Closed form expressions for the prediction of retention times and peak widths for gradient liquid chromatography are particularly useful in understanding, rationalizing and optimizing separations. These expressions are obtained by integrating differential equations, in conjunction with a model of the variation of the retention factor as a function of mobile phase composition. Two of these models, the linear solvent strength (LSS) model and the Neue-Kuss (NK) model are explored in the present work. Here, we expand on these closed form expressions to account for effects of sample volume overload and a mismatch between the sample solvent and the initial mobile phase composition for the gradient. We show that there have been errors in expressions reported in the literature, and we have evaluated the accuracy of the predictions from the closed form expressions reported here using a recently developed liquid chromatography simulator. The expressions assume a constant plate height and consider elution across four zones of the gradient profile - elution in the sample solvent, elution in the initial (isocratic) mobile phase caused by the gradient delay volume, elution during a linear gradient, and elution post-gradient at the final (isocratic) mobile phase composition. The expressions generally give reasonably accurate predictions for retention times and peak widths, except for cases where the solute elutes during transitions between the different zones. The average magnitude of the prediction errors for retention time and peak width relative to simulation were 0.093% and 0.40% for the LSS expressions for ten amphetamine solutes at 36 different separation conditions, and 0.22% and 1.8% for the NK expressions for eight alkylbenzene solutes at 36 different separation conditions, respectively.

In liquid chromatography differences between the pH of an injected sample and the pH of the mobile phase can have a significant impact on retention times, peak widths, and resolution.

While watching movies, audience members exhibit both subtle and coarse gestures (e.g., smiles, head-pose change, fidgeting, stretching) which convey sentiment (i.e., engaged or disengaged) during feature length movies. Noticing these behaviors using computer vision systems is a very challenging problem-especially in a movie theatre environment. The environment is dark and contains views of people at different scales and viewpoints. Feature length movies typically run 80-120 minutes, and tracking people uninterrupted for this duration is still an unsolved problem. Facial expressions of audience members are subtle, short, and sparse; making it difficult to detect and recognize activities. Finally, annotating audience sentiment at the frame-level is prohibitively time consuming. To circumvent these issues, we use an infrared illuminated test-bed to obtain a visually uniform input of audiences watching feature length movies. We present a method which can automatically detect the change in behavior (key-gestures) using "key-frames", which can convey audience sentiment. As the number of key-frames are many orders of magnitudes lower than the number of frames, the annotation problem is reduced to assigning a sentiment label for each key-frame. Using these discovered key-gestures, we create a movie rating classifier from crowd-sourced ratings and demonstrate its predictive capability. Our dataset consists of over 50 hours of audience behavior collected across 237 subjects.

Two-dimensional (2D) liquid chromatography (2DLC) methods have grown in popularity due to their enhanced peak capacity that allows for resolving complex samples. Given the large number of commercially available column types, one of the major challenges in implementing 2DLC methods is the selection of suitable column pairs. Column selection is typically informed by chemical intuition with subsequent experimental optimization. In this work a computational screening method for 2DLC is proposed whereby virtual 2D chromatograms are calculated utilizing the Snyder-Dolan hydrophobic subtraction model (HSM) for reversed-phase column selectivity. Towards this end, 319 225 column pairs resulting from the combination of 565 columns and 100 sets of 1000 diverse analytes are examined. Compared to other screening approaches, the present method is highly predictive for column pairs that are able to resolve the largest number of analytes. This approach shows a strong sensitivity to the choice of the second dimension column (having a shorter operating time) and a preference for those with embedded polar moieties, whereas a relatively weak preference for C-18 and phenyl columns is found for the first dimension. (C) 2018 Elsevier B.V. All rights reserved.

