의 기능을 갖춘 도구들은 도구마다 고유한 네트워크 구성 정보(노드의 식별자, 종류, 속성, 연결된 노드 등)를 입력으로 요구하기 때문에 범용적으로 사용하기 어렵다. 반면에 최소한의 네트워크 구성 정보인 노드간의 연결만을 사용하는 도구들은 네트워크의 실제 연결 형태를 표시하는 기능이 부족하다. 본 논문에서는 네트워크 노드간의 연결 정보만을 이용하여 토폴로지를 시각화하는 효율적인 방법을 제안한다. 이 방법은 네트워크에서 노드의 영향력을 나타내는 중심성 지수를 활용하여 중심노드를 찾고, 자식노드의 가중치를 이용하여 전체 노드들의 표시 영역을 동적 분할한 후 3D 공간 상에 노드들을 배치함으로써 토폴로지를 시각화한다. 매우 간단한 방법이지만 노드간의 연결 정보만으로 실제 네트워크 연결 형태를 시각화할 수 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.459-462
• /
• 2000

In this paper, we propose the initial optimized structure of the Radial Basis Function Network which is more simple in the part of the structure and converges more faster than Neural Network with the analysis method using Time-Frequency Localization. When we construct the hidden node with the Radial Basis Function whose localization is similar with an approximation target function in the plane of the Time and Frequency, we make a good decision of the initial structure having an ability of approximation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.113.1-113
• /
• 2001

The robust position control with the bound function of neural network structure is proposed for uncertain robot manipulators. The neural network structure presents the bound function and does not need the concave property of the bound function, The robust approach is to solve this problem as uncertainties are included in a model and the controller can achieve the desired properties in spite of the imperfect modeling. Simulation is performed to validate this law for four-axis SCARA type robot manipulators.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.49-52
• /
• 1998

Neural Network has good performance in pattern classification, control and many other fields by learning ability. However, there is effective rule or systematic approach to determine optimal structure. In this paper, we propose a new method to find optimal structure of feed-forward multi-layer neural network as a kind of pruning method. That eliminating redundant elements of neural network. To find redundant elements we analysis error and weight changing with Rough Set Theory, in condition of executing back-propagation leaning algorithm.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1171-1174
• /
• 1993

A promising approach to get the benefits of neural networks and fuzzy logic is to combine them into an integrated system to merge the computational power of neural networks and the representation and reasoning properties of fuzzy logic. In this context, this paper presents a fuzzy neural network which is able to code fuzzy knowledge in the form of it-then rules in its structure. The network also provides an efficient structure not only to code knowledge, but also to support fuzzy reasoning and information processing. A learning scheme is also derived for a class of membership functions.