A combined Bayesian Markovian approach for behaviour recognition

Numerous techniques exist which can be used for the task of behavioural analysis and recognition. Common amongst these are Bayesian networks and Hidden Markov Models. Although these techniques are extremely powerful and well developed, both have important limitations. By fusing these techniques together to form Bayes-Markov chains, the advantages of both techniques can be preserved, while reducing their limitations. The Bayes-Markov technique forms the basis of a common, flexible framework for supplementing Markov chains with additional features. This results in improved user output, and aids in the rapid development of flexible and efficient behaviour recognition systems.

Improvement of classification accuracy for stochastic discrimination - Multi-class classification

In this paper, an improved stochastic discrimination (SD) is introduced to reduce the error rate of the standard SD in the context of multi-class classification problem. The learning procedure of the improved SD consists of two stages. In the first stage, a standard SD, but with shorter learning period is carried out to identify an important space where all the misclassified samples are located. In the second stage, the standard SD is modified by (i) restricting sampling in the important space; and (ii) introducing a new discriminant function for samples in the important space. It is shown by mathematical derivation that the new discriminant function has the same mean, but smaller variance than that of standard SD for samples in the important space. It is also analyzed that the smaller the variance of the discriminant function, the lower the error rate of the classifier. Consequently, the proposed improved SD improves standard SD by its capability of achieving higher classification accuracy. Illustrative examples axe provided to demonstrate the effectiveness of the proposed improved SD.

Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands

In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into free, grass, building, and road regions by fusing remotely, sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and co-registered bands.

A camera based digit location and recognition system for garment tracking

Garment information tracking is required for clean room garment management. In this paper, we present a camera-based robust system with implementation of Optical Character Reconition (OCR) techniques to fulfill garment label recognition. In the system, a camera is used for image capturing; an adaptive thresholding algorithm is employed to generate binary images; Connected Component Labelling (CCL) is then adopted for object detection in the binary image as a part of finding the ROI (Region of Interest); Artificial Neural Networks (ANNs) with the BP (Back Propagation) learning algorithm are used for digit recognition; and finally the system is verified by a system database. The system has been tested. The results show that it is capable of coping with variance of lighting, digit twisting, background complexity, and font orientations. The system performance with association to the digit recognition rate has met the design requirement. It has achieved real-time and error-free garment information tracking during the testing.

Comparison of extrasystolic ECG signal classifiers using discrete wavelet transforms

This work compares and contrasts results of classifying time-domain ECG signals with pathological conditions taken from the MITBIH arrhythmia database. Linear discriminant analysis and a multi-layer perceptron were used as classifiers. The neural network was trained by two different methods, namely back-propagation and a genetic algorithm. Converting the time-domain signal into the wavelet domain reduced the dimensionality of the problem at least 10-fold. This was achieved using wavelets from the db6 family as well as using adaptive wavelets generated using two different strategies. The wavelet transforms used in this study were limited to two decomposition levels. A neural network with evolved weights proved to be the best classifier with a maximum of 99.6% accuracy when optimised wavelet-transform ECG data wits presented to its input and 95.9% accuracy when the signals presented to its input were decomposed using db6 wavelets. The linear discriminant analysis achieved a maximum classification accuracy of 95.7% when presented with optimised and 95.5% with db6 wavelet coefficients. It is shown that the much simpler signal representation of a few wavelet coefficients obtained through an optimised discrete wavelet transform facilitates the classification of non-stationary time-variant signals task considerably. In addition, the results indicate that wavelet optimisation may improve the classification ability of a neural network. (c) 2005 Elsevier B.V. All rights reserved.

On improvement of classification accuracy for stochastic discrimination

Stochastic discrimination (SD) depends on a discriminant function for classification. In this paper, an improved SD is introduced to reduce the error rate of the standard SD in the context of a two-class classification problem. The learning procedure of the improved SD consists of two stages. Initially a standard SD, but with shorter learning period is carried out to identify an important space where all the misclassified samples are located. Then the standard SD is modified by 1) restricting sampling in the important space, and 2) introducing a new discriminant function for samples in the important space. It is shown by mathematical derivation that the new discriminant function has the same mean, but with a smaller variance than that of the standard SD for samples in the important space. It is also analyzed that the smaller the variance of the discriminant function, the lower the error rate of the classifier. Consequently, the proposed improved SD improves standard SD by its capability of achieving higher classification accuracy. Illustrative examples are provided to demonstrate the effectiveness of the proposed improved SD.

Assessing the accuracy of a computerized decision support system for digoxin dosing in primary care: an observational study

Background: This study was carried out as part of a European Union funded project (PharmDIS-e+), to develop and evaluate software aimed at assisting physicians with drug dosing. A drug that causes particular problems with drug dosing in primary care is digoxin because of its narrow therapeutic range and low therapeutic index. Objectives: To determine (i) accuracy of the PharmDIS-e+ software for predicting serum digoxin levels in patients who are taking this drug regularly; (ii) whether there are statistically significant differences between predicted digoxin levels and those measured by a laboratory and (iii) whether there are differences between doses prescribed by general practitioners and those suggested by the program. Methods: We needed 45 patients to have 95% Power to reject the null hypothesis that the mean serum digoxin concentration was within 10% of the mean predicted digoxin concentration. Patients were recruited from two general practices and had been taking digoxin for at least 4 months. Exclusion criteria were dementia, low adherence to digoxin and use of other medications known to interact to a clinically important extent with digoxin. Results: Forty-five patients were recruited. There was a correlation of 0·65 between measured and predicted digoxin concentrations (P < 0·001). The mean difference was 0·12 μg/L (SD 0·26; 95% CI 0·04, 0·19, P = 0·005). Forty-seven per cent of the patients were prescribed the same dose as recommended by the software, 44% were prescribed a higher dose and 9% a lower dose than recommended. Conclusion: PharmDIS-e+ software was able to predict serum digoxin levels with acceptable accuracy in most patients.

