Search

This tutorial paper provides a general overview of symbolic regression (SR) with specific focus on standards of interpretability. We posit that interpretable modeling, although its definition is still disputed in the literature, is a practical way to support the evaluation of successful information fusion. In order to convey the benefits of SR as a modeling technique, we demonstrate an application within the field of health and nutrition using publicly available National Health and Nutrition Examination Survey (NHANES) data from the Centers for Disease Control and Prevention (CDC), fusing together anthropometric markers into a simple mathematical expression to estimate body fat percentage. We discuss the advantages and challenges associated with SR modeling and provide qualitative and quantitative analyses of the learned models. • Existing approaches for symbolic regression are presented and discussed. • Model interpretability standards are explored in the context of symbolic modeling. • An application of symbolic regression is demonstrated in the human health domain. [ABSTRACT FROM AUTHOR]

The analysis of climate data has relied heavily on hypothesis-driven statistical methods, while projections of future climate are based primarily on physics-based computational models. However, in recent years a wealth of new datasets has become available. Therefore, we take a more data-centric approach and propose a unified framework for studying climate, with an aim toward characterizing observed phenomena as well as discovering new knowledge in climate science. Specifically, we posit that complex networks are well suited for both descriptive analysis and predictive modeling tasks. We show that the structural properties of 'climate networks' have useful interpretation within the domain. Further, we extract clusters from these networks and demonstrate their predictive power as climate indices. Our experimental results establish that the network clusters are statistically significantly better predictors than clusters derived using a more traditional clustering approach. Using complex networks as data representation thus enables the unique opportunity for descriptive and predictive modeling to inform each other. © 2011 Wiley Periodicals, Inc. Statistical Analysis and Data Mining 4: 497-511, 2011 [ABSTRACT FROM AUTHOR]

LPmade is a complete cross-platform software solution for multi-core link prediction and related tasks and analysis. Its first principal contribution is a scalable network library supporting high-performance implementations of the most commonly employed unsupervised link prediction methods. Link prediction in longitudinal data requires a sophisticated and disciplined procedure for correct results and fair evaluation, so the second principle contribution of LPmade is a sophisticated GNU make architecture that completely automates link prediction, prediction evaluation, and network analysis. Finally, LPmade streamlines and automates the procedure for creating multivariate supervised link prediction models with a version of WEKA modified to operate effectively on extremely large data sets. With mere minutes of manual work, one may start with a raw stream of records representing a network and progress through hundreds of steps to generate plots, gigabytes or terabytes of output, and actionable or publishable results. [ABSTRACT FROM AUTHOR]

The availability of electronic health care records is unlocking the potential for novel studies on understanding and modeling disease co-morbidities based on both phenotypic and genetic data. Moreover, the insurgence of increasingly reliable phenotypic data can aid further studies on investigating the potential genetic links among diseases. The goal is to create a feedback loop where computational tools guide and facilitate research, leading to improved biological knowledge and clinical standards, which in turn should generate better data. We build and analyze disease interaction networks based on data collected from previous genetic association studies and patient medical histories, spanning over 12 years, acquired from a regional hospital. By exploring both individual and combined interactions among these two levels of disease data, we provide novel insight into the interplay between genetics and clinical realities. Our results show a marked difference between the well defined structure of genetic relationships and the chaotic co-morbidity network, but also highlight clear interdependencies. We demonstrate the power of these dependencies by proposing a novel multi-relational link prediction method, showing that disease co-morbidity can enhance our currently limited knowledge of genetic association. Furthermore, our methods for integrated networks of diverse data are widely applicable and can provide novel advances for many problems in systems biology and personalized medicine. [ABSTRACT FROM AUTHOR]

LPmade is a complete cross-platform software solution for multi-core link prediction and related tasks and analysis. Its first principal contribution is a scalable network library supporting high-performance implementations of the most commonly employed unsupervised link prediction methods. Link prediction in longitudinal data requires a sophisticated and disciplined procedure for correct results and fair evaluation, so the second principle contribution of LPmade is a sophisticated GNU make architecture that completely automates link prediction, prediction evaluation, and network analysis. Finally, LPmade streamlines and automates the procedure for creating multivariate supervised link prediction models with a version of WEKA modified to operate effectively on extremely large data sets. With mere minutes of manual work, one may start with a raw stream of records representing a network and progress through hundreds of steps to generate plots, gigabytes or terabytes of output, and actionable or publishable results. [ABSTRACT FROM AUTHOR]

Abstract: We compare and evaluate different metrics for community structure in networks. In this context we also discuss a simple approach to community detection, and show that it performs as well as other methods, but at lower computational complexity. [Copyright &y& Elsevier]

