Search

ObjectiveIdentify infants with abnormal suckling behavior from simple non-nutritive suckling devices.BackgroundWhile it is well known breastfeeding is beneficial to the health of both mothers and infants, breastfeeding ceases in 75 percent of mother-child dyads by 6 months. The current standard of care lacks objective measurements to screen infant suckling abnormalities within the first few days of life, a critical time to establish milk supply and successful breastfeeding practices.Materials and methodsA non-nutritive suckling vacuum measurement system, previously developed by the authors, is used to gather data from 91 healthy full-term infants under thirty days old. Non-nutritive suckling was recorded for a duration of sixty seconds. We establish normative data for the mean suck vacuum, maximum suck vacuum, suckling frequency, burst duration, sucks per burst, and vacuum signal shape. We then apply computational methods (Mahalanobis distance, KNN) to detect anomalies in the data to identify infants with abnormal suckling. We finally provide case studies of healthy newborn infants and infants diagnosed with ankyloglossia.ResultsIn a series of case evaluations, we demonstrate the ability to detect abnormal suckling behavior using statistical analysis and machine learning. We evaluate cases of ankyloglossia to determine how oral dysfunction and surgical interventions affect non-nutritive suckling measurements.ConclusionsStatistical analysis (Mahalanobis Distance) and machine learning [K nearest neighbor (KNN)] can be viable approaches to rapidly interpret infant suckling measurements. Particularly in practices using the digital suck assessment with a gloved finger, it can provide a more objective, early stage screening method to identify abnormal infant suckling vacuum. This approach for identifying those at risk for breastfeeding complications is crucial to complement complex emerging clinical evaluation technology.Clinical impactBy analyzing non-nutritive suckling using computational methods, we demonstrate the ability to detect abnormal and normal behavior in infant suckling that can inform breastfeeding intervention pathways in clinic.Clinical and Translational Impact Statement: The work serves to shed light on the lack of consensus for determining appropriate intervention pathways for infant oral dysfunction. We demonstrate using statistical analysis and machine learning that normal and abnormal infant suckling can be identified and used in determining if surgical intervention is a necessary solution to resolve infant feeding difficulties.

ABSTRACT In this article, we propose a novel classification approach for functional data based on a shrinkage estimate of functional Mahalanobis distance. We first introduce a new shrinkage functional Mahalanobis distance (SFMD), by using this new distance, we transform the functional observations into a set of vector‐valued pseudo‐samples. Furthermore, we adopt some good classification algorithms designed for multivariate data to this pseudo‐samples instead of the original functional data. The new approach has advantage of highly flexible and scalable, that is, it can easily combine with any classification algorithm, such as support vector machine, tree‐based methods, and neural networks. We demonstrate the performance of the proposed functional classifier through both extensive simulation studies and two real data applications. [ABSTRACT FROM AUTHOR]

We propose the Minimum Regularized Covariance Trace (MRCT) estimator, a novel method for robust covariance estimation and functional outlier detection designed primarily for dense functional data. The MRCT estimator employs a subset-based approach that prioritizes subsets exhibiting greater centrality based on the generalization of the Mahalanobis distance, resulting in a fast-MCD type algorithm. Notably, the MRCT estimator handles high-dimensional datasets without the need for preprocessing or dimension reduction techniques, due to the internal smoothening whose amount is determined by the regularization parameter α > 0 . The selection of α is automated. An extensive simulation study demonstrates the efficacy of the MRCT estimator in terms of robust covariance estimation and automated outlier detection, emphasizing the balance between noise exclusion and signal preservation achieved through appropriate selection of α. The method converges fast in practice and performs favorably when compared to other functional outlier detection methods. [ABSTRACT FROM AUTHOR]

Background: JS335 is a leading variety of soybean in central India with high stability, but YMV susceptible. These leads to the incorporation of the YMV resistance in the elite genotypes of soybean variety JS335. Methods: 45 breeding lines obtained from a cross between two parents SL525 (YMV resistant) and JS335 (YMV susceptible) along with two parents and a check SL958 were analysed for diversity using Mahalanobis D2 and 19 polymorphic SSR markers. These lines were evaluated for yield and component traits and YMV, during 2020 at two locations viz. Ludhiana and Gurdaspur, India. Result: Diversity analysis based on Mahalanobis D2 statistics divided genotypes into five clusters. The maximum (288464.1) and minimum (15103.7) inter-cluster distance were observed between clusters 4 and 5 and clusters 2 and 5, respectively. SSR marker analysis grouped a total of 48 genotypes into three major clusters. The mean for agronomic traits of genotypes was categorised and SLJS 41-2 was found YMV resistant and exhibited a high yield (32.1 g/plant). The contribution of JS 335 towards SLJS 41-2 was found to be 62.5%. This line could further be tested at multilocation to evaluate adaptability and subjected to different yield trials for varietal release or used as a potential YMV donor. [ABSTRACT FROM AUTHOR]

Normative studies are needed to obtain norms for comparing individuals with the reference population on relevant clinical or educational measures. Norms can be obtained in an efficient way by regressing the test score on relevant predictors, such as age and sex. When several measures are normed with the same sample, a multivariate regression-based approach must be adopted for at least two reasons: (1) to take into account the correlations between the measures of the same subject, in order to test certain scientific hypotheses and to reduce misclassification of subjects in clinical practice, and (2) to reduce the number of significance tests involved in selecting predictors for the purpose of norming, thus preventing the inflation of the type I error rate. A new multivariate regression-based approach is proposed that combines all measures for an individual through the Mahalanobis distance, thus providing an indicator of the individual's overall performance. Furthermore, optimal designs for the normative study are derived under five multivariate polynomial regression models, assuming multivariate normality and homoscedasticity of the residuals, and efficient robust designs are presented in case of uncertainty about the correct model for the analysis of the normative sample. Sample size calculation formulas are provided for the new Mahalanobis distance-based approach. The results are illustrated with data from the Maastricht Aging Study (MAAS). [ABSTRACT FROM AUTHOR]

