Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/127056
Title: Detecció i predicció d'anomalies en dispositius IoT en l'Edge computing
Author: Llussà Sala, Antoni
Director: Solé-Ribalta, Albert  
Tutor: Trilles Oliver, Sergi
Abstract: Nowadays, Internet of Things (IoT) devices can run machine learning (ML) models. Taking advantage of the computational power of these devices, the incorporation of a ML model to detect and predict anomalies in the data (time series) is intended. Data is collected real time by sensors connected to the device. Predicting and detecting anomalies within the IoT device can provide benefits such as reducing the sending of erroneous data to server, and so that saving on transmission as well as on the processing of these data in the cloud, and to make filtering of erroneous data. The field of the project is the environmental and focuses on measuring the air quality. Sensors will measure air particles and IoT devices will be managed through Particle platform (https://www.particle.io/) . Two types of sensors will be used, Particulate Matter Sensor SPS30 and Grove - Laser PM2.5 Dust Sensor, and several particle sizes will be measured. This work aims to develop an ML model for the detection and prediction of anomalous data captured by sensors connected to IoT devices, and run it within the IoT devices.
Keywords: anomaly prediction
machine learning
Internet of things
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 3-Jan-2021
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
tllusaTFM0121memoria.pdfMemòria del TFM11,89 MBAdobe PDFThumbnail
View/Open
tllusaTFM0121presentació.pdfPresentació del TFM829,41 kBAdobe PDFThumbnail
View/Open