Search Results (11)

The ceteris paribus assumption that all features are equal except the one(s) being examined limits the reliability of nutrient diagnosis and fertilizer recommendations. The objective of this paper is to review machine learning (ML) and compositional data analysis (CoDa) tools to make nutrient management feature specific. The accuracy of the ML methods averaged 84% across the crops. The additive and orthogonal log ratios of CoDa reduce a D-parts soil composition to D-1 variables, alleviating redundancy in the predictive ML models. Using a Brazilian onion (Allium cepa) database, the combined CoDa and ML methods returned crop response patterns, allowing feature-specific fertilizer recommendations to be made. The centered log ratio (clr) diagnoses plant nutrients as a compositional nutrient diagnosis (CND). Using a Quebec database of vegetable crops, the mean variance of clr variables ($\overline{VAR}$) allowed comparing total variance among species and growth stages. While clr is the summation of equally weighted dual log ratios, dual nutrient log ratios may show unequal importance regarding crop performance. The RReliefF scores, gain ratios or gini inequality coefficients can provide weighting coefficients for each dual log ratio. The widely contrasting coefficients of weighted log ratios (wlr) improved the accuracy of the ML models for a Quebec muck onion database. The ML models, $\overline{VAR}$ and wlr, are advanced tools to improve the accuracy of nutrient diagnosis. Full article

Abundant and rare bacteria exhibit unequal responses to environmental changes and disturbances, potentially resulting in differential contributions to the altitudinal characteristics of total community in natural and disturbed soils. Although the altitude patterns of soil bacteria have been widely studied, it remains unclear whether these patterns are consistent among bacteria with varying predominance levels, and which subpopulation contributes more to maintaining these patterns in natural and disturbed subalpine forest soils. In this study, we collected 18 natural subalpine forest soil samples and 18 disturbed ones from three altitudes (2900 m a.s.l., 3102 m a.s.l., and 3194 m a.s.l.) along the Wenma highway in Miyaluo, Lixian, Sichuan, Southwest China. By partitioning total bacterial communities based on species predominance, we found that bacteria with higher predominance levels tended to exhibit altitude patterns (α-diversity, community structure, and functional redundancy) similar to those of total bacteria in both natural and disturbed subalpine forest soils, although they only occupied a small portion of the community. Abundant bacteria might play critical roles in maintaining the regional ecological characteristics of total community across the altitude gradient, while the rare and hyper-rare ones might contribute more to local diversity and functional redundancy. In natural soils, the altitude patterns of α-diversity inferred from total, abundant, and rare bacteria were mainly shaped by ${\mathrm{NO}}_3^{-}$-N, while soil conductivity mainly drove the altitude patterns of α-diversity inferred from hyper-rare bacteria. Additionally, the community structures of total, abundant, rare, and hyper-rare bacteria were mainly shaped by ${\mathrm{NO}}_3^{-}$-N, while the altitude patterns of functional redundancy inferred from total, abundant, and rare bacteria were mainly shaped by soil conductivity in natural soils. In disturbed subalpine forest soils, the influences of ${\mathrm{NO}}_3^{-}$-N for the altitude patterns of α-diversity and community structure, and those of soil conductivity for functional redundancy, were relatively weak in total, abundant, rare, and hyper-rare bacteria. This study examined the roles of bacteria with varying predominance levels in maintaining the altitude pattern of bacteria in both natural and disturbed subalpine forest soils, providing novel insights for devising strategies to conserve biodiversity and ecologically restore disturbed soils in subalpine ecosystems. Full article

Evaluating classification accuracy is a key component of the training and validation stages of thematic map production, and the choice of metric has profound implications for both the success of the training process and the reliability of the final accuracy assessment. We explore key considerations in selecting and interpreting loss and assessment metrics in the context of data imbalance, which arises when the classes have unequal proportions within the dataset or landscape being mapped. The challenges involved in calculating single, integrated measures that summarize classification success, especially for datasets with considerable data imbalance, have led to much confusion in the literature. This confusion arises from a range of issues, including a lack of clarity over the redundancy of some accuracy measures, the importance of calculating final accuracy from population-based statistics, the effects of class imbalance on accuracy statistics, and the differing roles of accuracy measures when used for training and final evaluation. In order to characterize classification success at the class level, users typically generate averages from the class-based measures. These averages are sometimes generated at the macro-level, by taking averages of the individual-class statistics, or at the micro-level, by aggregating values within a confusion matrix, and then, calculating the statistic. We show that the micro-averaged producer’s accuracy (recall), user’s accuracy (precision), and F1-score, as well as weighted macro-averaged statistics where the class prevalences are used as weights, are all equivalent to each other and to the overall accuracy, and thus, are redundant and should be avoided. Our experiment, using a variety of loss metrics for training, suggests that the choice of loss metric is not as complex as it might appear to be, despite the range of choices available, which include cross-entropy (CE), weighted CE, and micro- and macro-Dice. The highest, or close to highest, accuracies in our experiments were obtained by using CE loss for models trained with balanced data, and for models trained with imbalanced data, the highest accuracies were obtained by using weighted CE loss. We recommend that, since weighted CE loss used with balanced training is equivalent to CE, weighted CE loss is a good all-round choice. Although Dice loss is commonly suggested as an alternative to CE loss when classes are imbalanced, micro-averaged Dice is similar to overall accuracy, and thus, is particularly poor for training with imbalanced data. Furthermore, although macro-Dice resulted in models with high accuracy when the training used balanced data, when the training used imbalanced data, the accuracies were lower than for weighted CE. In summary, the significance of this paper lies in its provision of readers with an overview of accuracy and loss metric terminology, insight regarding the redundancy of some measures, and guidance regarding best practices. Full article

