Using sensitivity analyses to understand bistable system behavior.

BACKGROUND: Bistable systems, i.e., systems that exhibit two stable steady states, are of particular interest in biology. They can implement binary cellular decision making, e.g., in pathways for cellular differentiation and cell cycle regulation. The onset of cancer, prion diseases, and neurodegenerative diseases are known to be associated with malfunctioning bistable systems. Exploring and characterizing parameter spaces in bistable systems, so that they retain or lose bistability, is part of a lot of therapeutic research such as cancer pharmacology. RESULTS: We use eigenvalue sensitivity analysis and stable state separation sensitivity analysis to understand bistable system behaviors, and to characterize the most sensitive parameters of a bistable system. While eigenvalue sensitivity analysis is an established technique in engineering disciplines, it has not been frequently used to study biological systems. We demonstrate the utility of these approaches on a published bistable system. We also illustrate scalability and generalizability of these methods to larger bistable systems. CONCLUSIONS: Eigenvalue sensitivity analysis and separation sensitivity analysis prove to be promising tools to define parameter design rules to make switching decisions between either stable steady state of a bistable system and a corresponding monostable state after bifurcation. These rules were applied to the smallest two-component bistable system and results were validated analytically. We showed that with multiple parameter settings of the same bistable system, we can design switching to a desirable state to retain or lose bistability when the most sensitive parameter is varied according to our parameter perturbation recommendations. We propose eigenvalue and stable state separation sensitivity analyses as a framework to evaluate large and complex bistable systems.

Identifying geopolitical event precursors using attention-based LSTMs.

Forecasting societal events such as civil unrest, mass protests, and violent conflicts is a challenging problem with several important real-world applications in planning and policy making. While traditional forecasting approaches have typically relied on historical time series for generating such forecasts, recent research has focused on using open source surrogate data for more accurate and timely forecasts. Furthermore, leveraging such data can also help to identify precursors of those events that can be used to gain insights into the generated forecasts. The key challenge is to develop a unified framework for forecasting and precursor identification that can deal with missing historical data. Other challenges include sufficient flexibility in handling different types of events and providing interpretable representations of identified precursors. Although existing methods exhibit promising performance for predictive modeling in event detection, these models do not adequately address the above challenges. Here, we propose a unified framework based on an attention-based long short-term memory (LSTM) model to simultaneously forecast events with sequential text datasets as well as identify precursors at different granularity such as documents and document excerpts. The key idea is to leverage word context in sequential and time-stamped documents such as news articles and blogs for learning a rich set of precursors. We validate the proposed framework by conducting extensive experiments with two real-world datasets-military action and violent conflicts in the Middle East and mass protests in Latin America. Our results show that overall, the proposed approach generates more accurate forecasts compared to the existing state-of-the-art methods, while at the same time producing a rich set of precursors for the forecasted events.

Once Upon A Time In Visualization: Understanding the Use of Textual Narratives for Causality.

Causality visualization can help people understand temporal chains of events, such as messages sent in a distributed system, cause and effect in a historical conflict, or the interplay between political actors over time. However, as the scale and complexity of these event sequences grows, even these visualizations can become overwhelming to use. In this paper, we propose the use of textual narratives as a data-driven storytelling method to augment causality visualization. We first propose a design space for how textual narratives can be used to describe causal data. We then present results from a crowdsourced user study where participants were asked to recover causality information from two causality visualizations-causal graphs and Hasse diagrams-with and without an associated textual narrative. Finally, we describe Causeworks, a causality visualization system for understanding how specific interventions influence a causal model. The system incorporates an automatic textual narrative mechanism based on our design space. We validate Causeworks through interviews with experts who used the system for understanding complex events.

Data analysis and modeling pipelines for controlled networked social science experiments.

