Subsampling Technique Research Articles

The intelligent brain and the energy heart: Synergistic evolution of artificial intelligence and energy storage technology in China.

In the context of China's ongoing industrial revolution and technological transformation, there is a growing demand for advanced energy management solutions and the increasing role of artificial intelligence in various industries. This paper aims to explore how artificial intelligence (AI) and Energy Storage Technology (EST) interact and co-evolve. Utilizing a full-sample Granger causality test, we identified significant interactions between AI and EST. Afterwards, we further revealed their dynamic influence relationship using advanced sub-sampling techniques. Quantitative analysis indicates that AI positively influences EST by optimizing energy management systems, with an improvement of 15% in efficiency, and by enhancing the intelligence level of energy storage. However, there are also negative effects, such as a 10% increase in operational risks due to over-reliance on AI. Similarly, EST facilitates the development of AI by providing a stable energy supply. AI and EST, like the intelligent brain and the energy heart, require mutual dependence for stable development. In context of the industrial revolution and technical advancement, this study provides meaningful recommendations. Strengthening technological research and innovation support, optimizing energy policies, and enhancing standardization will promote the deep integration and synergistic development of AI and EST. This will provide significant impetus for China's technological advancement and economic development, aiding in the achievement of sustainable development goals.

Sample size determination for multidimensional parameters and the A-optimal subsampling in a big data linear regression model

To efficiently approximate the least squares estimator (LSE) in a Big Data linear regression model using a subsampling approach, optimal sampling distributions were derived by minimizing the trace norm of the covariance matrix of a smooth function of the subsampling LSE. An algorithm was developed that significantly reduces the computation time for the subsampling LSE compared to the full-sample LSE. Additionally, the subsampling LSE was shown to be asymptotically normal almost surely for an arbitrary sampling distribution under suitable conditions. Motivated by the need for subsampling in Big Data analysis and data splitting in machine learning, we investigated sample size determination (SSD) for multidimensional parameters and derived analytical formulas for calculating sample sizes. Through extensive simulations and real-world data applications, we assessed the numerical properties of both the subsampling approach and SSD methodology. Our findings revealed that the A-optimal subsampling method significantly outperformed uniform and leverage-score subsampling techniques. Furthermore, the algorithm considerably reduced the computational time required for implementing the full sample LSE. Additionally, the SSD provided a theoretical basis for selecting sample sizes.

Subsampling Algorithms for Irregularly Spaced Autoregressive Models

With the exponential growth of data across diverse fields, applying conventional statistical methods directly to large-scale datasets has become computationally infeasible. To overcome this challenge, subsampling algorithms are widely used to perform statistical analyses on smaller, more manageable subsets of the data. The effectiveness of these methods depends on their ability to identify and select data points that improve the estimation efficiency according to some optimality criteria. While much of the existing research has focused on subsampling techniques for independent data, there is considerable potential for developing methods tailored to dependent data, particularly in time-dependent contexts. In this study, we extend subsampling techniques to irregularly spaced time series data which are modeled by irregularly spaced autoregressive models. We present frameworks for various subsampling approaches, including optimal subsampling under A-optimality, information-based optimal subdata selection, and sequential thinning on streaming data. These methods use A-optimality or D-optimality criteria to assess the usefulness of each data point and prioritize the inclusion of the most informative ones. We then assess the performance of these subsampling methods using numerical simulations, providing insights into their suitability and effectiveness for handling irregularly spaced long time series. Numerical results show that our algorithms have promising performance. Their estimation efficiency can be ten times as high as that of the uniform sampling estimator. They also significantly reduce the computational time and can be up to forty times faster than the full-data estimator.

A Subsampling Strategy for AIC-based Model Averaging with Generalized Linear Models

Subsampling is an effective approach to address computational challenges associated with massive datasets. However, existing subsampling methods do not consider model uncertainty. In this article, we investigate the subsampling technique for the Akaike information criterion (AIC) and extend the subsampling method to the smoothed AIC model-averaging framework in the context of generalized linear models. By correcting the asymptotic bias of the maximized subsample objective function used to approximate the Kullback–Leibler divergence, we derive the form of the AIC based on the subsample. We then provide a subsampling strategy for the smoothed AIC model-averaging estimator and study the corresponding asymptotic properties of the loss and the resulting estimator. A practically implementable algorithm is developed, and its performance is evaluated through numerical experiments on both real and simulated datasets.

Deep Neural Network-Based Accelerated Failure Time Models Using Rank Loss.