This paper presents Model Monitor (M²), a Java toolkit for robustly evaluating machine learning algorithms in the presence of changing data distributions. M² provides a simple and intuitive framework in which users can evaluate classifiers under hypothesized shifts in distribution and therefore determine the best model (or models) for their data under a number of potential scenarios. Additionally, M² is fully integrated with the WEKA machine learning environment, so that a variety of commodity classifiers can be used if desired. [ABSTRACT FROM AUTHOR]

Abstract: Enriching speech recognition output with sentence boundaries improves its human readability and enables further processing by downstream language processing modules. We have constructed a hidden Markov model (HMM) system to detect sentence boundaries that uses both prosodic and textual information. Since there are more nonsentence boundaries than sentence boundaries in the data, the prosody model, which is implemented as a decision tree classifier, must be constructed to effectively learn from the imbalanced data distribution. To address this problem, we investigate a variety of sampling approaches and a bagging scheme. A pilot study was carried out to select methods to apply to the full NIST sentence boundary evaluation task across two corpora (conversational telephone speech and broadcast news speech), using both human transcriptions and recognition output. In the pilot study, when classification error rate is the performance measure, using the original training set achieves the best performance among the sampling methods, and an ensemble of multiple classifiers from different downsampled training sets achieves slightly poorer performance, but has the potential to reduce computational effort. However, when performance is measured using receiver operating characteristics (ROC) or area under the curve (AUC), then the sampling approaches outperform the original training set. This observation is important if the sentence boundary detection output is used by downstream language processing modules. Bagging was found to significantly improve system performance for each of the sampling methods. The gain from these methods may be diminished when the prosody model is combined with the language model, which is a strong knowledge source for the sentence detection task. The patterns found in the pilot study were replicated in the full NIST evaluation task. The conclusions may be dependent on the task, the classifiers, and the knowledge combination approach. [Copyright &y& Elsevier]

Bagging forms a committee of classifiers by bootstrap aggregation of training sets from a pool of training data. A simple alternative to bagging is to partition the data into disjoint subsets. Experiments with decision tree and neural network classifiers on various datasets show that, given the same size partitions and bags, disjoint partitions result in performance equivalent to, or better than, bootstrap aggregates (bags). Many applications (e.g., protein structure prediction) involve use of datasets that are too large to handle in the memory of the typical computer. Hence, bagging with samples the size of the data is impractical. Our results indicate that, in such applications, the simple approach of creating a committee of n classifiers from disjoint partitions each of size 1/n (which will be memory resident during learning) in a distributed way results in a classifier which has a bagging-like performance gain. The use of distributed disjoint partitions in learning is significantly less complex and faster than bagging. [Copyright &y& Elsevier]

The article discusses the highlights of the Conference on Intelligent Data Understanding held at the Computer History Museum in Mountain View, California on October 5-6, 2010. Topics included the implementation of the methods attained in data mining and machine learning on issues dealing with earth sciences, space sciences and systems health management. Problems dealing with changes in the climate and environment, astronomical data flux and safety in aviation were also tackled.

People are looking for complementary contexts, such as team members of complementary skills for project team building and/or reading materials of complementary knowledge for effective student learning, to make their behaviors more likely to be successful. Complementarity has been revealed by behavioral sciences as one of the most important factors in decision making. Existing computational models that learn low-dimensional context representations from behavior data have poor scalability and recent network embedding methods only focus on preserving the similarity between the contexts. In this work, we formulate a behavior entry as a set of context items and propose a novel representation learning method, Multi-type Itemset Embedding, to learn the context representations preserving the itemset structures. We propose a measurement of complementarity between context items in the embedding space. Experiments demonstrate both effectiveness and efficiency of the proposed method over the state-of-the-art methods on behavior prediction and context recommendation. We discover that the complementary contexts and similar contexts are significantly different in human behaviors. [ABSTRACT FROM AUTHOR]

We consider multi-label crowdsourcing learning in two scenarios. In the first scenario, we aim at inferring instances' groundtruth given the crowds' annotations. We propose two approaches NAM/RAM (Neighborhood/Relevance Aware Multi-label crowdsourcing) modeling the crowds' expertise and label correlations from different perspectives. Extended from single-label crowdsourcing methods, NAM models the crowds' expertise on individual labels, but based on the idea that for rational workers, their annotations for instances similar in the feature space should also be similar, NAM utilizes information from the feature space and incorporates the local influence of neighborhoods' annotations. Noting that the crowds tend to act in an effort-saving manner while labeling multiple labels, i.e., rather than carefully annotating every proper label, they would prefer scanning and tagging a few most relevant labels, RAM models the crowds' expertise as their ability to distinguish the relevance between label pairs. In the second scenario, we care about cost-efficient crowdsourcing where the labeling and learning process are conducted in tandem. We extend NAM/RAM to the active paradigm and propose instance, label, and worker selection criteria such that the labeling cost is significantly saved compared to passive learning without labeling control. The proposals' effectiveness are validated on simulated and real data. [ABSTRACT FROM AUTHOR]