There is large interest in networked social science experiments for understanding human behavior at-scale. Significant effort is required to perform data analytics on experimental outputs and for computational modeling of custom experiments. Moreover, experiments and modeling are often performed in a cycle, enabling iterative experimental refinement and data modeling to uncover interesting insights and to generate/refute hypotheses about social behaviors. The current practice for social analysts is to develop tailor-made computer programs and analytical scripts for experiments and modeling. This often leads to inefficiencies and duplication of effort. In this work, we propose a pipeline framework to take a significant step towards overcoming these challenges. Our contribution is to describe the design and implementation of a software system to automate many of the steps involved in analyzing social science experimental data, building models to capture the behavior of human subjects, and providing data to test hypotheses. The proposed pipeline framework consists of formal models, formal algorithms, and theoretical models as the basis for the design and implementation. We propose a formal data model, such that if an experiment can be described in terms of this model, then our pipeline software can be used to analyze data efficiently. The merits of the proposed pipeline framework is elaborated by several case studies of networked social science experiments.

Physics-Guided Deep Learning for Drag Force Prediction in Dense Fluid-Particulate Systems.

Physics-based simulations are often used to model and understand complex physical systems in domains such as fluid dynamics. Such simulations, although used frequently, often suffer from inaccurate or incomplete representations either due to their high computational costs or due to lack of complete physical knowledge of the system. In such situations, it is useful to employ machine learning (ML) to fill the gap by learning a model of the complex physical process directly from simulation data. However, as data generation through simulations is costly, we need to develop models being cognizant of data paucity issues. In such scenarios, it is helpful if the rich physical knowledge of the application domain is incorporated in the architectural design of ML models. We can also use information from physics-based simulations to guide the learning process using aggregate supervision to favorably constrain the learning process. In this article, we propose PhyNet, a deep learning model using physics-guided structural priors and physics-guided aggregate supervision for modeling the drag forces acting on each particle in a computational fluid dynamics-discrete element method. We conduct extensive experiments in the context of drag force prediction and showcase the usefulness of including physics knowledge in our deep learning formulation. PhyNet has been compared with several state-of-the-art models and achieves a significant performance improvement of 7.09% on average. The source code has been made available*.

Deep Reinforcement Learning for Sequence-to-Sequence Models.

In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide state-of-the-art performance in a wide variety of tasks, such as machine translation, headline generation, text summarization, speech-to-text conversion, and image caption generation. The underlying framework for all these models is usually a deep neural network comprising an encoder and a decoder. Although simple encoder-decoder models produce competitive results, many researchers have proposed additional improvements over these seq2seq models, e.g., using an attention-based model over the input, pointer-generation models, and self-attention models. However, such seq2seq models suffer from two common problems: 1) exposure bias and 2) inconsistency between train/test measurement. Recently, a completely novel point of view has emerged in addressing these two problems in seq2seq models, leveraging methods from reinforcement learning (RL). In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with seq2seq models that enable remembering long-term memories. We present some of the most recent frameworks that combine the concepts from RL and deep neural networks. Our work aims to provide insights into some of the problems that inherently arise with current approaches and how we can address them with better RL models. We also provide the source code for implementing most of the RL models discussed in this paper to support the complex task of abstractive text summarization and provide some targeted experiments for these RL models, both in terms of performance and training time.

Collaborative efforts to forecast seasonal influenza in the United States, 2015-2016.

Since 2013, the Centers for Disease Control and Prevention (CDC) has hosted an annual influenza season forecasting challenge. The 2015-2016 challenge consisted of weekly probabilistic forecasts of multiple targets, including fourteen models submitted by eleven teams. Forecast skill was evaluated using a modified logarithmic score. We averaged submitted forecasts into a mean ensemble model and compared them against predictions based on historical trends. Forecast skill was highest for seasonal peak intensity and short-term forecasts, while forecast skill for timing of season onset and peak week was generally low. Higher forecast skill was associated with team participation in previous influenza forecasting challenges and utilization of ensemble forecasting techniques. The mean ensemble consistently performed well and outperformed historical trend predictions. CDC and contributing teams will continue to advance influenza forecasting and work to improve the accuracy and reliability of forecasts to facilitate increased incorporation into public health response efforts.

The Effect of Edge Bundling and Seriation on Sensemaking of Biclusters in Bipartite Graphs.