A temporally stable functional brain network pattern among coordinated brain regions is fundamental to stimulus selectivity and functional specificity during the critical period of brain development. Brain networks that are recruited in time to process internal states of others' bodies (like hunger and pain) versus internal mental states (like beliefs, desires, and emotions) of others' minds allow us to ask whether a quantitative characterization of the stability of these networks carries meaning during early development and constrain cognition in a specific way. Previous research provides critical insight into the early development of the theory-of-mind (ToM) network and its segregation from the Pain network throughout normal development using functional connectivity. However, a quantitative characterization of the temporal stability of ToM networks from early childhood to adulthood remains unexplored. In this work, reusing a large sample of children (n = 122, 3–12 years) and adults (n = 33) dataset that is available on the OpenfMRI database under the accession number ds000228, we addressed this question based on their fMRI data during a short and engaging naturalistic movie-watching task. The movie highlights the characters' bodily sensations (often pain) and mental states (beliefs, desires, emotions), and is a feasible experiment for young children. Our results tracked the change in temporal stability using an unsupervised characterization of ToM and Pain networks DFC patterns using Angular and Mahalanobis distances between dominant dynamic functional connectivity subspaces. Our findings reveal that both ToM and Pain networks exhibit lower temporal stability as early as 3-years and gradually stabilize by 5-years, which continues till adolescence and late adulthood (often sharing similarity with adult DFC stability patterns). Furthermore, we find that the temporal stability of ToM brain networks is associated with the performance of participants in the false belief task to access mentalization at an early age. Interestingly, higher temporal stability is associated with the pass group, and similarly, moderate and low temporal stability are associated with the inconsistent group and the fail group. Our findings open an avenue for applying the temporal stability of large-scale functional brain networks during cortical development to act as a biomarker for multiple developmental disorders concerning impairment and discontinuity in the neural basis of social cognition. [ABSTRACT FROM AUTHOR]

Canopy cover fraction is one of the most important criteria for investigating the crop growth and yield and is one of the input data of most plant models. Canopy cover fraction is an easier measurement than the other methods which id depended on field observations or image processing beyond the visible spectrum. In this study, drone images of the sugar beet field in the cropping season of 2015-2016 and on the four dates from late May to late June at the Lindau center of plant sciences research, Switzerland were used. The research was conducted by six plant discrimination indices and three distinct thresholding algorithms to segment sugar beet vegetation. Then, among the 18 investigated methods, the best 6 methods were evaluated by comparing their values with the ground truth values in 30 different regions of the farm and on four dates from the beginning of the four-leaf stage to the end of the six-leaf stage. Results showed that the ExG, GLI, and RGBVI indices, in combination with the Otsu and RidlerCalvard thresholding algorithms, demonstrate optimal performance in vegetation segmentation. The evaluation statistics of NRMSE and R² for the ExG&Otsu method as the most accurate method were obtained as 5.13 % and 0.96, respectively. Conversely, the RGBVI&RC method exhibits the least accuracy in the initial evaluation, with NRMSE and R² values of 8.18 % and 0.87, respectively. Comparative analysis of statistical indicators showed that the ExG&Otsu and ExG&RC methods with similar performance, displaying the highest correlation with ground truths. Additionally, the GLI&Otsu method consistently demonstrates the lowest error compared to ground truths. [ABSTRACT FROM AUTHOR]

Detection of abnormal situations in mobile systems not only provides predictions about risky situations but also has the potential to increase energy efficiency. In this study, two real-world drives of a battery electric vehicle and unsupervised hybrid anomaly detection approaches were developed. The anomaly detection performances of hybrid models created with the combination of Long Short-Term Memory (LSTM)-Autoencoder, the Local Outlier Factor (LOF), and the Mahalanobis distance were evaluated with the silhouette score, Davies–Bouldin index, and Calinski–Harabasz index, and the potential energy recovery rates were also determined. Two driving datasets were evaluated in terms of chaotic aspects using the Lyapunov exponent, Kolmogorov–Sinai entropy, and fractal dimension metrics. The developed hybrid models are superior to the sub-methods in anomaly detection. Hybrid Model-2 had 2.92% more successful results in anomaly detection compared to Hybrid Model-1. In terms of potential energy saving, Hybrid Model-1 provided 31.26% superiority, while Hybrid Model-2 provided 31.48%. It was also observed that there is a close relationship between anomaly and chaoticity. In the literature where cyber security and visual sources dominate in anomaly detection, a strategy was developed that provides energy efficiency-based anomaly detection and chaotic analysis from data obtained without additional sensor data. [ABSTRACT FROM AUTHOR]

Diabetes mellitus (DM) is a global health challenge that requires advanced strategies for its early detection and prevention. This study evaluates the South Korean population using the Korea National Health and Nutrition Examination Survey (KNHANES) dataset from 2015 to 2021, provided by the Korea Disease Control and Prevention Agency (KDCA), focusing on improving diabetes prediction models. Outlier removal was implemented using Mahalanobis distance (MAH), and feature selection was based on multicollinearity (MC) and reliability analysis (RA). The proposed Extreme Gradient Boosting (XGBoost) model demonstrated exceptional performance, achieving an accuracy of 98.04% (95% CI: 97.89~98.59), an F1-score of 98.24%, and an Area Under the Curve (AUC) of 98.71%, outperforming other state-of-the-art models. The study highlights the significance of rigorous outlier detection and feature selection in enhancing the predictive power of diabetes risk models. Notably, a significant increase in diabetes cases was observed during the COVID-19 pandemic, particularly linked to male sex, older age, rural location, hypertension, and obesity, underscoring the need for enhanced public health strategies for early intervention and targeted prevention. [ABSTRACT FROM AUTHOR]

