Search

Background: The exponential growth of location-based social media (LBSM) data has ushered in novel prospects for investigating the urban food environment in health geography research. However, previous studies have primarily relied on word dictionaries with a limited number of food words and employed common-sense categorizations to determine the healthiness of those words. To enhance the analysis of the urban food environment using LBSM data, it is crucial to develop a more comprehensive list of food-related words. Within the context, this study delves into the exploration of expanding food-related words along with their associated energy densities. Methods: This study addresses the aforementioned research gap by introducing a novel methodology for expanding the food-related word dictionary and predicting energy densities. Seed words are generated from official and crowdsourced food composition databases, and new food words are discovered by clustering food words within the word embedding space using the Gaussian mixture model. Machine learning models are employed to predict the energy density classifications of these food words based on their feature vectors. To ensure a thorough exploration of the prediction problem, ten widely used machine learning models are evaluated. Results: The approach successfully expands the food-related word dictionary and accurately predicts food energy density (reaching 91.62%.). Through a comparison of the newly expanded dictionary with the initial seed words and an analysis of Yelp reviews in the city of Toronto, we observe significant improvements in identifying food words and gaining a deeper understanding of the food environment. Conclusions: This study proposes a novel method to expand food-related vocabulary and predict the food energy density based on machine learning and word embedding. This method makes a valuable contribution to building a more comprehensive list of food words that can be used in geography and public health studies by mining geotagged social media data. [ABSTRACT FROM AUTHOR]

We consider a robust optimization problem with continuous decision-dependent uncertainty (RO-CDDU), which has two significant features: an uncertainty set linearly dependent on continuous decision variables, and a convex piecewise-linear objective function. We prove that ROCDDU is strongly NP-hard in general and reformulate it into an equivalent mixed-integer nonlinear program (MINLP) with a decomposable structure to address the computational challenges. Such an MINLP model can be further transformed into a mixed-integer linear program (MILP) using extreme points of the dual polyhedron of the uncertainty set. We propose an alternating direction algorithm and a column generation algorithm for RO-CDDU. We model a robust demand response (DR) management problem in electricity markets as RO-CDDU, where electricity demand reduction from users is uncertain and depends on the DR planning decision. Extensive computational results demonstrate the promising performance of the proposed algorithms in both speed and solution quality. The results also shed light on how different magnitudes of decision-dependent uncertainty affect the DR decision. [ABSTRACT FROM AUTHOR]

With numerous nodes on online heterogeneous networks, how to reach and extract target nodes of our specific interests is a pressing problem. In this paper, we propose a novel heterogeneous network crawler, MCrawl. It addresses the problem via iterative online heterogeneous network crawling by navigating its available APIs, starting from a set of target nodes, i.e., seed nodes. We are facing two challenges towards addressing the problem. First, to navigate within a vast network, how do we start from a small set of target nodes? In other words, which nodes in the “current frontier” and which direction shall we expand, to reach promising target nodes quickly? We propose motif-based crawling to exploit the complex structures and rich semantics of heterogeneous networks. Second, in many scenarios, we do not have a classifier to assess the quality of the harvested nodes and thus the motifs to expand. We develop a probabilistic inference framework to estimate the yield and harvest rates of motifs, achieving principled bootstrapping for crawling. Our experiment on real networks of MCrawl achieves significant margins over baselines. [ABSTRACT FROM AUTHOR]