Many leaders today do not rise through the ranks but are recruited directly out of graduate programs into leadership positions. We use a quasi-experiment and instrumental-variable regression to understand the link between students' graduate school social networks and placement into leadership positions of varying levels of authority. Our data measure students' personal characteristics and academic performance, as well as their social network information drawn from 4.5 million email correspondences among hundreds of students who were placed directly into leadership positions. After controlling for students' personal characteristics, work experience, and academic performance, we find that students' social networks strongly predict placement into leadership positions. For males, the higher a male student's centrality in the school-wide network, the higher his leadershipjob placement will be. Men with network centrality in the top quartile have an expected job placement level that is 1.5 times greater than men in the bottom quartile of centrality. While centrality also predicts women's placement, high-placing women students have one thing more: an inner circle of predominantly female contacts who are connected to many nonoverlapping third-party contacts. Women with a network centrality in the top quartile and a female-dominated inner circle have an expected job placement level that is 2.5 times greater than women with low centrality and a male-dominated inner circle. Women who have networks that resemble those of high-placing men are lowplacing, despite having leadership qualifications comparable to high-placing women. [ABSTRACT FROM AUTHOR]

The task of quantification consists in providing an aggregate estimation (e.g., the class distribution in a classification problem) for unseen test sets, applying a model that is trained using a training set with a different data distribution. Several real-world applications demand this kind of method that does not require predictions for individual examples and just focuses on obtaining accurate estimates at an aggregate level. During the past few years, several quantification methods have been proposed from different perspectives and with different goals. This article presents a unified review of the main approaches with the aim of serving as an introductory tutorial for newcomers in the field. [ABSTRACT FROM AUTHOR]

Faced with unsustainable costs and enormous amounts of under-utilized data, health care needs more efficient practices, research, and tools to harness the full benefits of personal health and healthcare-related data. Imagine visiting your physician's office with a list of concerns and questions. What if you could walk out the office with a personalized assessment of your health? What if you could have personalized disease management and wellness plan? These are the goals and vision of the work discussed in this paper. The timing is right for such a research direction--given the changes in health care, reimbursement, reform, meaningful use of electronic health care data, and patient-centered outcome mandate. We present the foundations of work that takes a Big Data driven approach towards personalized healthcare, and demonstrate its applicability to patient-centered outcomes, meaningful use, and reducing re-admission rates. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses various reports within the issue on topics including analyzing multidimensional text databases with micro-text clusters, discovering dynamic dipoles in climate data, and discovering strongly nonlinear dynamics based on climatic time series.

The self-supervised learning (SSL) paradigm is an essential exploration area, which tries to eliminate the need for expensive data labeling. Despite the great success of SSL methods in computer vision and natural language processing, most of them employ contrastive learning objectives that require negative samples, which are hard to define. This becomes even more challenging in the case of graphs and is a bottleneck for achieving robust representations. To overcome such limitations, we propose a framework for self-supervised graph representation learning — Graph Barlow Twins , which utilizes a cross-correlation-based loss function instead of negative samples. Moreover, it does not rely on non-symmetric neural network architectures — in contrast to state-of-the-art self-supervised graph representation learning method BGRL. We show that our method achieves as competitive results as the best self-supervised methods and fully supervised ones while requiring fewer hyperparameters and substantially shorter computation time (ca. 30 times faster than BGRL). [ABSTRACT FROM AUTHOR]

The prevalence of wearable sensors (e.g., smart wristband) is creating unprecedented opportunities to not only inform health and wellness states of individuals, but also assess and infer personal attributes, including demographic and personality attributes. However, the data captured from wearables, such as heart rate or number of steps, present two key challenges: (1) the time series is often of variable length and incomplete due to different data collection periods (e.g., wearing behavior varies by person); and (2) there is inter-individual variability to external factors like stress and environment. This article addresses these challenges and brings us closer to the potential of personalized insights about an individual, taking the leap from quantified self to qualified self. Specifically, HeartSpace proposed in this article learns embedding of the time-series data with variable length and missing values via the integration of a time-series encoding module and a pattern aggregation network. Additionally, HeartSpace implements a Siamese-triplet network to optimize representations by jointly capturing intra- and inter-series correlations during the embedding learning process. The empirical evaluation over two different real-world data presents significant performance gains over state-of-the-art baselines in a variety of applications, including user identification, personality prediction, demographics inference, job performance prediction, and sleep duration estimation. [ABSTRACT FROM AUTHOR]

Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommendation systems. In recent years, reinforcement learning (RL) based solutions for knowledge graphs have been demonstrated to be more interpretable and explainable than other deep learning models. However, the current solutions still struggle with performance issues due to incomplete state representations and large action spaces for the RL agent. We address these problems by developing HRRL (Heterogeneous Relational reasoning with Reinforcement Learning), a type-enhanced RL agent that utilizes the local heterogeneous neighborhood information for efficient path-based reasoning over knowledge graphs. HRRL improves the state representation using a graph neural network (GNN) for encoding the neighborhood information and utilizes entity type information for pruning the action space. Extensive experiments on real-world datasets show that HRRL outperforms state-of-the-art RL methods and discovers more novel paths during the training procedure, demonstrating the explorative power of our method. • Proposing a method to address the multi-hop reasoning problem. • Improving the choice of the action using the heterogeneous context. • Leveraging the neighborhood context for improving the reasoning precision. • Comprehensive evaluation of our model against state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Background Febrile neutropenia (FN) is an early indicator of infection in oncology patients post-chemotherapy. We aimed to determine clinical predictors of septic shock and/or bacteremia in pediatric cancer patients experiencing FN and to create a model that classifies patients as low-risk for these outcomes. Methods This is a retrospective analysis with clinical data of a cohort of pediatric oncology patients admitted during July 2015 to September 2017 with FN. One FN episode per patient was randomly selected. Statistical analyses include distribution analysis, hypothesis testing, and multivariate logistic regression to determine clinical feature association with outcomes. Results A total of 865 episodes of FN occurred in 429 subjects. In the 404 sampled episodes that were analyzed, 20.8% experienced outcomes of septic shock and/or bacteremia. Gram-negative bacteria count for 70% of bacteremias. Features with statistically significant influence in predicting these outcomes were hematological malignancy (P <.001), cancer relapse (P =.011), platelet count (P =.004), and age (P =.023). The multivariate logistic regression model achieves AUROC = 0.66 (95% CI 0.56–0.76). The optimal classification threshold achieves sensitivity = 0.96, specificity = 0.33, PPV = 0.40, and NPV = 0.95. Conclusions This model, based on simple clinical variables, can be used to identify patients at low-risk of septic shock and/or bacteremia. The model's NPV of 95% satisfies the priority to avoid discharging patients at high-risk for adverse infection outcomes. The model will require further validation on a prospective population. [ABSTRACT FROM AUTHOR]

Objectives: The impact and risk of SARS-CoV-2 transmission from asymptomatic and presymptomatic hosts remains an open question. This study measured the secondary attack rates (SARs) and relative risk (RR) of SARS-CoV-2 transmission from asymptomatic and presymptomatic index cases as compared with symptomatic index cases. Methods: We used COVID-19 test results, daily health check reports, and contact tracing data to measure SARs and corresponding RRs among close contacts of index cases in a cohort of 12 960 young adults at the University of Notre Dame in Indiana for 103 days, from August 10 to November 20, 2020. Further analysis included Fisher exact tests to determine the association between symptoms and COVID-19 infection and z tests to determine statistical differences between SARs. Results: Asymptomatic rates of transmission of SARS-CoV-2 were higher (SAR = 0.19; 95% CI, 0.14-0.24) than was estimated in prior studies, producing an RR of 0.75 (95% CI, 0.54-1.07) when compared with symptomatic transmission. In addition, the transmission rate associated with presymptomatic cases (SAR = 0.25; 95% CI, 0.21-0.30) was approximately the same as that for symptomatic cases (SAR = 0.25; 95% CI, 0.19-0.31). Furthermore, different symptoms were associated with different transmission rates. Conclusions: Asymptomatic and presymptomatic hosts of SARS-CoV-2 are a risk for community spread of COVID-19, especially with new variants emerging. Moreover, typical symptom checks may easily miss people who are asymptomatic or presymptomatic but still infectious. Our study results may be used as a guide to analyze the spread of SARS-CoV-2 variants and help inform appropriate public health measures as they relate to asymptomatic and presymptomatic cases. [ABSTRACT FROM AUTHOR]

