A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
An Ensemble Rate Adaptation Framework for Dynamic Adaptive Streaming Over HTTP
[article]
2019
arXiv
pre-print
Rate adaptation is one of the most important issues in dynamic adaptive streaming over HTTP (DASH). ...
In this paper, we propose an ensemble rate adaptation framework for DASH, which aims to leverage the advantages of multiple methods involved in the framework to improve the quality of experience (QoE) ...
ACKNOWLEDGMENT The authors would like to thank Institute of Information Technology (ITEC) at Klagenfurt University for the valuable and basis work of DASH. ...
arXiv:1912.11822v1
fatcat:g4hvtvwnqvchxpo2bo43lapq6m
Ensemble Dynamics in Non-stationary Data Stream Classification
[chapter]
2018
Studies in Big Data
This chapter studies ensembles' dynamic behaviour of existing ensemble methods (e.g. addition, removal and update of classifiers) in non-stationary data stream classification. ...
Ensemble learning techniques have been proven effective adapting to concept drifts. ...
Adapted from [Gama et al., 2014].
Fig. 2 2 An ensemble learning system, adapted from
Fig. 3 3 The proposed taxonomy for ensemble's dynamics in non-stationary data stream classification. ...
doi:10.1007/978-3-319-89803-2_6
fatcat:od6ibg7bnrgzregyd7np6wud4e
Two-Stage Cost-Sensitive Learning for Data Streams with Concept Drift and Class Imbalance
2020
IEEE Access
Moreover, a window adaptation and drift detection mechanism, which guarantees that an ensemble can adapt promptly to concept drift, is embedded in our method. ...
We propose a novel two-stage cost-sensitive framework for data stream classification by utilizing cost information in both feature selection stage and classification stage. ...
MOA is the most famous open source framework for data stream mining and it provide an environment for implementing the state-of-the-art algorithms of data stream mining.
a. ...
doi:10.1109/access.2020.3031603
fatcat:jv3i5kdvsbefrettjrbjdhjwk4
An Adaptive Deep Learning Framework for Dynamic Image Classification in the Internet of Things Environment
2020
Sensors
The proposed framework is an improved version of previous adaptive CNN ensemble with an additional online training (OT) and online classifier update (OCU) modules. ...
network (CNN) ensemble framework), which handles novel class arrival and class evaluation issue during dynamic image classification. ...
Data Availability: The CIFAR 10 dataset is available at "https://www.cs.toronto.edu/~kriz/cifar.html" and the ISIC 2019 challenge dataset is available at "https://challenge2019.isic-archive.com/". ...
doi:10.3390/s20205811
pmid:33066579
pmcid:PMC7602278
fatcat:4gsdv7tbfvhi3hsyz5achgrqye
Online AutoML: An adaptive AutoML framework for online learning
[article]
2022
arXiv
pre-print
For this purpose, we design an adaptive Online Automated Machine Learning (OAML) system, searching the complete pipeline configuration space of online learners, including preprocessing algorithms and ensembling ...
This study aims to automate pipeline design for online learning while continuously adapting to data drift. ...
We would like to give special thanks to Pieter Gijsbers for his help in integrating OAML into the GAMA library. ...
arXiv:2201.09750v2
fatcat:duuxbdlc3bes3ku2dv5c25jg3a
Machine Learning Based Classifiers for QoE Prediction Framework in Video Streaming over 5G Wireless Networks
2023
Computers Materials & Continua
It implements an enhanced hyperparameter tuning (EHPT) ensemble and decision tree (DT) classifier for video streaming categorization. ...
Second, A valuable framework for QoE-aware video streaming categorization is introduced in 5G networks based on machine learning (ML) by incorporating the hyperparameter tuning (HPT) principle. ...
Acknowledgement: The authors would like to acknowledge Vellore Institute of Technology, Chennai, India, for their valuable support. ...
doi:10.32604/cmc.2023.036013
fatcat:hyeqdr35tfav3gpgtwdfkkcs74
Learning in Nonstationary Environments: A Survey
2015
IEEE Computational Intelligence Magazine
(Matlab): Framework for generating data streams with concept drift [129]. http://pages.bangor.ac.uk/+mas00a/EPSRC_simulation_ framework/changing_environments_stage1a.htm ❏ Airlines Flight Delay Prediction ...
While sounding similar to ONSBoost, DWM allows for an adaptive ensemble size, whereas ONSBoost has a fixed sized ensemble. ...
doi:10.1109/mci.2015.2471196
fatcat:pspytwokmfahllwnm4uxqypx74
Online Ensemble Using Adaptive Windowing for Data Streams with Concept Drift
2016
International Journal of Distributed Sensor Networks
The ensembles for handling concept drift can be categorized into two different approaches: online and block-based approaches. ...