Abstract A temporally stable functional brain network pattern among coordinated brain regions is fundamental to stimulus selectivity and functional specificity during the critical period of brain development. Brain networks that are recruited in time to process internal states of others’ bodies (like hunger and pain) versus internal mental states (like beliefs, desires, and emotions) of others’ minds allow us to ask whether a quantitative characterization of the stability of these networks carries meaning during early development and constrain cognition in a specific way. Previous research provides critical insight into the early development of the theory-of-mind (ToM) network and its segregation from the Pain network throughout normal development using functional connectivity. However, a quantitative characterization of the temporal stability of ToM networks from early childhood to adulthood remains unexplored. In this work, reusing a large sample of children (n = 122, 3–12 years) and adults (n = 33) dataset that is available on the OpenfMRI database under the accession number ds000228, we addressed this question based on their fMRI data during a short and engaging naturalistic movie-watching task. The movie highlights the characters’ bodily sensations (often pain) and mental states (beliefs, desires, emotions), and is a feasible experiment for young children. Our results tracked the change in temporal stability using an unsupervised characterization of ToM and Pain networks DFC patterns using Angular and Mahalanobis distances between dominant dynamic functional connectivity subspaces. Our findings reveal that both ToM and Pain networks exhibit lower temporal stability as early as 3-years and gradually stabilize by 5-years, which continues till adolescence and late adulthood (often sharing similarity with adult DFC stability patterns). Furthermore, we find that the temporal stability of ToM brain networks is associated with the performance of participants in the false belief task to access mentalization at an early age. Interestingly, higher temporal stability is associated with the pass group, and similarly, moderate and low temporal stability are associated with the inconsistent group and the fail group. Our findings open an avenue for applying the temporal stability of large-scale functional brain networks during cortical development to act as a biomarker for multiple developmental disorders concerning impairment and discontinuity in the neural basis of social cognition.

In the past decade, various exact balancing‐based weighting methods were introduced to the causal inference literature. It eliminates covariate imbalance by imposing balancing constraints in a certain optimization problem, which can nevertheless be infeasible when there is bad overlap between the covariate distributions in the treated and control groups or when the covariates are high dimensional. Recently, approximate balancing was proposed as an alternative balancing framework. It resolves the feasibility issue by using inequality moment constraints instead. However, it can be difficult to select the threshold parameters. Moreover, moment constraints may not fully capture the discrepancy of covariate distributions. In this paper, we propose Mahalanobis balancing to approximately balance covariate distributions from a multivariate perspective. We use a quadratic constraint to control overall imbalance with a single threshold parameter, which can be tuned by a simple selection procedure. We show that the dual problem of Mahalanobis balancing is an ℓ2 norm‐based regularized regression problem, and establish interesting connection to propensity score models. We derive asymptotic properties, discuss the high‐dimensional scenario, and make extensive numerical comparisons with existing balancing methods. [ABSTRACT FROM AUTHOR]

Simulating sediment transfer processes in catchments has contributed significantly to solving environmental problems due to its importance in the silting of rivers and reservoirs and for controlling the pollution of water bodies. Among the methods used to improve data collection and modelling, the "sediment fingerprinting approach" uses tracers reflecting the composition of eroded soils and sediments in multivariate statistical analyses and mathematical models for optimizing equation systems. Based on generalized least squares (GLS) method and Mahalanobis distance, this study sought to present a computational framework to solve over-determined systems applied to sediment tracing, systematize the uncertainty analysis and sample number optimization. Hence, this approach takes into account the influence of collinearity among the chemical variables that compose the tracer set to be evaluated by the presence of the variance-covariance matrix. A dataset from the Arvorezinha experimental catchment in southern Brazil was used to validate the modeling, and our findings confirmed the assumption of increased uncertainty as the number of target samples decreases in the sources or eroded sediment samples. Sharing the code files with the PySASF (Python package for Source Apportionment with Sediment Fingerprinting) contributes to improving the technique as it allows other researchers to systematically improve the definition of the number of samples required based on the uncertainty analysis. [ABSTRACT FROM AUTHOR]

Abstract To compare the difference of non-volatile taste-active flavor components of different chicken breeds, four Chinese native yellow feather broilers including Langshan chicken, Chongren chicken, Luyuan chicken and Wenchang chicken were used in the experiment. The contents of free amino acids, 5'-nucleotides and minerals were determined by standard method, and then five principal components were extracted from the multi-index system based on the principal component analysis (PCA). Combined with the Mahalanobis distance analysis method and sensory evaluation results, the advantages and characteristics of each chicken breed were evaluated. The results showed that different kinds of chicken had their own advantages in different evaluation dimensions. The Equivalent umami concentration (ECU) of Wenchang chicken, which had the highest content of amino acids, was 12 g monosodium glutamate (MSG)/100 g, indicating the umami taste of it was very intense. The indexes of Langshan chicken were relatively uniform, with slightly higher mineral content, its overall Mahalanobis distance score was more similar to the "best standard". According to the Mahalanobis distance score, although the difference in amino acid content among each species was the largest, the overall score was more affected by the content of minerals and nucleotides, and there was interaction between each nutrient, which had an impact on the overall Mahalanobis distance score. The sensory evaluation results indicated that Wenchang chicken was the most superior among the taste of the four varieties investigated. Finally, taste compounds affecting the difference of chicken varieties were analyzed by partial least squares regression (PLS), resulting in order of mineral (Ca2+, Mg2+, PO4 3−) > nucleotide (AMP, IMP) > amino acid. This could provide a theoretical basis for quantitative oriented flavor processing and consumer choice of chicken. Graphical Abstract

The present study focuses on addressing the issue of too frequent triggers of deep convection in climate models, which are primarily based on physics-based classical trigger functions such as convective available potential energy (CAPE) or cloud work function (CWF). To overcome this problem, the study proposes using machine learning (ML) based deep convective triggers as an alternative. The deep convective trigger is formulated as a binary classification problem, where the goal is to predict whether deep convection will occur or not. Two elementary classification algorithms, namely support vector machines and neural networks, are adopted in this study. Additionally, a novel method is proposed to rank the importance of input variables for the classification problem, which may aid in understanding the underlying mechanisms and factors influencing deep convection. The accuracy of the ML-based methods is compared with the widely used convective available potential energy (CAPE)-based and dynamic generation of CAPE (dCAPE) trigger function found in many convective parameterization schemes. Results demonstrate that the elementary machine learning-based algorithms can outperform the classical CAPE-based triggers, indicating the potential effectiveness of ML-based approaches in dealing with this issue. Furthermore, a method based on the Mahalanobis distance is presented for binary classification, which is easy to interpret and implement. The Mahalanobis distance-based approach shows accuracy comparable to other ML-based methods, suggesting its viability as an alternative method for deep convective triggers. By correcting for deep convective triggers using ML-based approaches, the study proposes a possible solution to improve the probability density of rain in the climate model. This improvement may help overcome the issue of excessive drizzle often observed in many climate models. [ABSTRACT FROM AUTHOR]

