Search

Ground Delay Programs (GDP) comprise the main interventions to optimize flight operations in congested air traffic networks. The core GDP objective is to minimize flight delays, but this may result in optimal outcomes for passengers — especially with connecting itineraries. This paper proposes an original passenger-centric approach to GDP by leveraging data on passenger itineraries in flight networks. First, we identify analytical drivers of passenger-centric operations in transportation systems. Second, we develop an integer program that balances flight delays and passenger delays in large-scale GDP operations. A rolling procedure decomposes the problem while ensuring global feasibility, enabling the model’s implementation in short computational times. Third, we propose statistical learning models to predict passenger itineraries and optimize GDP operations accordingly, enabling the model’s implementation when passenger itineraries are unknown by air traffic managers. Computational results based on real-world data suggest that our modeling and computational framework can reduce passenger delays significantly at small increases in flight delay costs, and that these benefits are robust to imperfect knowledge of passenger itineraries. Results highlight two major levers of passenger-centric operations: (i) delay allocation (which flights to delay vs. prioritize), and (ii) delay introduction (whether to deliberately hold flights to avoid passenger misconnections).

Wildfire spread is a stochastic phenomenon driven by a multitude of geophysical and anthropogenic factors. In this study, we propose a spatiotemporal data-driven risk assessment framework to understand the effect of various geophysical/anthropogenic factors on wildfire size, leveraging a systematic machine learning approach. We apply this framework in the state of California—the most vulnerable US state to wildfires. Using county-level annual wildfire data from 2001-2015, and various geophysical (e.g., landcover, wind, surface temperature) and anthropogenic features (e.g., population density, housing type), we trained, tested, and validated a suite of ensemble tree-based learning algorithms to identify and evaluate the key factors associated with wildfire size. The extreme gradient boosting (XGBoost) algorithm outperformed all the other models in terms of generalization performance, categorization of important features, and risk performance. We found that standard deviations of meteorological variables with long-tailed distributions play a key role in predicting wildfire size. Specifically, the top ten factors associated with high risk of larger wildfires include larger standard deviations of surface temperature and vapor pressure deficit, higher wind gust, more grassy and barren land covers, lower night-time boundary layer height and higher population density. Our proposed risk assessment framework will help federal/state decision-makers to adequately plan for wildfire risk mitigation and resource allocation strategies.

Objectives: If statistical learning ability is critical for language acquisition and language development, it is necessary to confirm whether enhancing statistical learning ability can improve the children’s language skills. The present study investigated whether children with and without vocabulary delay (VD) show a difference in improving statistical learning (SL) tasks manipulated with implicit, implicit*2 and explicit conditions, and with visual and auditory domains; and also explores the relationship among SL, vocabulary, and quick incidental learning (QUIL).Methods: A total of 132 children between 3 to 8 years participated in this study, including vocabulary delayed children (N= 34) and typically developing children (N = 98). Participants completed SL tasks which were composed of three exposure conditions, and Quick incidental learning (QUIL) tasks to tap the novel word learning ability.Results: The VD group score was significantly lower than the TD group in the explicit condition of the auditory statistical learning task, and there was a significant correlation between QUIL and SL_auditory (implicit*2) only in the TD group.Conclusion: These results may explain that the TD group was ready to accept the explicit cues for learning as a domain-specific (auditory) benefit, and their auditory SL ability can be closely linked to vocabulary abilities. The current study suggests one possibility; that the VD group can increase the statistical learning ability through double auditory exposures. The novel quick incidental learning in the TD group was supported by the statistical learning, but this was not seen in the VD group.

Rapid growth in data, computational methods, and computing power is driving a remarkable revolution in what variously is termed machine learning (ML), statistical learning, computational learning, and artificial intelligence. In addition to highly visible successes in machine-based natural language translation, playing the game Go, and self-driving cars, these new technologies also have profound implications for computational and experimental science and engineering, as well as for the exascale computing systems that the Department of Energy (DOE) is developing to support those disciplines. Not only do these learning technologies open up exciting opportunities for scientific discovery on exascale systems, they also appear poised to have important implications for the design and use of exascale computers themselves, including high-performance computing (HPC) for ML and ML for HPC. The overarching goal of the ExaLearn co-design project is to provide exascale ML software for use by Exascale Computing Project (ECP) applications, other ECP co-design centers, and DOE experimental facilities and leadership class computing facilities.

