Prediction of GC retention values under various column temperature conditions from temperature programmed data

A numerical approach has been developed for the correlation of retention limes (total retention lime) with temperature in gas chromatography, which allows the calculation of retention parameters including retention index from data acquired under two or more different temperature program conditions. By using this procedure the optimization of temperature condition can be further achieved, especially when a temperature-programmed run is the most suitable mode in the preliminary development of an analytical method for the analysis of an unknown sample.

Prediction of soil organic partition coefficients by a soil leaching column chromatographic method

The soil organic partition coefficient (K-oc) is one of the most important parameters to depict the transfer and fate of a chemical in the soil-water system. Predicting K-oc by using a chromatographic technique has been developing into a convenient and low-cost method. In this paper, a soil leaching column chromatograpy (SLCC) method employing the soil column packed with reference soil GSE 17201 (obtained from Bayer Landwirtschaftszentrum, Monheim, Germany) and methanol-water eluents was developed to predict the K-oc of hydrophobic organic chemicals (HOCs), over a log K-oc range of 4.8 orders of magnitude, from their capacity factors. The capacity factor with water as an eluent (k(w)') could be obtained by linearly extrapolating capacity factors in methanol-water eluents (k') with various volume fractions of methanol (phi). The important effects of solute activity coefficients in water on k(w)' and K-oc were illustrated. Hence, the correlation between log K-oc and log k(w)' (and log k') exists in the soil. The correlation coefficient (r) of the log K-oc vs. log k(w)' correlation for 58 apolar and polar compounds could reach 0.987, while the correlation coefficients of the log K-oc-log k' correlations were no less than 0.968, with phi ranging from 0 to 0.50. The smaller the phi, the higher the r. Therefore, it is recommended that the eluent of smaller phi, such as water, be used for accurately estimating K-oc. Correspondingly, the r value of the log K-oc-log k(w)' correlation on a reversed-phase Hypersil ODS (Thermo Hypersil, Kleinostheim, Germany) column was less than 0.940 for the same solutes. The SLCC method could provide a more reliable route to predict K-oc indirectly from a correlation with k(w)' than the reversed-phase liquid chromatographic (RPLC) one.

Resolution prediction and optimization of temperature programme in comprehensive two-dimensional gas chromatography

A model is developed for predicting the resolution of interested component pair and calculating the optimum temperature programming condition in the comprehensive two-dimensional gas chromatography (GC x GC). Based on at least three isothermal runs, retention times and the peak widths at half-height on both dimensions are predicted for any kind of linear temperature-programmed run on the first dimension and isothermal runs on the second dimension. The calculation of the optimum temperature programming condition is based on the prediction of the resolution of "difficult-to-separate components" in a given mixture. The resolution of all the neighboring peaks on the first dimension is obtained by the predicted retention time and peak width on the first dimension, the resolution on the second dimension is calculated only for the adjacent components with un-enough resolution on the first dimension and eluted within a same modulation period on the second dimension. The optimum temperature programming condition is acquired when the resolutions of all components of interest by GC x GC separation meet the analytical requirement and the analysis time is the shortest. The validity of the model has been proven by using it to predict and optimize GC x GC temperature programming condition of an alkylpyridine mixture. (c) 2005 Elsevier B.V. All rights reserved.

Prediction of 30-day mortality in older patients with a first acute myocardial infarction

This study sought predictors of mortality in patients aged >or=75 years with a first ST-segment elevation myocardial infarction (STEMI) and evaluated the validity of the GUSTO-I and TIMI risk models. Clinical variables, treatment and mortality data from 433 consecutive patients were collected. Univariable and multivariable logistic regression analyses were applied to identify baseline factors associated with 30-day mortality. Subsequently a model predicting 30-day mortality was created and compared with the performance of the GUSTO-I and TIMI models. After adjustment, a higher Killip class was the most important predictor (OR 16.1; 95% CI 5.7-45.6). Elevated heart rate, longer time delay to admission, hyperglycemia and older age were also associated with increased risk. Patients with hypercholesterolemia had a significantly lower risk (OR 0.46; 95% CI 0.24-0.86). Discrimination (c-statistic 0.79, 95% CI 0.75-0.84) and calibration (Hosmer-Lemeshow 6, p = 0.5) of our model were good. The GUSTO-I and TIMI risk scores produced adequate discrimination within our dataset (c-statistic 0.76, 95% CI 0.71-0.81, and c-statistic 0.77, 95% CI 0.72-0.82, respectively), but calibration was not satisfactory (HL 21.8, p = 0.005 for GUSTO-I, and HL 20.6, p = 0.008 for TIMI). In conclusion, short-term mortality in elderly patients with a first STEMI depends most importantly on initial clinical and hemodynamic status. The GUSTO-I and TIMI models are insufficiently adequate for providing an exact estimate of 30-day mortality risk.

Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma

X. Wang, J. Yang, R. Jensen and X. Liu, 'Rough Set Feature Selection and Rule Induction for Prediction of Malignancy Degree in Brain Glioma,' Computer Methods and Programs in Biomedicine, vol. 83, no. 2, pp. 147-156, 2006.

Prediction of Physical Properties of Yeast Cell Suspensions using Dielectric Spectroscopy

D.J. Currie, M.H. Lee and R.W. Todd, 'Prediction of Physical Properties of Yeast Cell Suspensions using Dielectric Spectroscopy', Conference on Electrical Insulation and Dielectric Phenomena, (CEIDP 2006), Annual Report, pp 672 ? 675, October 15th -18th 2006, Kansas City, Missouri, USA. Organised by IEEE Dielectrics and Electrical Insulation Society.

Integration of relational and hierarchical network information for protein function prediction

BACKGROUND:In the current climate of high-throughput computational biology, the inference of a protein's function from related measurements, such as protein-protein interaction relations, has become a canonical task. Most existing technologies pursue this task as a classification problem, on a term-by-term basis, for each term in a database, such as the Gene Ontology (GO) database, a popular rigorous vocabulary for biological functions. However, ontology structures are essentially hierarchies, with certain top to bottom annotation rules which protein function predictions should in principle follow. Currently, the most common approach to imposing these hierarchical constraints on network-based classifiers is through the use of transitive closure to predictions.RESULTS:We propose a probabilistic framework to integrate information in relational data, in the form of a protein-protein interaction network, and a hierarchically structured database of terms, in the form of the GO database, for the purpose of protein function prediction. At the heart of our framework is a factorization of local neighborhood information in the protein-protein interaction network across successive ancestral terms in the GO hierarchy. We introduce a classifier within this framework, with computationally efficient implementation, that produces GO-term predictions that naturally obey a hierarchical 'true-path' consistency from root to leaves, without the need for further post-processing.CONCLUSION:A cross-validation study, using data from the yeast Saccharomyces cerevisiae, shows our method offers substantial improvements over both standard 'guilt-by-association' (i.e., Nearest-Neighbor) and more refined Markov random field methods, whether in their original form or when post-processed to artificially impose 'true-path' consistency. Further analysis of the results indicates that these improvements are associated with increased predictive capabilities (i.e., increased positive predictive value), and that this increase is consistent uniformly with GO-term depth. Additional in silico validation on a collection of new annotations recently added to GO confirms the advantages suggested by the cross-validation study. Taken as a whole, our results show that a hierarchical approach to network-based protein function prediction, that exploits the ontological structure of protein annotation databases in a principled manner, can offer substantial advantages over the successive application of 'flat' network-based methods.

Improved Tracking of Multiple Humans with Trajectory Prediction and Occlusion Modeling

A combined 2D, 3D approach is presented that allows for robust tracking of moving bodies in a given environment as observed via a single, uncalibrated video camera. Tracking is robust even in the presence of occlusions. Low-level features are often insufficient for detection, segmentation, and tracking of non-rigid moving objects. Therefore, an improved mechanism is proposed that combines low-level (image processing) and mid-level (recursive trajectory estimation) information obtained during the tracking process. The resulting system can segment and maintain the tracking of moving objects before, during, and after occlusion. At each frame, the system also extracts a stabilized coordinate frame of the moving objects. This stabilized frame is used to resize and resample the moving blob so that it can be used as input to motion recognition modules. The approach enables robust tracking without constraining the system to know the shape of the objects being tracked beforehand; although, some assumptions are made about the characteristics of the shape of the objects, and how they evolve with time. Experiments in tracking moving people are described.

Estimation and Prediction of Evolving Color Distributions for Skin Segmentation Under Varying Illumination

A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and based on predictions of the Markov model. The evolution of the skin color distribution at each frame is parameterized by translation, scaling and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and re-sampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using Maximum Likelihood Estimation, and also evolve over time. Quantitative evaluation of the method was conducted on labeled ground-truth video sequences taken from popular movies.

