首页|New Findings from Malaviya National Institute of Technology in Machine Learning Provides New Insights (Dievd: Disruptive Event Detection From Dynamic Datastream s Using Continual Machine Learning: a Case Study With Twitter)
New Findings from Malaviya National Institute of Technology in Machine Learning Provides New Insights (Dievd: Disruptive Event Detection From Dynamic Datastream s Using Continual Machine Learning: a Case Study With Twitter)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Researchers detail new data in Machine Learning. According to news originating from Jaipur, India, by NewsRx correspon dents, research stated, "Identifying disruptive events (riots, protests, natural calamities) from social media is important for maintaining social order and add ressing geopolitical concerns. Existing works on identifying disruptive events u se classical machine learning (ML) models on static datasets." Financial support for this research came from National Supercomputing Mission (I ndia). Our news journalists obtained a quote from the research from the Malaviya Nation al Institute of Technology, "However, social networks are dynamic entities and c annot be practically modeled using static techniques. A viable alternative is th e emerging Continual Machine Learning (CML) approach which applies the knowledge acquired from the past to learn future tasks. However, existing CML techniques are trained and tested on static data and are incapable of handling real-time da ta obtained from dynamic environments. This paper presents a novel DiEvD framewo rk for disruptive event detection using Continual Machine Learning (CML) specifi cally for dynamic data streams. We have used Twitter social media as a case stud y of the real-time and dynamic data provider. To the best of our knowledge, this is the first attempt to use CML for socially disruptive event detection. Compre hensive performance analysis show that our framework effectively identifies disr uptive events with 98% accuracy and can classify them with an aver age incremental accuracy of 76.8%."
JaipurIndiaAsiaCyborgsEmerging T echnologiesMachine LearningMalaviya National Institute of Technology
NETL
NSTL