Exploring coordinated relationships (e.g., shared relationships between two sets of entities) is an important analytics task in a variety of real-world applications, such as discovering similarly behaved genes in bioinformatics, detecting malware collusions in cyber security, and identifying products bundles in marketing analysis. Coordinated relationships can be formalized as biclusters. In order to support visual exploration of biclusters, bipartite graphs based visualizations have been proposed, and edge bundling is used to show biclusters. However, it suffers from edge crossings due to possible overlaps of biclusters, and lacks in-depth understanding of its impact on user exploring biclusters in bipartite graphs. To address these, we propose a novel bicluster-based seriation technique that can reduce edge crossings in bipartite graphs drawing and conducted a user experiment to study the effect of edge bundling and this proposed technique on visualizing biclusters in bipartite graphs. We found that they both had impact on reducing entity visits for users exploring biclusters, and edge bundles helped them find more justified answers. Moreover, we identified four key trade-offs that inform the design of future bicluster visualizations. The study results suggest that edge bundling is critical for exploring biclusters in bipartite graphs, which helps to reduce low-level perceptual problems and support high-level inferences.

Results from the second year of a collaborative effort to forecast influenza seasons in the United States.

Accurate forecasts could enable more informed public health decisions. Since 2013, CDC has worked with external researchers to improve influenza forecasts by coordinating seasonal challenges for the United States and the 10 Health and Human Service Regions. Forecasted targets for the 2014-15 challenge were the onset week, peak week, and peak intensity of the season and the weekly percent of outpatient visits due to influenza-like illness (ILI) 1-4 weeks in advance. We used a logarithmic scoring rule to score the weekly forecasts, averaged the scores over an evaluation period, and then exponentiated the resulting logarithmic score. Poor forecasts had a score near 0, and perfect forecasts a score of 1. Five teams submitted forecasts from seven different models. At the national level, the team scores for onset week ranged from <0.01 to 0.41, peak week ranged from 0.08 to 0.49, and peak intensity ranged from <0.01 to 0.17. The scores for predictions of ILI 1-4 weeks in advance ranged from 0.02-0.38 and was highest 1 week ahead. Forecast skill varied by HHS region. Forecasts can predict epidemic characteristics that inform public health actions. CDC, state and local health officials, and researchers are working together to improve forecasts.

Towards a Systematic Combination of Dimension Reduction and Clustering in Visual Analytics.

Dimension reduction algorithms and clustering algorithms are both frequently used techniques in visual analytics. Both families of algorithms assist analysts in performing related tasks regarding the similarity of observations and finding groups in datasets. Though initially used independently, recent works have incorporated algorithms from each family into the same visualization systems. However, these algorithmic combinations are often ad hoc or disconnected, working independently and in parallel rather than integrating some degree of interdependence. A number of design decisions must be addressed when employing dimension reduction and clustering algorithms concurrently in a visualization system, including the selection of each algorithm, the order in which they are processed, and how to present and interact with the resulting projection. This paper contributes an overview of combining dimension reduction and clustering into a visualization system, discussing the challenges inherent in developing a visualization system that makes use of both families of algorithms.

A framework for evaluating epidemic forecasts.

BACKGROUND: Over the past few decades, numerous forecasting methods have been proposed in the field of epidemic forecasting. Such methods can be classified into different categories such as deterministic vs. probabilistic, comparative methods vs. generative methods, and so on. In some of the more popular comparative methods, researchers compare observed epidemiological data from the early stages of an outbreak with the output of proposed models to forecast the future trend and prevalence of the pandemic. A significant problem in this area is the lack of standard well-defined evaluation measures to select the best algorithm among different ones, as well as for selecting the best possible configuration for a particular algorithm. RESULTS: In this paper we present an evaluation framework which allows for combining different features, error measures, and ranking schema to evaluate forecasts. We describe the various epidemic features (Epi-features) included to characterize the output of forecasting methods and provide suitable error measures that could be used to evaluate the accuracy of the methods with respect to these Epi-features. We focus on long-term predictions rather than short-term forecasting and demonstrate the utility of the framework by evaluating six forecasting methods for predicting influenza in the United States. Our results demonstrate that different error measures lead to different rankings even for a single Epi-feature. Further, our experimental analyses show that no single method dominates the rest in predicting all Epi-features when evaluated across error measures. As an alternative, we provide various Consensus Ranking schema that summarize individual rankings, thus accounting for different error measures. Since each Epi-feature presents a different aspect of the epidemic, multiple methods need to be combined to provide a comprehensive forecast. Thus we call for a more nuanced approach while evaluating epidemic forecasts and we believe that a comprehensive evaluation framework, as presented in this paper, will add value to the computational epidemiology community.

