Search

This article proposes a dynamic evolving fuzzy system (DEFS) for streaming data prediction. DEFS utilizes the enhanced data potential and prediction errors of individual local models as the main criteria for fuzzy rule generation. A vital feature of the proposed system is its novel rule merging scheme that can self-adjust its tolerance toward the degree of similarity between two similar fuzzy rules according to the size of the rule base. To better handle the shifts and drifts in the data patterns, a novel rule quality measure based on both the utility values and the prediction accuracy of individual fuzzy rules is further introduced to help DEFS identify these less activated fuzzy rules with poorer descriptive capabilities and, thereby, maintaining a healthier fuzzy rule base by removing these stale rules. Very importantly, the thresholds used by DEFS are self-adaptive toward the input data. The adaptive thresholds can help DEFS to precisely capture the underlying structure and dynamically changing patterns of streaming data, enabling the system to perform accurate approximation reasoning. Numerical examples based on several popular benchmark problems show the superior performance of DEFS over the state-of-the-art evolving fuzzy systems. The prediction performance of the proposed method is at least 2.88% better than the best-performing comparative EFSs on each individual regression benchmark problem considered in this study, and the average performance improvement across all the numerical experiments is approximately 30%.

Fuzzy systems offer a formal and practically popular methodology for modeling nonlinear problems with inherent uncertainties, entailing strong performance and model interpretability. Particularly, semisupervised boosting is widely recognized as a powerful approach for creating stronger ensemble classification models in the absence of sufficient labeled data without introducing any modification to the employed base classifiers. However, the potential of fuzzy systems in semisupervised boosting has not been systematically explored yet. In this study, a novel semisupervised boosting algorithm devised for zero-order evolving fuzzy systems is proposed. It ensures both the consistence among predictions made by individual base classifiers at successive boosting iterations and the respective levels of confidence toward their predictions throughout the process of sample weight updating and ensemble output generation. In so doing, the base classifiers are empowered to gradually focus more on challenging samples that are otherwise hard to generalize, enabling the development of more precise integrated classification boundaries. Numerical evaluations on a range of benchmark problems are carried out, demonstrating the efficacy of the proposed semisupervised boosting algorithm for constructing ensemble fuzzy classifiers with high accuracy.

Tropical cyclones (TCs), with an intensive wind pump impact, induce sea surface temperature cooling (SSTC) on the upper ocean. SSTC is a pronounced indicator to reveal TC evolution and oceanic conditions. However, there are few effective methods for accurately approximating the amplitude of the spatial structure of TC-induced SSTC. This study proposes a novel explainable machine learning framework to model and interpret the amplitude of the spatial structure of SSTC over the northwest Pacific (NWP). In particular, 12 predictors related to TC characteristics and pre-storm ocean states are considered as inputs. A composite analysis technique is used to characterize the amplitude of the spatial structure of SSTC across the TC track. Extreme gradient boosting (XGBoost) is utilized to predict the amplitude of SSTC from the 12 predictors. To better interpret the ocean–atmosphere interaction, a SHapely Additive explanations (SHAP) method is further employed to identify the contributions of predictors in determining the amplitude of the TC-induced SSTC, bringing the attribute-oriented explainability to the proposed method. The results showed that the proposed method could accurately predict the amplitude of the spatial structure of SSTC for different TC intensity groups and outperforms a numerical model. The proposed method also serves as an effective tool for reconstructing composite maps of both interannual and seasonal evolutions of SSTC spatial structure. The study offers insight into applying machine learning to model and interpret the responses of oceanic conditions triggered by extreme weather conditions (e.g., TCs).