The sense of school belonging refers to students' feelings of being accepted and connected to their particular school. School belonging has been considered an important determinant of a range of academic and socioemotional outcomes. Yet despite an extensive literature on the topic, it is not clear what factors are more strongly related to the students' sense of school belonging. Using a nationally representative dataset, we investigated the extent to which school belonging in fifth grade can be predicted by a wide range of individual and contextual-level factors using two statistical learning techniques (Lasso and MARS). The strongest predictor of school belonging across all models was students' feelings of peer social support, followed by students' feelings of loneliness at school. These results suggest that peer social relationships are a key component of students feeling of being connected to their school.

Background Biomarkers are urgently needed for pancreatic ductal adenocarcinoma (PDAC). Endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) is the cornerstone for diagnosing PDAC. We developed a method for discovery of PDAC biomarkers using the discarded EUS-FNA liquid. Methods This retrospective study included 58 patients with suspected pancreatic lesions who underwent EUS-FNA. Protein extracts from EUS-FNA liquid were analyzed by mass spectrometry. Proteomic and clinical data were modeled by supervised statistical learning to identify protein markers and clinical variables that distinguish PDAC. Results Statistical modeling revealed a protein signature for PDAC screening that achieved high sensitivity and specificity (0.92, 95 % confidence interval [CI] 0.79–0.98, and 0.85, 95 %CI 0.67–0.93, respectively). We also developed a protein signature score (PSS) to guide PDAC diagnosis. In combination with patient age, the PSS achieved 100 % certainty in correctly identifying PDAC patients > 54 years. In addition, 3 /4 inconclusive EUS-FNA biopsies were correctly identified using PSS. Conclusions EUS-FNA-derived fluid is a rich source of PDAC proteins with biomarker potential. The PSS requires further validation and verification of the feasibility of measuring these proteins in patient sera.

The starting point for the presentation of the similarities and differences between the principles of conducting statistical research according to the rules of both statistical inference and statistical learning is the paradigm theory, formulated by Thomas Kuhn. In the first section of this paper, the essential features of the statistical inference paradigm are characterised, with particular attention devoted to its limitations in contemporary statistical research. Subsequently, the article presents the challenges faced by this research jointly with the expanding opportunities for their effective reduction. The essence of learning from data is discussed and the principles of statistical learning are defined. Moreover, significant features of the statistical learning paradigm are formulated in the context of the differences between the statistical inference paradigm and the statistical learning paradigm. It is emphasised that the statistical learning paradigm, as the more universal one of the two discussed, broadens the possibilities of conducting statistical research, especially in socio-economic sciences.

Previous studies have shown that distributed practice-a training strategy that is known to facilitate memory-is likely to result in greater learning than massed practice. This effect has been demonstrated largely in explicit tasks. The purpose of this study was to test whether statistical learning of artificial grammar is affected by the lag between learning sessions overall, and by high and low complexity stimuli (as measure by chunk strength). Two groups (spaced-short and spaced-long) learned strings of letters created according to a set of rules and were required to produce new strings using given letter sets. For the spaced-short group, the two learning sessions, each including training and a test phase, took place sequentially with a 10-min break, whereas for the spaced-long group, learning sessions were distributed across two days (1-day lag). Overall results showed improved performance following spaced-long practice compared to spaced-short practice. The results also indicated that in the low chunk strength strings (indicating high complexity), both groups demonstrated similar improvement from first to second testing, while in the high chunk strength strings (indicating low complexity), improvement in letter reordering performance was significantly higher when the learning sessions were distributed across two days. This pattern of findings suggests that stimuli complexity affects the extent to which distributed practice enhance artificial grammar learning.

Mobility data, based on global positioning system (GPS) tracking, have been widely used in many areas, such as analyzing travel patterns, investigating transport safety and efficiency, and evaluating travel impacts. Transport modes are essential factors in understanding mobility within the transport system. Therefore, in this study, a significant number of algorithms were tested for transport mode detection. However, no conclusive recommendations can be drawn regarding which method should be used. The evaluation of the performance of the algorithms was not discussed systematically either in current literature. This paper aims to provide an in-depth review of the methods applied in transport mode detection based on GPS tracking data. The performances of the reviewed methods are then compared and evaluated to provide guidance in choosing algorithms for transport mode detection based on GPS tracking data. The results indicate that the majority of current studies are based on a supervised learning method for transport mode detection. Many of the reviewed methods first require manual dataset labeling, which can produce major drawbacks, such as inefficiency and human errors. It was also found that deep learning approaches have the potential to deal with large amounts of unlabeled raw GPS datasets and increase the accuracy and efficiency of transport mode detection.