Temporal Topic Modeling to Assess Associations between News Trends and Infectious Disease Outbreaks.

In retrospective assessments, internet news reports have been shown to capture early reports of unknown infectious disease transmission prior to official laboratory confirmation. In general, media interest and reporting peaks and wanes during the course of an outbreak. In this study, we quantify the extent to which media interest during infectious disease outbreaks is indicative of trends of reported incidence. We introduce an approach that uses supervised temporal topic models to transform large corpora of news articles into temporal topic trends. The key advantages of this approach include: applicability to a wide range of diseases and ability to capture disease dynamics, including seasonality, abrupt peaks and troughs. We evaluated the method using data from multiple infectious disease outbreaks reported in the United States of America (U.S.), China, and India. We demonstrate that temporal topic trends extracted from disease-related news reports successfully capture the dynamics of multiple outbreaks such as whooping cough in U.S. (2012), dengue outbreaks in India (2013) and China (2014). Our observations also suggest that, when news coverage is uniform, efficient modeling of temporal topic trends using time-series regression techniques can estimate disease case counts with increased precision before official reports by health organizations.

Multi-Source Models for Civil Unrest Forecasting.

Civil unrest events (protests, strikes, and "occupy" events) range from small, nonviolent protests that address specific issues to events that turn into large-scale riots. Detecting and forecasting these events is of key interest to social scientists and policy makers because they can lead to significant societal and cultural changes. We forecast civil unrest events in six countries in Latin America on a daily basis, from November 2012 through August 2014, using multiple data sources that capture social, political and economic contexts within which civil unrest occurs. The models contain predictors extracted from social media sites (Twitter and blogs) and news sources, in addition to volume of requests to Tor, a widely used anonymity network. Two political event databases and country-specific exchange rates are also used. Our forecasting models are evaluated using a Gold Standard Report (GSR), which is compiled by an independent group of social scientists and subject matter experts. We use logistic regression models with Lasso to select a sparse feature set from our diverse datasets. The experimental results, measured by F1-scores, are in the range 0.68 to 0.95, and demonstrate the efficacy of using a multi-source approach for predicting civil unrest. Case studies illustrate the insights into unrest events that are obtained with our method. The ablation study demonstrates the relative value of data sources for prediction. We find that social media and news are more informative than other data sources, including the political event databases, and enhance the prediction performance. However, social media increases the variation in the performance metrics.

BiSet: Semantic Edge Bundling with Biclusters for Sensemaking.

Identifying coordinated relationships is an important task in data analytics. For example, an intelligence analyst might want to discover three suspicious people who all visited the same four cities. Existing techniques that display individual relationships, such as between lists of entities, require repetitious manual selection and significant mental aggregation in cluttered visualizations to find coordinated relationships. In this paper, we present BiSet, a visual analytics technique to support interactive exploration of coordinated relationships. In BiSet, we model coordinated relationships as biclusters and algorithmically mine them from a dataset. Then, we visualize the biclusters in context as bundled edges between sets of related entities. Thus, bundles enable analysts to infer task-oriented semantic insights about potentially coordinated activities. We make bundles as first class objects and add a new layer, "in-between", to contain these bundle objects. Based on this, bundles serve to organize entities represented in lists and visually reveal their membership. Users can interact with edge bundles to organize related entities, and vice versa, for sensemaking purposes. With a usage scenario, we demonstrate how BiSet supports the exploration of coordinated relationships in text analytics.