Classical estimators fail to be efficient in practical scenarios when data is riddled with extreme values known as outliers. Robust estimation strategies are insensitive to outliers and may be used in such cases. The current work is focused on developing a novel robust estimation strategy using Huber M-estimation. A new chain-product type estimator for population mean has been suggested utilizing data on two auxiliary variables. A numerical comparison has been carried out between the proposed robust estimator and the corresponding classical estimator using real and simulated data containing outliers. Recommendations have been made for its practical use based on the encouraging results. [ABSTRACT FROM AUTHOR]

Bearings are foundational supporting components in diverse mechanical systems, essential for the reliable operation of these systems through real‐time monitoring and precise health state assessment. However, vibration signals from bearings in practical equipment often contain excessive noise and redundant information, complicating health state assessment. To address this challenge, this paper proposes a neural network‐based method named parallel encoder‐decoder (PED). This method features a parallel architecture that combines the long short‐term memory network and the temporal convolutional network for the encoder, along with a self‐attention module for the decoder. PED is adept at learning the temporal representations hidden in original signals and filtering vibration signals to remove noise and redundant information. Additionally, a multi‐objective loss function is developed to enhance the prediction results. A normalized Mahalanobis distance‐based metric is then employed to compare residual signals during bearing operation with those under normal conditions. The case study evaluates the PED observer's proficiency in accurately predicting vibration signals and assessing the performance of health indicator curves, demonstrating the proposed PED observer's superiority over conventional networks. [ABSTRACT FROM AUTHOR]

The visual analysis method of educational data statistics based on big data mining is studied to improve students' academic performance. Introducing the Mahalanobis distance and covariance matrix into the Fuzzy C-Means (FCM) clustering algorithm improves the FCM clustering algorithm. Through the improvement of the FCM clustering algorithm, the education data is mined from the massive original education data. The mining results are analyzed statistically, and the statistical analysis chart of education data is drawn. By improving the force-guided layout algorithm, the mined educational data points are written into the elastic graph layout to realize the visual layout. The ECharts data visualization analysis component presents the visual layout results of education data points and the statistical analysis charts of education data. Experiments show that this method can effectively mine educational data and draw statistical analysis charts of educational data. Among them, learning analysis data occupy the highest proportion (15%), and privacy protection data occupy the lowest proportion (only 1%). The method can effectively lay out the educational data points and has a better visual effect. This method can effectively present the results of statistical analysis of educational data in visual form, in which learning analysis data is the most important. [ABSTRACT FROM AUTHOR]

Although an autonomous underwater vehicle (AUV) is noted for its good autonomy, concealment and anti-interference ability, errors in its inertial navigation system (INS) inevitably increase over time, leading to positional failure during long-term voyages. Terrain-assisted navigation can help the INS to correct its position. The traditional iterative closest contour point (ICCP) achieves high matching accuracy when the initial position error of the INS is small, but is prone to mismatching when the initial error is large. This study combines ICCP with particle swarm optimization (PSO) to overcome this problem. First, the global optimization ability of PSO is improved by changing the acceleration factor and introducing an artificial bee colony (ABC) onlooker bee greedy search (ABC- ω APSO). Second, the Euclidean distance of ICCP is replaced by the Mahalanobis distance to abate the influence of system error on the matching accuracy. Finally, the initial position error is reduced by rough matching using the ABC- ω APSO, which has global optimization capability. Next, fine matching is performed by ICCP. This two-step process resolves the sensitivity problem of ICCP to the initial position error. The experimental results revealed a good matching effect after the double-matching procedure. When the initial INS errors were 0.55′ to the east and 0.55′ to the north, the matching error was reduced to 89.3 m, suggesting that the approach can realize autonomous passive navigation of AUVs. [ABSTRACT FROM AUTHOR]

Due to the rapid development of internet technology, knowledge acquisition has become more convenient and efficient in network operations. University libraries serve as important resources for readers to acquire knowledge, and online resources and services in libraries have become the main direction for readers to acquire knowledge at present. Research the use of binary K-means clustering algorithm and library reader portrait technology to optimize the design of the reader portrait module and construct a multidimensional and multi perspective reader feature system. Reuse Spark programming language and support vector machine to perform computational processing on reader profile data to ensure accurate segmentation of the dataset. Finally, three datasets were used to test the accuracy and efficiency of the algorithm. The experimental comparison shows that the mining and precision segmentation of parallel SVM on the dataset are 93.20%, 85.16%, and 79.35% on the sample set, respectively, in order to optimize the mining performance of the data. The MD multi view binary K-means algorithm has a total Mahalanobis distance of 3.543, 5.268, and 22.385 on the sample dataset, respectively, to demonstrate its superiority in clustering performance. Therefore, the multi view binary K-means algorithm based on Mahalanobis distance has high advantages in reader portrait technology design, and provides technical support and theoretical reference for library reader portrait technology. [ABSTRACT FROM AUTHOR]

Based on the amplitude attribute analysis of ground penetrating radar (GPR) data, this paper applies GPR to the identification of internal damages and abnormal objects in stone walls of Tibetan ruins. The corresponding relationship between the characteristics of internal damages and abnormal objects and the radar data is explored through the Tibetan stone walls (TSWs) simulation test. The identification of location and size of the damages and abnormal objects in TSWs is realized based on the Mahalanobis distance abnormal data discrimination method. Using the normal distribution and the noncentral chi-square distribution, the identification law of types of the damages and abnormal objects is constructed, which takes root mean square (RMS) amplitude and interface reflection coefficient as the characteristic values. The field detection results of TSWs at three Tibetan sites are taken as an extension and supplement to the simulation results, and a set of identification atlas for the location, size and type of the internal damages and abnormal objects in TSWs is established. The application results of the identification atlas were verified by the field detection and the results show that the atlas has a high accuracy, which can significantly improve the efficiency of the identification, and can provide a basis for the performance research, protection and maintenance of TSWs. [ABSTRACT FROM AUTHOR]