Penyakit arteri koroner (coronary artery disease) menjadi penyebab utama kematian penduduk di dunia setidaknya selama dua dekade (2000-2019) dan mengalami peningkatan kematian terbesar dalam rentang waktu tersebut dibandingkan dengan penyebab kematian lainnya. Keberhasilan memprediksi penyakit arteri koroner secara dini berdasarkan data medis bermanfaat bagi pasien dan juga bagi kestabilan perekonomian negara. Tujuan penelitian ini adalah memprediksi penyakit arteri koroner jantung dengan mengimplementasikan dua metode statistical learning yaitu Multinomial Naïve Bayes dan pohon keputusan dengan validasi silang 10-fold, dimana variabel-variabel numerik didiskritisasi untuk memperoleh variabel-variabel kategorik. Hasil penelitian menunjukkan bahwa metode Pohon Keputusan memiliki kinerja yang lebih baik dibandingkan metode Multinomial Naïve Bayes dalam memprediksi penyakit arteri koroner. Ukuran kinerja metode Pohon Keputusan memperoleh tingkat akurasi 99,63 %, sensitivitas 100 %, spesifisitas 99,33%, presisi 99,23 %, dan nilai prediksi negatif (NPV) 100 %. Ukuran-ukuran ini mengindikasikan bahwa metode Pohon Keputusan layak digunakan untuk memprediksi penyakit arteri coroner, termasuk data independent berupa data penyakit arteri coroner lainnya dengan variable predictor yang sama. Hasil penelitian ini juga menunjukkan bahwa perbedaan rujukan dengan penelitian-penelitian sebelumnya dalam mendiskritisasi variabel numerik mampu meningkatkan kinerja metode dalam memprediksi penyakit arteri coroner.

Several emerging applications call for a fusion of statistical learning and stochastic programming (SP). We introduce a new class of models which we refer to as Predictive Stochastic Programming (PSP). Unlike ordinary SP, PSP models work with datasets which represent random covariates, often refered to as predictors (or features) and responses (or labels) in the machine learning literature. As a result, these PSP models call for methodologies which borrow relevant concepts from both learning and optimization. We refer to such a methodology as Learning Enabled Optimization (LEO). This paper sets forth the foundation for such a framework by introducing several novel concepts such as statistical optimality, hypothesis tests for model-fidelity, generalization error of PSP, and finally, a non-parametric methodology for model selection. These new concepts, which are collectively referred to as LEO, provide a formal framework for modeling, solving, validating, and reporting solutions for PSP models. We illustrate the LEO framework by applying it to a production-marketing coordination model based on combining a pedagogical production planning model with an advertising dataset intended for sales prediction.

Contending with talker variability has been found to lead to processing costs but also benefits by focusing learners on invariant properties of the signal, indicating that talker variability acts as a desirable difficulty. That is, talker variability may lead to initial costs followed by long-term benefits for retention and generalization. Adult participants learned an artificial grammar affording learning of multiple components in two experiments varying in difficulty. They learned from one, two, or eight talkers and were tested at three time points. The eight-talker condition did not impact learning. The two-talker condition negatively impacted some aspects of learning, but only under more difficult conditions. Generalization of the grammatical dependency was difficult. Thus, we discovered that high and limited talker variability can differentially impact artificial grammar learning. However, talker variability did not act as a desirable difficulty in the current paradigm as the few evidenced costs were not related to long-term benefits.

Humans automatically and unintentionally detect and remember regularities in the visual environment−a type of learning termed visual statistical learning (VSL). Many aspects of learning from reward resemble statistical learning in some respects, yet whether and how reward learning impacts VSL is largely unexamined. In two studies, we investigated the impact of reward on VSL and examined the neural basis of this interaction using fMRI. Subjects completed a risky choice task, in which they learned the values (high or low) of fractal images through a trial-and-error binary-choice task. Unbeknownst to subjects, we paired images so that some images always predicted other images on the following trial. This led to four types of pairings (High-High, High-Low, Low-High, and Low-Low). In a subsequent recognition task and reward memory task, we asked them to choose the more familiar of two pairs (a target and a foil) and to recall the value of images (high or low). We found better recognition when the first image of a pair was a high-value image, with High-High pairs showing the highest recognition rate. To investigate the neural basis of this effect, we measured brain responses to visual images that were associated with both varying levels of reward and sequential contingencies with event-related fMRI. Subjects completed the same risky choice task and then passively viewed a stream of the images with pairwise relationships intact. Brain responses to images during the risky choice task were affected by both value and statistical contingencies. When we compared responses between the first image of a pair that was high-value and the first image of a pair that was low-value, we found greater activation in regions that included inferior frontal gyrus, left anterior cingulate gyrus, middle temporal gyrus, superior temporal gyrus, hippocampus, orbitofrontal cortex, caudate, nucleus accumbens, hippocampus, and lateral occipital cortex. These findings are not driven solely by the value difference, but rather the interaction between statistically structured information and reward − the same value contrast yielded no regions for either second-image contrasts or for singletons. Our results suggest that the first images of pairs that were associated with high-value, in comparison to those associated with low-value, were involved in greater attentional engagement, potentially enabling better memory for statistically learned pairs and reward information. Additionally, we found neural evidence that when an image contains both statistical structure and reward information, the reward learning may be predicted by the type of the statistical structure it is associated with. We conclude that reward contingencies affect VSL, with high-value associated with stronger behavioral and neural signatures of such learning.