It is widely recognized that learning systems have to go deeper to exchange for more powerful representational learning capabilities in order to precisely approximate nonlinear complex problems. However, the best-known computational intelligence approaches with such characteristics, namely, deep neural networks, are often criticized for lacking transparency. In this article, a novel multilayer evolving fuzzy neural network (MEFNN) with a transparent system structure is proposed. The proposed MEFNN is a metalevel stacking ensemble learning system composed of multiple cascading evolving neuro-fuzzy inference systems (ENFISs), processing input data layer-by-layer to automatically learn multilevel nonlinear distributed representations from data. Each ENFIS is an evolving fuzzy system capable of learning from new data sample by sample to self-organize a set of human-interpretable IF– THEN fuzzy rules that facilitate approximate reasoning. Adopting ENFIS as its ensemble component, the multilayer system structure of the MEFNN is flexible and transparent, and its internal reasoning and decision-making mechanism can be explained and interpreted to/by humans. To facilitate information exchange between different layers and attain stronger representation learning capability, the MEFNN utilizes error backpropagation to self-update the consequent parameters of the IF–THEN rules of each ensemble component based on the approximation error propagated backward. To enhance the capability of the MEFNN to handle complex problems, a nonlinear activation function is introduced to modeling the consequent parts of the IF–THEN rules of ENFISs, thereby empowering both the representation and the reflection of nonlinearity in the resulting fuzzy outputs. Numerical examples on a wide variety of challenging (benchmark and real-world) classification and regression problems demonstrate the superior practical performance of the MEFNN, revealing the effectiveness and validity of the proposed approach.

Evolving intelligent systems (EISs), particularly, the zero-order ones have demonstrated strong performance on many real-world problems concerning data stream classification while offering high model transparency and interpretability thanks to their prototype-based nature. Zero-order EISs typically learn prototypes by clustering streaming data online in a “one pass” manner for greater computation efficiency. However, such identified prototypes often lack optimality, resulting in less precise classification boundaries, thereby hindering the potential classification performance of the systems. To address this issue, a commonly adopted strategy is to minimize the training error of the models on historical training data or alternatively to iteratively minimize the intracluster variance of the clusters obtained via online data partitioning. This recognizes the fact that the ultimate classification performance of zero-order EISs is driven by the positions of prototypes in the data space. Yet, simply minimizing the training error may potentially lead to overfitting while minimizing the intracluster variance does not necessarily ensure the optimized prototype-based models to attain improved classification outcomes. To achieve better classification performance while avoiding overfitting for zero-order EISs, this article presents a novel multiobjective optimization approach, enabling EISs to obtain optimal prototypes via involving these two disparate but complementary strategies simultaneously. Five decision-making schemes are introduced for selecting a suitable solution to deploy from the final nondominated set of the resulting optimized models. Systematic experimental studies are carried out to demonstrate the effectiveness of the proposed optimization approach in improving the classification performance of zero-order EISs.

Testis differentiation is initiated when Sryin pre-Sertoli cells directs the gonad toward a male-specific fate. Sertoli cells are essential for testis development, but cell types within the interstitial compartment, such as immune and endothelial cells, are also critical for organ formation. Our previous work implicated macrophages in fetal testis morphogenesis, but little is known about genes underlying immune cell development during organogenesis. Here, we examine the role of the immune-associated genes Mafband Mafin mouse fetal gonad development, and we demonstrate that deletion of these genes leads to aberrant hematopoiesis manifested by supernumerary gonadal monocytes. Mafb; Mafdouble knockout embryos underwent initial gonadal sex determination normally, but exhibited testicular hypervascularization, testis cord formation defects, Leydig cell deficit, and a reduced number of germ cells. In general, Mafband Mafalone were dispensable for gonad development; however, when both genes were deleted, we observed significant defects in testicular morphogenesis, indicating that Mafband Mafwork redundantly during testis differentiation. These results demonstrate previously unappreciated roles for Mafband Mafin immune and vascular development and highlight the importance of interstitial cells in gonadal differentiation.Deletion of Mafband Mafgenes leads to supernumerary monocytes in fetal mouse gonads, resulting in vascular, morphogenetic, and differentiation defects during testicular organogenesis.