Biased ART: A Neural Architecture that Shifts Attention Toward Previously Disregarded Features Following an Incorrect Prediction

Memories in Adaptive Resonance Theory (ART) networks are based on matched patterns that focus attention on those portions of bottom-up inputs that match active top-down expectations. While this learning strategy has proved successful for both brain models and applications, computational examples show that attention to early critical features may later distort memory representations during online fast learning. For supervised learning, biased ARTMAP (bARTMAP) solves the problem of over-emphasis on early critical features by directing attention away from previously attended features after the system makes a predictive error. Small-scale, hand-computed analog and binary examples illustrate key model dynamics. Twodimensional simulation examples demonstrate the evolution of bARTMAP memories as they are learned online. Benchmark simulations show that featural biasing also improves performance on large-scale examples. One example, which predicts movie genres and is based, in part, on the Netflix Prize database, was developed for this project. Both first principles and consistent performance improvements on all simulation studies suggest that featural biasing should be incorporated by default in all ARTMAP systems. Benchmark datasets and bARTMAP code are available from the CNS Technology Lab Website: http://techlab.bu.edu/bART/.

Integrating Symbolic and Neural Processing in a Self-Organizing Architechture for Pattern Recognition and Prediction

British Petroleum (89A-1204); Defense Advanced Research Projects Agency (N00014-92-J-4015); National Science Foundation (IRI-90-00530); Office of Naval Research (N00014-91-J-4100); Air Force Office of Scientific Research (F49620-92-J-0225)

ART-EMAP: A Neural Network Architecture for Learning and Prediction by Evidence Accumulation

This paper introduces ART-EMAP, a neural architecture that uses spatial and temporal evidence accumulation to extend the capabilities of fuzzy ARTMAP. ART-EMAP combines supervised and unsupervised learning and a medium-term memory process to accomplish stable pattern category recognition in a noisy input environment. The ART-EMAP system features (i) distributed pattern registration at a view category field; (ii) a decision criterion for mapping between view and object categories which can delay categorization of ambiguous objects and trigger an evidence accumulation process when faced with a low confidence prediction; (iii) a process that accumulates evidence at a medium-term memory (MTM) field; and (iv) an unsupervised learning algorithm to fine-tune performance after a limited initial period of supervised network training. ART-EMAP dynamics are illustrated with a benchmark simulation example. Applications include 3-D object recognition from a series of ambiguous 2-D views.

A Neural Network Architecture for Autonomous Learning, Recognition, and Prediction in a Nonstationary World

In a constantly changing world, humans are adapted to alternate routinely between attending to familiar objects and testing hypotheses about novel ones. We can rapidly learn to recognize and narne novel objects without unselectively disrupting our memories of familiar ones. We can notice fine details that differentiate nearly identical objects and generalize across broad classes of dissimilar objects. This chapter describes a class of self-organizing neural network architectures--called ARTMAP-- that are capable of fast, yet stable, on-line recognition learning, hypothesis testing, and naming in response to an arbitrary stream of input patterns (Carpenter, Grossberg, Markuzon, Reynolds, and Rosen, 1992; Carpenter, Grossberg, and Reynolds, 1991). The intrinsic stability of ARTMAP allows the system to learn incrementally for an unlimited period of time. System stability properties can be traced to the structure of its learned memories, which encode clusters of attended features into its recognition categories, rather than slow averages of category inputs. The level of detail in the learned attentional focus is determined moment-by-moment, depending on predictive success: an error due to over-generalization automatically focuses attention on additional input details enough of which are learned in a new recognition category so that the predictive error will not be repeated. An ARTMAP system creates an evolving map between a variable number of learned categories that compress one feature space (e.g., visual features) to learned categories of another feature space (e.g., auditory features). Input vectors can be either binary or analog. Computational properties of the networks enable them to perform significantly better in benchmark studies than alternative machine learning, genetic algorithm, or neural network models. Some of the critical problems that challenge and constrain any such autonomous learning system will next be illustrated. Design principles that work together to solve these problems are then outlined. These principles are realized in the ARTMAP architecture, which is specified as an algorithm. Finally, ARTMAP dynamics are illustrated by means of a series of benchmark simulations.