An accelerated failure time (AFT) model assumes a log-linear relationship between failure times and a set of covariates. In contrast to other popular survival models that work on hazard functions, the effects of covariates are directly on failure times, the interpretation of which is intuitive. The semiparametric AFT model that does not specify the error distribution is sufficiently flexible and robust to depart from the distributional assumption. Owing to its desirable features, this class of model has been considered a promising alternative to the popular Cox model in the analysis of censored failure time data. However, in these AFT models, a linear predictor for the mean is typically assumed. Little research has addressed the non-linearity of predictors when modeling the mean. Deep neural networks (DNNs) have received much attention over the past few decades and have achieved remarkable success in a variety of fields. DNNs have a number of notable advantages and have been shown to be particularly useful in addressing non-linearity. Here, we propose applying a DNN to fit AFT models using Gehan-type loss combined with a sub-sampling technique. Finite sample properties of the proposed DNN and rank-based AFT model (DeepR-AFT) were investigated via an extensive simulation study. The DeepR-AFT model showed superior performance over its parametric and semiparametric counterparts when the predictor was nonlinear. For linear predictors, DeepR-AFT performed better when the dimensions of the covariates were large. The superior performance of the proposed DeepR-AFT was demonstrated using three real datasets.

First detection in Australia of cryptotephra likely to be derived from the 25.6 ka Ōruanui supereruption in New Zealand

Cryptotephra subsampling techniques were used to identify a high concentration (c. 700 shards/g) of glass shards within the Yellow Marsh sediments in northwest Tasmania, Australia. Radiocarbon dating from the overlying sediments coupled with geochemical analysis of the glass shards indicate their similarity to the Kawakawa-Ōruanui Tephra (KOT), derived from the Ōruanui supereruption of 25,568 ± 232 cal yr BP (±2sd) from the Taupō Volcanic Zone, New Zealand. Although cryptotephra from this eruption has previously been identified in Antarctica and modelled to have been transported over parts of southern and eastern Australia, to date glass shards from this eruption have not been identified in Australia. If the correlation of the cryptotephra to the Ōruanui supereruption is correct, this finding has the potential to allow Last Glacial deposits in the SW Pacific (including those in Australia, New Zealand and Antarctica) to be irrefutably linked.

Ensemble Kalman inversion for image guided guide wire navigation in vascular systems

This paper addresses the challenging task of guide wire navigation in cardiovascular interventions, focusing on the parameter estimation of a guide wire system using Ensemble Kalman Inversion (EKI) with a subsampling technique. The EKI uses an ensemble of particles to estimate the unknown quantities. However, since the data misfit has to be computed for each particle in each iteration, the EKI may become computationally infeasible in the case of high-dimensional data, e.g. high-resolution images. This issue can been addressed by randomised algorithms that utilize only a random subset of the data in each iteration. We introduce and analyse a subsampling technique for the EKI, which is based on a continuous-time representation of stochastic gradient methods and apply it to on the parameter estimation of our guide wire system. Numerical experiments with real data from a simplified test setting demonstrate the potential of the method.

Fuzzy Logic Prediction of Hypertensive Disorders in Pregnancy Using the Takagi–Sugeno and C-Means Algorithms

Hypertensive disorders in pregnancy, which include preeclampsia, eclampsia, and chronic hypertension, complicate approximately 10% of all pregnancies in the world, constituting one of the most serious causes of mortality and morbidity in gestation. To help predict the occurrence of hypertensive disorders, a study based on algorithms that help model this health problem using mathematical tools is proposed. This study proposes a fuzzy c-means (FCM) model based on the Takagi–Sugeno (T-S) type of fuzzy rule to predict hypertensive disorders in pregnancy. To test different modeling methodologies, cross-validation comparisons were made between random forest, decision tree, support vector machine, and T-S and FCM methods, which achieved 80.00%, 66.25%, 70.00%, and 90.00%, respectively. The evaluation consisted of calculating the true positive rate (TPR) over the true negative rate (TNR), with equal error rate (EER) curves achieving a percentage of 20%. The learning dataset consisted of a total of 371 pregnant women, of which 13.2% were diagnosed with a condition related to gestational hypertension. The dataset for this study was obtained from the Secretaría de Salud del Estado de Hidalgo (SSEH), México. A random sub-sampling technique was used to adjust the class distribution of the data set, and to eliminate the problem of unbalanced classes. The models were trained using a total of 98 samples. The modeling results indicate that the T-S and FCM method has a higher predictive ability than the other three models in this research.

