Sökning: "one-class classifier"

Visar resultat 1 - 5 av 6 uppsatser innehållade orden one-class classifier.

1. 1. Automating Root Cause Analysis of Anomalies in Ericsson Wallet Platform using Machine Learning

   Master-uppsats, Blekinge Tekniska Högskola

   Författare :Simron Padhi; Devi Priya Battina; [2023]
   Nyckelord :Anomaly detection; Isolation forest algorithm; K-means algorithm; Local Outlier Factor algorithm; One class Support Vector Machine;

   Sammanfattning : Background: In this era of mobile wallet platforms, to ensure key requirements like high availability and performance, the company must have mechanisms in place to detect anomalies at any given point in time. Ericsson Wallet Platform(EWP), a mobile wallet platform, is facing the problem of manually analyzing all the logs and reports and taking comprehensive action decisions accordingly. LÄS MER

3. 2. Semi-supervised anomaly detection in mask writer servo logs : An investigation of semi-supervised deep learning approaches for anomaly detection in servo logs of photomask writers

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Toomas Liiv; [2023]
   Nyckelord :anomaly detection; semi-supervision; HSC; DeepSAD; photomasks; anomalidetektion; semi-övervakad; HSC; DeepSAD; fotomasker;

   Sammanfattning : Semi-supervised anomaly detection is the setting, where in addition to a set of nominal samples, predominantly normal, a small set of labeled anomalies is available at training. In contrast to supervised defect classification, these methods do not learn the anomaly class directly and should have better generalization capability as new kinds of anomalies are introduced at test time. LÄS MER

4. 3. Modification of the RusBoost algorithm : A comparison of classifiers on imbalanced data

   Magister-uppsats, Umeå universitet/Statistik

   Författare :Isak Forslund; [2022]
   Nyckelord :;

   Sammanfattning : In many situations data is imbalanced, meaning the proportion of one class is larger than the other(s). Standard classifiers often produce undesirable results when the data is imbalanced and different methods have been developed in the attempt to improve classification under such conditions. LÄS MER

5. 4. A Scalable Approach for Detecting Dumpsites using Automatic Target Recognition with Feature Selection and SVM through Satellite Imagery

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för visuell information och interaktion

   Författare :Markus Skogsmo; [2020]
   Nyckelord :satellite imagery; earth observation; remote sensing; sentinel-2; Copernicus; ESA; global watch center; sentinelhub; support vector machine; big data analysis; big data visualization; detection; classification; automatic target recognition; machine learning; one-class classifier;

   Sammanfattning : Throughout the world, there is a great demand to map out the increasing environmental changes and life habitats on Earth. The vast majority of Earth Observations today, are collected using satellites. LÄS MER

7. 5. RGB and Multispectral UAV image classification of agricultural fields using a machine learning algorithm

   Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskap

   Författare :Sigurbjörn Jónsson; [2019]
   Nyckelord :Physical Geography and Ecosystem Analysis; UAV; classification; Random Forest; Geomatics; segmentation; Earth and Environmental Sciences;

   Sammanfattning : A common technique within image analysis is image classification which describes the process of reducing the information content of an image into few user-defined classes. With the emergence of unmanned aerial vehicles (UAVs), high spatial resolution (cm-level) images can be collected. LÄS MER