Terrorism is a major problem worldwide, causing thousands of fatalities and billions of dollars in damage every year. To address this threat, we propose a novel feature representation method and evaluate machine learning models that learn from localized news data in order to predict whether a terrorist attack will occur on a given calendar date and in a given state. The best model (a Random Forest aided by a novel variable-length moving average method) achieved area under the receiver operating characteristic (AUROC) of ≥ 0.667 (statistically significant w.r.t. random guessing with p ≤.0001) on four of the five states that were impacted most by terrorism between 2015 and 2018. These results demonstrate that treating terrorism as a set of independent events, rather than as a continuous process, is a fruitful approach—especially when historical events are sparse and dissimilar—and that large-scale news data contains information that is useful for terrorism prediction. Our analysis also suggests that predictive models should be localized (i.e., state models should be independently designed, trained, and evaluated) and that the characteristics of individual attacks (e.g., responsible group or weapon type) were not correlated with prediction success. These contributions provide a foundation for the use of machine learning in efforts against terrorism in the United States and beyond. [ABSTRACT FROM AUTHOR]

Social status, defined as the relative rank or position that an individual holds in a social hierarchy, is known to be among the most important motivating forces in social behaviors. In this paper, we consider the notion of status from the perspective of a position or title held by a person in an enterprise. We study the intersection of social status and social networks in an enterprise. We study whether enterprise communication logs can help reveal how social interactions and individual status manifest themselves in social networks. To that end, we use two enterprise datasets with three communication channels — voice call, short message, and email — to demonstrate the social-behavioral differences among individuals with different status. We have several interesting findings and based on these findings we also develop a model to predict social status. On the individual level, high-status individuals are more likely to be spanned as structural holes by linking to people in parts of the enterprise networks that are otherwise not well connected to one another. On the community level, the principle of homophily, social balance and clique theory generally indicate a “rich club” maintained by high-status individuals, in the sense that this community is much more connected, balanced and dense. Our model can predict social status of individuals with 93% accuracy. [ABSTRACT FROM AUTHOR]

Centrality of a node measures its relative importance within a network. There are a number of applications of centrality, including inferring the influence or success of an individual in a social network, and the resulting social network dynamics. While we can compute the centrality of any node in a given network snapshot, a number of applications are also interested in knowing the potential importance of an individual in the future. However, current centrality is not necessarily an effective predictor of future centrality. While there are different measures of centrality, we focus on degree centrality in this paper. We develop a method that reconciles preferential attachment and triadic closure to capture a node's prominence profile. We show that the proposed node prominence profile method is an effective predictor of degree centrality. Notably, our analysis reveals that individuals in the early stage of evolution display a distinctive and robust signature in degree centrality trend, adequately predicted by their prominence profile. We evaluate our work across four real-world social networks. Our findings have important implications for the applications that require prediction of a node's future degree centrality, as well as the study of social network dynamics. [ABSTRACT FROM AUTHOR]

Here we present a range-limited approach to centrality measures in both nonweighted and weighted directed complex networks. We introduce an efficient method that generates for every node and every edge its betweenness centrality based on shortest paths of lengths not longer than ℓ = 1…., L in the case of nonweighted networks, and for weighted networks the corresponding quantities based on minimum weight paths with path weights not larger than wℓ = ℓΔ, ℓ = 1,2…, L = R/Δ. These measures provide a systematic description on the positioning importance of a node (edge) with respect to its network neighborhoods one step out, two steps out, etc., up to and including the whole network. They are more informative than traditional centrality measures, as network transport typically happens on all length scales, from transport to nearest neighbors to the farthest reaches of the network. We show that range-limited centralities obey universal scaling laws for large nonweighted networks. As the computation of traditional centrality measures is costly, this scaling behavior can be exploited to efficiently estimate centralities of nodes and edges for all ranges, including the traditional ones. The scaling behavior can also be exploited to show that the ranking top list of nodes (edges) based on their range-limited centralities quickly freezes as a function of the range, and hence the diameter-range top list can be efficiently predicted. We also show how to estimate the typical largest node-to-node distance for a network of N nodes, exploiting the afore-mentioned scaling behavior. These observations were made on model networks and on a large social network inferred from cell-phone trace logs (∼5.5 x 106 nodes and ∼2.7 x 107 edges). Finally, we apply these concepts to efficiently detect the vulnerability backbone of a network (defined as the smallest percolating cluster of the highest betweenness nodes and edges) and illustrate the importance of weight-based centrality measures in weighted networks in detecting such backbones. [ABSTRACT FROM AUTHOR]

