The State‐of‐the‐Art in Predictive Visual Analytics

Predictive analytics embraces an extensive range of techniques including statistical modeling, machine learning, and data mining and is applied in business intelligence, public health, disaster management and response, and many other fields. To date, visualization has been broadly used to support tasks in the predictive analytics pipeline. Primary uses have been in data cleaning, exploratory analysis, and diagnostics. For example, scatterplots and bar charts are used to illustrate class distributions and responses. More recently, extensive visual analytics systems for feature selection, incremental learning, and various prediction tasks have been proposed to support the growing use of complex models, agent‐specific optimization, and comprehensive model comparison and result exploration. Such work is being driven by advances in interactive machine learning and the desire of end‐users to understand and engage with the modeling process. In this state‐of‐the‐art report, we catalogue recent advances in the visualization community for supporting predictive analytics. First, we define the scope of predictive analytics discussed in this article and describe how visual analytics can support predictive analytics tasks in a predictive visual analytics (PVA) pipeline. We then survey the literature and categorize the research with respect to the proposed PVA pipeline. Systems and techniques are evaluated in terms of their supported interactions, and interactions specific to predictive analytics are discussed. We end this report with a discussion of challenges and opportunities for future research in predictive visual analytics.     

Aesthetic 3D model evolution

A new research frontier for evolutionary 2D image generation is the use of mathematical models of aesthetics, with the goal of automatically evolving aesthetically pleasing images. This paper investigates the application of similar models of aesthetics towards the evolution of 3-dimensional structures. We extend existing models of aesthetics used for image evaluation to the 3D realm, by considering quantifiable properties of surface geometry. Analyses used include entropy, complexity, deviation from normality, 1/f noise, and symmetry. A new 3D L-system implementation promotes accurate analyses of surface features, as well as productive rule sets when used with genetic programming. Multi-objective evaluation reconciles multiple aesthetic criteria. Experiments resulted in the generation of many models that satisfied multiple criteria. A human survey was conducted, and survey takers showed a statistically significant preference for high-fitness highly-evolved models over low-fitness unevolved ones. This research shows that aesthetic evolution of 3D structures is a promising new research area for evolutionary design.     

Relationship between NP GCL Internal and HDPE GMX/NP GCL Interface Shear Strengths

An investigation was conducted on the relationship between the internal shear strength of hydrated needle-punched (NP) geosynthetic clay liners (GCLs) and the interface shear strength between hydrated NP GCLs (nonwoven side) and high-density polyethylene (HDPE) textured geomembranes (GMXs). New large-scale direct shear data are presented and compared to previous results obtained using similar materials and procedures. The data indicate that both GCLs and GMX/GCL interfaces display large postpeak strength reduction, even at high normal stress. Peak and large-displacement failure envelopes are nonlinear; except for the GCL internal residual strength envelope, which passes through the origin and has a friction angle of 4.8°. GMX/GCL interfaces can be expected to have lower peak strengths and higher large-displacement strengths than GCL internal shear specimens. However, the failure mode for GMX/GCL specimens can change from interface shear to GCL internal shear as normal stress increases. Design for peak strength conditions should be based on the lowest peak strength interface in a liner system, and design for large displacement conditions should be on the basis of the residual strength of the same interface.     

On the formalization and reuse of scientific research

The reuse of scientific knowledge obtained from one investigation in another investigation is basic to the advance of science. Scientific investigations should therefore be recorded in ways that promote the reuse of the knowledge they generate. The use of logical formalisms to describe scientific knowledge has potential advantages in facilitating such reuse. Here, we propose a formal framework for using logical formalisms to promote reuse. We demonstrate the utility of this framework by using it in a worked example from biology: demonstrating cycles of investigation formalization [F] and reuse [R] to generate new knowledge. We first used logic to formally describe a Robot scientist investigation into yeast (Saccharomyces cerevisiae) functional genomics [f₁]. With Robot scientists, unlike human scientists, the production of comprehensive metadata about their investigations is a natural by-product of the way they work. We then demonstrated how this formalism enabled the reuse of the research in investigating yeast phenotypes [r₁ = R(f₁)]. This investigation found that the removal of non-essential enzymes generally resulted in enhanced growth. The phenotype investigation was then formally described using the same logical formalism as the functional genomics investigation [f₂ = F(r₁)]. We then demonstrated how this formalism enabled the reuse of the phenotype investigation to investigate yeast systems-biology modelling [r₂ = R(f₂)]. This investigation found that yeast flux-balance analysis models fail to predict the observed changes in growth. Finally, the systems biology investigation was formalized for reuse in future investigations [f₃ = F(r₂)]. These cycles of reuse are a model for the general reuse of scientific knowledge.     

