Anomaly detection in IoT data streams
Authors
Date
2024Copyright
© The Author(s)
Kiinnostus IoT-järjestelmiin on selkeästi kasvussa ja sen myötä on entistä tärkeämpää tunnistaa, että IoT-datavirrat sisältävät poikkeavuuksia. Näitä voivat aiheuttaa järjestelmien tai tietoliikenteen toimimattomuus tai kyberhyökkäykset. Poikkeavuudet voivat johtaa vääriin johtopäätelmiin, jos niitä ei löydetä ja käsitellä ajoissa. Poikkeavuuksien löytämiseen IoT-datavirroista on erilaisia menettelytapoja ja menettelytavan valinta on riippuvainen erilaisista seikoista, kuten IoT-arkkitehtuurista ja poikkeavuuden tyypistä. Tämän pro gradun aiheena on luoda skaalautuva menettelytapa poikkeavuuksien havaitsemiseksi lennosta IoT-datavirroista. Suunnittelutieteen artifaktana esitellään prosessikaavio ja tarkistuslista, joiden avulla löydetään parhaiten sopiva menettelytapa IoT-datavirtojen poikkeavuuksien havaitsemiseksi. Since the interest to IoT systems is constantly increasing, it is vital to recognize that the IoT data streams contain anomalies. Anomalies can be caused by system failure, network issues or malicious attacks and can lead to misinterpreted results if they are not found and handled properly. There are different ways to find the abnormal values from IoT data streams. The approach varies based on different aspects such as the IoT architecture and type of the anomaly. This Master's thesis presents a scalable procedure to detect anomalies from IoT data streams on the fly. As an artifact of design science it was created a procedure diagram and checklist to find the appropriate solution for each project of detecting anomalies from IoT data streams.
Keywords
Metadata
Show full item recordCollections
- Pro gradu -tutkielmat [29787]
License
Related items
Showing items with similar title or keywords.
-
Multilayer perceptron training with multiobjective memetic optimization
Nieminen, Paavo (University of Jyväskylä, 2016)Machine learning tasks usually come with several mutually conflicting objectives. One example is the simplicity of the learning device contrasted with the accuracy of its performance after learning. Another common example ... -
On data mining applications in mobile networking and network security
Zolotukhin, Mikhail (University of Jyväskylä, 2014) -
Accelerating joint species distribution modelling with Hmsc-HPC by GPU porting
Rahman, Anis Ur; Tikhonov, Gleb; Oksanen, Jari; Rossi, Tuomas; Ovaskainen, Otso (Public Library of Science (PLoS), 2024)Joint species distribution modelling (JSDM) is a widely used statistical method that analyzes combined patterns of all species in a community, linking empirical data to ecological theory and enhancing community-wide ... -
Unsupervised network intrusion detection systems for zero-day fast-spreading network attacks and botnets
Vahdani Amoli, Payam (University of Jyväskylä, 2015)Today, the occurrence of zero-day and complex attacks in high-speed networks is increasingly common due to the high number vulnerabilities in the cyber world. As a result, intrusions become more sophisticated and fast ... -
The Max-Product Algorithm Viewed as Linear Data-Fusion : A Distributed Detection Scenario
Abdi, Younes; Ristaniemi, Tapani (Institute of Electrical and Electronics Engineers (IEEE), 2020)In this paper, we disclose the statistical behavior of the max-product algorithm configured to solve a maximum a posteriori (MAP) estimation problem in a network of distributed agents. Specifically, we first build a ...