EXTRACTING CONTEXTUALIZED COMPLEX BIOLOGICAL EVENTS WITH RICH GRAPH‐BASED FEATURE SETS

We describe a system for extracting complex events among genes and proteins from biomedical literature, developed in context of the BioNLP’09 Shared Task on Event Extraction. For each event, the system extracts its text trigger, class, and arguments. In contrast to the approaches prevailing prior to the shared task, events can be arguments of other events, resulting in a nested structure that better captures the underlying biological statements. We divide the task into independent steps which we approach as machine learning problems. We define a wide array of features and in particular make extensive use of dependency parse graphs. A rule‐based postprocessing step is used to refine the output in accordance with the restrictions of the extraction task. In the shared task evaluation, the system achieved an F‐score of 51.95% on the primary task, the best performance among the participants. Currently, with modifications and improvements described in this article, the system achieves 52.86% F‐score on Task 1, the primary task, improving on its original performance. In addition, we extend the system also to Tasks 2 and 3, gaining F‐scores of 51.28% and 50.18%, respectively. The system thus addresses the BioNLP’09 Shared Task in its entirety and achieves the best performance on all three subtasks.     

Revisiting shrinking particle and product layer models for fluid-solid reactions - From ideal surfaces to real surfaces

A general model based on an arbitrary geometry was developed for reactive solid particles which have surface defects and porosity. The model equations comprising intrinsic kinetics as well as mass transfer effects through the product layer and the fluid film surrounding the solid particle were derived for shrinking particle and product layer models. From the model equations, the fluid (gas or liquid) concentrations at the reaction surface can be calculated and the change of the solid phase can be predicted. The approach was illustrated with monodisperse particle distributions in batch reactors. Complex kinetics as well as simpler special cases were treated. In general, the model predicts a higher reaction order with respect to the solid component than the previous ideal models, which assume slab, cylindrical or spherical geometries for solid particles.     

MORE – a multimodal observation and analysis system for social interaction research

The MORE system is designed for observation and machine-aided analysis of social interaction in real life situations, such as classroom teaching scenarios and business meetings. The system utilizes a multichannel approach to collect data whereby multiple streams of data in a number of different modalities are obtained from each situation. Typically the system collects a 360-degree video and audio feed from multiple microphones set up in the space. The system includes an advanced server backend component that is capable of performing video processing, feature extraction and archiving operations on behalf of the user. The feature extraction services form a key part of the system and rely on advanced signal analysis techniques, such as speech processing, motion activity detection and facial expression recognition in order to speed up the analysis of large data sets. The provided web interface weaves the multiple streams of information together, utilizes the extracted features as metadata on the audio and video data and lets the user dive into analyzing the recorded events. The objective of the system is to facilitate easy navigation of multimodal data and enable the analysis of the recorded situations for the purposes of, for example, behavioral studies, teacher training and business development. A further unique feature of the system is its low setup overhead and high portability as the lightest MORE setup only requires a laptop computer and the selected set of sensors on site.     

Common potholes in modeling solid–liquid reactions—methods for avoiding them

The reaction rate of a solid in fluids depends on the reactive surface area rather than its concentration. Even though, analytical techniques have been developed enormously during the past decades, the reliable quantification of solid surface areas during a reaction still remains a challenge. Due to this, still today indirect methods such as test plots play a key role in determining reaction mechanisms and kinetics. The modeling of solid–liquid reactions is a challenge as several assumptions and simplifications need to be made and distinguishing between different hypothesis is not always straightforward. The influence of the particle size distribution (PSD) and the change in the morphology of the solid phase during the reaction are one of the most crucial factors in determining the kinetics, as they are directly related to the quantification of the reactive surface area. Neglecting to consider these factors in modeling can cause misleading conclusions and wrongful parameter estimation with traditional methodology.Techniques for evaluation when it is adequate to use the traditional methodologies and when these factors need to be accounted for are provided in the current work. If the particle size distribution is close to the Gaussian distribution and if the particles are not very rough or porous, the traditional modeling practices can soundly be used. These properties are measured and quantified with the help of a variation coefficient (PSD) and a shape factor (particle morphology). It is demonstrated that how these factors influence the results obtained with traditional approaches. A practical technique for implementing the PSD into kinetic models by using the Gamma distribution is provided. Moreover, a method for taking into account different particle morphologies with the help of a shape factor and solid phase exponents is presented. The dissolution of gibbsite in NaOH is used as an example case. The methodology can be extended to unconventional changes in particle morphology during the reaction as well as different reaction mechanisms, e.g. product layer formation.