The thermal design of highly reliable modular multilevel converters (MMCs) is significant for the voltage-source converter based high-voltage direct current (VSC-HVdc) systems, especially under the ac unbalanced fault. In this paper, the surplus submodule is employed as new control freedom to optimize the thermal behavior of the MMCs, because its number is linearly increased with the ac voltage dip. With the surplus submodule active bypassed (SSAB), the total submodules of the MMC in one arm can be taken turns to reduce the thermal stress of the hottest power device. In order to obtain equal ac voltages in three phases to improve the SSAB strategy, the neutral-point-shift (NPS) scheme is introduced under the unbalanced conditions, especially single-phase-to-ground fault. Through the balancing of the amplitude of the MMC ac voltages with the NPS scheme, the thermal stress asymmetry of theMMC under the single-phaseto-ground fault is mitigated, and the junction temperature of the most stressed power devices is significantly reduced. Finally, the simulation and experiment results show that the junction temperature rise of the most stressed power device is reduced by nearly 30% with the SSAB plus NPS scheme.

In this paper, a new compact, vialess and vertical microstrip-to-microstrip differential transition is presented based on half-wavelength slotline structure. The equivalent-circuit model is constructed, and theoretical analyses based on equivalent circuit model reveal that good differential mode (DM) signal transmission between the top- and bottom-layer differential microstrip lines can be achieved over a wide frequency range determined while the common mode (CM) signal is rejected. Moreover, the systematic design method is presented to extract the values of electrical parameters from prescribed performance in terms of its operating bandwidth and ripple levels. In addition, owing to the employment of half-wavelength slot, the proposed differential transition has a compact size. Finally, the proposed differential transition and design theories are well vindicated by an exemplary circuit centered at 2.45 GHz with the measured relative frequency bandwidth (FBW) of 114 %.

This study proposes to construct a model using random forest method, an efficient machine learning‐based method, to predict the spatial structure and temporal evolution of the sea surface temperature (SST) cooling induced by northwest Pacific tropical cyclones (TCs), a process of the so‐called wind pump. The predictors in use include 12 predictors related to TC characteristics and pre‐storm ocean conditions. The model is shown to skillfully predict the spatiotemporal evolutions of the cold wake generated by TCs of different intensity groups, and capture the cross‐case variance in the observed SST response. Another model is further built based on the same method to assess the relative importance of the 12 predictors in determining the magnitude of the maximum cooling. Computations of feature scores of those predictors show that TC intensity, translation speed and size, and pre‐storm mixed layer depth and SST dominate, depending on the area where the cooling is considered. While many studies have been devoted to understanding the processes and mechanisms underlying the sea surface temperature (SST) cooling induced by tropical cyclones (TCs), few studies have attempted to predict the spatial and temporal evolution of the sea surface temperature (SST) cooling triggered by TCs. In this study, we proposed to achieve this goal by building a model using an efficient and robust machine learning‐based method. The constructed model uses 12 predictors associated with TC characteristics (e.g., intensity, and translation speed) and pre‐storm ocean states (e.g., mixed layer depth). The model performs well in producing the TC‐induced spatial structure and temporal evolution of the cold wake and can capture most of the variance in the observed SST response. We quantified the relative importance of the 12 predictors, and found that TC intensity, translation speed and size, and pre‐storm mixed layer depth and SST dominate in deciding the magnitude of the SST response. The results and proposed method have important implications for predicting the response of ocean primary production to the TC wind pump effects. A machine learning‐based model is built to predict the spatiotemporal evolution of the tropical cyclone‐induced sea surface temperature responseThe model well predicts the spatial structure and temporal evolution of the observed response and captures the observed cross‐case varianceFeature scores are computed to assess the relative importance of the predictors in determining the magnitude of the SST response A machine learning‐based model is built to predict the spatiotemporal evolution of the tropical cyclone‐induced sea surface temperature response The model well predicts the spatial structure and temporal evolution of the observed response and captures the observed cross‐case variance Feature scores are computed to assess the relative importance of the predictors in determining the magnitude of the SST response

