A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked Indoors
Currently, there are billions of connected devices, and the Internet of Things (IoT) has boosted these numbers. In the case of private networks, a few hundred devices connected can cause instability and even data loss in communication. In this article, we propose a machine learning-based modeling to...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Journal of Sensor and Actuator Networks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2224-2708/11/2/29 |
| _version_ | 1797485503789924352 |
|---|---|
| author | Daniel Carvalho Daniel Sullivan Rafael Almeida Carlos Caminha |
| author_facet | Daniel Carvalho Daniel Sullivan Rafael Almeida Carlos Caminha |
| author_sort | Daniel Carvalho |
| collection | DOAJ |
| description | Currently, there are billions of connected devices, and the Internet of Things (IoT) has boosted these numbers. In the case of private networks, a few hundred devices connected can cause instability and even data loss in communication. In this article, we propose a machine learning-based modeling to solve network overload caused by continuous monitoring of the trajectories of several devices tracked indoors. The proposed modeling was evaluated with over a hundred thousand of coordinate locations of objects tracked in three synthetic environments and one real environment. It has been shown that it is possible to solve the network overload problem by increasing the latency in sending data and predicting intermediate coordinates of the trajectories on the server-side with ensemble models, such as Random Forest, and using Artificial Neural Networks without relevant data loss. It has also been shown that it is possible to predict at least thirty intermediate coordinates of the trajectories of objects tracked with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> greater than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.8</mn></mrow></semantics></math></inline-formula>. |
| first_indexed | 2024-03-09T23:19:44Z |
| format | Article |
| id | doaj.art-a58fca9c8712493eab5b78047ed38121 |
| institution | Directory Open Access Journal |
| issn | 2224-2708 |
| language | English |
| last_indexed | 2024-03-09T23:19:44Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Sensor and Actuator Networks |
| spelling | doaj.art-a58fca9c8712493eab5b78047ed381212023-11-23T17:29:35ZengMDPI AGJournal of Sensor and Actuator Networks2224-27082022-06-011122910.3390/jsan11020029A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked IndoorsDaniel Carvalho0Daniel Sullivan1Rafael Almeida2Carlos Caminha3Programa de Pós Graduação em Informática Aplicada, Unifor, Fortaleza 60811-905, BrazilPrograma de Pós Graduação em Informática Aplicada, Unifor, Fortaleza 60811-905, BrazilCentro de Ciências Tecnológicas, Unifor, Fortaleza 60811-905, BrazilPrograma de Pós Graduação em Informática Aplicada, Unifor, Fortaleza 60811-905, BrazilCurrently, there are billions of connected devices, and the Internet of Things (IoT) has boosted these numbers. In the case of private networks, a few hundred devices connected can cause instability and even data loss in communication. In this article, we propose a machine learning-based modeling to solve network overload caused by continuous monitoring of the trajectories of several devices tracked indoors. The proposed modeling was evaluated with over a hundred thousand of coordinate locations of objects tracked in three synthetic environments and one real environment. It has been shown that it is possible to solve the network overload problem by increasing the latency in sending data and predicting intermediate coordinates of the trajectories on the server-side with ensemble models, such as Random Forest, and using Artificial Neural Networks without relevant data loss. It has also been shown that it is possible to predict at least thirty intermediate coordinates of the trajectories of objects tracked with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> greater than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.8</mn></mrow></semantics></math></inline-formula>.https://www.mdpi.com/2224-2708/11/2/29network overloadInternet of Thingsmachine learning |
| spellingShingle | Daniel Carvalho Daniel Sullivan Rafael Almeida Carlos Caminha A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked Indoors Journal of Sensor and Actuator Networks network overload Internet of Things machine learning |
| title | A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked Indoors |
| title_full | A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked Indoors |
| title_fullStr | A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked Indoors |
| title_full_unstemmed | A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked Indoors |
| title_short | A Machine Learning Approach to Solve the Network Overload Problem Caused by IoT Devices Spatially Tracked Indoors |
| title_sort | machine learning approach to solve the network overload problem caused by iot devices spatially tracked indoors |
| topic | network overload Internet of Things machine learning |
| url | https://www.mdpi.com/2224-2708/11/2/29 |
| work_keys_str_mv | AT danielcarvalho amachinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors AT danielsullivan amachinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors AT rafaelalmeida amachinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors AT carloscaminha amachinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors AT danielcarvalho machinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors AT danielsullivan machinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors AT rafaelalmeida machinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors AT carloscaminha machinelearningapproachtosolvethenetworkoverloadproblemcausedbyiotdevicesspatiallytrackedindoors |