Anomaly detection in set-top boxes using machine learning technologies (Record no. 6539)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02024nam a22002177a 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | OSt |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20220107122852.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 190704b xxu||||| |||| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE | |
| Transcribing agency | IIITMK |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Vijitha V (92217027) |
| 9 (RLIN) | 16040 |
| 245 ## - TITLE STATEMENT | |
| Title | Anomaly detection in set-top boxes using machine learning technologies |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | MSC DA 2017-2019 |
| 500 ## - GENERAL NOTE | |
| General note | Anomaly detection is a common goal shared by dierent domains. Anomalies<br/>are generally dened as an error or as an unexpected event in reality .It is<br/>the practice of identifying items or events that do not conform to an expected<br/>behavior or do not correlate with other items in a dataset. Anomalies are<br/>detected in performance data of set top boxes using both supervised and unsupervised<br/>machine learning Techniques.The eectiveness of each algorithm<br/>was evaluated and compared.Which have shown sucient performance and<br/>sensitivity. Anomalies are patterns in data that do not conform to a welldened<br/>notion of normal behavior.Anomaly detection is the process of identifying<br/>unexpected items or events in datasets,which dier from the norm.<br/>In contrast to standard classication tasks, anomaly detection is often applied<br/>on unlabeled data, taking only the internal structure of the dataset into<br/>account. This challenge is known as unsupervised anomaly detection and<br/>is addressed in many practical applications.This project Principal Component<br/>Analysis (PCA) for feature selection, then unsupervised machinelearning<br/>techniques like K-Means are applied on the detected anomalies to dene<br/>their classes.supervised machine learning techniques like KNN,OCSVM and<br/>Isolation forest. The results show that OCSVM mostly give better results than<br/>Isolation forest , but for certain anomalies KNN give the best results |
| 502 ## - DISSERTATION NOTE | |
| Degree type | MSC DA |
| Name of granting institution | 2017-2019 |
| Year degree granted | INT |
| -- | Dr T K Manoj Kumar |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | ANOMALY DETECTION |
| 9 (RLIN) | 16041 |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | ISOLATION FOREST |
| 9 (RLIN) | 16042 |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | KNN |
| 9 (RLIN) | 16043 |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | OCSVM |
| 9 (RLIN) | 16044 |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MACHINE LEARNING TECHNIQUES |
| 9 (RLIN) | 16045 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Koha item type | |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Shelving location | Date acquired | Total Checkouts | Barcode | Date last seen | Price effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | IIITM-K | Kerala University of Digital Sciences, Innovation and Technology Knowledge Centre | 04/07/2019 | R-1566 | 04/07/2019 | 04/07/2019 | Project Reports |