In deep engineering, rockburst hazards frequently result in injuries, fatalities, and the destruction of contiguous structures. Due to the complex nature of rockbursts, predicting the severity of rockburst damage (intensity) without the aid of computer models is challenging. Although there are various predictive models in existence, effectively identifying the risk severity in imbalanced data remains crucial. The ensemble boosting method is often better suited to dealing with unequally distributed classes than are classical models. Therefore, this paper employs the ensemble categorical gradient boosting (CGB) method to predict short-term rockburst risk severity. After data collection, principal component analysis (PCA) was employed to avoid the redundancies caused by multi-collinearity. Afterwards, the CGB was trained on PCA data, optimal hyper-parameters were retrieved using the grid-search technique to predict the test samples, and performance was evaluated using precision, recall, and F1 score metrics. The results showed that the PCA-CGB model achieved better results in prediction than did the single CGB model or conventional boosting methods. The model achieved an F1 score of 0.8952, indicating that the proposed model is robust in predicting damage severity given an imbalanced dataset. This work provides practical guidance in risk management. Full article

The existing motor fault classification methods mostly use sensors to detect a single fault feature, which makes it difficult to ensure high diagnostic accuracy. In this paper, a motor fault classification method based on multi-source information fusion Naive Bayes classification algorithm is proposed. Firstly, this paper introduces the concept and advantages of multi-source information fusion, as well as its problems of miscellaneous information and inconsistent data magnitude. For example, as this paper classifies the fault of generators, there are many physical quantities, such as voltage, current and temperature, which are not in the same dimension, therefore it is difficult to fuse. Then, aiming at the corresponding problems, this paper uses a PCA dimension reduction method to remove redundant information and reduce the dimension of multi-dimensional complex information. Aiming at the problem of unequal data magnitude, the interval mapping method is adopted to effectively solve the misjudgment caused by unequal data magnitude. After the initial multi-source information processing, the classical Naive Bayes classification algorithm is used for fault classification, and the algorithm diagnosis and verification are carried out according to the statistical fault data. Use of the algorithm increases accuracy to more than 97%. Full article

The existing range of the centrosymmetric, triclinic RE(OAc)₃ · 2AcOH structure type has been extended for RE = Eu and Gd while the structure data of the Nd- and Sm-compounds have been revised and corrected, respectively, using low temperature (T = 100 K), well resolved (2?_max = 56°), highly redundant SCXRD data in order to evaluate the structural evolution within this class of acetic acid solvates by statistical methods. Within the nine-fold mono-capped square-antiprismatic coordination spheres of the RE³⁺ ions, RE-O distances decrease as a result of lanthanide contraction; some with different rates depending on the coordination modes (2.11/2.21) of the acetate ions. The experimental data show that the internal structural parameters of the acetate ions also correlate with their coordination modes. Both acetic acid molecules act as hydrogen bond donors but only one as monodentate ligand. The geometries of the hydrogen bonds reveal that they are strongly influenced by the size of the rare earth atom. The non-linear, one-dimensional coordination polymer propagates with unequal RE···RE distances along the a-axis. Rods of the coordination polymer are arranged in layers congruently stacked above each other with the hydrogen bonded acetic acid molecules as filler in between. In most cases, data fitting is best described in terms of a quadratic rather than a linear regression analysis. Full article

Modular multilevel converter (MMC) is well suited for high-power and medium-voltage applications. However, its performance is adversely affected by asymmetry that might be introduced by the failure of a limited number of submodules (SMs) or even by severe deviations in the values of SM capacitors and arm inductors, particularly when the number of SMs per arm is relatively low. Although a safe-failed operation is easily achieved through the incorporation of redundant SMs, the SMs’ faults make MMC arms present unequal impedances, which leads to undesirable internal dynamics because of unequal power distribution between the arms. The severity of these undesirable dynamics varies with the implementation of auxiliary controllers that regulate the MMC internal dynamics. This paper studied the impact of SMs failure on the MMC internal dynamics performance, considering two implementations of internal dynamics control, including a direct control method for suppressing the fundamental component that may arise in the dc-link current. Performances of the presented and widely-appreciated conventional methods for regulating MMC internal dynamics were assessed under normal and SM fault conditions, using detailed time-domain simulations and considering both active and reactive power applications. The effectiveness of control methods is also verified by the experiment. Related trade-offs of the control methods are presented, whereas it is found that the adverse impact of SMs failure on MMC ac and dc side performances could be minimized with appropriate control countermeasures. Full article