Pricing a Protest: Forecasting the Dynamics of Civil Unrest Activity in Social Media.

Online social media activity can often be a precursor to disruptive events such as protests, strikes, and "occupy" movements. We have observed that such civil unrest can galvanize supporters through social networks and help recruit activists to their cause. Understanding the dynamics of social network cascades and extrapolating their future growth will enable an analyst to detect or forecast major societal events. Existing work has primarily used structural and temporal properties of cascades to predict their future behavior. But factors like societal pressure, alignment of individual interests with broader causes, and perception of expected benefits also affect protest participation in social media. Here we develop an analysis framework using a differential game theoretic approach to characterize the cost of participating in a cascade, and demonstrate how we can combine such cost features with classical properties to forecast the future behavior of cascades. Using data from Twitter, we illustrate the effectiveness of our models on the "Brazilian Spring" and Venezuelan protests that occurred in June 2013 and November 2013, respectively. We demonstrate how our framework captures both qualitative and quantitative aspects of how these uprisings manifest through the lens of tweet volume on Twitter social media.

ThemeDelta: Dynamic Segmentations over Temporal Topic Models.

We present ThemeDelta, a visual analytics system for extracting and visualizing temporal trends, clustering, and reorganization in time-indexed textual datasets. ThemeDelta is supported by a dynamic temporal segmentation algorithm that integrates with topic modeling algorithms to identify change points where significant shifts in topics occur. This algorithm detects not only the clustering and associations of keywords in a time period, but also their convergence into topics (groups of keywords) that may later diverge into new groups. The visual representation of ThemeDelta uses sinuous, variable-width lines to show this evolution on a timeline, utilizing color for categories, and line width for keyword strength. We demonstrate how interaction with ThemeDelta helps capture the rise and fall of topics by analyzing archives of historical newspapers, of U.S. presidential campaign speeches, and of social messages collected through iNeighbors, a web-based social website. ThemeDelta is evaluated using a qualitative expert user study involving three researchers from rhetoric and history using the historical newspapers corpus.

Forecasting Social Unrest Using Activity Cascades.

Social unrest is endemic in many societies, and recent news has drawn attention to happenings in Latin America, the Middle East, and Eastern Europe. Civilian populations mobilize, sometimes spontaneously and sometimes in an organized manner, to raise awareness of key issues or to demand changes in governing or other organizational structures. It is of key interest to social scientists and policy makers to forecast civil unrest using indicators observed on media such as Twitter, news, and blogs. We present an event forecasting model using a notion of activity cascades in Twitter (proposed by Gonzalez-Bailon et al., 2011) to predict the occurrence of protests in three countries of Latin America: Brazil, Mexico, and Venezuela. The basic assumption is that the emergence of a suitably detected activity cascade is a precursor or a surrogate to a real protest event that will happen "on the ground." Our model supports the theoretical characterization of large cascades using spectral properties and uses properties of detected cascades to forecast events. Experimental results on many datasets, including the recent June 2013 protests in Brazil, demonstrate the effectiveness of our approach.

Monitoring disease trends using hospital traffic data from high resolution satellite imagery: a feasibility study.

Challenges with alternative data sources for disease surveillance include differentiating the signal from the noise, and obtaining information from data constrained settings. For the latter, events such as increases in hospital traffic could serve as early indicators of social disruption resulting from disease. In this study, we evaluate the feasibility of using hospital parking lot traffic data extracted from high-resolution satellite imagery to augment public health disease surveillance in Chile, Argentina and Mexico. We used archived satellite imagery collected from January 2010 to May 2013 and data on the incidence of respiratory virus illnesses from the Pan American Health Organization as a reference. We developed dynamical Elastic Net multivariable linear regression models to estimate the incidence of respiratory virus illnesses using hospital traffic and assessed how to minimize the effects of noise on the models. We noted that predictions based on models fitted using a sample of observations were better. The results were consistent across countries with selected models having reasonably low normalized root-mean-squared errors and high correlations for both the fits and predictions. The observations from this study suggest that if properly procured and combined with other information, this data source could be useful for monitoring disease trends.