Background: Complexity and noise in expression quantitative trait loci (eQTL) studies make it difficult to distinguish potential regulatory relationships among the many interactions. The predominant method of identifying eQTLs finds associations that are significant at a genome-wide level. The vast number of statistical tests carried out on these data make false negatives very likely. Corrections for multiple testing error render genome-wide eQTL techniques unable to detect modest regulatory effects. We propose an alternative method to identify eQTLs that builds on traditional approaches. In contrast to genomewide techniques, our method determines the significance of an association between an expression trait and a locus with respect to the set of all associations to the expression trait. The use of this specific information facilitates identification of expression traits that have an expression profile that is characterized by a single exceptional association to a locus. Our approach identifies expression traits that have exceptional associations regardless of the genome-wide significance of those associations. This property facilitates the identification of possible false negatives for genome-wide significance. Further, our approach has the property of prioritizing expression traits that are affected by few strong associations. Expression traits identified by this method may warrant additional study because their expression level may be affected by targeting genes near a single locus. Results: We demonstrate our method by identifying eQTL hotspots in Plasmodium falciparum (malaria) and Saccharomyces cerevisiae (yeast). We demonstrate the prioritization of traits with few strong genetic effects through Gene Ontology (GO) analysis of Yeast. Our results are strongly consistent with results gathered using genome-wide methods and identify additional hotspots and eQTLs. Conclusions: New eQTLs and hotspots found with this method may represent regions of the genome or biological processes that are controlled through few relatively strong genetic interactions. These points of interest warrant experimental investigation. [ABSTRACT FROM AUTHOR]

Traditional classification algorithms can be limited in their performance on highly unbalanced data sets. A popular stream of work for countering the problem of class imbalance has been the application of a sundry of sampling strategies. In this correspondence, we focus on designing modifications to support vector machines (SVMs) to appropriately tackle the problem of class imbalance. We incorporate different "rebalance" heuristics in SVM modeling, including cost-sensitive learning, and over- and undersampling. These SVM-based strategies are compared with various state-of-the-art approaches on a variety of data sets by using various metrics, including C-mean, area under the receiver operating characteristic curve, F-measure, and area under the precision/recall curve. We show that we are able to surpass or match the previously known best algorithms on each data set. In particular, of the four SVM variations considered in this correspondence, (he novel granular SVMs-repetitive undersampling algorithm (GSVM-RU) is the best in terms of both effectiveness and efficiency. GSVM-RU is effective, as it can minimize the negative effect of information loss while maximizing the positive effect of data cleaning in the undersampling process. GSVM-RU is efficient by extracting much less support vectors arid, hence, greatly speeding up SVM prediction. [ABSTRACT FROM AUTHOR]

Web personalization, e.g., recommendation or relevance search, tailoring a service/product to accommodate specific online users, is becoming increasingly important. Inductive personalization aims to infer the relations between existing entities and unseen new ones, e.g., searching relevant authors for new papers or recommending new items to users. This problem, however, is challenging since most of recent studies focus on transductive problem for existing entities. In addition, despite some inductive learning approaches have been introduced recently, their performance is sub-optimal due to relatively simple and inflexible architectures for aggregating entity's content. To this end, we propose the inductive contextual personalization (ICP) framework through contextual relation learning. Specifically, we first formulate the pairwise relations between entities with a ranking optimization scheme that employs neural aggregator to fuse entity's heterogeneous contents. Next, we introduce a node embedding term to capture entity's contextual relations, as a smoothness constraint over the prior ranking objective. Finally, the gradient descent procedure with adaptive negative sampling is employed to learn the model parameters. The learned model is capable of inferring the relations between existing entities and inductive ones. Thorough experiments demonstrate that ICP outperforms numerous baseline methods for two different applications, i.e., relevant author search and new item recommendation. [ABSTRACT FROM AUTHOR]

As the global prevalence of childhood obesity continues to rise, researchers and clinicians have sought to develop more effective and personalized intervention techniques. In doing so, obesity interventions have expanded beyond the traditional context of nutrition to address several facets of a child's life, including their psychological state. While the consideration of psychological features has significantly advanced the view of obesity as a holistic condition, attempts to associate such features with outcomes of treatment have been inconclusive. We posit that such uncertainty may arise from the univariate manner in which features are evaluated, focusing on a particular aspect such as loneliness or insecurity, but failing to account for the impact of co-occurring psychological characteristics. Moreover, co-occurrence of psychological characteristics (both child and parent/guardian) have not been studied from the perspective of their relationship with nutritional intervention outcomes. To that end, this work looks to broaden the prevailing view: laying the foundation for the existence of complex interactions among psychological features. In collaboration with a non-profit nutritional clinic in Brazil, this paper demonstrates and models these interactions and their associations with the outcomes of a nutritional intervention. [ABSTRACT FROM AUTHOR]