Issues in the assimilation of the sources of a trace gas by inverse modelling

The problem of reconstructing the (otherwise unknown) source and sink field of a tracer in a fluid is studied by developing and testing a simple tracer transport model of a single-level global atmosphere and a dynamic data assimilation system. The source/sink field (taken to be constant over a 10-day assimilation window) and initial tracer field are analysed together by assimilating imperfect tracer observations over the window.Experiments show that useful information about the source/sink field may be determined from relatively few observations when the initial tracer field is known very accurately a-priori, even when a-priori source/sink information is biased (the source/sink a-priori is set to zero). In this case each observation provides information about the source/sink field at positions upstream and the assimilation of many observations together can reasonably determine the location and strength of a test source.     

Development of an automated testing system for vehicle infotainment system

A current premium vehicle is implemented with a variety of information, entertainment, and communication functions, which are generally referred as an infotainment system. During vehicle development, testing of the infotainment system at an overall level is conventionally carried out manually by an expert who can observe at a customer level. This approach has significant limitations with regard to test coverage and effectiveness due to the complexity of the system functions and human’s capability. Hence, it is highly demanded by car manufacturers for an automated infotainment testing system, which replicates a human expert encompassing relevant sensory modalities relating to control (i.e., touch) and observation (i.e., sight and sound) of the system under test. This paper describes the design, development, and evaluation of such a system that consists of simulation of vehicle network, vision-based inspection, automated navigation of features, random cranking waveform generation, sound detection, and test automation. The system developed is able to: stimulate a vehicle system across a wide variety of initialisation conditions, exercise each function, check for system responses, and record failure situations for post-testing analysis.     

Quality assurance of PASADENA hyperpolarization for 13C biomolecules

Object  Define MR quality assurance procedures for maximal PASADENA hyperpolarization of a biological ¹³C molecular imaging reagent. Materials and methods  An automated PASADENA polarizer and a parahydrogen generator were installed. ¹³C enriched hydroxyethyl acrylate, 1-¹³C, 2,3,3-d₃ (HEA), was converted to hyperpolarized hydroxyethyl propionate, 1-¹³C, 2,3,3-d₃ (HEP) and fumaric acid, 1-¹³C, 2,3-d₂ (FUM) to hyperpolarized succinic acid, 1-¹³C, 2,3-d₂ (SUC), by reaction with parahydrogen and norbornadiene rhodium catalyst. Incremental optimization of successive steps in PASADENA was implemented. MR spectra and in vivo images of hyperpolarized ¹³C imaging agents were acquired at 1.5 and 4.7 T. Results  Application of quality assurance (QA) criteria resulted in incremental optimization of the individual steps in PASADENA implementation. Optimal hyperpolarization of HEP of P = 20% was achieved by calibration of the NMR unit of the polarizer (B ₀ field strength ± 0.002 mT). Mean hyperpolarization of SUC, P = [15.3 ± 1.9]% (N = 16) in D ₂O, and P = [12.8 ± 3.1]% (N = 12) in H ₂O, was achieved every 5–8 min (range 13–20%). An in vivo ¹³C succinate image of a rat was produced. Conclusion  PASADENA spin hyperpolarization of SUC to 15.3% in average was demonstrated (37,400 fold signal enhancement at 4.7 T). The biological fate of ¹³C succinate, a normally occurring cellular intermediate, might be monitored with enhanced sensitivity.     

Monitoring Highly Correlated Multivariate Processes Using Hotelling's T2 Statistic: Problems and Possible Solutions

Hotelling's T² statistic is the default control statistic for continuous multivariate data, but there are dangers in applying this statistic without the appropriate level of checks and balances. This paper discusses the potential issues with using the Hotelling's T² statistic when the quality variable measures are highly correlated and provides some solutions that will help mitigate the risks with applying the Hotelling's T² control charts in such practical examples. Copyright © 2014 John Wiley & Sons, Ltd.     

Potential Pro-Inflammatory Effect of Vitamin E Analogs through Mitigation of Tetrahydrocannabinol (THC) Binding to the Cannabinoid 2 Receptor

Vitamin E acetate, which is used as a diluent of tetrahydrocannabinol (THC), has been reported as the primary causative agent of e-cigarette, or vaping, product use-associated lung injury (EVALI). Here, we employ in vitro assays, docking, and molecular dynamics (MD) computer simulations to investigate the interaction of vitamin E with the membrane-bound cannabinoid 2 receptor (CB2R), and its role in modulating the binding affinity of THC to CB2R. From the MD simulations, we determined that vitamin E interacts with both CB2R and membrane phospholipids. Notably, the synchronized effect of these interactions likely facilitates vitamin E acting as a lipid modulator for the cannabinoid system. Furthermore, MD simulation and trajectory analysis show that when THC binds to CB2R in the presence of vitamin E, the binding cavity widens, facilitating the entry of water molecules into it, leading to a reduced interaction of THC with CB2R. Additionally, the interaction between THC and vitamin E in solution is stabilized by several H bonds, which can directly limit the interaction of free THCs with CB2R. Overall, both the MD simulations and the in vitro dissociation assay results indicate that THC binding to CB2R is reduced in the presence of vitamin E. Our study discusses the role of vitamin E in limiting the effect of THCs and its implications on the reported pathology of EVALI.