In comparative studies, covariate balance and sequential allocation schemes have attracted growing academic interest. Although many theoretically justified adaptive randomization methods achieve the covariate balance, they often allocate patients in pairs or groups. To better meet the practical requirements where the clinicians cannot wait for other participants to assign the current patient for some economic or ethical reasons, we propose a method that randomizes patients individually and sequentially. The proposed method conceptually separates the covariate imbalance, measured by the newly proposed modified Mahalanobis distance, and the marginal imbalance, that is the sample size difference between the 2 groups, and it minimizes them with an explicit priority order. Compared with the existing sequential randomization methods, the proposed method achieves the best possible covariate balance while maintaining the marginal balance directly, offering us more control of the randomization process. We demonstrate the superior performance of the proposed method through a wide range of simulation studies and real data analysis, and also establish theoretical guarantees for the proposed method in terms of both the convergence of the imbalance measure and the subsequent treatment effect estimation. [ABSTRACT FROM AUTHOR]

When building a classification model, the scenario where the samples of one class are significantly more than those of the other class is called data imbalance. Data imbalance causes the trained classification model to be in favor of the majority class (usually defined as the negative class), which may do harm to the accuracy of the minority class (usually defined as the positive class), and then lead to poor overall performance of the model. A method called MSHR-FCSSVM for solving imbalanced data classification is proposed in this article, which is based on a new hybrid resampling approach (MSHR) and a new fine cost-sensitive support vector machine (CS-SVM) classifier (FCSSVM). The MSHR measures the separability of each negative sample through its Silhouette value calculated by Mahalanobis distance between samples, based on which, the so-called pseudo-negative samples are screened out to generate new positive samples (over-sampling step) through linear interpolation and are deleted finally (under-sampling step). This approach replaces pseudo-negative samples with generated new positive samples one by one to clear up the inter-class overlap on the borderline, without changing the overall scale of the dataset. The FCSSVM is an improved version of the traditional CS-SVM. It considers influences of both the imbalance of sample number and the class distribution on classification simultaneously, and through finely tuning the class cost weights by using the efficient optimization algorithm based on the physical phenomenon of rime-ice (RIME) algorithm with cross-validation accuracy as the fitness function to accurately adjust the classification borderline. To verify the effectiveness of the proposed method, a series of experiments are carried out based on 20 imbalanced datasets including both mildly and extremely imbalanced datasets. The experimental results show that the MSHR-FCSSVM method performs better than the methods for comparison in most cases, and both the MSHR and the FCSSVM played significant roles. [ABSTRACT FROM AUTHOR]

To compare the difference of non-volatile taste-active flavor components of different chicken breeds, four Chinese native yellow feather broilers including Langshan chicken, Chongren chicken, Luyuan chicken and Wenchang chicken were used in the experiment. The contents of free amino acids, 5'-nucleotides and minerals were determined by standard method, and then five principal components were extracted from the multi-index system based on the principal component analysis (PCA). Combined with the Mahalanobis distance analysis method and sensory evaluation results, the advantages and characteristics of each chicken breed were evaluated. The results showed that different kinds of chicken had their own advantages in different evaluation dimensions. The Equivalent umami concentration (ECU) of Wenchang chicken, which had the highest content of amino acids, was 12 g monosodium glutamate (MSG)/100 g, indicating the umami taste of it was very intense. The indexes of Langshan chicken were relatively uniform, with slightly higher mineral content, its overall Mahalanobis distance score was more similar to the "best standard". According to the Mahalanobis distance score, although the difference in amino acid content among each species was the largest, the overall score was more affected by the content of minerals and nucleotides, and there was interaction between each nutrient, which had an impact on the overall Mahalanobis distance score. The sensory evaluation results indicated that Wenchang chicken was the most superior among the taste of the four varieties investigated. Finally, taste compounds affecting the difference of chicken varieties were analyzed by partial least squares regression (PLS), resulting in order of mineral (Ca2+, Mg2+, PO43−) > nucleotide (AMP, IMP) > amino acid. This could provide a theoretical basis for quantitative oriented flavor processing and consumer choice of chicken. [ABSTRACT FROM AUTHOR]

The stock price is affected by many factors, such as policy, macro-economy and the company's operating conditions, among which there is a certain degree of correlation. So the stock data of high noise and non- stationary feature makes stock prediction difficult. Based on the separability between classes of Mahalanobis distance, this paper proposes structured maximum margin twin suport vector machine (SMM-TWSVM). The method finds two nonparallel hyperplane for positive class samples and negative class samples respectively, so that the Euclidean distance of each class of samples from their own hyperplane is as small as possible, and the Mahalanobis distance of divorced class hyperplane is as large as possible. The experimental results of 8 benchmark datasets show that this method has a stable accuracy in the classification of noisy data, thus improving the prediction performance and anti-noise ability of the model. Meanwhile, it is applied to the prediction of the fluctuation tend of stock price, through the empirical analysis of 14 stocks such as Ping An of China and Shanghai Composite Index, Shanghai A Index, Shanghai 380 Index, the results show that compared with other comparison models, SMM-TWSVM shows better prediction results and has certain practical value. [ABSTRACT FROM AUTHOR]