Social networks influence health-related behavior, such as obesity and smoking. While researchers have studied social networks as a driver for diffusion of influences and behavior, it is less understood how the structure or topology of the network, in itself, impacts an individual's health behavior and wellness state. In this paper, we investigate whether the structure or topology of a social network offers additional insight and predictability on an individual's health and wellness. We develop a method called the Network-Driven health predictor (NetCARE) that leverages features representative of social network structure. Using a large longitudinal data set of students enrolled in the NetHealth study at the University of Notre Dame, we show that the NetCARE method improves the overall prediction performance over the baseline models—that use demographics and physical attributes—by 38%, 65%, 55%, and 54% for the wellness states—stress, happiness, positive attitude, and self-assessed health—considered in this paper. [ABSTRACT FROM AUTHOR]

Highlights • Health topic consumption is highly impacted by demographic features: gender, age and location. • Using demographic attributes allow us to model health interests with low RMSE of 0.3217. • Health interests can be revealed by consumption patterns without medical or search history. • Demographics are more predictive of health interests than socioeconomic and time features. Abstract To seek answers to health queries, we often find ourselves on a quest to assimilate information from varied online sources. This information search and fusion from different sources elicits user preferences, which can be driven by demographics, context, and socio-economic factors. To that end, we study these factors as part of health-information seeking behavior of users on a large health and wellness-based knowledge sharing online platform. We begin by identifying the topical interests of users from different content consumption sources. Using these topical preferences, we explore information consumption and health-seeking behavior across three contextual dimensions: user-based demographic attributes, time-related features, and community-based socioeconomic factors. We then study how these context signals can be used to explain specific user health topic preferences. Our findings suggest that linking demographic features to user profiles is more effective in explaining health preferences than other features. Our work demonstrates the value of using contextual factors to characterize and understand the content consumption of users seeking health and wellness information online. [ABSTRACT FROM AUTHOR]

Background: Hypoxia Inducible Factor 3 Alpha Subunit (HIF3A) DNA has been demonstrated to be associated with obesity in the methylation level, and it also has a Body Mass Index (BMI)-independent association with plasma alanine aminotransferase (ALT). However, the relation among obesity, plasma ALT, HIF3A polymorphism and methylation remains unclear. This study aims to identify the association between HIF3A polymorphism and plasma ALT, and further to determine whether the effect of HIF3A polymorphism on ALT could be modified by obesity or mediated by DNA methylation. Methods: The HIF3A rs3826795 polymorphism was genotyped in a case-control study including 2030 Chinese children aged 7-18 years (705 obese cases and 1325 non-obese controls). Furthermore, the HIF3A DNA methylation of the peripheral blood was measured in 110 severely obese children and 110 age- and gender-matched normal-weight controls. Results: There was no overall association between the HIF3A rs3826795 polymorphism and ALT. A significant interaction between obesity and rs3826795 in relation with ALT was found (Pinter = 0.042), with rs3826795 G-allele number elevating ALT significantly only in obese children (β′ = 0.075, P = 0.037), but not in non-obese children (β′ = -0.009, P = 0.741). Additionally, a mediation effect of HIF3A methylation was found in the association between the HIF3A rs3826795 polymorphism and ALT among obese children (β′ = 0.242, P = 0.014). Conclusion: This is the first study to report the interaction between obesity and HIF3A gene in relation with ALT, and also to reveal a mediation effect among the HIF3A polymorphism, methylation and ALT. This study provides new evidence to the function of HIF3A gene, which would be helpful for future risk assessment and personalized treatment of liver diseases. [ABSTRACT FROM AUTHOR]

Analysis of electroencephalogram (EEG) signal is crucial due to its non-stationary characteristics, which could lead the way to proper detection method for the treatment of patients with neurological abnormalities, especially for epilepsy. The performance of EEG-based epileptic seizure detection relies largely on the quality of selected features from an EEG data that characterize seizure activity. This paper presents a novel analysis method for detecting epileptic seizure from EEG signal using Improved Correlation-based Feature Selection method (ICFS) with Random Forest classifier (RF). The analysis involves, first applying ICFS to select the most prominent features from the time domain, frequency domain, and entropy based features. An ensemble of Random Forest (RF) classifiers is then learned on the selected set of features. The experimental results demonstrate that the proposed method shows better performance compared to the conventional Correlation-based method and also outperforms some other state-of-the-art methods of epileptic seizure detection using the same benchmark EEG dataset. [ABSTRACT FROM AUTHOR]