An efficient subsampling method for estimating corn root characteristics with scanner‐based image analysis

AbstractQuantifying root length, surface area, average diameter, and volume of fully‐matured corn (Zea mays L.) is labor intensive, time consuming, and costly. Accurate and efficient subsampling techniques are needed to overcome these limitations. In this study, eight corn root systems were grown to maturity in a sand‐culture hydroponics system to develop and test root system subsampling techniques for accuracy (uncertainty assessment) and efficiency (time). Each entire root system was separated into coarse and fine roots, which were then composited into 65 subsamples, either visually or by mass, followed by subsample scanning to quantify root characteristics. A bootstrap non‐parametric procedure was used to determine the sample size needed to represent the total root system and quantify uncertainty based on the number of subsamples analyzed. When subsamples were composited visually, as many as 60 subsamples (92% of the total root system) were necessary to represent the characteristics of the root system within ±5% of the true mean at a 95% confidence level. In contrast, when subsamples were composited by equal mass, a maximum of 15 subsamples (23% of the total root system) were needed to be representative, requiring 2 h and 15 min per root system. The findings show that separating the entire root system by coarse and fine roots and then weighing into equal mass subsamples before scanning decreased the number of subsamples and time required to accurately estimate corn root characteristics. Thus, this subsampling approach considerably reduced the effort and cost of processing corn root systems.

Detection of explosives residue using a novel subsampling technique for DART-HRMS analysis

In the ensuing investigation after an explosion, determining the explosive used is of prime importance to establish investigative leads. Post-blast samples have many interferences and considerations that make quick, reliable identification a challenge. The use of a novel subsampling technique with DART-HRMS provides the ability to quickly detect and identify explosive residue after detonation. Simulated improvised explosive devices were constructed with a variety of materials and detonated with the help of the Montgomery County Fire Marshal’s Office (TX). Post-blast debris was subsequently collected and swabbed with a novel subsampling technique, utilizing filter paper. This filter paper was then introduced into the DART gas stream, with an internal standard to minimize potential false negatives. After introducing explosive residue from swabbed post-blast substrates, characteristic ions of selected constituents of smokeless powder including diphenylamine, ethyl centralite, di-n-butyl phthalate, and nitroglycerin were detected and confirmed through comparison of accurate mass measurements to theoretical exact masses. Additionally, characteristic ions of 2,4,6-trinitrotoluene (TNT) and Royal Demolition eXplosive (RDX) were also detected using this technique. Overall, the detection of characteristic ions was more successful when recovering residue from plastic compared to wood or metal, with success rates routinely at 100%. Implementing this screening technique enables rapid detection and reliable identification of explosive residue in a detonation incident. The developed subsampling technique provides practitioners with a practical method of screening post-blast debris in a laboratory setting, requiring minimal sample preparation.

Finding the pioneers of China's smart cities: From the perspective of construction efficiency and construction performance

Existing problems such as waste of resources and lack of public access indicate that sustainable smart city construction should consider the balanced development of construction efficiency and performance. The study adopts the slacks-based measurement (SBM)-DEA model to measure the efficiency of smart city construction, a subsampling technique is adopted as a bootstrapping method, and applies the entropy weight technology to measure the performance of smart city construction. Finally, a model for categorizing the smart city construction is developed using the Boston matrix technique. Results show the following: (a) The smart city development patterns of the 33 prefecture-level cities show gradual improvement during the study period. Seven cities, including Yinchuan, Shenzhen, and Xiamen, are smart city pioneers. (b) Regional differences characterize the level of smart city construction in prefecture-level cities, with the eastern region exhibiting better smart city construction status than the central and western regions. (c) The four municipalities achieve outstanding results in terms of the smart city construction performance. However, apart from Beijing, which is a pioneer in smart city construction, the other three municipalities are not efficient in their construction. Finally, the study proposes policy recommendations for the promotion of the development of different types of smart cities.

Distributed optimal subsampling for quantile regression with massive data

Methods for reducing distributed subsample sizes have increasingly become popular statistical problems in the big data era. Existing works of optimal subsample selection on the massive linear and generalized linear models with distributed data sources have been solidly investigated and widely applied. Nevertheless, few studies have developed distributed optimal subsample selection procedures for quantile regression in massive data. In such settings, the distributed optimal subsampling probabilities and subset sizes selection criteria need to be established simultaneously. In this work, we propose a distributed subsampling technique for the quantile regression models. The estimation approach is based on a two-step algorithm for the distributed subsampling procedures. Furthermore, the theoretical results, such as consistency and asymptotic normality of resultant estimators, are rigorously established under some regularity conditions. The empirical evaluation and performance of the proposed subsampling method are conducted in simulation experiments and real data applications.

