In this paper, we propose an automatic shape matching method which can be used to match two non-rigid deformation shapes with isometric or nearly isometric transformations. the main purpose of our method is to enhance...
详细信息
ISBN:
(纸本)9781450389532
In this paper, we propose an automatic shape matching method which can be used to match two non-rigid deformation shapes with isometric or nearly isometric transformations. the main purpose of our method is to enhance the effectiveness of the linear assignment matrix, and then obtain the final matching result by using a combinatorial optimization algorithm to solve the objective function. First, we calculate each point in the two matching shapes separately by using SHOT and HKS descriptors. then, we combine two assignment matrices constructed by the SHOT and HKS descriptors, which combination can fully capture the Euclidean structure information and Riemann structure information of the graph and effectively enhances the relationship between points. In the final, we construct our new objective function by using descriptors and heat distribution matrix, all of which are enhanced by Riemann structure information. the final matching result is obtained by solving the objective function using the projected descent optimization procedure. In light of this, our algorithm is better than other state-of-the-art methods. the effectiveness of this method is proven by geodesic error distance statistics from two commonly used datasets with ground truth.
the task of identifying influencers provides a lot of benefits for various practical applications such as recommendation systems, viral marketing, and information monitoring. this issue can traditionally be solved via...
详细信息
ISBN:
(纸本)9781450388436
the task of identifying influencers provides a lot of benefits for various practical applications such as recommendation systems, viral marketing, and information monitoring. this issue can traditionally be solved via a network structure with several proposed graph algorithms. However, most of them employ a global computation with much time-consuming; some consider only undirected and unweighted networks which may be inconsistent withthe nature of data. Inspired by the law of gravity in Physics, we present the Topic-oriented Gravity Model (TopicGM) that investigates a directed and weighted network incorporating users' topical aspects. the key concept is that an individual is first represented as a textual content he created or read. Afterwards, TopicGM simply adopts a topic modeling, i.e., the Hierarchical Dirichlet Process (HDP), to classify topics over those contents. A topical network is then constructed where nodes represent individuals and an edge connects two individuals in the direction from the poster to the reader with a topical confidence weight. Finally, we apply the gravity formula to calculate influence scores and rank individuals. the experimental results, conducted on real-world data gathered from *** (famous thai web forum), show that our approach outperforms many state-of-the-art baselines by accurately identifying influencers within the top of rankings.
Subspace clustering method based on kernel learning shows superior performance when dealing with nonlinear high dimensional data. However, the clustering performance of existing single kernel subspace clustering metho...
详细信息
ISBN:
(纸本)9781450387811
Subspace clustering method based on kernel learning shows superior performance when dealing with nonlinear high dimensional data. However, the clustering performance of existing single kernel subspace clustering methods largely depends on the selected kernel function, and the low-rank structure of the data in the feature space after kernel mapping is not considered. In addition, the learned affinity matrix cannot maintain the block diagonal property, which may reduce the clustering performance. In this paper, we propose a robust multiple kernel subspace clustering based on low rank consensus kernel learning (MKLRSC) method for data clustering. Our model has three innovations: (1) the introduction of correntropy in the multiple kernel weighting strategy helps to learn the optimal consensus kernel. (2) In order to maintain the low-rank structure of input data, we impose a nuclear norm constraint on the optimal consensus kernel matrix. (3) Considering the block diagonal property of the affinity matrix, MKLRSC applies block diagonal constraint to the coefficient matrix. Compared with several state-of-the-art multiple kernel subspace clustering methods, experiments on three datasets confirm that MKLRSC achieves more competitive clustering results.
Recently, medicinal imaging has shown significant growth in demand due to its ability to provide useful information from human anatomical images, which helps understand symptoms and diagnose patients (Garz43;n &...