Background: Recent studies indicated that eating behaviors are under genetic influence, and the melanocortin 4 receptor (MC4R) gene polymorphisms can affect the total energy intake and the consumption of fat, protein and carbohydrates. Our study aims at investigating the association of the MC4R polymorphism with appetite and food intake among Chinese children. Methods: A family-based association study was conducted among 151 Chinese trios whose offsprings were overweight/obese children aged 9–15 years. The rs12970134 near MC4R was genotyped, and the Children Eating Behavior Questionnaire (CEBQ) and a self-designed questionnaire measuring food intake were performed. The FBAT and PBAT software packages were used. Results: The family-based association analysis showed that there was a significant association between rs12970134 and obesity (Z = 2.449, P = 0.014). After adjusting for age, gender and standardized BMI, rs12970134 was significantly associated with food responsiveness (FR) among children (β'b = 0.077, Pb = 0.028), and with satiety responsiveness (SR) in trios (P = -0.026). The polymorphism was associated with beverage intake (β'b = 0.331, Pb = 0.00016 in children; P = 0.043 in trios), but not significantly associated with vegetable, fruit or meat intake (P>0.050). We further found a significant mediation effect among the rs12970134, FR and beverage intake (b = 0.177, P = 0.047). Conclusions: Our study is the first to report that rs12970134 near MC4R was associated with appetite and beverage intake, and food responsiveness could mediate the effect of rs12970134 on beverage intake in overweight and obese Chinese children population. Further studies are needed to uncover the genetic basis for eating behaviors, which could lead to develop and implement effective interventional strategies early in life. [ABSTRACT FROM AUTHOR]

Representation learning on graphs has emerged as a powerful mechanism to automate feature vector generation for downstream machine learning tasks. The advances in representation on graphs have centered on both homogeneous and heterogeneous graphs, where the latter presenting the challenges associated with multi-typed nodes and/or edges. In this paper, we consider the additional challenge of evolving graphs. We ask the question of whether the advances in representation learning for static graphs can be leveraged for dynamic graphs and how? It is important to be able to incorporate those advances to maximize the utility and generalization of methods. To that end, we propose the Framework for Incremental Learning of Dynamic Networks Embedding (FILDNE), which can utilize any existing static representation learning method for learning node embeddings while keeping the computational costs low. FILDNE integrates the feature vectors computed using the standard methods over different timesteps into a single representation by developing a convex combination function and alignment mechanism. Experimental results on several downstream tasks, over seven real-world datasets, show that FILDNE is able to reduce memory (up to 6x) and computational time (up to 50x) costs while providing competitive quality measure gains (e.g., improvements up to 19 pp AUC on link prediction and up to 33 pp mAP on graph reconstruction) with respect to the contemporary methods for representation learning on dynamic graphs. [ABSTRACT FROM AUTHOR]

The article discusses the introduction of framework in the healthcare which will secure the confidential information communicated between the patient and his physician. It informs that the framework was structured to prevent data from the accession of unauthorized users. It further informs use of Secure Processing Architecture (SPA) and Anonymous Contribution Architecture (ACA) in the framework which will maintain the privacy and security of the data of patients.

Abstract: The field of dataset shift has received a growing amount of interest in the last few years. The fact that most real-world applications have to cope with some form of shift makes its study highly relevant. The literature on the topic is mostly scattered, and different authors use different names to refer to the same concepts, or use the same name for different concepts. With this work, we attempt to present a unifying framework through the review and comparison of some of the most important works in the literature. [Copyright &y& Elsevier]

Rapid climate change has wide-ranging implications for the Arctic region, including sea ice loss, increased geopolitical attention, and expanding economic activity resulting in a dramatic increase in shipping activity. As a result, the risk of harmful non-native marine species being introduced into this critical region will increase unless policy and management steps are implemented in response. Using data about shipping, ecoregions, and environmental conditions, we leverage network analysis and data mining techniques to assess, visualize, and project ballast water-mediated species introductions into the Arctic and dispersal of non-native species within the Arctic. We first identify high-risk connections between the Arctic and non-Arctic ports that could be sources of non-native species over 15 years (1997–2012) and observe the emergence of shipping hubs in the Arctic where the cumulative risk of non-native species introduction is increasing. We then consider how environmental conditions can constrain this Arctic introduction network for species with different physiological limits, thus providing a tool that will allow decision-makers to evaluate the relative risk of different shipping routes. Next, we focus on within-Arctic ballast-mediated species dispersal where we use higher-order network analysis to identify critical shipping routes that may facilitate species dispersal within the Arctic. The risk assessment and projection framework we propose could inform risk-based assessment and management of ship-borne invasive species in the Arctic. [ABSTRACT FROM AUTHOR]