Background Excess body fatness, commonly approximated by a one-off determination of body mass index (BMI), is associated with increased risk of at least 13 cancers. Modelling of longitudinal BMI data may be more informative for incident cancer associations, e.g. using latent class trajectory modelling (LCTM) may offer advantages in capturing changes in patterns with time. Here, we evaluated the variation in cancer risk with LCTMs using specific age recall versus decade recall BMI. Methods We obtained BMI profiles for participants from the Prostate, Lung, Colorectal and Ovarian Cancer Screening Trial. We developed gender-specific LCTMs using recall data from specific ages 20 and 50 years (72,513 M; 74,837 W); decade data from 30s to 70s (42,113 M; 47,352 W) and a combination of both (74,106 M, 76,245 W). Using an established methodological framework, we tested 1:7 classes for linear, quadratic, cubic and natural spline shapes, and modelled associations for obesity-related cancer (ORC) incidence using LCTM class membership. Results Different models were selected depending on the data type used. In specific age recall trajectories, only the two heaviest classes were associated with increased risk of ORC. For the decade recall data, the shapes appeared skewed by outliers in the heavier classes but an increase in ORC risk was observed. In the combined models, at older ages the BMI values were more extreme. Conclusions Specific age recall models supported the existing literature changes in BMI over time are associated with increased ORC risk. Modelling of decade recall data might yield spurious associations.

Ultra-reliable communication (URC) is a key enabler for supporting immersive and mission-critical 5G applications. Meeting the strict reliability requirements of these applications is challenging due to the absence of accurate statistical models tailored to URC systems. In this letter, the wireless connectivity over dynamic channels is characterized via statistical learning methods. In particular, model-based and data-driven learning approaches are proposed to estimate the non-blocking connectivity statistics over a set of training samples with no knowledge on the dynamic channel statistics. Using principles of survival analysis, the reliability of wireless connectivity is measured in terms of the probability of channel blocking events. Moreover, the maximum transmission duration for a given reliable non-blocking connectivity is predicted in conjunction with the confidence of the inferred transmission duration. Results show that the accuracy of detecting channel blocking events is higher using the model-based method for low to moderate reliability targets requiring low sample complexity. In contrast, the data-driven method shows higher detection accuracy for higher reliability targets at the cost of 100$\times$ sample complexity., Comment: 5 pages, 5 figures, Accepted for IEEE Communications Letters

Background Early diagnosis of severe acute pancreatitis (SAP) is essential to minimize its mortality and improve prognosis. We aimed to develop an accurate and applicable machine learning predictive model based on routine clinical testing results for stratifying acute pancreatitis (AP) severity. Results We identified 11 markers predictive of AP severity and trained an AP stratification model called APSAVE, which classified AP cases within 24 hours at an average area under the curve (AUC) of 0.74 +/- 0.04. It was further validated in 568 validation cases, achieving an AUC of 0.73, which is similar to that of Ranson's criteria (AUC = 0.74) and higher than APACHE II and BISAP (AUC = 0.69 and 0.66, respectively). Conclusions We developed and validated a venous blood marker-based AP severity stratification model with higher accuracy and broader applicability, which holds promises for reducing SAP mortality and improving its clinical outcomes. Materials and methods Nine hundred and forty-five AP patients were enrolled into this study. Clinical venous blood tests covering 65 biomarkers were performed on AP patients within 24 hours of admission. An SAP prediction model was built with statistical learning to select biomarkers that are most predictive for AP severity.

Application Traffic Identification is an imperative device for sorting out the system as it is the most popular approach to distinguish and characterize the network traffic created from different applications. The classification using conventional Port-based and Payload-based techniques has become counterproductive due to inconsistencies. However, in recent times, approaches with machine learning and statistical techniques have guaranteed higher accuracy. However, learning techniques are inadequate for solving problems with Time and Memory intricacies in vast datasets. Hence, the proposed paper presents a novel scheme of Statistical based traffic classification named Multi-Phased Statistical Based Classification methodology that renders Semi-supervised machines with advanced K-medoid clustering and C5.0 Classification algorithm. The proposed system displays a classic competence in observing the known and unknown application flows by statistical features utilization scheme that enhances the classification preciseness. Further, the trial results show that the proposed work outperforms previous approaches by achieving a higher granularity of 98–99% and reducing complexities. Ultimately, the new proposed work is evaluated on our campus traffic traces (AU-IDS). It is proven that the proposed approach accomplishes a higher exactness rate and thus encourages its implementation in real-time.