The biggest challenge in data streams mining is to deal with concept drifts, during which ensemble methods are widely employed. ...
supported by the National Natural Science Foundation of China (no. 61572417, no. 61563001, and no. 61572005), the Natural Science Foundation of Beijing (no. 4142042), and the Fundamental Research Funds for ...
doi:10.1155/2016/4218973
fatcat:m7dppglrv5d2vm3zd2vpupcdme
Adaptive learning for dynamic environments: A comparative approach
2017
Engineering applications of artificial intelligence
In this work we present the Drift Adaptive Retain Knowledge (DARK) framework to tackle adaptive learning in dynamic environments based on recent and retained knowledge. ...
DARK handles an ensemble of multiple Support Vector Machine (SVM) models that are dynamically weighted and have distinct training window sizes. ...
The goal of DARK framework is to build an ensemble of Support Vector Machines (SVM) with dynamic weighting schemes and variable train size windows for model adaptation in incremental learning, and therefore ...
doi:10.1016/j.engappai.2017.08.004
fatcat:vswzkgxswvexbhvklx4zb275ey
Comparative study between incremental and ensemble learning on data streams: Case study
2014
Journal of Big Data
In stream data, hidden patterns commonly evolve over time (i.e.,concept drift), where many dynamic learning strategies have been proposed, such as the incremental learning and ensemble learning. ...
With unlimited growth of real-world data size and increasing requirement of real-time processing, immediate processing of big stream data has become an urgent problem. ...
of dynamic ensemble learning is to dividing large data-stream into small data chunks. ...
doi:10.1186/2196-1115-1-5
fatcat:oz7cihr4ofg6nev2y22xa4mbye
A Lightweight Concept Drift Detection and Adaptation Framework for IoT Data Streams
[article]
2021
arXiv
pre-print
In this article, we propose an adaptive IoT streaming data analytics framework for anomaly detection use cases based on optimized LightGBM and concept drift adaptation. ...
However, IoT data analytics faces concept drift challenges due to the dynamic nature of IoT systems and the ever-changing patterns of IoT data streams. ...
., OASW), an ensemble ML algorithm (i.e., LightGBM), and a hyperparameter method (i.e., PSO), the proposed model has the capacity to automatically adapt to the ever-changing data streams of dynamic IoT ...
arXiv:2104.10529v1
fatcat:tx3or6snhnh6xhbxyab4y2cz6u
ADES: A New Ensemble Diversity-Based Approach for Handling Concept Drift
2021
Mobile Information Systems
With the prevalence of streaming real-world applications that are associated with changes in the underlying data distribution, the need for applications that are capable of adapting to evolving and time-varying ...
This work proposes a novel and evolving data stream classifier called Adaptive Diversified Ensemble Selection Classifier (ADES) that significantly optimizes adaptation to different types of concept drifts ...
Learning models adaptation to new concepts is an important task for classification problems in dynamic and nonstationary environments.
Related Work. ...
doi:10.1155/2021/5549300
fatcat:7djzzsolineg7duijijn2yuy64
Cost-Sensitive Classification for Evolving Data Streams with Concept Drift and Class Imbalance
2021
Computational Intelligence and Neuroscience
Besides, a change detection mechanism is embedded in our algorithm, which guarantees that an ensemble can capture and react to drift promptly. ...
During the data preprocessing, a cost-sensitive learning strategy is introduced into the ReliefF algorithm for alleviating the class imbalance at the data level. ...
Zyblewski et al. proposed a dynamic classifier ensemble selection for imbalanced drifted data streams [36] . ...
doi:10.1155/2021/8813806
fatcat:g2xhryjvsraelfxb5xxefs3rk4
Automated Machine Learning Techniques for Data Streams
[article]
2021
arXiv
pre-print
These assumptions do not hold in a data stream mining setting where an unbounded stream of data cannot be stored and is likely to manifest concept drift. ...
accuracy over time. ...
Datasets used for experiments
https://pypi.org/project/automl-streams 2 https://github.com/AlexImb/automl-streams 3 https://github.com/AlexImb/automl-streams/tree/ master/demos
https://www.automl.org ...
arXiv:2106.07317v1
fatcat:2phpd2s6j5fpre455jpvrhj5ce
A Novel Ensemble Classification for Data Streams with Class Imbalance and Concept Drift
2017
International Journal of Performability Engineering
Motivated by this challenge, a novel ensemble classification for mining imbalanced streaming data is proposed to overcome both issues simultaneously. ...
The algorithm utilizes the under-sampling and over-sampling techniques to balance the positive and negative instances. Moreover, dynamic weighting strategy was adopted to deal with concept drift. ...
Acknowledgements The authors would like to thank the anonymous reviewers for their insightful comments and constructive suggestions. ...
doi:10.23940/ijpe.17.06.p15.945955
fatcat:qkizzbojm5fgrlvzuye6rykfte
« Previous
Showing results 1 — 15 out of 13,989 results