Reliable CA-(Q)SAR generation based on entropy weight optimized by grid search and correction factors

Compared with the strong background noise, the impact characteristics of wind turbine yaw bearing are weak in the initial damage stage. In order to completely eliminate unnecessary noise and detect damage characteristics, the useful component should be extracted from the complex vibration signal. To solve the problem that existing methods cannot effectively extract the useful component, an innovative hybrid strategy fusing weighted dual tree complex wavelet packet transform (WDTCWPT) with optimized minimum noise amplitude deconvolution (OMNAD) is developed. First, the envelope variable Rényi entropy indicator is defined, which reflects the impact strength. Meanwhile, this indicator is used to determine the optimal number of WDTCWPT decomposition level, and the weighted wavelet coefficient reconstruction is executed to get the enhanced signal. Subsequently, a square envelope correlation L-Kurtosis (SECLK) indicator is further defined and SECLK spectrum is utilized for estimating the deconvolution period. Ulteriorly, the multiple grid search algorithm is designed to automatically determine the optimal filter length as well as the noise ratio. And the optimal deconvolution signal with obvious damage characteristics can be obtained by OMNAD. Finally, the damage type of yaw bearing can be judged by performing envelope spectrum analysis on the deconvolution signal. The detection results of simulation and experiment signals demonstrate this developed hybrid strategy can accurately detect the local damage of yaw bearing under strong interference environment, which has certain engineering application value.

show abstract

Comprehensive hepatotoxicity prediction: ensemble model integrating machine learning and deep learning

Khan,

Ren,

Cao

et al. 2024

Front. Pharmacol.

View full text Add to dashboard Cite

BackgroundChemicals may lead to acute liver injuries, posing a serious threat to human health. Achieving the precise safety profile of a compound is challenging due to the complex and expensive testing procedures. In silico approaches will aid in identifying the potential risk of drug candidates in the initial stage of drug development and thus mitigating the developmental cost.MethodsIn current studies, QSAR models were developed for hepatotoxicity predictions using the ensemble strategy to integrate machine learning (ML) and deep learning (DL) algorithms using various molecular features. A large dataset of 2588 chemicals and drugs was randomly divided into training (80%) and test (20%) sets, followed by the training of individual base models using diverse machine learning or deep learning based on three different kinds of descriptors and fingerprints. Feature selection approaches were employed to proceed with model optimizations based on the model performance. Hybrid ensemble approaches were further utilized to determine the method with the best performance.ResultsThe voting ensemble classifier emerged as the optimal model, achieving an excellent prediction accuracy of 80.26%, AUC of 82.84%, and recall of over 93% followed by bagging and stacking ensemble classifiers method. The model was further verified by an external test set, internal 10-fold cross-validation, and rigorous benchmark training, exhibiting much better reliability than the published models.ConclusionThe proposed ensemble model offers a dependable assessment with a good performance for the prediction regarding the risk of chemicals and drugs to induce liver damage.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Reliable CA-(Q)SAR generation based on entropy weight optimized by grid search and correction factors

Cited by 3 publications

References 41 publications

Risk substance identification of asphalt VOCs integrating machine learning and network pharmacology

Risk substance identification of asphalt VOCs integrating machine learning and network pharmacology

A novel hybrid strategy for damage detection of wind turbine yaw bearing

Comprehensive hepatotoxicity prediction: ensemble model integrating machine learning and deep learning

Contact Info

Product

Resources

About