Rise and diversification of chondrichthyans in the Paleozoic

AbstractThe Paleozoic represents a key time interval in the origins and early diversification of chondrichthyans (cartilaginous fishes), but their diversity and macroevolution are largely obscured by heterogenous spatial and temporal sampling. The predominantly cartilaginous skeletons of chondrichthyans pose an additional limitation on their preservation potential and hence on the quality of their fossil record. Here, we use a newly compiled genus-level dataset and the application of sampling standardization methods to analyze global total-chondrichthyan diversity dynamics through time from their first appearance in the Ordovician through to the end of the Permian. Subsampled estimates of chondrichthyan genus richness were initially low in the Ordovician and Silurian but increased substantially in the Early Devonian. Richness reached its maximum in the middle Carboniferous before dropping across the Carboniferous/Permian boundary and gradually decreasing throughout the Permian. Sampling is higher in both the Devonian and Carboniferous compared with the Silurian and most of the Permian stages. Shark-like scales from the Ordovician are too limited to allow for some of the subsampling techniques. Our results detect two Paleozoic radiations in chondrichthyan diversity: the first in the earliest Devonian, led by acanthodians (stem-group chondrichthyans), which then decline rapidly by the Late Devonian, and the second in the earliest Carboniferous, led by holocephalans, which increase greatly in richness across the Devonian/Carboniferous boundary. Dispersal of chondrichthyans, specifically holocephalans, into deeper-water environments may reflect a niche expansion following the faunal displacement in the aftermath of the Hangenberg extinction event at the end of the Devonian.

Subsampled cubic regularization method for finite-sum minimization

This paper proposes and analyses a subsampled Cubic Regularization Method (CRM) for solving finite-sum optimization problems. The new method uses random subsampling techniques to approximate the functions, gradients and Hessians in order to reduce the overall computational cost of the CRM. Under suitable hypotheses, first- and second-order iteration-complexity bounds and global convergence analyses are presented. We also discuss the local convergence properties of the method. Numerical experiments are presented to illustrate the performance of the proposed scheme.

Optimal subsampling for high-dimensional ridge regression

We investigate the feature compression of high-dimensional ridge regression using the optimal subsampling technique. Specifically, based on the basic framework of random sampling algorithm on feature for ridge regression and the A-optimal design criterion, we first obtain a set of optimal subsampling probabilities. Considering that the obtained probabilities are uneconomical, we then propose the nearly optimal ones. With these probabilities, a two step iterative algorithm is established which has lower computational cost and higher accuracy. We provide theoretical analysis and numerical experiments to support the proposed methods. Numerical results demonstrate the decent performance of our methods.

Key Grazing Behaviours of Beef Cattle Identify Specific Genotypes of the Glutamate Metabotropic Receptor 5 Gene (GRM5)

Genotype-phenotype associations between the bovine genome and grazing behaviours measured over time and across contexts have been reported in the past decade, with these suggesting the potential for genetic control over grazing personalities in beef cattle. From the large array of metrics used to describe grazing personality behaviours (GP-behaviours), it is still unclear which ones are linked to specific genes. Our prior observational study has reported associations and trends towards associations between genotypes of the glutamate metabotropic receptor 5 gene (GRM5) and four GP-behaviours, yet the unbalanced representation of GRM5 genotypes occurring in observational studies may have limited the ability to detect associations. Here, we applied a subsampling technique to create a genotypically-balanced dataset in a quasi-manipulative experiment with free ranging cows grazing in steep and rugged terrain of New Zealand’s South Island. Using quadratic discriminant analysis, two combinations of eleven GP-behaviours (and a total of fifteen behaviours) were selected to build an exploration model and an elevation model, respectively. Both models achieved ∼ 86% accuracy in correctly discriminating cows’ GRM5 genotypes with the training dataset, and the exploration model achieved 85% correct genotype prediction of cows from a testing dataset. Our study suggests a potential pleiotropic effect, with GRM5 controlling multiple grazing behaviours, and with implications for the grazing of steep and rugged grasslands. The study highlights the importance of grazing behavioural genetics in cattle and the potential use of GRM5 markers to select individuals with desired grazing personalities and built herds that collectively utilize steep and rugged rangelands sustainably.

Improving the Performance of Low-resourced Speaker Identification with Data Preprocessing

Automatic speaker identification is done to tackle daily security problems. Speech data collection is an essential but very challenging task for under-resourced languages like Burmese. The speech quality is crucial to accurately recognize the speaker’s identity. This work attempted to find the optimal speech quality appropriate for Burmese tone to enhance identification compared with other more richy resourced languages on Mel-frequency cepstral coefficients (MFCCs). A Burmese speech dataset was created as part of our work because no appropriate dataset available for use. In order to achieve better performance, we preprocessed the foremost recording quality proper for not only Burmese tone but also for nine other Asian languages to achieve multilingual speaker identification. The performance of the preprocessed data was evaluated by comparing with the original data, using a time delay neural network (TDNN) together with a subsampling technique that can reduce time complexity in model training. The experiments were investigated and analyzed on speech datasets of ten Asian languages to reveal the effectiveness of the data preprocessing. The dataset outperformed the original dataset with improvements in terms of equal error rate (EER). The evaluation pointed out that the performance of the system with the preprocessed dataset improved that of the original dataset.

