Handling Concept Drift in Data Streams by Using Drift Detection Methods

Patil, Malini M.

doi:10.1007/978-981-13-1274-8_12

Cited by 4 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a number of interesting avenues for future work. Other studies have included analysis of online algorithms' resilience to concept drift, including an evaluation of data streams mining (Mittal and Kashyap, n.d.), techniques for concept drift detection (Patil, 2019), and the utilization of online ensemble classifiers to learn from non-stationary data streams (Verdecia-Cabrera, Blanco, & Carvalho, 2018). Additionally, the study of a multiclass online classifiers would be important, since customer's behavior is often non-binary.…”

Section: Discussionmentioning

confidence: 99%

An Online Machine Learning Approach to Sentiment Analysis in Social Media

Alwidian¹,

Khasawneh²,

Alsahlee³

et al. 2022

MAS

View full text Add to dashboard Cite

The online learning, is one that continuously adapts to arriving data, and gets updated incrementally instance by instance. In this paper, we compare the performance of different online machine learning algorithms for the task of sentiment analysis on challenging text datasets. We assess the models using a wide range of metrics, such as microF1, macroF1, accuracy, and running time. Our experiments have revealed that these online models provide a viable alternative to traditional offline machine learning in sentiment analysis, in fraction of the time.

show abstract

Section: Discussionmentioning

confidence: 99%

An Online Machine Learning Approach to Sentiment Analysis in Social Media

Alwidian¹,

Khasawneh²,

Alsahlee³

et al. 2022

MAS

View full text Add to dashboard Cite

show abstract

“…This method uses a sliding windowing approach with variable size to detect concept drift [15]. Both abrupt and gradual drift scenarios have been tested with this method [56].…”

Section: Approach Goal Task Supportmentioning

confidence: 99%

Concept Drift Adaptation Techniques in Distributed Environment for Real-World Data Streams

et al. 2021

View full text Add to dashboard Cite

Real-world data streams pose a unique challenge to the implementation of machine learning (ML) models and data analysis. A notable problem that has been introduced by the growth of Internet of Things (IoT) deployments across the smart city ecosystem is that the statistical properties of data streams can change over time, resulting in poor prediction performance and ineffective decisions. While concept drift detection methods aim to patch this problem, emerging communication and sensing technologies are generating a massive amount of data, requiring distributed environments to perform computation tasks across smart city administrative domains. In this article, we implement and test a number of state-of-the-art active concept drift detection algorithms for time series analysis within a distributed environment. We use real-world data streams and provide critical analysis of results retrieved. The challenges of implementing concept drift adaptation algorithms, along with their applications in smart cities, are also discussed.

show abstract

“…The network traffic fits this definition, as well as, data around network analysis such as logs, traffic, monitoring requests, and so on. As clearly stated by [29], data streams are typically divided into two types: static and evolving. Static data streams are those relating to historical data or with a regular bulk arrival.…”

Section: Experiments Setupmentioning

confidence: 99%

Selection of Online Network Traffic Discriminators for on-the-Fly Traffic Classification

Vargas-Arcila

Corrales

Gallón

et al. 2021

rev.ing.univ.Medellin

View full text Add to dashboard Cite

There are several techniques to select a set of traffic features for traffic classification. However, most studies ignore the domain knowledge where traffic analysis or classification is performed and do not consider the always moving information carried in the networks. This paper describes a selection process of online network-traffic discriminators. We obtained 24 traffic features that can be processed on the fly and propose them as a base attribute set for future domain-aware online analysis, processing, or classification. For the selection of a set of traffic discriminators, and to avoid the inconveniences mentioned, we carried out three steps. The first step is a context knowledge-based manual selection of traffic features that meet the condition of being obtained on the fly from the flow. The second step is focused on the quality analysis of previously selected attributes to ensure the relevance of each one when performing a traffic classification. In the third step, the implementation of several incremental learning algorithms verified the usefulness of such attributes in online traffic classification processes.

show abstract

Handling Concept Drift in Data Streams by Using Drift Detection Methods

Cited by 4 publications

References 14 publications

An Online Machine Learning Approach to Sentiment Analysis in Social Media

An Online Machine Learning Approach to Sentiment Analysis in Social Media

Concept Drift Adaptation Techniques in Distributed Environment for Real-World Data Streams

Selection of Online Network Traffic Discriminators for on-the-Fly Traffic Classification

Contact Info

Product

Resources

About