Zobrazeno 1 - 10
of 5 668
pro vyhledávání: '"Takatsuka A"'
In recent years, there has been an increasing demand for underwater cameras that monitor the condition of offshore structures and check the number of individuals in aqua culture environments with long-period observation. One of the significant issues
Externí odkaz:
http://arxiv.org/abs/2410.01365
Publikováno v:
Array, Volume 15, 2022
Graph-based clustering methods like spectral clustering and SpectralNet are very efficient in detecting clusters of non-convex shapes. Unlike the popular $k$-means, graph-based clustering methods do not assume that each cluster has a single mean. How
Externí odkaz:
http://arxiv.org/abs/2302.13165
Publikováno v:
IEEE Access, Volume 10, 2022
Partitioning trees are efficient data structures for $k$-nearest neighbor search. Machine learning libraries commonly use a special type of partitioning trees called $k$d-trees to perform $k$-nn search. Unfortunately, $k$d-trees can be ineffective in
Externí odkaz:
http://arxiv.org/abs/2302.13160
Publikováno v:
Array, Volume 17, 2023
SpectralNet is a graph clustering method that uses neural network to find an embedding that separates the data. So far it was only used with $k$-nn graphs, which are usually constructed using a distance metric (e.g., Euclidean distance). $k$-nn graph
Externí odkaz:
http://arxiv.org/abs/2302.13168
Publikováno v:
Pattern Recognition Letters, Volume 128, 2019
Approximate spectral clustering (ASC) was developed to overcome heavy computational demands of spectral clustering (SC). It maintains SC ability in predicting non-convex clusters. Since it involves a preprocessing step, ASC defines new similarity mea
Externí odkaz:
http://arxiv.org/abs/2302.11298
Publikováno v:
Pattern Recognition Letters, Volume 122, 2019
The recently emerged spectral clustering surpasses conventional clustering methods by detecting clusters of any shape without the convexity assumption. Unfortunately, with a computational complexity of $O(n^3)$, it was infeasible for multiple real ap
Externí odkaz:
http://arxiv.org/abs/2302.11297
Publikováno v:
Pattern Recognition, Volume 114, 2021
Spectral clustering became a popular choice for data clustering for its ability of uncovering clusters of different shapes. However, it is not always preferable over other clustering methods due to its computational demands. One of the effective ways
Externí odkaz:
http://arxiv.org/abs/2302.11296
Publikováno v:
MethodsX, Volume 11, December 2023, 102315
Graph convolutional networks (GCNs) were a great step towards extending deep learning to unstructured data such as graphs. But GCNs still need a constructed graph to work with. To solve this problem, classical graphs such as $k$-nearest neighbor are
Externí odkaz:
http://arxiv.org/abs/2302.12001
Graph Neural Networks (GNNs) are increasingly becoming the favorite method for graph learning. They exploit the semi-supervised nature of deep learning, and they bypass computational bottlenecks associated with traditional graph learning methods. In
Externí odkaz:
http://arxiv.org/abs/2302.12000
Publikováno v:
Plant Signaling & Behavior, Vol 19, Iss 1 (2024)
Root hair, single-celled tubular structures originating from the epidermis, plays a vital role in the uptake of nutrients from the soil by increasing the root surface area. Therefore, optimizing root hair growth is crucial for plants to survive in fl
Externí odkaz:
https://doaj.org/article/31b1c31a07d7474987ce612135a6bb00