In 1995, Theeuwes and Godthelp published a paper called “self-explaining roads,” in which they argued for the development of a new concept for approaching safe road design. Since this publication, self-explaining roads (SER) became one of the leading principles in road design worldwide. The underlying notion is that roads should be designed in such a way that road users immediately know how to behave and what to expect on these roads. In other words, the environment should be designed such that it elicits adequate and safe behavior. The present paper describes in detail the theoretical basis for the idea of SER and explains why this has such a large effect on human behavior. It is argued that the notion is firmly rooted in the theoretical framework of statistical learning, subjective road categorization and the associated expectations. The paper illustrates some successful implementation and describes recent developments worldwide.

Distal radius fractures (DRFs) are one of the most common major fractures. Despite their frequency, the tradeoffs in different outcomes after casting or surgery for closed extraarticular DRFs in older adults are unknown.(1) For adults older than 60 years with closed extraarticular DRFs, what are the tradeoffs in outcomes for choosing casting versus surgery? (2) In what settings would surgery be preferred over casting?This is a secondary analysis of data from the Wrist and Radius Injury Surgical Trial (WRIST), a randomized, multicenter clinical trial that enrolled patients from April 10, 2012 to December 31, 2016. For WRIST, researchers recruited patients older than 60 years who sustained closed extraarticular distal radius fractures from 24 sites in the United States, Canada, and Singapore. We conducted a secondary analysis using data from WRIST, which had longitudinal data from a robust collection of covariates for patients who underwent surgery and casting. Among the 296 patients recruited in the WRIST study, 59% (174) of patients (mean age 71 ± 9 years) with complete sociodemographic data and 12-month follow-up for each primary outcome were included in the main analysis. More patients underwent surgery than casting (72% [126 of 174] versus 28% [48 of 174]). Most sociodemographic variables were similar between the surgery and casting groups, except for age and volar tilt. The surgical cohort was composed of patients randomized to external fixation, closed reduction percutaneous pinning, or volar locking plate internal fixation. The casting cohort consisted of patients who elected to be treated with closed reduction and casting. A tree-based reinforcement statistical learning method was used to determine the best treatment, either surgery or casting, to maximize functional and esthetic outcomes while minimizing pain. Tree-based reinforcement learning is a statistical learning method to build an unsupervised decision tree within a causal inference framework that will identify useful variables and their cutoff values to tailor treatment assignment accordingly to achieve the best health outcome desired. The primary outcome was minimization of pain (12-month Michigan Hand Outcomes Questionnaire pain subdomain score), maximization of grip strength, total ROM (supination and wrist arc of motion), and esthetics (12-month Michigan Hand Outcomes Questionnaire esthetics subdomain score).Casting was the best treatment to reduce pain and maximize esthetics, whereas surgery maximized grip strength and ROM. When the patient favored gaining ROM over pain reduction (more than 80:20), surgery was the preferred treatment. When the patient prioritized the importance of grip strength over pain reduction (more than 70:30), surgery was also the preferred treatment.There are tradeoffs in outcomes after treating patients older than 60 years with closed extraarticular distal radius fractures with casting or surgery. When patients are attempting to balance minimizing pain and improving functional outcomes, unless they desire maximal functional recovery, casting may be the better treatment. Surgery may be beneficial if patients want to regain as much grip strength and ROM as possible, even with the possibility of having residual pain. These findings can be referenced for more concrete preoperative counseling and patient expectation management before treatment selection.Level III, therapeutic study.

A training image free, high-order sequential simulation method is proposed herein, which is based on the efficient inference of high-order spatial statistics from the available sample data. A statistical learning framework in kernel space is adopted to develop the proposed simulation method. Specifically, a new concept of aggregated kernel statistics is proposed to enable sparse data learning. The conditioning data in the proposed high-order sequential simulation method appear as data events corresponding to the attribute values associated with the so-called spatial templates of various geometric configurations. The replicates of the data events act as the training data in the learning framework for inference of the conditional probability distribution and generation of simulated values. These replicates are mapped into spatial Legendre moment kernel spaces, and the kernel statistics are computed thereafter, encapsulating the high-order spatial statistics from the available data. To utilize the incomplete information from the replicates, which partially match the spatial template of a given data event, the aggregated kernel statistics combine the ensemble of the elements in different kernel subspaces for statistical inference, embedding the high-order spatial statistics of the replicates associated with various spatial templates into the same kernel subspace. The aggregated kernel statistics are incorporated into a learning algorithm to obtain the target probability distribution in the underlying random field, while preserving in the simulations the high-order spatial statistics from the available data. The proposed method is tested using a synthetic dataset, showing the reproduction of the high-order spatial statistics of the sample data. The comparison with the corresponding high-order simulation method using TIs emphasizes the generalization capacity of the proposed method for sparse data learning.