The key to the effective control of a diffusion system lies in how accurately we could predict its unfolding dynamics based on the observation of its current state. However, in the real-world applications, it is often infeasible to conduct a timely and yet comprehensive observation due to resource constraints. In view of such a practical challenge, the goal of this work is to develop a novel computational method for performing active observations, termed active surveillance, with limited resources. Specifically, we aim to predict the dynamics of a large spatio-temporal diffusion system based on the observations of some of its components. Towards this end, we introduce a novel measure, the $\boldsymbol{\gamma }$ γ value, that enables us to identify the key components by means of modeling a sentinel network with a row sparsity structure. Having obtained a theoretical understanding of the $\boldsymbol{\gamma }$ γ value, we design a backward-selection sentinel network mining algorithm (SNMA) for deriving the sentinel network via group sparse Bayesian learning. In order to be practically useful, we further address the issue of scalability in the computation of SNMA, and moreover, extend SNMA to the case of a non-linear dynamical system that could involve complex diffusion mechanisms. We show the effectiveness of SNMA by validating it using both synthetic datasets and five real-world datasets. The experimental results are appealing, which demonstrate that SNMA readily outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Researchers often query online social platforms through their application programming interfaces (API) to find target populations such as people with mental illness (De Choudhury et al. in Proceedings of the 2017 ACM conference on computer supported cooperative work and social computing, CSCW '17. ACM, New York, pp 353–369, https://doi.org/10.1145/2998181.2998220, 2017) and jazz musicians (Heckathorn and Jeffri in Poetics 28(4):307, 2001). Entities of such target population satisfy a property that is typically identified using an oracle (human or a pre-trained classifier). When the property of the target entities is not directly queryable via the API, we refer to the property as 'hidden' and the population as hidden population. Our objective in this paper is to sample such target populations that satisfy a certain property that can be verified by an oracle (typically a pre-trained classifier). However, the property itself cannot be a part of the query. We refer to such populations which are not directly queryable via the API as a hidden population. Finding individuals who belong to these populations on social networks is hard because they are non-queryable, and the sampler has to explore from a combinatorial query space within a finite budget limit. Further, limited API calls, a limited number of queryable attributes to explore from and an exponential query space to select a query from make the problem very challenging. To address the challenges, we model the search for hidden population search as a decision problem. By exploiting the correlation between queryable attributes and the population of interest and by hierarchically ordering the query space, we propose a decision-tree-based Thompson sampler (DT-TMP) that efficiently discovers the right combination of attributes to query. Additionally, DT-TMP alleviates the problem of exploring the exponentially large query space through a hierarchical ordering of the queries. Our proposed sampler outperforms the state-of-the-art samplers in online experiments, for example, by 54% in Twitter. When the number of matching entities to a query is known in offline experiments, DT-TMP performs exceedingly well by a factor of 0.9–1.5 × over the baseline samplers. In future, we wish to explore the option of finding hidden populations by formulating more complex queries. [ABSTRACT FROM AUTHOR]

Data in the form of graphs are prevalent, ranging from biological and social networks to citation graphs and the Web. In particular, most real-world graphs are heterogeneous, containing objects of multiple types, which present new opportunities for many problems on graphs. Consider a typical proximity search problem on graphs, which boils down to measuring the proximity between two given nodes. Most earlier studies on homogeneous or bipartite graphs only measure a generic form of proximity, without accounting for different “semantic classes”—for instance, on a social network two users can be close for different reasons, such as being classmates or family members, which represent two distinct semantic classes. Learning these semantic classes are made possible on heterogeneous graphs through the concept of metagraphs. In this study, we identify metagraphs as a novel and effective means to characterize the common structures for a desired class of proximity. Subsequently, we propose a family of metagraph-based proximity, and employ a learning-to-rank technique that automatically learns the right parameters to suit the desired semantic class. In terms of efficiency, we develop a symmetry-based matching algorithm to speed up the computation of metagraph instances. Empirically, extensive experiments reveal that our metagraph-based proximity substantially outperforms the best competitor by more than 10 percent, and our matching algorithm can reduce matching time by more than half. As a further generalization, we aim to derive a general node and edge representation for heterogeneous graphs, in order to support arbitrary machine learning tasks beyond proximity search. In particular, we propose the finer-grained anchored metagraph, which is capable of discriminating the roles of nodes within the same metagraph. Finally, further experiments on the general representation show that we can outperform the state of the art significantly and consistently across various machine learning tasks. [ABSTRACT FROM AUTHOR]

Psychological stress has been linked to developmental problems and poor health in children, but it is unclear whether it is also related to otitis media (OM). As part of a long-term study surveying the characteristics of childcare and development in Taiwan, we analyzed the relationship between OM and sources of psychological stress in children, such as poor maternal mental health and harsh parental discipline. We analyzed the data of 1998 children from the “Kids in Taiwan: National Longitudinal Study of Child Development & Care (KIT) Project” at the age of 3 years. Using bivariate and multivariate logistic regression models, we tested several risk factors as potential independent predictors of two outcomes: parent-reported incidence of OM and child health. The proportion of children who had developed OM in the first 3 years of their life was 12.5%. Daycare attendance (odds ratio [OR]: 1.475; 95% confidence interval [CI]: 1.063–2.046), poor maternal mental health (OR: 1.913; 95% CI: 1.315–2.784), and harsh parental discipline (OR: 1.091; 95% CI: 1.025–1.161) correlated with parent-reported occurrence of OM. These findings suggest that providing psychosocial support to both parents and children might be a novel strategy for preventing OM. [ABSTRACT FROM AUTHOR]