As enterprises look forward to new market share and supply chain opportunities, innovative strategies and sustainable manufacturing play important roles for micro-, small, and mid-sized enterprises worldwide. Sustainable manufacturing is one of the practices aimed towards deploying green energy initiatives to ease climate change, presenting three main pillars—economic, social, and environmental. The issue of how to reach sustainability goals within the sustainable manufacturing of pillars is a less-researched area. This paper's main purpose and novelty is two-fold. First, it aims to provide a hierarchy of the green energy indicators and their measurements through a multi-criteria decision-making point of view to implement them as an alliance strategy towards sustainable manufacturing. Moreover, we aim to provide researchers and practitioners with a forecasting method to re-prioritize green energy indicators through a linearity factor model. The CODAS–Hamming–Mahalanobis method is used to obtain preference scores and rankings from a 50-item list. The resulting top 10 list shows that enterprises defined nine items within the economic pillar as more important and one item on the environmental pillar; items from the social pillar were less important. The implication for MSMEs within the manufacturing sector represents an opportunity to work with decision makers to deploy specific initiatives towards sustainable manufacturing, focused on profit and welfare while taking care of natural resources. In addition, we propose a continuous predictive analysis method, the linearity factor model, as a tool for new enterprises to seek a green energy hierarchy according to their individual needs. The resulting hierarchy using the predictive analysis model presented changes in the items' order, but it remained within the same two sustainable manufacturing pillars: economic and environmental. [ABSTRACT FROM AUTHOR]

Image classification depends substantially on the remote sensing method to generate maps of land use and land cover. This study used machine learning algorithms for classifying land cover, evaluating algorithms, and choosing the best way based on accuracy assessment matrices for land cover classifications. Satellite images from the Landsat by the United States Geological Survey (USGS) were used to classify the Babylon Governorate Land Use Land Cover (LULC). This study employed multispectral satellite images utilizing a spatial resolution of 30 meters and organized the data using three different algorithms to see the most accuracy. The process of categorization was carried out with the use of three distinct algorithms, which are as follows: Support Vector Machine (SVM), Mahalanobis Distance (MD), and Maximum Likelihood Classification (MLC). The classification algorithms utilized ArcGIS 10.8 and ENVI 5.3 software to detect four LULC classes: (Built-up Land, Water, Barren Land, and Agricultural Land). When applied to Landsat images, the results showed that the SVM approach gives greater overall accuracy and a larger kappa coefficient than the MD and MLC methods. SVM, MD, and MLC algorithms each have respective overall accuracy values of 86.88%, 85.00%, and 79.38%, respectively.

Monte Carlo simulations and theoretical analyses have repeatedly demonstrated the impact of outliers on statistical analysis. Most simulation studies generate outliers using one of two general approaches: by multiplying an arbitrary point by a constant or through a finite mixture. The latter can be extended to multivariate settings by defining the Mahalanobis distance between the centroids of two clusters of points. Nevertheless, when researchers aim to simulate individual data points with population-level Mahalanobis distances, the number of available procedures is very limited. This article generalizes one of the few existing methods to simulate an arbitrary number of outliers in an arbitrary number of dimensions, for both multivariate normal and non-normal data. A small simulation demonstration showcases how this methodology enables new simulation designs that were either unpopular or not possible due to the lack of a data-generating algorithm. A discussion of potential implications highlights the importance of considering multivariate outliers in simulation settings.

With the rapid development of the economy, a large amount of financial data will be generated during the continuous growth of enterprises. However, due to the explosive growth of the financial data range index, the use of machine learning methods to mine and analyse financial data is extremely important. Among them, accurate financial risk evaluation is an effective measure to prevent and resolve corporate financial crises. In this article, we use fuzzy clustering method to establish a financial risk early warning and evaluation model. Specifically, we use fuzzy C‐mean (FCM), half‐suppressed FCM, and interval FCM clustering algorithms‐based state construction financial risk early warning and evaluation models, to give an evaluation from two aspects of corporate financial indicators and non‐financial indicators system. In order to verify the feasibility and effectiveness of the fuzzy clustering algorithms used in financial data mining, we conducted experiments in financial data mining and early warning in real estate companies and ST companies. The experimental results show that the fuzzy clustering algorithms represented by the FCM clustering algorithm has achieved good results in financial data mining, and can achieve good results in financial risk analysis and financial risk early warning. [ABSTRACT FROM AUTHOR]

Learning in neural networks with locally-tuned neuron models such as radial Basis Function (RBF) networks is often seen as instable, in particular when multi-layered architectures are used. Furthermore, universal approximation theorems for single-layered RBF networks are very well established; therefore, deeper architectures are theoretically not required. Consequently, RBFs are mostly used in a single-layered manner. However, deep neural networks have proven their effectiveness on many different tasks. In this paper, we show that deeper RBF architectures with multiple radial basis function layers can be designed together with efficient learning schemes. We introduce an initialization scheme for deep RBF networks based on k-means clustering and covariance estimation. We further show how to make use of convolutions to speed up the calculation of the Mahalanobis distance in a partially connected way, which is similar to the convolutional neural networks (CNNs). Finally, we evaluate our approach on image classification as well as speech emotion recognition tasks. Our results show that deep RBF networks perform very well, with comparable results to other deep neural network types, such as CNNs. [ABSTRACT FROM AUTHOR]

We examine the risk–return tradeoff of a portfolio of firms that have tangible environmental, social, and governance (ESG) attributes. We introduce a new type of penalized regression using the Mahalanobis distance-based method and show its usefulness using our sample of ESG firms. Our results show that ESG companies are exposed to financial state variables that capture the changes in investment opportunities. However, we find that there is no economically significant difference between the risk-adjusted returns of various ESG-rating-based portfolios and that the risk associated with a poor ESG rating portfolio is not significantly different than that of a good ESG rating portfolio. Although investors require return compensation for holding ESG stocks, the fact that the risk of a poor ESG rating portfolio is comparable to that of a good ESG rating portfolio suggests risk dimensions that go beyond ESG attributes. We further show that the new covariance-adjusted penalized regression improves the out-of-sample cross-sectional predictions of the ESG portfolio's expected returns. Overall, our approach is pragmatic and based on the ease of an empirical appeal. [ABSTRACT FROM AUTHOR]