详细信息
ISBN:
(数字)9798350364729
ISBN:
(纸本)9798350364736
Recently, medicinal imaging has shown significant growth in demand due to its ability to provide useful information from human anatomical images, which helps understand symptoms and diagnose patients (Garzón & Cardenas-Villa 2020), with astrocytoma’s separation among the crucial tasks popular the field that can assist clinicians on diagnosis, treatment planning as well as monitoring of patient they are concerned about. Deep learning algorithms have started to show impressive results in the segmentation of brain tumors from MRI images over recent years. therefore, this study presents a new deep learning algorithm that utilizes kernel-based Convolutional Neural Networks (CNN) and multi-class Support Vector Machines (M-SVM) for more correct separation of astrocytoma’s. the latter is a kernel-based CNN method that efficiently learns deep structures as of the contribution MRI pictures. the features remain input into the mm classifier, which accurately classifies them to different tumor regions (necrotic core, edema and enhancing tumor). Besides, we introduce a boundary refinement module into the framework to fine-tune results at segmentation boundaries for better accuracy. Here, we attempted to analyze our analyze algorithm over publicly available annotation datasets experimentally and compared them against the state-of-the-art as baselines. Our approach outperformed previous studies with an normal Dice comparation constant of 0.93, illustrating the capacity to segment brain tumor regions accurately. In addition, our algorithm demonstrated a resilience to noise and differences in image resolution.
Underwater Wireless Sensor Networks (UWSNs), is one of the stat-of-the-art research areas if the present day oceanography domain is concerned due to the kind of support it offers for the wide range of underwater appli...
详细信息
ISBN:
(数字)9781728163871
ISBN:
(纸本)9781728163888
Underwater Wireless Sensor Networks (UWSNs), is one of the stat-of-the-art research areas if the present day oceanography domain is concerned due to the kind of support it offers for the wide range of underwater applications. Due to the drastic increase in the number of potential underwater applications the effective communication between different underwater nodes need to be ensured. But when putting in place an Underwater Wireless Sensor Networks, one of the most important tasks is the deployment of nodes, which plays an important role in achieving seamless routing in the tricky underwater environment. Because only based on the node deployment, most of the essential network services such as network boundary detection, routing, and topology control of network are carried out. A huge amount of research is done with respect to 2D node deployments in terrestrial networks, but the amount of attention given to 3D node deployments are very limited. So the scope of this article revolves around analyzing the effects of node deployment techniques on the localization performance of the UWSN environment which is 3 dimensional in nature. this research work has considered three different node deployment strategies such as regular tetrahedron, cube, and random node deployment techniques for conducting simulation study. As a result of the simulation study carried out in this research article, it is clear that the performance of regular tetrahedron node deployment is a way better than cube node deployment and random node deployment techniques. Since most of the present day applications use random node deployment, the results of this article may lead to the improved design of UWSN in the upcoming years.
20204thinternationalconference on Material science and Technology (ICMST 2020) has been held successfully in Wuhan, P.R. China from January 22nd-23rd, 2020, organized by Hubei Zhongke Institute of Geology and Envir...
详细信息
20204thinternationalconference on Material science and Technology (ICMST 2020) has been held successfully in Wuhan, P.R. China from January 22nd-23rd, 2020, organized by Hubei Zhongke Institute of Geology and Environment Technology. ICMST 2020 proceeding tends to collect the most up-to-date, comprehensive, and worldwide state-of-art knowledge on Material science and Technology. All the accepted papers have been submitted to strict peer-review by 2-4 expert referees, and selected based on originality, significance and clarity for the purpose of the conference. the conference program is extremely rich, profound and featuring high-impact presentations of selected papers and additional late-breaking contributions. We sincerely hope that the conference would not only show the participants a broad overview of the latest research results on related fields, but also provide them with a significant platform for academic connection and exchange. the Technical Program Committee members have been working very hard to meet the deadline of review. We have collected more than 350 submissions during the conference period. the final conference consists of 149 papers divided into 12 sessions.
暂无评论