Considering the escalating rates of exhaustion of non-renewable energy resources, coupled with the harmful environmental side effects of harnessing them (e.g. damage to public health via air pollut...

This study explores online insurance ventures by customers’ behavioral profiles from data mining and visualization. First, we employ a simple decision-tree statistical learning method on unique hand-collected and processed data in Taiwan. This method considers first-time online insurance subscribers as new ones without a proper marketing connection after six months. Second, using advanced clustering technique and decision tree statistical learning on first-time purchasing customers, we find they repurchase online travel insurance for different purposes varying periods. Finally, we get robust results engaging different segmentations of customer data. In these ways, we enable marketing strategies to work with generating decision rules.

In a highly competitive and liberalized energy market, where the retail of electricity is open to many potential companies, it is essential to have tools that help make decisions and guide the design of marketing strategies. In this sense, it is essential for retailers to know the behavior of their customers to correctly define their commercial strategies. One of the most commonly used methods for this is the characterization of their consumption profiles. Fortunately, for regulatory reasons, in some countries, the monthly electricity demand of each customer is openly available to any competitor. This paper explores whether this information, especially the economic sector and geographic location of a client, is useful for determining the client’s demand profile. Specifically, data on electricity demand in Spain from more than 27 million users and for a period of 3 years are analyzed. For this purpose, the electricity consumption of every client is grouped by month and normalized. The resulting demand profiles are later clustered according to different criteria. The main finding of the research is that the combined information on economic activity and location definitely enables prediction of the demand profile. Additionally, profile quality metrics are defined and obtained for the entire dataset. The resulting profiles have a mean dispersion of 10% and a confidence interval of ±17%. To clarify the use of these metrics, several examples are detailed, showing how this profile information can be used to improve the marketing decision-making process for electricity retailers.

Melt pool temperature contains abundant information on metallurgical and mechanical aspects of products produced by additive manufacturing. Forecasting melt pool temperature profile during a process can help in reducing microstructural porosity and residual stresses. Although analytical and numerical models were reported, the performance of these are questionable when applied in real-time. Hence, we developed data-driven models to address this challenge, for continuous forecasting layer-wise melt pool temperature using a hybrid deep learning technique. The melt pool temperature forecasting by the proposed CNN-LSTM model is found to be better than other benchmark models in terms of accuracy and efficiency. The model results have shown that combining CNN and LSTM networks can extract the spatial and temporal information from the melt pool temperature data. Further, the proposed model results are compared with existing statistical and machine learning models. The performance measures of the proposed CNN-LSTM model indicate a greater potential for in-situ monitoring of additive manufacturing process.

The autoencoder concept has fostered the reinterpretation and the design of modern communication systems. It consists of an encoder, a channel and a decoder block that modify their internal neural structure in an end-to-end learning fashion. However, the current approach to train an autoencoder relies on the use of the cross-entropy loss function. This approach can be prone to overfitting issues and often fails to learn an optimal system and signal representation (code). In addition, less is known about the autoencoder ability to design channel capacity-approaching codes, i.e., codes that maximize the input-output mutual information under a certain power constraint. The task being even more formidable for an unknown channel for which the capacity is unknown and therefore it has to be learnt. In this paper, we address the challenge of designing capacity-approaching codes by incorporating the presence of the communication channel into a novel loss function for the autoencoder training. In particular, we exploit the mutual information between the transmitted and received signals as a regularization term in the cross-entropy loss function, with the aim of controlling the amount of information stored. By jointly maximizing the mutual information and minimizing the cross-entropy, we propose a theoretical approach that a) computes an estimate of the channel capacity and b) constructs an optimal coded signal approaching it. Theoretical considerations are made on the choice of the cost function and the ability of the proposed architecture to mitigate the overfitting problem. Simulation results offer an initial evidence of the potentiality of the proposed method.