Coal fly ash (CFA), an industrial solid waste, has been predominantly used a substitute for material in the concrete industry. Its reactivity is usually a crucial factor for use in cementitious composites. Conventionally physical and chemical treatments have been used to modify CFA for improving reactivity, but there still are some limitations such as easy agglomeration of particles, high cost, high energy-consumption, environmental pollution, etc. Herein, a feasible bio-modification treatment on CFA using Paenibacillus mucilaginosusis proposed. Adhesion and desilication of the bacteria & metabolites change the morphology, size distribution and surface properties of CFA. Compared with CFA, the bio-modified CFA (BCFA) has coarser surface, finer particle size, larger specific surface area (SSA), higher surface calcium content and lower surface Si/Al ratio. The characteristic changes contribute to enhancing the reactivity of BCFA relating to morphological, pozzolanic, micro-aggregate and interfacial effects in cementitious composites. The strength activity index (SAI) of BCFA reaches 90.8% at 28 d and increases 27.7% compared to that of CFA. Soluble silicon content in the bioleaching system shows significantly positive correlations with the SSA and SAI of BCFA (P < 0.05). The cementitious composites containing 30% BCFA show higher mechanical properties, lower early hydration heat and denser microstructure compared to those containing 30% CFA. This work could provide a promising green and low-carbon way to produce highly active BCFA for concrete industry and other fields.

Granites are inevitably subjected to the effects of repeated water quenching in the process of geothermal energy exploitation. To gain a greater understanding of the mechanical responses and cracking mechanisms of granites affected by quenching cycling, conventional triaxial compression tests were conducted involving granite samples after high temperature treatment (150–750 °C) with multiple water quenching cycles (1–15). The findings indicated that, when the heating temperature values or quenching cycles increase, both the longitudinal wave velocity and bulk density declined, while both the mass loss and volume increase rates were enhanced. The peak intensity of diffraction for quartz exhibited a reduction of 61.38% and 27.25%, respectively. Gradually enhanced thermal damage against the increase in temperature values or quenching cycles resulted in a loose matrix structure within the granite samples with complicated crack networks. With increasing number of cycles, the peak strength exhibited a negative linear decrease, and the reduction in peak strength with increasing temperature could be divided into two stages, with a threshold temperature value of 450 °C, while the peak axial strain experienced an exponential increasing trend. Both the elastic and secant moduli decreased with the temperature and number of cycles due to primary thermal damage accumulation in the granite, and the post peak rock brittleness weakened. As the temperature levels and quenching cycles were increased, the cohesion respectively decreased by 44.12–56.99% and 27.07–36.55%, due to the weakened bonding force between mineral grains, while the Poisson's ratio increased. Defining the crack damage stress (maximum volumetric strain) as the initial yield position, variations in the plastic shear strain and subsequent strength characteristics were analysed. Both the subsequent cohesion and internal friction angle increased with the plastic shear strain but decreased with both the temperature and number of cycles. At a low temperature level, typical oblique or V-shaped shear cracks, traversing the whole sample height, resulted in ultimate sample failure, while at a larger temperature level or a larger number of cycles, the sample was characterized by progressive failure of the loose matrix structure generated by 3D crack networks, rather than large penetrating macro cracks.

Incineration bottom ash (IBA) is the residue of municipal solid waste (MSW) after incineration, which is often used for land backfilling (in the anaerobic environment). This study reports a method of anaerobic bacteria for IBA treatment, and the mechanism of heavy metals immobilization by anaerobic bacteria is discussed in depth. In this study, the IBA from three cities, namely Shenyang, Wuhan, and Guangzhou in China, were treated with anaerobic bacterial grouting, and the leaching concentrations of heavy metals were detected. Their IBA production ranks among the top ten cities in China. The results show that the anaerobic bacteria can reduce the leaching concentration of Zn, Cu, Cd, Cr, As, and Pb, and the immobilization ratios reach 50-90%. Biotreatment improves the carbonate-bound form of the noted heavy metals, and the carbonate-bound form is positively correlated with bioprecipitation of calcium carbonate. It is observed by scanning electron microscope (SEM) and optical microscope that fragmentized calcium carbonate crystals are still generated when the upper surface of the sample exposes to air. The mechanism of immobilization during the biomineralization process is revealed by the fluorescence spectrum and chemical reaction. In an anaerobic environment, the anaerobic bacteria enrich calcium ions and carbonate ions to generate biogel, which can physically envelop heavy metals. The induction of anaerobic bacteria can stabilize heavy metals by changing chemical speciation. They all reach the strength limitation of land backfill. This study provides a new idea to reduce the environmental harm from the IBA and improves the sustainable utilization of IBA.