Applying simulated evolution to scheduling in high level synthesis

Ly, Tai; Mowchenko, J.T.

doi:10.1109/mwscas.1990.140679

Cited by 8 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lee et al [76] introduced a novel approach employing inverse reinforcement learning coupled with agent-based modeling for Bitcoin price prediction. Ly et al [77] employed LSTM networks to predict Bitcoin trends, demonstrating the models' capability to forecast price changes and classify market movements with varying degrees of accuracy. Saad et al [13] found LSTM to be the most accurate in forecasting Bitcoin prices compared to various machine learning modelsPatel et al Lucarelli and Borrotti [78] investigated automated cryptocurrency trading using deep reinforcement learning, employing double deep Qlearning networks trained by Sharpe ratio rewards, which outperformed traditional models in Bitcoin trading.…”

Section: Deep Learning Models For Cryptocurrency Predictionmentioning

confidence: 99%

Prediction models for atopic dermatitis diagnosis and evaluation：based on Machine learning (Preprint)

Wu¹,

Li²,

Hu³

et al. 2022

Preprint

View full text Add to dashboard Cite

BACKGROUND Atopic dermatitis (AD) is the most common chronic inflammatory skin disease that seriously affects patients’ quality of life. Reliable and accurate evaluation methods are necessary for early diagnosis and individual treatment of AD, machine learning (ML) approaches may support clinical decision making for patients with AD. OBJECTIVE This study uses ML to explore a novel diagnosis and therapeutic effect evaluation prediction model for AD. METHODS GEO transcriptome datasets were integrated to identify differentially expressed genes, candidate model genes were further screened using Robust Rank Aggregation (RRA), constructed PPI network, and literature review. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyzed the biological functions of candidate model genes. Then, three recognized models (REC) and three AD-associated gene models (AAG) were trained and tested separately in different datasets. The therapeutic effect and Scoring of Atopic Dermatitis (SCORD) were used to confirm the practicality of these models. Finally, single sample gene set enrichment analysis (ssGSEA) and immune infiltration analysis were performed to explore the potential relationship between model genes and immune cells in AD. RESULTS REC model of Lasso (model genes including IL7R, KRT16, CCL2, CD53, CCL18 and CCL22) and AAG model of Logistic linear regression (LR) (model genes including MX1, CCNB1, SERPINB13, ADAM19, CEP55, VMP1, TTC39A, and FCHSD1) could accurately classified AD lesions and non-lesions in training and testing data and showed good AUC (basically above 0.8). In Dupilumab, Crisaborole, and Fezakinumab-treated samples, the expression of model genes was positively correlated with the severity of lesions and negatively correlated with treatment length. In addition, the two models can also accurately predict the infiltration of immune cells in the skin lesions and non-lesions. CONCLUSIONS ML can be used to construct a predictive model for the diagnosis and evaluation of the therapeutic effects of AD.

show abstract

Section: Deep Learning Models For Cryptocurrency Predictionmentioning

confidence: 99%