The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
기계 학습은 실제 문제를 해결하는 데 있어 입증된 효율성과 성능으로 인해 컴퓨팅 지능 분야의 연구원 및 산업 기업에게 매력적인 주제가 되고 있습니다. 그러나 정확한 검색, 지능형 발견, 지능형 학습과 같은 몇 가지 과제를 해결해야 합니다. 가장 중요한 과제 중 하나는 온라인 학습 및 운영 중에 다양한 기계 학습 모델의 불안정한 성능입니다. 온라인 학습은 새로운 정보가 제공될 때 체계를 재교육하지 않고 정보를 현대화하는 기계 학습 모델의 기능입니다. 이 문제를 해결하기 위해 우리는 OSELM(Online Sequential Extreme Learning Machine), FA-OSELM(Feature Adaptive OSELM), KP-OSELM(Knowledge Preserving OSELM) 및 Infinite Term Memory OSELM( ITM-OSELM). 구체적으로, 모델의 위상적, 수학적 측면에서 다양한 요소를 고려하여 프레임워크를 구축하고 다양한 평가 시나리오를 구성함으로써 모델에 대한 테스트베드를 제공합니다. 또한 학습할 시계열의 다양한 특성을 생성합니다. 결과는 테스트된 매개변수와 시나리오가 모델에 미치는 실제 영향을 입증합니다. 정확도 측면에서 KP-OSELM 및 ITM-OSELM은 OSELM 및 FA-OSELM보다 우수합니다. 활성 기능 감소 비율과 관련된 시간 효율성 측면에서 ITM-OSELM은 KP-OSELM보다 우수합니다.
Ahmed Salih AL-KHALEEFA
Imam Jafar Al-Sadiq University
Rosilah HASSAN
Universiti Kebangsaan Malaysia (UKM)
Mohd Riduan AHMAD
Universiti Teknikal Malaysia Melaka (UTeM)
Faizan QAMAR
Universiti Kebangsaan Malaysia (UKM)
Zheng WEN
Waseda University
Azana Hafizah MOHD AMAN
Universiti Kebangsaan Malaysia (UKM)
Keping YU
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Ahmed Salih AL-KHALEEFA, Rosilah HASSAN, Mohd Riduan AHMAD, Faizan QAMAR, Zheng WEN, Azana Hafizah MOHD AMAN, Keping YU, "Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 8, pp. 1172-1184, August 2021, doi: 10.1587/transinf.2020BDP0002.
Abstract: Machine learning is becoming an attractive topic for researchers and industrial firms in the area of computational intelligence because of its proven effectiveness and performance in resolving real-world problems. However, some challenges such as precise search, intelligent discovery and intelligent learning need to be addressed and solved. One most important challenge is the non-steady performance of various machine learning models during online learning and operation. Online learning is the ability of a machine-learning model to modernize information without retraining the scheme when new information is available. To address this challenge, we evaluate and analyze four widely used online machine learning models: Online Sequential Extreme Learning Machine (OSELM), Feature Adaptive OSELM (FA-OSELM), Knowledge Preserving OSELM (KP-OSELM), and Infinite Term Memory OSELM (ITM-OSELM). Specifically, we provide a testbed for the models by building a framework and configuring various evaluation scenarios given different factors in the topological and mathematical aspects of the models. Furthermore, we generate different characteristics of the time series to be learned. Results prove the real impact of the tested parameters and scenarios on the models. In terms of accuracy, KP-OSELM and ITM-OSELM are superior to OSELM and FA-OSELM. With regard to time efficiency related to the percentage of decreases in active features, ITM-OSELM is superior to KP-OSELM.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020BDP0002/_p
부
@ARTICLE{e104-d_8_1172,
author={Ahmed Salih AL-KHALEEFA, Rosilah HASSAN, Mohd Riduan AHMAD, Faizan QAMAR, Zheng WEN, Azana Hafizah MOHD AMAN, Keping YU, },
journal={IEICE TRANSACTIONS on Information},
title={Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series},
year={2021},
volume={E104-D},
number={8},
pages={1172-1184},
abstract={Machine learning is becoming an attractive topic for researchers and industrial firms in the area of computational intelligence because of its proven effectiveness and performance in resolving real-world problems. However, some challenges such as precise search, intelligent discovery and intelligent learning need to be addressed and solved. One most important challenge is the non-steady performance of various machine learning models during online learning and operation. Online learning is the ability of a machine-learning model to modernize information without retraining the scheme when new information is available. To address this challenge, we evaluate and analyze four widely used online machine learning models: Online Sequential Extreme Learning Machine (OSELM), Feature Adaptive OSELM (FA-OSELM), Knowledge Preserving OSELM (KP-OSELM), and Infinite Term Memory OSELM (ITM-OSELM). Specifically, we provide a testbed for the models by building a framework and configuring various evaluation scenarios given different factors in the topological and mathematical aspects of the models. Furthermore, we generate different characteristics of the time series to be learned. Results prove the real impact of the tested parameters and scenarios on the models. In terms of accuracy, KP-OSELM and ITM-OSELM are superior to OSELM and FA-OSELM. With regard to time efficiency related to the percentage of decreases in active features, ITM-OSELM is superior to KP-OSELM.},
keywords={},
doi={10.1587/transinf.2020BDP0002},
ISSN={1745-1361},
month={August},}
부
TY - JOUR
TI - Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series
T2 - IEICE TRANSACTIONS on Information
SP - 1172
EP - 1184
AU - Ahmed Salih AL-KHALEEFA
AU - Rosilah HASSAN
AU - Mohd Riduan AHMAD
AU - Faizan QAMAR
AU - Zheng WEN
AU - Azana Hafizah MOHD AMAN
AU - Keping YU
PY - 2021
DO - 10.1587/transinf.2020BDP0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2021
AB - Machine learning is becoming an attractive topic for researchers and industrial firms in the area of computational intelligence because of its proven effectiveness and performance in resolving real-world problems. However, some challenges such as precise search, intelligent discovery and intelligent learning need to be addressed and solved. One most important challenge is the non-steady performance of various machine learning models during online learning and operation. Online learning is the ability of a machine-learning model to modernize information without retraining the scheme when new information is available. To address this challenge, we evaluate and analyze four widely used online machine learning models: Online Sequential Extreme Learning Machine (OSELM), Feature Adaptive OSELM (FA-OSELM), Knowledge Preserving OSELM (KP-OSELM), and Infinite Term Memory OSELM (ITM-OSELM). Specifically, we provide a testbed for the models by building a framework and configuring various evaluation scenarios given different factors in the topological and mathematical aspects of the models. Furthermore, we generate different characteristics of the time series to be learned. Results prove the real impact of the tested parameters and scenarios on the models. In terms of accuracy, KP-OSELM and ITM-OSELM are superior to OSELM and FA-OSELM. With regard to time efficiency related to the percentage of decreases in active features, ITM-OSELM is superior to KP-OSELM.
ER -