Hierarchical Discriminant Analysis

Lu, Di; Ding, Chuntao; Xu, Jinliang; Wang, Shangguang

doi:10.3390/s18010279

“…S4 [55], and it is found that these methods are not as efficient as TS-LPP. Recently, several reports have suggested that two-step analysis for dimension reduction is useful, such as PCA-LPP, PCA-t-SNE, and PCA-UMAP [61][62][63][64]. Our results show that there is a useful case even if the same dimensionality reduction method is repeated in the two-step analysis, although the different algorithms are usually combined.…”

Section: A Structural Analysis Of Crystalline Liquid and Amorphous St...mentioning

confidence: 61%

Structural analysis based on unsupervised learning: Search for a characteristic low-dimensional space by local structures in atomistic simulations

Matsuda

¹

,

Lin

²

,

Futamura

³

et al. 2022

View full text Add to dashboard Cite

Owing to the advances in computational techniques and the increase in computational power, atomistic simulations of materials can simulate large systems with higher accuracy. Complex phenomena can be observed in such state-of-the-art atomistic simulations. However, it has become increasingly difficult to understand what is actually happening and mechanisms, for example, in molecular dynamics (MD) simulations. We propose an unsupervised machine learning method to analyze the local structure around a target atom. The proposed method, which uses the two-step locality preserving projections (TS-LPP), can find a low-dimensional space wherein the distributions of datapoints for each atom or groups of atoms can be properly captured. We demonstrate that the method is effective for analyzing the MD simulations of crystalline, liquid, and amorphous states and the melt-quench process from the perspective of local structures. The proposed method is demonstrated on a silicon single-component system, a silicon-germanium binary system, and a copper single-component system.

show abstract

“…S4, and it is found that these methods are not as efficient as TS-LPP. Recently, several reports have suggested that two-step analysis for dimension reduction is useful, such as PCA-LPP, PCA-t-SNE, and PCA-UMAP [58][59][60][61]. Our results show that there is a useful case even if the same dimensionality reduction method is repeated in the two-step analysis, although the different algorithms are usually combined.…”

Section: A Structural Analysis Of Crystalline Liquid and Amorphous St...mentioning

confidence: 61%

Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations

Tamura,

Matsuda,

Lin

et al. 2021

Preprint

0

View full text Add to dashboard Cite

Owing to the advances in computational techniques and the increase in computational power, atomistic simulations of materials can simulate large systems with higher accuracy. Complex phenomena can be observed in such state-of-the-art atomistic simulations. However, it has become increasingly difficult to understand what is actually happening and mechanisms, for example, in molecular dynamics (MD) simulations. We propose an unsupervised machine learning method to analyze the local structure around a target atom. The proposed method, which uses the two-step locality preserving projections (TS-LPP), can find a low-dimensional space wherein the distributions of datapoints for each atom or groups of atoms can be properly captured. We demonstrate that the method is effective for analyzing the MD simulations of crystalline, liquid, and amorphous states and the melt-quench process from the perspective of local structures. The proposed method is demonstrated on a silicon single-component system, a silicon-germanium binary system, and a copper single-component system.

show abstract

“…The network's availability and coverage area must allow for the use of networks to continue regardless of mobility, complex network topology changes, or changes in current technologies. All of this necessitates interoperability, handover, and recovery processes in the event of unattended operations [97].…”

Section: Availabilitymentioning

confidence: 99%

Revolutionary Strategies Analysis and Proposed System for Future Infrastructure in Internet of Things

Kumar

¹

,

Sharma

²

,

Singh

³

et al. 2021

View full text Add to dashboard Cite

The Internet of Things (IoT) has changed the worldwide network of people, smart devices, intelligent things, data, and information as an emergent technology. IoT development is still in its early stages, and numerous interrelated challenges must be addressed. IoT is the unifying idea of embedding everything. The Internet of Things offers a huge opportunity to improve the world’s accessibility, integrity, availability, scalability, confidentiality, and interoperability. However, securing the Internet of Things is a difficult issue. The IoT aims to connect almost everything within the framework of a common infrastructure. This helps in controlling devices and, will allow device status to be updated everywhere and at any time. To develop technology via IoT, several critical scientific studies and inquiries have been carried out. However, many obstacles and problems remain to be tackled in order to reach IoT’s maximum potential. These problems and concerns must be taken into consideration in different areas of the IoT, such as implementation in remote areas, threats to the system, development support, social and environmental impacts, etc. This paper reviews the current state of the art in different IoT architectures, with a focus on current technologies, applications, challenges, IoT protocols, and opportunities. As a result, a detailed taxonomy of IoT is presented here which includes interoperability, scalability, security and energy efficiency, among other things. Moreover, the significance of blockchains and big data as well as their analysis in relation to IoT, is discussed. This article aims to help readers and researchers understand the IoT and its applicability to the real world.

show abstract

Hierarchical Discriminant Analysis

Cited by 8 publications

References 17 publications

Structural analysis based on unsupervised learning: Search for a characteristic low-dimensional space by local structures in atomistic simulations

Structural analysis based on unsupervised learning: Search for a characteristic low-dimensional space by local structures in atomistic simulations

Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations

Revolutionary Strategies Analysis and Proposed System for Future Infrastructure in Internet of Things

Contact Info

Product

Resources

About