Given the growing popularity of nonprobability samples as a cost- and time-efficient alternative to probability sampling, a variety of adjustment approaches have been proposed to correct for self-selection bias in nonrandom samples. Popular methods such as inverse propensity-score weighting (IPSW) and propensity-score (PS) adjustment by subclassification (PSAS) utilize a probability sample as a reference to estimate pseudo-weights for the nonprobability sample based on PSs. A recent contribution, kernel weighting (KW), has been shown to be able to improve over IPSW and PSAS with respect to mean squared error. However, the effectiveness of these methods for reducing bias critically depends on the ability of the underlying propensity model to reflect the true (self-)selection process, which is a challenging task with parametric regression. In this study, we propose a set of pseudo-weights construction methods, KW-ML, utilizing both machine learning (ML) methods (to estimate PSs) and KW (to construct pseudo-weights based on the ML-estimated PSs), which provides added flexibility over logistic regression-based methods. We compare the proposed KW-ML pseudo-weights that are based on model-based recursive partitioning, conditional random forests, gradient tree boosting, and model-based boosting, with KW pseudo-weights based on parametric logistic regression in population mean estimation via simulations and a real data example. Our results indicate that particularly boosting methods represent promising alternatives to logistic regression and result in KW estimates with lower bias in a variety of settings, without increasing variance.

Enhanced Conversational Recast (ECR) is an input-based grammatical intervention approach developed from research on statistical learning. Recent research reported evidence demonstrating the efficacy of ECR on the learning of grammatically obligatory morphemes in English-speaking preschool children with developmental language disorder (DLD). This single-case experimental design study, which adopted a within-participant design with single baseline and control item, investigated the efficacy of ECR in promoting the learning of aspect markers in four Cantonese-speaking typically-developing preschool children. Two children demonstrated positive outcomes with the progressive aspect marker ‘ gan2’ given 12 ECR training sessions within a mean dosage of 288. One of these children demonstrated statistically significant gains in the percentage of correct use in the probes. The lack of positive outcomes in the other two children on the earlier developing aspect marker ‘ zo2’ and limitations of the study were discussed. With early evidence established in the typically developing children in this study, future research on Cantonese speaking children with DLD can be considered.

Abstract. The predictive accuracy of personality-criterion regression models may be improved with statistical learning (SL) techniques. This study introduced a novel SL technique, BISCUIT (Best Items Scale that is Cross-validated, Unit-weighted, Informative, and Transparent). The predictive accuracy and parsimony of BISCUIT were compared with three established SL techniques (the lasso, elastic net, and random forest) and regression using two sets of scales, for five criteria, across five levels of data missingness. BISCUIT’s predictive accuracy was competitive with other SL techniques at higher levels of data missingness. BISCUIT most frequently produced the most parsimonious SL model. In terms of predictive accuracy, the elastic net and lasso dominated other techniques in the complete data condition and in conditions with up to 50% data missingness. Regression using 27 narrow traits was an intermediate choice for predictive accuracy. For most criteria and levels of data missingness, regression using the Big Five had the worst predictive accuracy. Overall, loss in predictive accuracy due to data missingness was modest, even at 90% data missingness. Findings suggest that personality researchers should consider incorporating planned data missingness and SL techniques into their designs and analyses.

We provide an overview of how to apply statistical learning methods to directly track the role of alloying additions in the multiscale properties of alloys. This leads to a mapping process analogous to the Periodic Table where the resulting visualization scheme exhibits the grouping and proximity of elements based on their impact on the properties of alloys. Unlike the conventional Periodic Table of elements, the distance between neighboring elements in our Alloy Periodic Table uncovers relationships in a complex high-dimensional information space that would not be easily seen otherwise. We embed this machine learning approach with an epistemic uncertainty assessment between data. We provide examples of how this data-driven exploratory platform appears to capture the alloy chemistry of known engineering alloys as well as to provide potential new directions for tuning chemistry for enhanced performance, consistent with accepted mechanistic paradigms governing alloy mechanical properties.

With the advent of the era of big data, privacy issues have been becoming a hot topic in public. Local differential privacy (LDP) is a state-of-the-art privacy preservation technique that allows to perform big data analysis (e.g., statistical estimation, statistical learning, and data mining) while guaranteeing each individual participant’s privacy. In this paper, we present a comprehensive survey of LDP. We first give an overview on the fundamental knowledge of LDP and its frameworks. We then introduce the mainstream privatization mechanisms and methods in detail from the perspective of frequency oracle and give insights into recent studied on private basic statistical estimation (e.g., frequency estimation and mean estimation) and complex statistical estimation (e.g., multivariate distribution estimation and private estimation over complex data) under LDP. Furthermore, we present current research circumstances on LDP including the private statistical learning/inferencing, private statistical data analysis, privacy amplification techniques for LDP, and some application fields under LDP. Finally, we identify future research directions and open challenges for LDP. This survey can serve as a good reference source for the research of LDP to deal with various privacy-related scenarios to be encountered in practice.

