L2,1-Extreme Learning Machine: An Efficient Robust Classifier for Tumor Classification

Ren, Liang-Rui; Gao, Ying-Lian; Liu, Jin-Xing; Zhu, Rong; Kong, Xiang-Zhen

doi:10.1016/j.compbiolchem.2020.107368

Cited by 11 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extreme learning machines can boost generalization ability by determining the lower training error and lower norm of output weights (Ren et al, 2020). This optimization problem can be presented by Equation :

\min \frac{1}{2} ∥ {normalβ}^{2} ∥ + \frac{C}{2} {false\sum}_{i = 1}^{N} ∥ {normalξ}_{normali} ∥^{2}

s \cdot t h (x_{i}) β = t_{normali}^{T} - {normalξ}_{normali}^{T}, i = 1 \dots N,

where

C

shows the balance parameter,

N

shows the training data and

{normalξ}_{normali}

is the i th neuron's error vector.…”

Section: Methods and The Proposed Vmd‐denetworkmentioning

confidence: 99%

See 1 more Smart Citation

Time series forecasting based on a novel ensemble‐based network and variational mode decomposition

Nazarieh

Dehkordi

2023

Expert Systems

View full text Add to dashboard Cite

Statistical and computational intelligence methods contain weaknesses in handling nonlinearity, non-stationarity and noise. This research develops a novel decomposition ensemble-based network named VMD-DENetwork for time series forecasting over different horizons. A robust decomposition technique called variational mode decomposition (VMD) is applied to decompose the input sequence into several intrinsic modes in a non-recursive manner. The optimal number of intrinsic modes is selected based on a comprehensive analysis to ensure the stability of the framework. The proposed DENetwork is developed based on stacking architecture and constitutes heterogeneous learners to model the nonlinear and complex relationships. It combines a convolutional neural network, long short-term memory and an extreme learning machine. A firefly optimization algorithm is adopted for utilizing hyperparameters of the proposed model to enhance the efficiency of VMD-DENetwork. The forecasting performance is verified by using six real-world data sets from the New York Mercantile and International Petroleum Exchange. The final obtained results are compared with several peer-advanced algorithms using the root mean squared error (RMSE), mean absolute error (MAE), Theil inequality coefficient (TIC) and correlation coefficient (R) metrics. The experimental results confirm that the proposed model demonstrates outstanding prediction performance. The employed optimization algorithm is compared with three frequently used bio-inspired optimization algorithms, and their performance is tested using standard CEC benchmarks.

show abstract

\min \frac{1}{2} ∥ {normalβ}^{2} ∥ + \frac{C}{2} {false\sum}_{i = 1}^{N} ∥ {normalξ}_{normali} ∥^{2}

s \cdot t h (x_{i}) β = t_{normali}^{T} - {normalξ}_{normali}^{T}, i = 1 \dots N,

where

C

shows the balance parameter,

N

shows the training data and

{normalξ}_{normali}

is the i th neuron's error vector.…”

Section: Methods and The Proposed Vmd‐denetworkmentioning

confidence: 99%

Section: Extreme Learning Machinementioning

confidence: 99%

Time series forecasting based on a novel ensemble‐based network and variational mode decomposition

Nazarieh

Dehkordi

2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…This diversity poses substantial challenges in predicting responses to personalized anti-cancer treatments[4]. In this context, single-cell RNA sequencing (scRNA-seq) analysis has emerged as a powerful tool, providing novel insights into the cellular composition of tumors[5] and enabling the identification of distinct cellular subpopulations that contribute to resistance[6, 7]. The analysis of scRNA-seq holds great promise for enhancing drug response prediction, tailoring therapies to individual patients, and facilitating personalized oncology[8].…”

Section: Introductionmentioning

confidence: 99%

SCREP: Towards Single-Cell Drug Response Prediction by Pharmacogenomic Embedding Enhanced Meta-Pretraining and Few-Shot Transfer Learning

Ge,

Sun,

Ren

et al. 2024

Preprint

View full text Add to dashboard Cite

Analyzing the drug response at the cellular level is crucial for identifying biomarkers and understanding the mechanisms of resistance. Although studies on the drug response of individual cells can provide novel insights into tumor heterogeneity, pharmacogenomic data related to single-cell (SC) RNA sequencing is often limited. Transfer learning provides a promising approach to translate the knowledge of drug response from bulk cell lines to SC analysis, potentially providing an effective solution to this challenge. Previous studies often use data from single drug-cell lines to pre-train specific models and adapt the models on SC datasets, which lack pharmacogenomic information from other drugs and hinder model generalization. In this work, we introduce MetaSCDrug as a unified meta pre-training framework that integrates molecular information with transcriptomic data to simultaneously modeling cellular heterogeneity in response to multiple pre-trained drugs and generalize to unseen drugs. Our model requires only one pre-training session, followed by fine-tuning on multiple single-cell datasets by few-shot learning, achieving an average of 4.58% accuracy increase in drug response prediction compared to the baselines. Furthermore, our meta pre-training strategy effectively captures transcriptome heterogeneity in the generalization of unseen drugs, achieving a 20% improvement over the model without meta pre-training. Case studies of our framework highlight its capability to identify critical genes for resistance, providing a method for exploring drug action pathways and understanding resistance mechanisms.

show abstract

“…Several machine learning studies have been conducted. Yadav et al [4] used machine learning methods to analyze the novel coronavirus, Liu et al [5] studied dynamic kernel-based ELM to predict water treatment processes in paper manufacturing, and ELM has even been used in the classification of tumor diseases [6] and the diagnosis of COVID-19 [7].…”

Section: Introductionmentioning

confidence: 99%

Particle Swarm Optimization – Extreme Learning Machine with Decreasing Inertia Weight for COVID-19 Prediction in Surabaya

Tuloli,

Anam,

Shofianah

2023

JELS

View full text Add to dashboard Cite

has spread all throughout the world, even to Indonesia. Surabaya becomes one of Indonesia's major cities where COVID-19 is fast spreading, culminating in a large number of positive cases and over 1000 deaths from the disease by November 2020. The number of positive COVID-19 cases predicted can be utilized to limit hospital facility availability and develop plans and policies for tackling the illness outbreak. One of the many prediction systems identified is the Extreme Learning Machine (ELM). ELM has a quick and precise training speed. However, the performance of ELM depends on the number of neurons. When the number of neurons is not precisely specified, prediction accuracy suffers. Particle Swarm Optimization (PSO) has the ability to optimize the number of node ELM neurons so the ELM can achieve better results. The number of neurons is determined using Particle Swarm Optimization (PSO) with decreased inertia weight. As a result, this research proposes predicting COVID-19 instances in Surabaya using a hybrid of PSO and ELM (PSO-ELM) with decreased inertia weight. The studies reveal that the offered techniques with different activation functions work comparably well in predicting COVID-19 instances in Surabaya. The best MAPE is achieved using the sigmoid activation function with the number of hidden layer nodes around 𝐿 = 25.

show abstract

L2,1-Extreme Learning Machine: An Efficient Robust Classifier for Tumor Classification

Cited by 11 publications

References 35 publications

Time series forecasting based on a novel ensemble‐based network and variational mode decomposition

Time series forecasting based on a novel ensemble‐based network and variational mode decomposition

SCREP: Towards Single-Cell Drug Response Prediction by Pharmacogenomic Embedding Enhanced Meta-Pretraining and Few-Shot Transfer Learning

Particle Swarm Optimization – Extreme Learning Machine with Decreasing Inertia Weight for COVID-19 Prediction in Surabaya

Contact Info

Product

Resources

About