Knowledge Preserving OSELM Model for Wi-Fi-Based Indoor Localization

Al-Khaleefa, Ahmed Salih; Ahmad, Mohd Riduan; Isa, Azmi Awang Md; Esa, Mazlina; Aljeroudi, Yazan; Jubair, Mohammed Ahmed; Malik, Reza Firsandaya

doi:10.3390/s19102397

Cited by 16 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A drawback of FA-OSELM is that it transfers merely the last state of knowledge. This limitation was addressed by the work of [40]. This work resulted in the modification of the widely used OSELM to achieve enhanced localization results using dynamic and cyclical behavior.…”

Section: Related Workmentioning

confidence: 99%

“…The EM preserves knowledge specific to the old non-active features and restores knowledge specific to new active features. This work, along with the study of [40], provides the framework for the only OSELM variants capable of processing online learning while preserving old knowledge regardless of knowledge aging.…”

Section: Related Workmentioning

confidence: 99%

“…For feature adaptive online sequential extreme learning (FA-OSELM), transfer learning is useful for transferring knowledge related to active features in the current and previous NNs; this process causes knowledge loss while the NNs transform. Two novel approaches, namely, knowledge preserving OSELM (KP-OSELM) [40] and infinite term memory OSELM (ITM-OSELM) [41], were proposed in previous research. In KP-OSELM, the NN is fixed with many inputs equal to the total number of features with the use of an encoding approach for non-active features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series

Al-Khaleefa

Hassan

Ahmad

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series

Al-Khaleefa

Hassan

Ahmad

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Applying multiple techniques, such as first-in, first-out (FIFO), CBWFQ, low-latency queuing, class-based weighted random early detection, explicit congestion notification, and link fragmentation and interleaving (LFI), can result in high network performance levels [17]. The more advanced the method, the better the quality of the transmission [18]. The issues in using advanced methods include packet delay in transmission.…”

Section: Online Sequential Extreme Learning Machinementioning

confidence: 99%

Quality of Service (QoS) Management for Local Area Network (LAN) Using Traffic Policy Technique to Secure Congestion

et al. 2020

Self Cite

View full text Add to dashboard Cite

This study presents the proposed testbed implementation for the Advanced Technology Training Center (ADTEC) Batu Pahat, one of Malaysia’s industrial training institutes. The objectives of this study are to discover the issues regarding network congestion, propose a suitable method to overcome such issues, and generate output data for the comparison of the results before and after the proposed implementation. The internet is directly connected to internet service providers (ISPs), which neither impose any rule nor filter the traffic components; all connections comply on the basis of the base effort services provided by the ISP. The congestion problem has been raised several times and the information technology (IT) department has been receiving complaints about poor and sometimes intermittent internet connection. Such issues provide some ideas for a possible solution because the end client is a human resource core business. In addition, budget constraints contribute to this problem. After a comprehensive review of related literature and discussion with experts, the implementation of quality of service through add-on rules, such as traffic policing on network traffic, was proposed. The proposed testbed also classified the traffic. Results show that the proposed testbed is stable. After the implementation of the generated solution, the IT department no longer receives any complaints, and thus fulfills the goal of having zero internet connection issues.

show abstract

“…In [ 43 ], KP-OSELM was introduced, which is a modified version of OSELM that aims to retain the weights of inactive features and utilise them when they become active. The learning equations of this method closely resemble those of classical OSELM but with the use of tensing as the objective function and changes to the constraint of zero features within one data chunk.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Intrusion Detection with Data Stream Classification and Concept Drift Guided by the Incremental Learning Genetic Programming Combiner

Shyaa

Zainol

Abdullah

et al. 2023

Sensors

View full text Add to dashboard Cite

Concept drift (CD) in data streaming scenarios such as networking intrusion detection systems (IDS) refers to the change in the statistical distribution of the data over time. There are five principal variants related to CD: incremental, gradual, recurrent, sudden, and blip. Genetic programming combiner (GPC) classification is an effective core candidate for data stream classification for IDS. However, its basic structure relies on the usage of traditional static machine learning models that receive onetime training, limiting its ability to handle CD. To address this issue, we propose an extended variant of the GPC using three main components. First, we replace existing classifiers with alternatives: online sequential extreme learning machine (OSELM), feature adaptive OSELM (FA-OSELM), and knowledge preservation OSELM (KP-OSELM). Second, we add two new components to the GPC, specifically, a data balancing and a classifier update. Third, the coordination between the sub-models produces three novel variants of the GPC: GPC-KOS for KA-OSELM; GPC-FOS for FA-OSELM; and GPC-OS for OSELM. This article presents the first data stream-based classification framework that provides novel strategies for handling CD variants. The experimental results demonstrate that both GPC-KOS and GPC-FOS outperform the traditional GPC and other state-of-the-art methods, and the transfer learning and memory features contribute to the effective handling of most types of CD. Moreover, the application of our incremental variants on real-world datasets (KDD Cup ‘99, CICIDS-2017, CSE-CIC-IDS-2018, and ISCX ‘12) demonstrate improved performance (GPC-FOS in connection with CSE-CIC-IDS-2018 and CICIDS-2017; GPC-KOS in connection with ISCX2012 and KDD Cup ‘99), with maximum accuracy rates of 100% and 98% by GPC-KOS and GPC-FOS, respectively. Additionally, our GPC variants do not show superior performance in handling blip drift.

show abstract

Knowledge Preserving OSELM Model for Wi-Fi-Based Indoor Localization

Cited by 16 publications

References 26 publications

Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series

Performance Evaluation of Online Machine Learning Models Based on Cyclic Dynamic and Feature-Adaptive Time Series

Quality of Service (QoS) Management for Local Area Network (LAN) Using Traffic Policy Technique to Secure Congestion

Enhanced Intrusion Detection with Data Stream Classification and Concept Drift Guided by the Incremental Learning Genetic Programming Combiner

Contact Info

Product

Resources

About