A novel GA-ELM model for patient-specific mortality prediction over large-scale lab event data

Krishnan, Gokul; Kamath, S. Sowmya

doi:10.1016/j.asoc.2019.04.019

Cited by 53 publications

(21 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can be seen that the computational complexity of NBPSOSEE-SBS algorithm is obviously highly compared with the BPSO and CBPSO algorithms. However, R 4 , R 5 , and R 6 are the only simple numerical operations according to equations (10), (13), (14), (19), and (20). Furthermore, a large number of redundant or irrelevant features are deleted by the NBPSOSEE algorithm.…”

Section: Computational Complexity Of Nbpsosee-sbsmentioning

confidence: 99%

“…However, there is no interaction between classification algorithm and features in the process of feature selection by filter approaches. e wrapper approaches rely on classification algorithms to evaluate the selected feature subsets, which can achieve a higher classification accuracy than filter methods [20]. However, wrapper algorithms have high computational complexity in feature selection of highdimensional data sets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Improved Hybrid Feature Selection Algorithm for Electric Charge Recovery Risk

Suxiang

Shi

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In order to extract more information that affects customer arrears behavior, the feature extraction method is used to extend the low-dimensional features to the high-dimensional features for the warning problem of user arrears risk model of electric charge recovery (ECR). However, there are many irrelevant or redundant features in data, which affect prediction accuracy. In order to reduce the dimension of the feature and improve the prediction result, an improved hybrid feature selection algorithm is proposed, integrating nonlinear inertia weight binary particle swarm optimization with shrinking encircling and exploration mechanism (NBPSOSEE) with sequential backward selection (SBS), namely, NBPSOSEE-SBS, for selecting the optimal feature subset. NBPSOSEE-SBS can not only effectively reduce the redundant or irrelevant features from the feature subset selected by NBPSOSEE but also improve the accuracy of classification. The experimental results show that the proposed NBPSOSEE-SBS can effectively reduce a large number of redundant features and stably improve the prediction results in the case of low execution time, compared with one state-of-the-art optimization algorithm, and seven well-known wrapper-based feature selection approaches for the risk prediction of ECR for power customers.

show abstract

Section: Computational Complexity Of Nbpsosee-sbsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Improved Hybrid Feature Selection Algorithm for Electric Charge Recovery Risk

Suxiang

Shi

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…O estudo apresentado por [Ma et al 2020] O modelo de predição de mortalidade proposto por [Krishnan and S. 2019] analisa inicialmente um conjunto complexo de 578 variáveis entre resultados de exames e dados demográficos. Algoritmos genéticos são utilizados para selecionar pacientes afins e as 10 variáveis mais significativas do conjunto inicial são utilizadas como entrada do modelo baseado em ELM.…”

Section: Trabalhos Relacionadosunclassified

“…O conceito de individualização deve ser entendido aqui como a seleção de pacientes similares baseado na idade. Onde, a utilização da idadeé respaldada pela análise das variáveis dos escores de risco heurísticos como APACHE 1 e SAPS 2 que foram desenvolvidos por profissionais da saúde e são amplamente utilizados em Unidade de Terapia Intensiva (UTI) para avaliar o risco de morte dos pacientes [Krishnan and S. 2019]. Tais escores atribuem uma pontuação específica para faixas de idade dos pacientes.…”

Section: Introductionunclassified

Um Modelo para Predição Individualizada da Deterioração da Saúde de Pacientes no âmbito da Internet das Coisas

Kaieski¹,

Schmidt²,

Kelsh³

et al. 2020

Anais Principais Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2020)

View full text Add to dashboard Cite

Este artigo apresenta o desenvolvimento de um modelo baseado em internet das coisas de saúde e inteligência artificial para prever a deterioração do estado de saúde de pacientes. Foi construído um modelo de Deep Learning baseado em Redes Neurais Convolucionais para processar os dados que podem ser coletados por sensores ubíquos. Foram utilizadas duas estratégias diferentes para treinar o modelo, uma baseada na abordagem populacional tradicional e outra mais individualizada onde os dados de treinamento são oriundos de pacientes similares em termos de idade ao indivíduo monitorado. Os resultados mostraram uma sensível melhora na acurácia da predição de mortalidade do modelo individualizado com AUC média de 0,73 para todas as faixas de idade enquanto o modelo populacional apresentou AUC de 0,70.

show abstract

“…The statistical characteristics of data sets and the way of generating random parameters have a significant impact on the performance of ELM [10]- [12]. Recently, there have been many research of ELM based on parameter optimization, such as ELM based on Principal Component Analysis ELM(PCA-ELM) [13], ELM based on Particle Swarm Optimization (PSO-ELM) [14] and ELM based on Genetic Algorithm(GA-ELM) [15]. Compared with the traditional neural network learning methods, ELM has significant learning efficiency.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Distributed and Parallel Extreme Learning Machine for Big Data

et al. 2020

View full text Add to dashboard Cite

Extreme learning machine (ELM) is characterized by good generalization performance, fast training speed and less human intervention. With the explosion of large amount of data generated on the Internet, the learning algorithm in the single-machine environment cannot meet the huge memory consumption of matrix computing, so the implement of distributed ELM algorithm has gradually become one of the research focuses. In view of the research significance and implementation value of distributed ELM, this paper first introduced the research background of ELM and improved ELM. Secondly, this paper elaborated the implementation method of distributed ELM from the two directions: ensemble and matrix operation. Finally, we summarized the development status of distributed ELM and discussed the future research direction.

show abstract

A novel GA-ELM model for patient-specific mortality prediction over large-scale lab event data

Cited by 53 publications

References 33 publications

An Improved Hybrid Feature Selection Algorithm for Electric Charge Recovery Risk

An Improved Hybrid Feature Selection Algorithm for Electric Charge Recovery Risk

Um Modelo para Predição Individualizada da Deterioração da Saúde de Pacientes no âmbito da Internet das Coisas

A Survey of Distributed and Parallel Extreme Learning Machine for Big Data

Contact Info

Product

Resources

About