efficient machine
Recently Published Documents


TOTAL DOCUMENTS

256
(FIVE YEARS 157)

H-INDEX

13
(FIVE YEARS 6)

2021 ◽  
Author(s):  
Jingjing Xia ◽  
Jin Zeng

Abstract Water is an indispensable resource for human production and life. The evaluation of water quality by scientific method that provides sufficient support for the regeneration and recycling utilization of water resources. At present, water quality is mainly evaluated by water quality index (WQI) with weighted entropy value, which comprehensively considers the influence of different relevant environmental factors on the water quality. The calculation process is very complicated and time-consuming. In this paper, the method of correlation analysis is used to select the best combination of relevant environmental factors to assist the prediction model. Two typical kinds of machine learning methods are adopted and compared to realize the prediction of entropy water quality index (EWQI). After the better framework of prediction model is selected, four different kinds of optimization algorithms are used to optimize the prediction model to realize non-linear regression prediction and classification of water quality. According to the results of evaluation indicators, the framework of SVM is more suitable for realizing the prediction of EWQI. Meanwhile, the optimization algorithm of DE-GWO show great potential to improve the performance of SVM, which can make further contribution to the rational use and protection of water resources.


2021 ◽  
Author(s):  
Kazuki Morita ◽  
Daniel Davies ◽  
Keith Butler ◽  
Aron Walsh

While traditional crystallographic representations of structure play an important role in materials science, they are unsuitable for efficient machine learning. A range of effective numerical descriptors have been developed for molecular and crystal structures. We are interested in a special case, where distortions emerge relative to an ideal high-symmetry parent structure. We demonstrate that irreducible representations form an efficient basis for the featurisation of polyhedral deformations with respect to such an aristotype. Applied to dataset of 552 octahedra in ABO3 perovskite-type materials, we use unsupervised machine learning with irreducible representation descriptors to identify four distinct classes of behaviour, associated with predominately corner, edge, face, and mixed connectivity between neighbouring octahedral units. Through this analysis, we identify SrCrO3 as a material with tuneable multiferroic behaviour. We further show, through supervised machine learning, that thermally activated structural distortions of CsPbI3 are well described by this approach.


2021 ◽  
Author(s):  
Kazuki Morita ◽  
Daniel Davies ◽  
Keith Butler ◽  
Aron Walsh

While traditional crystallographic representations of structure play an important role in materials science, they are unsuitable for efficient machine learning. A range of effective numerical descriptors have been developed for molecular and crystal structures. We are interested in a special case, where distortions emerge relative to an ideal high-symmetry parent structure. We demonstrate that irreducible representations form an efficient basis for the featurisation of polyhedral deformations with respect to such an aristotype. Applied to dataset of 552 octahedra in ABO3 perovskite-type materials, we use unsupervised machine learning with irreducible representation descriptors to identify four distinct classes of behaviour, associated with predominately corner, edge, face, and mixed connectivity between neighbouring octahedral units. Through this analysis, we identify SrCrO3 as a material with tuneable multiferroic behaviour. We further show, through supervised machine learning, that thermally activated structural distortions of CsPbI3 are well described by this approach.


2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Xu Zhang ◽  
Haibo Hou ◽  
Zhao Fang ◽  
Zhiqian Wang

With the development of Internet of Things (IoT), 5G, and industrial technology, Industrial Internet has become an emerging research field. Due to the industrial specialty, higher requirements are put forward for time delay, safety, and stability of the identification analysis service. The traditional domain name system (DNS) cannot meet the requirements of industrial Internet because of the single form of identification subject and weak awareness of security protection. As a solution, this work applies blockchain and federated learning (FL) to the industrial Internet identification. Blockchain is a decentralized infrastructure widely used in digital encrypted currencies such as Bitcoin, which can make secure data storage and access possible. Federated learning protects terminal personal data privacy and can carry out efficient machine learning among multiple participants. The numerical results justify that our proposed federated learning and blockchain combination lays a strong foundation for the development of future industrial Internet.


2021 ◽  
Vol 13 (21) ◽  
pp. 4470
Author(s):  
Teo Nguyen ◽  
Benoît Liquet ◽  
Kerrie Mengersen ◽  
Damien Sous

Coral reefs are an essential source of marine biodiversity, but they are declining at an alarming rate under the combined effects of global change and human pressure. A precise mapping of coral reef habitat with high spatial and time resolutions has become a necessary step for monitoring their health and evolution. This mapping can be achieved remotely thanks to satellite imagery coupled with machine-learning algorithms. In this paper, we review the different satellites used in recent literature, as well as the most common and efficient machine-learning methods. To account for the recent explosion of published research on coral reel mapping, we especially focus on the papers published between 2018 and 2020. Our review study indicates that object-based methods provide more accurate results than pixel-based ones, and that the most accurate methods are Support Vector Machine and Random Forest. We emphasize that the satellites with the highest spatial resolution provide the best images for benthic habitat mapping. We also highlight that preprocessing steps (water column correction, sunglint removal, etc.) and additional inputs (bathymetry data, aerial photographs, etc.) can significantly improve the mapping accuracy.


2021 ◽  
Vol 2 (4) ◽  
pp. 418-433
Author(s):  
Nabi Rezvani ◽  
Amin Beheshti

Cyberbullying detection is a rising research topic due to its paramount impact on social media users, especially youngsters and adolescents. While there has been an enormous amount of progress in utilising efficient machine learning and NLP techniques for tackling this task, recent methods have not fully addressed contextualizing the textual content to the highest possible extent. The textual content of social media posts and comments is normally long, noisy and mixed with lots of irrelevant tokens and characters, and therefore utilizing an attention-based approach that can focus on more relevant parts of the text can be quite pertinent. Moreover, social media information is normally multi-modal in nature and may contain various metadata and contextual information that can contribute to enhancing the Cyberbullying prediction system. In this research, we propose a novel machine learning method that, (i) fine tunes a variant of BERT, a deep attention-based language model, which is capable of detecting patterns in long and noisy bodies of text; (ii)~extracts contextual information from multiple sources including metadata information, images and even external knowledge sources and uses these features to complement the learner model; and (iii) efficiently combines textual and contextual features using boosting and a wide-and-deep architecture. We compare our proposed method with state-of-the-art methods and highlight how our approach significantly outperforming the quality of results compared to those methods in most cases.


Sign in / Sign up

Export Citation Format

Share Document