sensors-logo

Journal Browser

Journal Browser

Machine Learning and Intelligent Optimization Data Aggregation in Internet of Things 2022

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (20 January 2023) | Viewed by 3559

Special Issue Editor

Special Issue Information

Dear Colleagues,

Machine Learning (ML) and Intelligent Optimization are two of the most advanced fields in data science benefiting from the modern computational facilities. Taking the advantage of the powerful computing system, ML has evolved into the deep learning model, which includes more layers in the whole model structure, and is available to be trained mission-ready in a feasible time. The intelligent optimization technology is now capable of operating with large population and multigroup structures for handling large-scale of data.

The Internet of Things (IoT) is the latest Internet evolution that incorporates billions of Internet-connected devices that range from cameras, sensors, RFIDs, smart phones, and wearables, to smart meters, vehicles, medication pills, signs and industrial machines. Such IoT things are often owned by different organizations and people who are deploying and using them for their own purposes. Federations of such IoT devices (referred to as IoT things) can also deliver timely and accurate information that is needed to solve internet-scale problems that have been too difficult to tackle before.

In recent years, research outcomes have shown evidence that data aggregation and data process operations can be smart by combining ML and/or intelligent optimization with IoT. To realize its enormous potential, IoT must provide IoT solutions for discovering needed IoT devices, collecting and integrating their data with efficient ML or optimization techniques, and distilling the high value information each application needs. Such IoT solutions must be capable of filtering, aggregating, correlating, and contextualizing IoT information in real-time, on the move, in the edge and the cloud, and securely and must be capable of introducing data-driven changes to the physical world.

The MDPI Sensors solicits paper submissions and aim to bring together researchers and application developers working on the intersection of ML, optimization, and IoT with next-generation sensor development, distributed, cloud, internet, mobile, ambient, semantic, real-time, secure and privacy-preserving computing. We also aim to explore the application of novel IoT computing results and describe and assess their impact. The Special Issue seeks to compile original contributions that have not been published previously or already submitted to other conferences or journals. Review articles in the related subjects are also welcome.

Prof. Dr. Dimitrios Georgakopoulos
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

26 pages, 2908 KiB  
Article
Deep Reinforcement Learning–Based Online One-to-Multiple Charging Scheme in Wireless Rechargeable Sensor Network
by Zheng Gong, Hao Wu, Yong Feng and Nianbo Liu
Sensors 2023, 23(8), 3903; https://0-doi-org.brum.beds.ac.uk/10.3390/s23083903 - 12 Apr 2023
Cited by 3 | Viewed by 1471
Abstract
Wireless rechargeable sensor networks (WRSN) have been emerging as an effective solution to the energy constraint problem of wireless sensor networks (WSN). However, most of the existing charging schemes use Mobile Charging (MC) to charge nodes one-to-one and do not optimize MC scheduling [...] Read more.
Wireless rechargeable sensor networks (WRSN) have been emerging as an effective solution to the energy constraint problem of wireless sensor networks (WSN). However, most of the existing charging schemes use Mobile Charging (MC) to charge nodes one-to-one and do not optimize MC scheduling from a more comprehensive perspective, leading to difficulties in meeting the huge energy demand of large-scale WSNs; therefore, one-to-multiple charging which can charge multiple nodes simultaneously may be a more reasonable choice. To achieve timely and efficient energy replenishment for large-scale WSN, we propose an online one-to-multiple charging scheme based on Deep Reinforcement Learning, which utilizes Double Dueling DQN (3DQN) to jointly optimize the scheduling of both the charging sequence of MC and the charging amount of nodes. The scheme cellularizes the whole network based on the effective charging distance of MC and uses 3DQN to determine the optimal charging cell sequence with the objective of minimizing dead nodes and adjusting the charging amount of each cell being recharged according to the nodes’ energy demand in the cell, the network survival time, and MC’s residual energy. To obtain better performance and timeliness to adapt to the varying environments, our scheme further utilizes Dueling DQN to improve the stability of training and uses Double DQN to reduce overestimation. Extensive simulation experiments show that our proposed scheme achieves better charging performance compared with several existing typical works, and it has significant advantages in terms of reducing node dead ratio and charging latency. Full article
Show Figures

Figure 1

18 pages, 26210 KiB  
Article
Can Satellite Remote Sensing Assist in the Characterization of Yeasts Related to Biogeographical Origin?
by David Castrillo, Pilar Blanco and Sergio Vélez
Sensors 2023, 23(4), 2059; https://0-doi-org.brum.beds.ac.uk/10.3390/s23042059 - 11 Feb 2023
Cited by 1 | Viewed by 1396
Abstract
Biogeography is a key concept associated with microbial terroir, which is responsible for the differentiation and uniqueness of wines. One of the factors influencing this microbial terroir is the vegetation, which in turn is influenced by climate, soil, and cultural practices. Remote sensing [...] Read more.
Biogeography is a key concept associated with microbial terroir, which is responsible for the differentiation and uniqueness of wines. One of the factors influencing this microbial terroir is the vegetation, which in turn is influenced by climate, soil, and cultural practices. Remote sensing instruments can provide useful information about vegetation. This study analyses the relationship between NDVI, calculated using Sentinel-2 and Landsat-8 satellite images of different veraison dates, and microbial data obtained in 2015 from 14 commercial (organic and conventional) vineyards belonging to four Designations of Origin (DOs) from Galicia (northwest Spain). Microbial populations in grapes and musts were identified using PCR techniques and confirmed by sequencing. Statistical analyses were made using PCA, CCA, TB-PLS, and correlation analyses. This study confirms that the NDVI is positively correlated with the diversity of yeasts, both in grapes’ surface and must samples. Moreover, the results of this study show: (i) Sentinel-2 images, as well as Landsat-8 images, can establish differences in NDVI related to yeast terroir in grapes and musts, as it is the most relevant DO factor, (ii) Sentinel-2 NDVI and yeast biogeography are moderately to strongly correlated, (iii) Sentinel-2 achieved a better delimitation of the DOs than Landsat-8 and can establish more accurate differences in NDVI–yeast terroir correlations, and (iv) a higher NDVI was associated with the yeast biogeographical patterns of the DOs with higher species richness (S) consisting of weakly fermenting yeasts (Hanseniaspora uvarum, Pichia spp., Starmerella bacillaris, and Zygosaccharomyces spp). However, NDVI values did not correlate well with biogeographic patterns of yeasts previously studied at frequency level (proportion or percentage of each species) in each particular DO. This study suggests that satellite imagery has the potential to be a valuable tool for wine quality management and a decision-making instrument for DO regulators and winegrowers. Full article
Show Figures

Graphical abstract

Back to TopTop