Published online: 31 August 2020 Despite theoretical debate on the extent to which statistical learning is incidental or modulated by explicit instructions and conscious awareness of the content of statistical learning, no study has ever investigated the metacognition of statistical learning. We used an artificial language-learning paradigm and a segmentation task that required splitting a continuous stream of syllables into discrete recurrent constituents. During this task, statistical learning potentially produces knowledge of discrete constituents as well as about statistical regularities that are embodied in familiarization input. We measured metacognitive sensitivity and efficiency (using hierarchical Bayesian modelling to estimate metacognitive sensitivity and efficiency) to probe the role of conscious awareness in recognition of constituents extracted from the familiarization input and recognition of novel constituents embodying the same statistical regularities as these extracted constituents. Novel constituents are conceptualized to represent recognition of statistical structure rather than recognition of items retrieved from memory as whole constituents. We found that participants are equally sensitive to both types of learning products, yet subject them to varying degrees of conscious processing during the postfamiliarization recognition test. The data point to the contribution of conscious awareness to at least some types of statistical learning content This study was supported by the European Commission via H2020 Marie Skłodowska-Curie Actions (Grant Number DLV-792331), and Spanish Ministerio de Economía y Competitividad (Grant Number RTI2018-098317-B-I00). The research institute is supported by the Spanish Ministry of Economy and Competitiveness through the “Severo Ochoa” Programme for Centres/ Units of Excellence in Research and Development (SEV-2015-490).

When repeatedly selected features have predictive value, an observer can learn to prioritize them. However, relatively little is known about the mechanisms underlying this persistent statistical learning. In two experiments, we investigated the boundary conditions of statistical learning. Each task included a training phase where targets appeared more frequently in one of two target colors, followed by a test phase where targets appeared equally in both colors. A posttest survey probed awareness of target color probability differences. Experiment 1 tested whether statistical learning requires the predictive feature to be inherently bound to the target. Participants searched for a horizontal or vertical line among diagonal distractors and reported its length (long or short). In the bound condition, targets and distractors were colored, whereas targets were presented in white font and surrounded by colored boxes in the unbound condition. Experiment 2 tested whether reducing task difficulty by simplifying the judgment (horizontal or vertical) would eliminate statistical learning. The results suggested that statistical learning is robust to manipulations of binding, but is attenuated when task difficulty is reduced. Finally, we found evidence that explicit awareness may contribute to statistical learning, but its effects are small and require large sample sizes for adequate detection. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

PM10 can be stated as a particulate matter smaller than 10 micrometer and it can be suspended in the air. The incremental concentration of PM10 affects both human and environment drastically. In this study, an air quality assessment by exhibiting the potential relationships among the secondary indicators and PM10 has been focused. For the analyses, statistical learning-based regularization procedures such as Ridge, the Lasso and Elastic-net algorithms have been practiced. In particular, use of Elastic-net algorithm in predicting PM10 concentration includes a novelty. As a result of the computational studies, it has been recorded that all the models showed high accuracy capacities. However, the elastic-net model outperforms the other models both accuracy and robustness (stability). Considering the error measurements (MSE and MAPE), the best numerical results have been provided by the Elastic-net model. Use of machine learning-based regularization algorithms in environmental problems can provide accurate model structures as well as generality and transparency.

Drug-induced long QT syndrome (diLQTS) can lead to seemingly healthy patients experiencing cardiac arrest, specifically Torsades de Pointes (TdP). A goal of this study is to identify genetic risk m...

Random forests (Breiman, 2001, Machine Learning 45: 5–32) is a statistical- or machine-learning algorithm for prediction. In this article, we introduce a corresponding new command, rforest. We overview the random forest algorithm and illustrate its use with two examples: The first example is a classification problem that predicts whether a credit card holder will default on his or her debt. The second example is a regression problem that predicts the logscaled number of shares of online news articles. We conclude with a discussion that summarizes key points demonstrated in the examples.

Background E-commerce services provide online shopping sites and mobile applications for small and medium sellers. To provide more efficient buying and selling experiences, a machine learning system can be applied to predict the optimal organization and display of products that maximize the chance of bringing useful information to user that facilitate the online purchases. Therefore, it is important to understand the relevant products for a gender to facilitate the online purchases. In this work, we present a statistical machine learning (ML)-based gender prediction system to predict the gender “male” or “female” from transactional E-commerce data. We introduce different sets of learning algorithms including unique IDs decomposition, context window-based history generation, and extract identical hierarchy from training set to address the gender prediction classification system from online transnational data. Results The experiment result shows that different feature augmentation approaches as well as different term or feature weighting approaches can significantly enhance the performance of statistical machine learning-based gender prediction system. Conclusions This work presents a ML-based implementational approach to address E-commerce-based gender prediction system. Different session augmentation approaches with support vector machines (SVMs) classifier can significantly improve the performance of gender prediction system.