In this paper, we present a new segmentation founded on the theory of quantum mechanics and the Havrda–Charvat entropy. This segmentation method is a continuous improvement of the method developed in 2014 by Mechkouri et al. (J Theor Appl Inf Technol 62(2):539–545, 2014). The segmentation was performed using an unsupervised segmentation method using the hierarchical analysis of the 2D histograms, which was constructed using the wave function and Havrda–Charvat entropy. We upgrade the quality of the segmentation method by reclassifying no segmented pixels into the classes defined by the Euclidean distance and Mahalanobis distance. The proposed approach was first tested on the synthetic image; it was applied to the segmentation of the environment for the QuickBird data of a selected urban area in the region of Rabat- Sale-Kénitra, prefecture of Skhirate-Temara, Morocco. The segmentation result obtained is more satisfactory than that obtained in the previous study (Mechkouri et al. in J Theor Appl Inf Technol 62(2):539–545, 2014). The development method is very hopeful and needs to be more investigating. [ABSTRACT FROM AUTHOR]

Abiotic stresses pose significant challenges to wheat farming, yet exploiting the genetic variability within germplasm collections offers an opportunity to effectively address these challenges. In this study, we investigated the genetic diversity of key agronomic traits among twenty durum wheat cultivars, with the intention to pinpoint those better suited to semi-arid conditions. Field trials were conducted at the ITGC-FDPS Institute, Setif, Algeria, during the winter season of 2021/22. A completely randomized design was used with three replicates. Statistical analyses revealed significant variation among the genotypes for most of the studied traits, with some cultivars exhibiting a superior performance in a stressful environment. Notably, traits like the number of grains per spike (NGS) and the grain yield (GY) displayed high genotypic coefficients of variation (CVg). Except for membrane thermostability (MT) and biological yield (BY), the majority of the assessed traits exhibited moderate-to-high heritability estimates. Genotypic and phenotypic correlation studies have confirmed the importance of many yield-related traits in the expression of GY. The harvest index (HI) underscored the highest genotypic direct effect on GY, followed closely by spike number (SN), serving as consistent pathways through which most of the measured traits indirectly influenced GY. The cluster analysis categorized the durum wheat cultivars into seven distinct clusters. The largest inter-cluster distance was observed between clusters G3 and G4 (D2 = 6145.86), reflecting maximum dissimilarity between the individuals of these clusters. Hybridizing divergent clusters may benefit future breeding programs aiming to develop potential durum wheat varieties through cross combinations. This study's findings contribute to sustainable agriculture efforts by facilitating the selection of genotypes with enhanced resilience and productivity, particularly for cultivation in challenging semi-arid regions. [ABSTRACT FROM AUTHOR]

The progress of science and using remote sensing technologies could help farmers to finds valuable information from field such as crop health, determining of the area and type of cultivation, calculating crop growth rate and various indices. Canopy cover percent is one of the vital parameters for modeling and prediction of yield production. Field observation methods of estimating CCP are expensive and time consuming. Using drones for arial imaging at field scale and image processing algorism to estimate CCP are fast and accurate. At this study, 441 arial photos was taken at height of 30 m above ground surface via DJI drone (Mavic 2 pro) for estimating maize CCP. The field was located at Alvand cityQazvin province. Two different methods of segmentation and classification were used for assessing CCP. Region of interest separability test and linear regression between calculated data were used for result evaluation. Results showed that, although the accuracy of both methods was high, on average the segmentation methods obtained CCP 10 percent lower that classification algorism. Also, the high R-square coefficient of 97% between the data showed that the accuracy of methods based on image processing, such as segmentation, is lower than classification methods, but in case of lack of access to the required software, that are based on artificial intelligence methods, it is easy to achieve a favorable result by implementing programming codes based on segmentation methods in high-level and open-source languages, including Python. [ABSTRACT FROM AUTHOR]

The Global Navigation Satellite System (GNSS) is widely used for its high accuracy, wide coverage, and strong real-time performance. However, limited by the navigation signal mechanism, satellite signals in urban canyons, bridges, tunnels, and other environments are seriously affected by non-line-of-sight and multipath effects, which greatly reduce positioning accuracy and positioning continuity. In order to meet the positioning requirements of human and vehicle navigation in complex environments, it was necessary to carry out this research on the integration of multiple signal sources. The Fifth Generation (5G) signal possesses key attributes, such as low latency, high bandwidth, and substantial capacity. Simultaneously, 5G Base Stations (BSs), serving as a fundamental mobile communication infrastructure, extend their coverage into areas traditionally challenging for GNSS technology, including indoor environments, tunnels, and urban canyons. Based on the actual needs, this paper proposes a system algorithm based on 5G and GNSS joint positioning, aiming at the situation that the User Equipment (UE) only establishes the connection with the 5G base station with the strongest signal. Considering the inherent nonlinear problem of user position and angle measurements in 5G observation, an angle cosine solution is proposed. Furthermore, enhancements to the Sage–Husa Adaptive Kalman Filter (SHAKF) algorithm are introduced to tackle issues related to observation weight distribution and adaptive updates of observation noise in multi-system joint positioning, particularly when there is a lack of prior information. This paper also introduces dual gross error detection adaptive correction of the forgetting factor based on innovation in the iterative Kalman filter to enhance accuracy and robustness. Finally, a series of simulation experiments and semi-physical experiments were conducted. The numerical results show that compared with the traditional method, the angle cosine method reduces the average number of iterations from 9.17 to 3 with higher accuracy, which greatly improves the efficiency of the algorithm. Meanwhile, compared with the standard Extended Kalman Filter (EKF), the proposed algorithm improved 48.66 % , 35.17 % , and 38.23 % at 1 σ / 2 σ / 3 σ , respectively. [ABSTRACT FROM AUTHOR]

Full comprehension of precipitation patterns is crucially needed, especially in Pekan, a district in Pahang, Malaysia. The area is renowned for its elevated levels of precipitation, making it imperative to precisely categorize and enhance the analysis of rainfall patterns to facilitate effective resource allocation, agricultural productivity, and catastrophe readiness. The variability of rainfall patterns is contingent upon geographical location, necessitating the collection of a comprehensive data set that includes several characteristics that influence precipitation to make reliable predictions. Data were collected from the Vantage Pro2 weather station, which is located on the UMP Pekan campus. This study used the RT method to classify rainfall and T-Method 1 to determine the degree of contribution of each parameter. Significant parameters were validated using a data set from the same type of weather station but in a different district. The results showed that the Mahalanobis-Taguchi Bee Algorithm (MTBA) is more effective than the Mahalanobis-Taguchi System (MTS) in finding the significant parameters, but the parameters were a subset of MTS Teshima. Finally, the validation with T mean-based error (Tmbe) using Mean Absolute Error (MAE) revealed a pattern of errors to provide insight to find the significant parameters of MTS. [ABSTRACT FROM AUTHOR]