Evidence that indirect inhibition of saccade initiation improves saccade accuracy

Saccadic eye-movements to a visual target are less accurate if there are distracters close to its location (local distracters). The addition of more distracters, remote from the target location (remote distracters), invokes an involuntary increase in the response latency of the saccade and attenuates the effect of local distracters on accuracy. This may be due to the target and distracters directly competing (direct route) or to the remote distracters acting to impair the ability to disengage from fixation (indirect route). To distinguish between these we examined the development of saccade competition by recording saccade latency and accuracy responses made to a target and local distracter compared with those made with an addition of a remote distracter. The direct route would predict that the remote distracter impacts on the developing competition between target and local distracter, while the indirect route would predict no change as the accuracy benefit here derives from accessing the same competitive process but at a later stage. We found that the presence of the remote distracter did not change the pattern of accuracy improvement. This suggests that the remote distracter was acting along an indirect route that inhibits disengagement from fixation, slows saccade initiation, and enables more accurate saccades to be made.

A β-amino acid modified heptapeptide containing a designed recognition element disrupts fibrillization of the amyloid β-peptide

We study the complex formation of a peptide betaAbetaAKLVFF, previously developed by our group, with Abeta(1–42) in aqueous solution. Circular dichroism spectroscopy is used to probe the interactions between betaAbetaAKLVFF and Abeta(1–42), and to study the secondary structure of the species in solution. Thioflavin T fluorescence spectroscopy shows that the population of fibers is higher in betaAbetaAKLVFF/Abeta(1–42) mixtures compared to pure Abeta(1–42) solutions. TEM and cryo-TEM demonstrate that co-incubation of betaAbetaAKLVFF with Abeta(1–42) causes the formation of extended dense networks of branched fibrils, very different from the straight fibrils observed for Abeta(1–42) alone. Neurotoxicity assays show that although betaAbetaAKLVFF alters the fibrillization of Abeta(1–42), it does not decrease the neurotoxicity, which suggests that toxic oligomeric Abeta(1–42) species are still present in the betaAbetaAKLVFF/Abeta(1–42) mixtures. Our results show that our designed peptide binds to Abeta(1–42) and changes the amyloid fibril morphology. This is shown to not necessarily translate into reduced toxicity.

Sterically controlled recognition of macromolecular sequence information by molecular tweezers

Sequence-specific binding is demonstrated between pyrene-based tweezer molecules and soluble, high molar mass copolyimides. The binding involves complementary pi - pi stacking interactions, polymer chain-folding, and hydrogen bonding and is extremely sensitive to the steric environment around the pyromellitimide binding-site. A detailed picture of the intermolecular interactions involved has been obtained through single-crystal X-ray studies of tweezer complexes with model diimides. Ring-current magnetic shielding of polyimide protons by the pyrene '' arms '' of the tweezer molecule induces large complexation shifts of the corresponding H-1 NMR resonances, enabling specific triplet sequences to be identified by their complexation shifts. Extended comonomer sequences (triplets of triplets in which the monomer residues differ only by the presence or absence of a methyl group) can be '' read '' by a mechanism which involves multiple binding of tweezer molecules to adjacent diimide residues within the copolymer chain. The adjacent-binding model for sequence recognition has been validated by two conceptually different sets of tweezer binding experiments. One approach compares sequence-recognition events for copolyimides having either restricted or unrestricted triple-triplet sequences, and the other makes use of copolymers containing both strongly binding and completely nonbinding diimide residues. In all cases the nature and relative proportions of triple-triplet sequences predicted by the adjacent-binding model are fully consistent with the observed H-1 NMR data.

Threshold-free object and ground point separation in LIDAR data

Light Detection And Ranging (LIDAR) is an important modality in terrain and land surveying for many environmental, engineering and civil applications. This paper presents the framework for a recently developed unsupervised classification algorithm called Skewness Balancing for object and ground point separation in airborne LIDAR data. The main advantages of the algorithm are threshold-freedom and independence from LIDAR data format and resolution, while preserving object and terrain details. The framework for Skewness Balancing has been built in this contribution with a prediction model in which unknown LIDAR tiles can be categorised as “hilly” or “moderate” terrains. Accuracy assessment of the model is carried out using cross-validation with an overall accuracy of 95%. An extension to the algorithm is developed to address the overclassification issue for hilly terrain. For moderate terrain, the results show that from the classified tiles detached objects (buildings and vegetation) and attached objects (bridges and motorway junctions) are separated from bare earth (ground, roads and yards) which makes Skewness Balancing ideal to be integrated into geographic information system (GIS) software packages.