Here, we use a structure-based, machine learning algorithm to engineer a robust and active PET hydrolase. Our mutant and scaffold combination (FAST-PETase: functional, active, stable and tolerant PETase) contains five mutations compared to wild-type PETase (N233K/R224Q/S121E from prediction ...
Engineering servicesCost overrunHigh-rise residential buildingsMachine learningRandom forest regressionA robust random forest regression model to predict ESCOs is proposed.A database consisting of 95 high-rise residential building projects is used.The proposed model performance is compared with SVR and MLR...
Machine learning-aided engineering of hydrolases for PET depolymerization 来自 国家科技图书文献中心 喜欢 0 阅读量: 260 摘要: Plastic waste poses an ecological challengeand enzymatic degradation offers one, potentially green and scalable, route for polyesters waste recycling. Poly(ethylene terephthalate)...
Lu XZ, Intelligent design method for beam and slab of shear wall structure based on deep learnin...
Machine learning-aided engineering of hydrolases for PET depolymerization. Nature 604, 662–667 (2022). CAS PubMed ADS Google Scholar Giessel, A. et al. Therapeutic enzyme engineering using a generative neural network. Sci. Rep. 12, 1536 (2022). CAS PubMed PubMed Central ADS Google Scholar...
Keywordscomputer aided engineeringmachine learningcarbon footprint assessmentEstimating the carbon footprint of products at the early stage of design is crucial ... T Hasebe,E Katayama,K Yoshiteru - 《Procedia Cirp》 被引量: 0发表: 2024年 A hybrid mechanistic machine learning approach to model indu...
Also, engineering design tasks such as topology optimization, generating unique design concepts, and even computer-aided engineering and simulation can be performed by deep learning methods (Oh et al., 2019). More details on such specific applications are given in the following sections. GAN, ...
Machine Learning: New Ideas and Tools in Environmental Science and Engineering 7032 01:09:00 如何识别陆地与海洋气溶胶来源? 3784 53:00 Carbon source/sink functions of rice paddies: Biogeochemical processes underlying the trade-off 1937 01:28:00 ...
An unsupervised machine learning approach for ground-motion spectra clustering and selection Clustering analysis of sequence data continues to address many applications in engineering design, aided with the rapid growth of machine learning in appli... RB Bond,P Ren,JFSH Hajjar - 《Earthquake Engineeri...
layer. The last layer is an output layer which only has two neurons. Batch normalization was applied to a one-to-one layer and each hidden layer to accelerate the training process. SGD optimizer was used to train the DNN model and the learning rate was fixed as 0.01. Default values of ...