Smartphone user verification is important as personal daily activities are increasingly conducted on the phone and sensitive information is constantly logged. The commonly adopted user verification methods are typically active, i.e., they require a user's cooperative input of a security token to gain access permission. Though popular, these methods impose heavy burden to smartphone users to memorize, maintain, and input the token at a high frequency. To alleviate this imposition onto the users and to provide additional security, we propose a new nonintrusive and continuous mobile user verification framework that can reduce the frequency required for a user to input his/her security token. Using tailored Hidden Markov Models and sequential likelihood ratio test, our verification is built on low-cost, readily available, anonymized, and multimodal smartphone data without additional effort of data collection and risk of privacy leakage. With extensive evaluation, we achieve a high rate of about 94 percent for detecting illegitimate smartphone uses and a rate of 74 percent for confirming legitimate uses. In a practical setting, this can translate into 74 percent of frequency reduction of inputting a security token using an active authentication method with only about 6 percent risk of miss detection of a random intruder, which is highly desirable. [ABSTRACT FROM AUTHOR]

Graph is an important data representation which appears in a wide diversity of real-world scenarios. Effective graph analytics provides users a deeper understanding of what is behind the data, and thus can benefit a lot of useful applications such as node classification, node recommendation, link prediction, etc. However, most graph analytics methods suffer the high computation and space cost. Graph embedding is an effective yet efficient way to solve the graph analytics problem. It converts the graph data into a low dimensional space in which the graph structural information and graph properties are maximumly preserved. In this survey, we conduct a comprehensive review of the literature in graph embedding. We first introduce the formal definition of graph embedding as well as the related concepts. After that, we propose two taxonomies of graph embedding which correspond to what challenges exist in different graph embedding problem settings and how the existing work addresses these challenges in their solutions. Finally, we summarize the applications that graph embedding enables and suggest four promising future research directions in terms of computation efficiency, problem settings, techniques, and application scenarios. [ABSTRACT FROM AUTHOR]

As the emphasis on value-based care within total joint arthroplasty increases, this procedure is becoming more prevalent in the outpatient setting. The goals of this study were to report on the authors' early experiences with same-day discharge and to identify patient characteristics that are associated with failure to discharge after total hip arthroplasty within this program. All patients who were enrolled in the same-day discharge total hip arthroplasty program at the study institution between January 2015 and July 2016 were included. Demographics, baseline characteristics, and clinical and quality outcomes were compared between patients who successfully completed this program and those who did not. Of the 163 study subjects, 143 (87.7%) were discharged successfully on the same day as surgery. Women, patients younger than 40 years, and patients older than 60 years all had an increased risk of failing the program. Body mass index of 26 kg/m2 or less was associated with a 40% greater risk of failure. Patients with an American Society of Anesthesiologists score of 3 had a 3-fold risk of failure compared with patients with an American Society of Anesthesiologists score of 2 or less. The screening protocol for same-day discharge at the study institution had an 87.7% rate of successful same-day discharge. Further investigation is needed to identify patients who are at risk of failing the same-day discharge initiative. [Orthopedics. 2018; 41(1):35-42.]. [ABSTRACT FROM AUTHOR]

Background: Acute stress triggers transient alterations in the synaptic release and metabolism of brain monoamine neurotransmitters. These rapid changes are essential to activate neuroplastic processes aimed at the appraisal of the stressor and enactment of commensurate defensive behaviors. Threat evaluation has been recently associated with the dendritic morphology of pyramidal cells in the orbitofrontal cortex (OFC) and basolateral amygdala (BLA); thus, we examined the rapid effects of restraint stress on anxiety-like behavior and dendritic morphology in the BLA and OFC of mice. Furthermore, we tested whether these processes may be affected by deficiency of monoamine oxidase A (MAO-A), the primary enzyme catalyzing monoamine metabolism. Methods: Following a short-term (1-4 h) restraint schedule, MAO-A knockout (KO) and wild-type (WT) mice were sacrificed, and histological analyses of dendrites in pyramidal neurons of the BLA and OFC of the animals were performed. Anxiety-like behaviors were examined in a separate cohort of animals subjected to the same experimental conditions. Results: In WT mice, short-term restraint stress significantly enhanced anxiety-like responses, as well as a time-dependent proliferation of apical (but not basilar) dendrites of the OFC neurons; conversely, a retraction in BLA dendrites was observed. None of these behavioral and morphological changes were observed in MAO-A KO mice. Conclusions: These findings suggest that acute stress induces anxiety-like responses by affecting rapid dendritic remodeling in the pyramidal cells of OFC and BLA; furthermore, our data show that MAO-A and monoamine metabolism are required for these phenomena. [ABSTRACT FROM AUTHOR]