The Fuzzy C-means (FCM) algorithm is one of the most widely used algorithms in unsupervised pattern recognition. As the intensity of observation noise increases, FCM tends to produce large center deviations and even overlap clustering problems. The relative entropy fuzzy C-means algorithm (REFCM) adds relative entropy as a regularization function to the fuzzy C-means algorithm, which has a good ability for noise detection and membership assignment to observed values. However, REFCM still tends to generate overlapping clusters as the size of the cluster increases and becomes imbalanced. Moreover, the convergence speed of this algorithm is slow. To solve this problem, modified suppressed relative entropy fuzzy c-means clustering (MSREFCM) is proposed. Specifically, the MSREFCM algorithm improves the convergence speed of the algorithm while maintaining the accuracy and anti-noise capability of the REFCM algorithm by adding a suppression strategy based on the intra-class average distance measurement. In addition, to further improve the clustering performance of MSREFCM for multidimensional imbalanced data, the center overlapping problem and the center offset problem of elliptical data are solved by replacing the Euclidean distance in REFCM with the Mahalanobis distance. Experiments on several synthetic and UCI datasets indicate that MSREFCM can improve the convergence speed and classification performance of the REFCM for spherical and ellipsoidal datasets with imbalanced sizes. In particular, for the Statlog dataset, the running time of MSREFCM is nearly one second less than that of REFCM, and the accuracy of MSREFCM is 0.034 higher than that of REFCM. [ABSTRACT FROM AUTHOR]

Despite the development of alternative modes of urban transport, the private car is still the most popular transport option in many regions around the world. Various spatial and socio-economic characteristics of metropolitan areas (MAs) seem to be generally correlated with levels of car use, and thus with car dependency. In this research, we study car dependency in a subgroup of global MAs, that are characterized profiles of car dependency, and are therefore considered outliers. Drawing on data that are available from the Mobility in Cities Database (MCD), we consider 56 MAs and use Mahalanobis distance to identify 7 outlier MAs that are either more, or less car dependent than anticipated by the regression model. We investigate the driving forces behind unpredicted levels of car use and position the outlier MAs in a catalogue of mobility profiles. A combination of urban form, convenience of car use, availability of alternative modes to car and car ownership characteristics were found to contribute to the level of car dependency in these MAs. [ABSTRACT FROM AUTHOR]

Mahalanobis distance of covariate means between treatment and control groups is often adopted as a balance criterion when implementing a rerandomization strategy. However, this criterion may not work well for high‐dimensional cases because it balances all orthogonalized covariates equally. We propose using principal component analysis (PCA) to identify proper subspaces in which Mahalanobis distance should be calculated. Not only can PCA effectively reduce the dimensionality for high‐dimensional covariates, but it also provides computational simplicity by focusing on the top orthogonal components. The PCA rerandomization scheme has desirable theoretical properties for balancing covariates and thereby improving the estimation of average treatment effects. This conclusion is supported by numerical studies using both simulated and real examples. [ABSTRACT FROM AUTHOR]

One of the crucial steps in the multi-criteria decision analysis involves establishing the importance of criteria and determining the relationship between them. This paper proposes an extended Hellwig's method (H_EM) that utilizes entropy-based weights and Mahalanobis distance to address this issue. By incorporating the concept of entropy, weights are determined based on their information content represented by the matrix data. The Mahalanobis distance is employed to address interdependencies among criteria, contributing to the improved performance of the proposed framework. To illustrate the relevance and effectiveness of the extended H_EM method, this study utilizes it to assess the progress toward achieving Sustainable Development Goal 4 of the 2030 Agenda within the European Union countries for education in the year 2021. Performance comparison is conducted between results obtained by the extended Hellwig's method and its other variants. The results reveal a significant impact on the ranking of the EU countries in the education area, depending on the choice of distance measure (Euclidean or Mahalanobis) and the system of weights (equal or entropy-based). Overall, this study highlights the potential of the proposed method in addressing complex decision-making scenarios with interdependent criteria. [ABSTRACT FROM AUTHOR]

The current study compared the achievements of higher secondary level students before and during the COVID 19 pandemic in five subjects-English, Biology, Physics, Chemistry, and Mathematics. This study was conducted on higher secondary level students from Bodoland Territorial Region (BTR), Assam, India. Dichotomous variables like rural and urban, tribal and non-tribal are considered for sample collection. A stratified random sampling technique is used for data collection. When five subjects are considered as a unit, the Mahalanobis Distance (MD) is used to measure the difference in dynamical character of achievements. There is a significant difference in the achievement of students between pre-COVID 19 and during COVID 19 pandemic. [ABSTRACT FROM AUTHOR]

Copyright of Revista Brasileira de Engenharia Agricola e Ambiental - Agriambi is the property of Revista Brasileira de Engenharia Agricola e Ambiental and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Because satellites cannot be repaired once launched, operators must detect anomalies early and prevent failures before they occur. Thus, satellite telemetry monitoring systems need to alert operators of anomalies and provide them with useful information to deal with these anomalies. However, traditional knowledge-based monitoring systems have the challenges of difficulty in building comprehensive models and a high dependency on experts. In recent years, data-driven approaches have been actively studied with the development of machine learning algorithms. These approaches solve the challenges of knowledge-based methods; however, they are often less capable of explaining anomalies than knowledge-based methods. In this study, we propose the new telemetry monitoring system with feature engineering to explain anomalies. The proposed method realizes identifiability of anomaly types and unusual telemetry by designing features based on moving averages, telemetry periods, waveform differences, and the Mahalanobis distance. We applied the proposed features to artificial and practical abnormal datasets and evaluated their usefulness. The results showed that the proposed method is capable of identifying trend, periodic, and waveform anomalies, specifying the telemetry in which the anomaly occurred and providing the information to operators.