Tree-Based Learning Models for Botnet Malware Classification in Real World Sub-Sample Dataset

The use of machine learning techniques for botnet detection has been an active area of research in security field for some years now. Some of the past machine learning-based botnet detection studies used datasets that were generated synthetically. The release of a large and real-life botnet dataset, named CTU-13, allowed researchers to build machine learning-based models from real-world data. In fact, the real-life traces in the dataset makes it more promising for being used for botnet identification studies. The current study proposed the use of a single tree-based learning algorithm in the classification of botnet evidence from sub-sampled portion of three captures in CTU-13 dataset. Random sub-sampling was used to arrive at three different datasets that was used in the study. The first step in the methodology involved experimental analyses on three captures out of thethirteen in the whole dataset. The analyses revealed the basic characteristics of the datasets which further guided the study further. The missing values and categorical data types in the dataset were handled through mixed imputation and feature encoding, respectively. The big data nature of the dataset was handled through random sub-sampling technique with a view to building a botnet detection model that is less computationally intensive. The random sub-sampling technique was used without changing the data distributions in thedataset. The botnet detection models were built by using decision-tree algorithm from the three sub-sampled dataset captures. The performances of the models were evaluated by using accuracy, precision, recall, and f1-score, respectively. In all, the model built with scenario5 capture slightly performed better than the ones built using scenario 6 and scenario 7 captures, respectively.

DeepWalk with Reinforcement Learning (DWRL) for node embedding

DeepWalk is used to convert nodes in an original graph into equivalent vectors in a latent space for performing various predictive tasks. To ensure second-order structural similarity between nodes in the original graph and their vectors in the latent space, dot products are applied to each pair of nodes explored on the random walk (RW) in the latent space. However. dot products for graphs with millions of nodes and billions of edges are computationally expensive. To minimize the computation time required for calculating the second-order structural similarity, DeepWalk with reinforcement learning (DWRL) is proposed herein. In DWRL, a level pointer for each node in the original graph is prepared. By identifying common nodes between each pair of nodes in the original graph, the number of computations in the dot product in the latent space is reduced, thereby ensuring second-order structural similarity. Additionally, repeated selection of the same node during RWs produces redundant samples for training. Therefore, the subsampling technique is used to choose the next node based on its degree, which improves the generalization of node representations in the latent space and increases accuracy. The proposed techniques are applied to popular datasets to perform multilabel classification and link prediction tasks, and their efficiency in reducing the computation time is verified. The proposed DWRL minimizes the computation time 47% for large graphs to build latent vectors and improves the average micro and macro F1 scores up to 12%. The link prediction performance also increases up to 20%.

Dimethylmercury in natural waters—analytical and experimental considerations

AbstractMono‐ and dimethylmercury (MMHg and DMHg, respectively) are the two primary organic forms of mercury (Hg) found in natural waters. While experimental approaches to characterize the environmental behavior of MMHg and inorganic forms of Hg are widely used today, few laboratories conduct experimental studies entailing the use of DMHg. In this paper, we have evaluated and developed different analytical and experimental approaches to quantify and use DMHg in laboratory studies. We demonstrate that DMHg can be analyzed from samples where MMHg is derivatized using sodium tetraethyl borate and where the matrix effects of dissolved sulfide are masked using copper sulfate. Tests, where the calibration curves of MMHg and DMHg were used, showed that MMHg may be used to calibrate for DMHg. For the pre‐concentration of DMHg, both traps filled with Tenax® TA and Bond Elut ENV were found suitable. We observed good recoveries of DMHg added to different types of natural waters or purified water containing aquarium salt, sodium chloride and dissolved sulfide, iron sulfide, and cadmium sulfide at DMHg : sulfide molar ratios > 10−6. In addition to evaluating these analytical aspects, we present suitable subsampling techniques for DMHg‐containing solutions, the recovery of DMHg when filtering DMHg through different types of filters, and experimental data on the long‐term stability of DMHg added to different types of waters and stored at different temperatures. Finally, we present and discuss a new synthetization protocol for preparing aqueous solutions containing DMHg free of organic solvents and where handling DMHg in a pure form is prevented.