Video-based person re-identification matches video clips of people across non-overlapping cameras. Most existing methods tackle this problem by encoding each video frame in its entirety and computing an aggregate representation across all frames. In practice, people are often partially occluded, which can corrupt the extracted features. Instead, we propose a new spatiotemporal attention model that automatically discovers a diverse set of distinctive body parts. This allows useful information to be extracted from all frames without succumbing to occlusions and misalignments. The network learns multiple spatial attention models and employs a diversity regularization term to ensure multiple models do not discover the same body part. Features extracted from local image regions are organized by spatial attention model and are combined using temporal attention. As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence. Extensive evaluations on three datasets show that our framework outperforms the state-of-the-art approaches by large margins on multiple metrics.

Current state-of-the-art sports metrics such as “Wins-above-Replacement” in baseball, “Expected Point Value” in basketball, and “Expected Goal Value” in soccer and hockey are now commonplace in performance analysis. These measures have enhanced our ability to compare and value performance in sport. But they are inherently limited because they are tied to a discrete outcome of a specific event. With the widespread (and growing) availability of player and ball tracking data comes the potential to quantitatively analyze and compare fine-grain movement patterns. An excellent example of this was the “ghosting” system developed by the Toronto Raptors to analyze player decision-making in STATS SportVU tracking data. Specifically, the Raptors created software to predict what a defensive player should have done instead of what they actually did. Motivated by the original “ghosting” work, we showcase an automatic “data-driven ghosting” method using advanced machine learning methodologies called “deep imitation learning”, applied to a season’s worth of tracking data from a recent professional league in soccer. Our ghosting method, which avoids substantial manual human annotation, results in a data-driven system that allows us to answer the question “how should this player or team have played in a given game situation compare to the league average?”. In addition, by “fine-tuning” our league average model to the tracking data from a particular team, our ghosting technique can estimate how each team might have approached the situation. Our method enables counterfactual analysis of effectiveness of defensive positioning as both a measurable and viewable quantity for the first time.

Re-identification refers to the task of finding the same subject across a network of surveillance cameras. This task must deal with appearance changes caused by variations in illumination, a person's pose, camera viewing angle and background clutter. State-of-the-art approaches usually focus either on feature modeling — designing image descriptors that are robust to changes in imaging conditions, or dissimilarity functions — learning effective metrics to compare images from different cameras. Typically, with novel deep architectures both approaches can be merged into a single end-to-end training, but to become effective, this requires annotating thousands of subjects in each camera pair. Unlike standard CNN-based approaches, we introduce a spatial pyramid-like structure to the image and learn CNNs for image sub-regions at different scales. When training a CNN using only image sub-regions, we force the model to recognize not only the person's identity but also the spatial location of the sub-region. This results in highly effective feature representations, which when combined with Mahalanobis-like metric learning significantly outperform state-of-the-art approaches.

In this tutorial, we discuss the motivations for doing two-dimensional liquid chromatography (2D-LC) and describe the commonly used implementations of the method. We review important guiding principles for method development, discuss the state of the art in 2D-LC performance as measured by peak capacity, and describe example applications from different fields that we hope will inspire new users to adopt 2D-LC for their analytical problems.

The best separation possible at a given analysis time and maximum system pressure is achieved by simultaneously optimizing column length, eluent velocity, and particle size. However, this three-parameter optimization is rarely practicable because only a few commercially available particle sizes exist. Practical optimization for systems described by the van Deemter equation therefore proceeds by first selecting an available particle size and then optimizing eluent velocity and column length. This two parameter ("Poppe") optimization must result in poorer performance with respect to both speed and efficiency because one fewer degree of freedom is used. A deeper analysis identifies a distinct point on each pair of "Poppe" curves beyond which the more efficient (and faster) separation is maintained by changing from smaller to larger particles. Here, we present simple equations identifying these "crossover points" in terms of analysis time and plate count thereby allowing a practitioner to rapidly identify the correct particle size for use in tackling a particular separation problem. Additionally, we can now quantitatively compare two-parameter and three-parameter optimization. Surprisingly, we find that for systems well-described by the van Deemter equation there is little separating power lost (only about 11% in the worst case) as a result of the limited availability of different particle sizes in using two-parameter optimization when compared to the ideal three-parameter optimization so long as one changes particle size at the prescribed crossover points. If these crossover times are not used, a great deal of separating power will be needlessly lost.