Assessment of different machine learning techniques in predicting the compressive strength of self-compacting concrete

The compressive strength of self-compacting concrete (SCC) needs to be determined during the construction design process. This paper shows that the compressive strength of SCC (CS of SCC) can be successfully predicted from mix design and curing age by a machine learning (ML) technique named the Extreme Gradient Boosting (XGB) algorithm, including non-hybrid and hybrid models. Nine ML techniques, such as Linear regression (LR), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees (DTR), Random Forest (RF), Gradient Boosting (GB), and Artificial Neural Network using two training algorithms LBFGS and SGD (denoted as ANN_LBFGS and ANN_SGD), are also compared with the XGB model. Moreover, the hybrid models of eight ML techniques and Particle Swarm Optimization (PSO) are constructed to highlight the reliability and accuracy of SCC compressive strength prediction by the XGB_PSO hybrid model. The highest number of SCC samples available in the literature is collected for building the ML techniques. Compared with previously published works’ performance, the proposed XGB method, both hybrid and non-hybrid models, is the most reliable and robust of the examined techniques, and is more accurate than existing ML methods (R² = 0.9644, RMSE = 4.7801, and MAE = 3.4832). Therefore, the XGB model can be used as a practical tool for engineers in predicting the CS of SCC.     

A PCR Assay for Specific Detection of the Pandemic Vibrio parahaemolyticus O3:K6 Clone from Shellfish

: The current standard method for identifying Vibrio parahaemolyticus serotype O3:K6, an emerging pathogen with apparent enhanced virulence characteristics, typically takes 4 to 6 d to complete and requires serotyping. To provide a more rapid strategy, we optimized a polymerase chain reaction (PCR)‐based assay for specific detection of V. parahaemolyticus O3:K6. Of 78 V. parahaemolyticus isolates and other related species; only strains classified into the V. parahaemolyticus O3:K6 clonal group (n= 39) showed positive results in the PCR assay. The assay detected 2.3 cells/PCR reaction and 310 cells/g using bacterial cultures and inoculated oyster samples, respectively. Sensitive and specific detection of V. parahaemolyticus O3:K6 was possible following a 6‐h enrichment.     

Improving learning accuracy of fuzzy decision trees by hybridneural networks

Although the induction of fuzzy decision tree (FDT) has been a very popular learning methodology due to its advantage of comprehensibility, it is often criticized to result in poor learning accuracy. Thus, one fundamental problem is how to improve the learning accuracy while the comprehensibility is kept. This paper focuses on this problem and proposes using a hybrid neural network (HNN) to refine the FDT. This HNN, designed according to the generated FDT and trained by an algorithm derived in this paper, results in a FDT with parameters, called weighted FDT. The weighted FDT is equivalent to a set of fuzzy production rules with local weights (LW) and global weights (GW) introduced in our previous work (1998). Moreover, the weighted FDT, in which the reasoning mechanism incorporates the trained LW and GW, significantly improves the FDTs' learning accuracy while keeping the FDT comprehensibility. The improvements are verified on several selected databases. Furthermore, a brief comparison of our method with two benchmark learning algorithms, namely, fuzzy ID3 and traditional backpropagation, is made. The synergy between FDT induction and HNN training offers new insight into the construction of hybrid intelligent systems with higher learning accuracy     

Microstructural evolution in NiTi alloy subjected to surface mechanical attrition treatment and mechanism

Both nanocrystalline and amorphous phases are observed from the near surface of nickel titanium shape memory alloy (NiTi SMA) with the B2 austenite phase after surface mechanical attrition treatment (SMAT). The microstructure and phase changes are systematically studied by cross-sectional and plane-view transmission electron microscopy. The strain induces grain refinement and it is accompanied by increased strain in the surface layer triggering the onset of highly dense dislocations and dislocation tangles (DTs), formation of the martensite plate via stress-induced martensite (SIM) transformation (B2 to B19′), and dislocation lines (DLs) as well as dense dislocation walls (DDWs) inside the martensite plate leading to the subdivision of the martensite plate. In addition, reverse martensite transformation (B19′ to B2) and amorphization take place concurrently in the surface region, and successive subdivision and amorphization finally result in the formation of well separated nanocrystalline and amorphous phases in the near surface. The average grain size of the nanocrystallites is about 20 nm. Owing to the almost complete reverse martensite transformation as well as thermal stability, the strain-induced nanocrystalline structure has the B2 austenite phase in the surface layer and no transformation occurs.     

Termination of translation in eukaryotes: new results and new hypotheses

The viscoelastic properties of the human and canine pharyngeal tissue in tension were evaluated, based on both an experimental protocol-consisting of cyclic load, tensile stress relaxation, and incremental step load tests-and the quasi-linear viscoelastic theory. The reduced stress relaxation function and the elastic response of the pharyngeal tissues were derived from the experimental results specifically obtained from those tissues. The characteristic features of viscoelastic property were obtained for both human and canine pharyngeal tissues by applying the quasi-linear viscoelastic theory and compared with each other. The material properties of the pharyngeal tissue were sought to facilitate the three-dimensional biomechanical model of the pharyngeal function by using the finite element method.     

High-throughput enzyme kinetics using microarrays

We report a microanalytical method to study enzyme kinetics. The technique involves immobilizing horseradish peroxidase on a poly-L-lysine (PLL)-coated glass slide in a microarray format, followed by applying substrate solution onto the enzyme microarray. Enzyme molecules are immobilized on the PLL-coated glass slide through electrostatic interactions, and no further modification of the enzyme or glass slide is needed. In situ detection of the products generated on the enzyme spots is made possible by monitoring the light intensity of each spot using a scientific-grade charged-coupled device (CCD). Reactions of substrate solutions of various types and concentrations can be carried out sequentially on one enzyme microarray. To account for the loss of enzyme from washing in between runs, a standard substrate solution is used for calibration. Substantially reduced amounts of substrate solution are consumed for each reaction on each enzyme spot. The Michaelis constant K_m obtained by using this method is comparable to the result for homogeneous solutions. Absorbance detection allows universal monitoring, and no chemical modification of the substrate is needed. High-throughput studies of native enzyme kinetics for multiple enzymes are therefore possible in a simple, rapid, and low-cost manner.     

A NUMERICAL SCHEME FOR NON-FOURIER HEAT CONDUCTION,PART II: TWO-DIMENSIONAL PROBLEM FORMULATION AND VERIFICATION

A flux-splitting algorithm based on the Godunov numerical scheme developed for the solution of the one-dimensional non-Fourier heat conduction equation by Yeung and Lam [1] is extended for the investigation of thermal wave propagation in rectangular media. The derivation of the solution method and the stability criteria are presented in detail. Physical problems subjected to various boundary conditions (e.g., first, second, and third kinds) can be studied with the numerical scheme. A comparison of the exact solution with the one calculated by the proposed procedure is presented to confirm the validity of the numerical procedure. The numerical scheme is applicable for the study of short-pulse heating in advanced materials, microstructures, thin films, semiconductor devices, and superconductors.