Agrima Seth

Agrima Seth

Ph.D. student, School of Information

Sparse Model and SVM for proactive fault detection

less than 1 minute read

Published:

Pro-active fault detection in Cloud System using Machine Learning Algorithms like- Sparse Coding and Single label SVM

In November 2014, I got an opportunity to work as a research apprentice to Prof M.C. Govil at Malaviya National Institute of Technology on fault tolerance in cloud systems.

During, this period I tried re-implementing Fault Management in Map-Reduce through Early Detection of Anomalous Nodes” by Selvi Kadirvel, Jeffrey Ho, José A. B. Fortes. I monitored the heartbeat of the Hadoop cluster using Ganglia. Further, I created a Model and performed Single label SVM to classify the healthy nodes and recognize the anomalous nodes.

The complete project report for the same is available here.

You May Also Enjoy

COVID-19 Risk Calculator

less than 1 minute read

Published:

With the world trying to resume all activities as they were before the COVID-19 pandemic, citizens need to judge their risk levels from gatherings and activities. The numerous determinants and the evolving nature of risk make it confusing for the public to understand the risk from various activities. Hence we created this risk calculator app, the paper was accepted at Nature Scientific Reports.

Anomaly Detection using Machine Learning for Data Quality Monitoring in the CMS Experiment

less than 1 minute read

Published:

The project aims at applying recent progress in Machine Learning techniques to the automation of quality assessment allowing the check of large volumes of data in real-time and improving the ability to detect unexpected features. The test implementation was presented to a panel of Physicist and Computer scientists; I was awarded the 2nd position for my work.

CERN Webfest

less than 1 minute read

Published:

Created a text summarization and analytics platform that works on top of messaging systems being used at CERN, Switzerland. Programmed various natural language processing and machine learning routines for answering users’ queries (summary, most important chats and keywords). ParityApp