東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Internet of Things (IoT) Anomaly Detection Using Machine Learning Techniques: Parameter Optimization and Algorithm Comparison.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Internet of Things (IoT) Anomaly Detection Using Machine Learning Techniques: Parameter Optimization and Algorithm Comparison./
作者:	Dankwa, Richard Wahyee.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	61 p.
附註:	Source: Masters Abstracts International, Volume: 83-03.
Contained By:	Masters Abstracts International83-03.
標題:	Mathematics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28543504
ISBN:	9798535569628

Internet of Things (IoT) Anomaly Detection Using Machine Learning Techniques: Parameter Optimization and Algorithm Comparison.
Dankwa, Richard Wahyee.

Internet of Things (IoT) Anomaly Detection Using Machine Learning Techniques: Parameter Optimization and Algorithm Comparison. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 61 p.

Source: Masters Abstracts International, Volume: 83-03.

Thesis (M.S.)--Indiana University of Pennsylvania, 2021.

This item must not be sold to any third party vendors.

With the increased use of data-driven infrastructures, attacks and anomalies on IoT devices have risen. Thus, anomaly detection has become a critical topic in this domain. Recently, a range of methods of anomaly detection for different kinds of anomalies is being researched. However, the search for excellent machine learning algorithms that can balance the statistical and computational efficiencies for a given IoT anomaly detection task has been widely recognized as a challenging area in the data science community. To drive progress in this research field, we seek to develop a multi-objective investigation procedure that can merge statistical and computational considerations and allow for trade-offs between the two for algorithm comparison and selection. The investigation procedure is to be carried out as follows; first, we produce the frontier of Pareto-optimal algorithms by optimizing the out-sample predictive performance and reducing the execution time/ memory usage simultaneously. Second, a decision-making process can be implemented using visualizations and simple evaluation metrics concurrently. The method will be evaluated on a real dataset that contains traces captured in an IoT environment using Distributed Smart Space Orchestrated system (DS2OS) for anomaly detection. All the machine learning algorithms studied in this research were run on the world-class H2O AI platform in software R 4.0.3.

ISBN: 9798535569628Subjects--Topical Terms:

515831
Mathematics.

Internet of Things (IoT) Anomaly Detection Using Machine Learning Techniques: Parameter Optimization and Algorithm Comparison.
LDR:02453nmm a2200313 4500 001 2344643
005 20220531064615.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798535569628
035 $a (MiAaPQ)AAI28543504
035 $a AAI28543504
040 $a MiAaPQ $c MiAaPQ
100 1 $a Dankwa, Richard Wahyee. $3 3683427
245 1 0 $a Internet of Things (IoT) Anomaly Detection Using Machine Learning Techniques: Parameter Optimization and Algorithm Comparison.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 61 p.
500 $a Source: Masters Abstracts International, Volume: 83-03.
500 $a Advisor: Cao, Yongtao.
502 $a Thesis (M.S.)--Indiana University of Pennsylvania, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a With the increased use of data-driven infrastructures, attacks and anomalies on IoT devices have risen. Thus, anomaly detection has become a critical topic in this domain. Recently, a range of methods of anomaly detection for different kinds of anomalies is being researched. However, the search for excellent machine learning algorithms that can balance the statistical and computational efficiencies for a given IoT anomaly detection task has been widely recognized as a challenging area in the data science community. To drive progress in this research field, we seek to develop a multi-objective investigation procedure that can merge statistical and computational considerations and allow for trade-offs between the two for algorithm comparison and selection. The investigation procedure is to be carried out as follows; first, we produce the frontier of Pareto-optimal algorithms by optimizing the out-sample predictive performance and reducing the execution time/ memory usage simultaneously. Second, a decision-making process can be implemented using visualizations and simple evaluation metrics concurrently. The method will be evaluated on a real dataset that contains traces captured in an IoT environment using Distributed Smart Space Orchestrated system (DS2OS) for anomaly detection. All the machine learning algorithms studied in this research were run on the world-class H2O AI platform in software R 4.0.3.
590 $a School code: 0318.
650 4 $a Mathematics. $3 515831
650 4 $a Accuracy. $3 3559958
650 4 $a Deep learning. $3 3554982
650 4 $a Datasets. $3 3541416
650 4 $a Regression analysis. $3 529831
650 4 $a Optimization. $3 891104
650 4 $a Decision making. $3 517204
650 4 $a Neural networks. $3 677449
650 4 $a Classification. $3 595585
650 4 $a Variables. $3 3548259
650 4 $a Internet of Things. $3 3538511
650 4 $a Algorithms. $3 536374
650 4 $a Decision trees. $3 827433
650 4 $a Objectives. $3 3561496
650 4 $a Visualization. $3 586179
650 4 $a Artificial intelligence. $3 516317
650 4 $a Information technology. $3 532993
690 $a 0405
690 $a 0489
690 $a 0800
710 2 $a Indiana University of Pennsylvania. $b Mathematics. $3 3180075
773 0 $t Masters Abstracts International $g 83-03.
790 $a 0318
791 $a M.S.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28543504