The beef cattle industry is facing multiple problems, from the unequal distribution of added value to the poor matching of its product with fast-changing demand. Therefore, the aim of this study was to examine the interactions between the main variables, evaluating the nutritional and organoleptic properties of meat and cattle performances, including carcass properties, to assess a new method of managing the trade-off between these four performance goals. For this purpose, each variable evaluating the parameters of interest has been statistically modeled and based on data collected on 30 Blonde d’Aquitaine heifers. The variables were obtained after a statistical pre-treatment (clustering of variables) to reduce the redundancy of the 62 initial variables. The sensitivity analysis evaluated the importance of each independent variable in the models, and a graphical approach completed the analysis of the relationships between the variables. Then, the models were used to generate virtual animals and study the relationships between the nutritional and organoleptic quality. No apparent link between the nutritional and organoleptic properties of meat (r = −0.17) was established, indicating that no important trade-off between these two qualities was needed. The 30 best and worst profiles were selected based on nutritional and organoleptic expectations set by a group of experts from the INRA (French National Institute for Agricultural Research) and Institut de l’Elevage (French Livestock Institute). The comparison between the two extreme profiles showed that heavier and fatter carcasses led to low nutritional and organoleptic quality. Full article

Sub-module (SM) faults in modular multilevel converters (MMCs) without redundancies result in unbalanced converter output voltages and improper control of modulation due to an unequal number of SMs inserted between the different phase-legs. The derived mathematics model of the MMC demonstrates the impact of the SM fault in the circulating currents and capacitor voltages. For achieving the SM fault-tolerance, detailed analysis of the MMC’s electrical quantities under SM fault-tolerant algorithms is provided together with two modulation reconfiguration techniques for maintaining voltage balance. Fault-tolerant abilities of the two modulation algorithms are also discussed and defined. Simulation results from a 21-level converter and experimental work in a three-phase five-level converter demonstrate the feasibility and performance of the proposed fault-tolerant control strategies. Full article

A PACLOBUTRAZOL-RESISTANCE (PRE) gene family, consisting of six genes in Arabidopsis thaliana, encodes a group of helix-loop-helix proteins that act in the growth-promoting transcriptional network. To delineate the specific role of each of the PRE genes in organ growth, we took a reverse genetic approach by constructing high order pre loss-of-function mutants of Arabidopsis thaliana. In addition to dwarf vegetative growth, some double or high order pre mutants exhibited defective floral development, resulting in reduced fertility. While pre2pre5 is normally fertile, both pre2pre6 and pre5pre6 showed reduced fertility. Further, the reduced fertility was exacerbated in the pre2pre5pre6 mutant, indicative of the redundant and critical roles of these PREs. Self-pollination assay and scanning electron microscopy analysis showed that the sterility of pre2pre5pre6 was mainly ascribed to the reduced cell elongation of anther filament, limiting access of pollens to stigma. We found that the expression of a subset of flower-development related genes including ARGOS, IAA19, ACS8, and MYB24 was downregulated in the pre2pre5pre6 flowers. Given these results, we propose that PREs, with unequal functional redundancy, take part in the coordinated growth of floral organs, contributing to successful autogamous reproduction in Arabidopsis thaliana. Full article

Solid State Transformers (SST) are attracting considerable attention due to their great application potential in future smart grids. It is an essential technology capable of promoting the modernization of the electric power distribution system and it is considered a key element for interfacing future microgrid systems to medium voltage utility grids, allowing plug-and-play integration with multiple renewable energy sources, storage devices and DC power systems. Its main advantages in relation to conventional transformers are substantial reduction of volume and weight, fault isolation capability, voltage regulation, harmonic filtering, reactive power compensation and power factor correction. A three-stage modular cascaded topology has been considered as an adequate candidate for the SST implementation, consisting of multiple power modules with input series and output parallel connection. The modular structure presents many advantages, e.g., redundancy, flexibility, lower current harmonic content and voltage stress on the power switches, however component tolerances and mismatches between modules can lead to DC link voltage imbalance and unequal power sharing that can damage the solid state transformer. This paper proposes a decentralized strategy based on adaptive droop control capable of promoting voltage and power balance among modules of a modular cascaded SST, without relying on a communication network. The behavior of the proposed strategy is assessed through a MATLAB/Simulink simulation model of an 100 kVA SST and shows that power and voltage balance are attained through inner power distribution of the SST modules, being transparent to elements connected to the transformer input and output ports. Besides that, real-time simulation results are presented to validate the proposed control strategies. The performance of embedded algorithms is evaluated by the implementation of the SST in a real-time simulation hardware, using a Digital Signal Processor (DSP) and high level programming. Full article