Many application developers have been recently interested in applying deep learning techniques to their works but have little knowledge and experience on them. This paper presents the methods for a GUI-based modeling ...
详细信息
Many application developers have been recently interested in applying deep learning techniques to their works but have little knowledge and experience on them. This paper presents the methods for a GUI-based modeling tool to easily build deep learning models and automatically transform them into executable program codes. For reuse of existing deep learning codes, it introduces a method that imports such a program code, extracts the deep learning model architecture, and transforms it into a graphical representation that can be modified on a graphical interface. Meanwhile, a deep learning model with many layers is difficult to be visualized on a small display screen. To handle the difficulty, it proposes a method to identify the submodules called articulable subgraphs in a deep learning model and to organize the deep learning model into a hierarchical architecture using the nesting relationships of articulable subgraphs. It introduces a method to identify frequent substractures as well as articulable subgraphs as building blocks for deep learning models for levelwise views. The hierarchical representation easily enables to build deep learning models with many layers. The GUI-based modeling tool employing the proposed methods makes nonexpert developers easily use deep learning techniques in their practical applications.
Online social network has developed significantly in recent years. Most of current research has utilized the property of online social network to spread information and ideas. Motivated by applications in social netwo...
详细信息
ISBN:
(纸本)9781921770227
Online social network has developed significantly in recent years. Most of current research has utilized the property of online social network to spread information and ideas. Motivated by applications in social networks (such as alcohol intervention strategies), a variation of the dominating set called a positive influence dominating set (PIDS) has been studied in the literature. However, the existing work all focused on greedy algorithms for the PIDS problem with different approximation ratios, which are limited to find approximate solutions to PIDS in large networks. In order to select a minimal PIDS (MPIDS) in large social networks, we first present a self-stabilizing algorithm for the MPIDS problem in this paper, which can find a MPIDS in an arbitrary network graph without any isolated node. It is assumed that the nodes in the proposed algorithm have globally unique identifiers, and the algorithm works under a central daemon. We further prove that the worst case convergence time of the algorithm from any arbitrary initial state is O(n2) steps where n is the number of nodes in the network.
A linear-time algorithm for decomposing a graph into split components is presented. The algorithm uses a new graph transformation technique to gradually transform the given graph so that every split component in it is...
详细信息
ISBN:
(纸本)9781921770098
A linear-time algorithm for decomposing a graph into split components is presented. The algorithm uses a new graph transformation technique to gradually transform the given graph so that every split component in it is transformed into a subgraph with very simple structure which can be easily identified. Once the split components are determined, the triconnected components of the graph are easily determined. The algorithm is conceptually simple and makes one less pass over the input graph than the existing best known algorithm which could mean substantial saving in actual execution time. The new graph transformation technique may be useful in other context.
We present an unsupervised blood cell segmentation algorithm for images taken from peripheral blood smear slides. Unlike prior algorithms the method is fast; fully automated; finds all objects---cells, cell groups and...
详细信息
ISBN:
(纸本)9781920682439
We present an unsupervised blood cell segmentation algorithm for images taken from peripheral blood smear slides. Unlike prior algorithms the method is fast; fully automated; finds all objects---cells, cell groups and cell fragments---that do not intersect the image border; identifies the points interior to each object; finds an accurate one pixel wide border for each object; separates objects that just touch; and has been shown to work with a wide selection of red blood cell morphologies. The full algorithm was tested on two sets of images. In the first set of 47 images, 97.3% of the 2962 image objects were correctly segmented. The second test set---51 images from a different source---contained 5417 objects for which the success rate was 99.0%. The time taken for processing a 2272x1704 image ranged from 4.86 to 11.02 seconds on a Pentium 4, 2.4 GHz machine, depending on the number of objects in the image.
The traditional network flow estimation requires monitoring on every node which consumes too much resourceSo how to increase the deployment of new distributed monitors as the network expanding is becoming a new resear...
详细信息
The traditional network flow estimation requires monitoring on every node which consumes too much resourceSo how to increase the deployment of new distributed monitors as the network expanding is becoming a new research focusThis paper analyses the monitors adding mechanism and present a novel algorithm for finding candidate locations for additional deployment in the networkThe algorithm is based on Apriori search method that combines with the link weight change algorithm that aims to facilitate origin-destination flow computationWe also develop the greedy algorithm with Group Betweenness Centrality(GBC) involved for the purpose of comparingThe result shows that the new algorithm need less additional monitors than greedy algorithm.
Given a graph G = (V, E) and a requirement function r: W1 x W2 → R+ for two families W1, W2 ⊆ 2V - {θ}, we consider the problem (called area-to-area edge-connectivity augmentation problem) of augmenting G by a small...
详细信息
ISBN:
(纸本)9781920682750
Given a graph G = (V, E) and a requirement function r: W1 x W2 → R+ for two families W1, W2 ⊆ 2V - {θ}, we consider the problem (called area-to-area edge-connectivity augmentation problem) of augmenting G by a smallest number of new edges so that the resulting graph G satisfies δG (X) ≥ r(W1, W2) for all X ⊆ V, W1 ∈ W1, and W2 ∈ W2 with W1 ⊆ X ⊆ V - W2, where δG(X) denotes the degree of a vertex set X in G. This problem can be regarded as a natural generalization of the global, local, and node-to-area edge-connectivity augmentation *** this paper, we show that there exists a constant c such that the problem is inapproximable within a ratio of clog α(W1, W2), unless P=NP, even restricted to the directed global node-to-area edge-connectivity augmentation or undirected local node-to-area edge-connectivity augmentation, where α(W1, W2) denotes the number of pairs W1 ∈ W1 and W2 ∈ W2 with r(W1, W2) > 0. We also provide an O(log α (W1, W2))-approximation algorithm for the area-to-area edge-connectivity augmentation problem. This together with the negative result implies that the problem is Θ(log α (W1, W2))-approximable, unless P=NP, which solves open problems for node-to-area edge-connectivity augmentation (Ishii et al. 2008, Ishii and Hagiwara 2006, Miwa and Ito 2004).Furthermore, we characterize the node-to-area and area-to-area edge-connectivity augmentation problems as the augmentation problems with modulotone and extended modulotone functions.
This paper is motivated by the concept of the signed k-domination problem and dedicated to the complexity of the problem on graphs. For any fixed nonnegative integer k, we show that the signed k-domination problem is ...
详细信息
This paper is motivated by the concept of the signed k-domination problem and dedicated to the complexity of the problem on graphs. For any fixed nonnegative integer k, we show that the signed k-domination problem is NP-complete for doubly chordal graphs. For strongly chordal graphs and distance-hereditary graphs, we show that the signed k-domination problem can be solved in polynomial time. We also show that the problem is linear-time solvable for trees, interval graphs,and chordal comparability graphs.
Echocardiography is the most convenient means for both physicians and patients for heart disease diagnosis. The 3D+1D echocardiogram provides important information for evaluation of the 3D heart function such as the e...
详细信息
Echocardiography is the most convenient means for both physicians and patients for heart disease diagnosis. The 3D+1D echocardiogram provides important information for evaluation of the 3D heart function such as the ejection fraction or the wall motion. The most basic task to evaluate such functions of a heart is to segment the left ventricles and reconstruct the 3D geometric model of left ventricle from a set of echocardiographic images. Since there are many images involved, the method should not need too many user assists. In this work, we design a method for reconstructing the left ventricles with very few user assists.
暂无评论