Normal and anomalous classification of category exemplars in schizophrenia

Background Schizophrenia has been associated with semantic memory impairment and previous studies report a difficulty in accessing semantic category exemplars (Moelter et al. 2005 Schizophr Res 78:209–217). The anterior temporal cortex (ATC) has been implicated in the representation of semantic knowledge (Rogers et al. 2004 Psychol Rev 111(1):205–235). We conducted a high-field (4T) fMRI study with the Category Judgment and Substitution Task (CJAST), an analogue of the Hayling test. We hypothesised that differential activation of the temporal lobe would be observed in schizophrenia patients versus controls. Methods Eight schizophrenia patients (7M : 1F) and eight matched controls performed the CJAST, involving a randomised series of 55 common nouns (from five semantic categories) across three conditions: semantic categorisation, anomalous categorisation and word reading. High-resolution 3D T1-weighted images and GE EPI with BOLD contrast and sparse temporal sampling were acquired on a 4T Bruker MedSpec system. Image processing and analyses were performed with SPM2. Results Differential activation in the left ATC was found for anomalous categorisation relative to category judgment, in patients versus controls. Conclusions We examined semantic memory deficits in schizophrenia using a novel fMRI task. Since the ATC corresponds to an area involved in accessing abstract semantic representations (Moelter et al. 2005), these results suggest schizophrenia patients utilise the same neural network as healthy controls, however it is compromised in the patients and the different ATC activity might be attributable to weakening of category-to-category associations.

Genetic organization of Pasteurella multocida cap Loci and development of a multiplex capsular PCR typing system

Current serotyping methods classify Pasteurella multocida into five capsular serogroups (serogroups A, B, D, E, and F) and 16 somatic serotypes (serotypes 1 to 16). In the present study, we have developed a multiplex PCR assay as a rapid alternative to the conventional capsular serotyping system. The serogroup-specific primers used in this assay were designed following identification, sequence determination, and analysis of the capsular biosynthetic loci of each capsular serogroup. The entire capsular biosynthetic loci of P. multocida A:1 (X-73) and B:2 (M1404) have been cloned and sequenced previously (J. Y. Chung, Y. M. Zhang, and B. Adler, FEMS Microbiol. Lett. 166:289-296, 1998; J. D. Boyce, J. Y. Chung, and B. Adler, Vet. Microbiol. 72:121-134, 2000). Nucleotide sequence analysis of the biosynthetic region (region 2) from each of the remaining three serogroups, serogroups D, E, and F, identified serogroup-specific regions and gave an indication of the capsular polysaccharide composition. The multiplex capsular PCR assay was highly specific, and its results, with the exception of those for some serogroup F strains, correlated well with conventional serotyping results. Sequence analysis of the strains that gave conflicting results confirmed the validity of the multiplex PCR and indicated that these strains were in fact capsular serogroup A. The multiplex PCR will clarify the distinction between closely related serogroups A and F and constitutes a rapid assay for the definitive classification of P. multocida capsular types

Using the EM Algorithm to Train Neural Networks: Misconceptions and a New Algorithm for Multiclass Classification

The expectation-maximization (EM) algorithm has been of considerable interest in recent years as the basis for various algorithms in application areas of neural networks such as pattern recognition. However, there exists some misconceptions concerning its application to neural networks. In this paper, we clarify these misconceptions and consider how the EM algorithm can be adopted to train multilayer perceptron (MLP) and mixture of experts (ME) networks in applications to multiclass classification. We identify some situations where the application of the EM algorithm to train MLP networks may be of limited value and discuss some ways of handling the difficulties. For ME networks, it is reported in the literature that networks trained by the EM algorithm using iteratively reweighted least squares (IRLS) algorithm in the inner loop of the M-step, often performed poorly in multiclass classification. However, we found that the convergence of the IRLS algorithm is stable and that the log likelihood is monotonic increasing when a learning rate smaller than one is adopted. Also, we propose the use of an expectation-conditional maximization (ECM) algorithm to train ME networks. Its performance is demonstrated to be superior to the IRLS algorithm on some simulated and real data sets.

Hierarchical organisation of neuro-anatomical constraints in interlimb coordination

Based on the observation that bimanual finger tapping movements tend toward mirror symmetry with respect to the body midline, despite the synchronous activation of non-homologous muscles, F. Mechsner, D. Kerzel, G. Knoblich, and W. Prinz (2001) [Perceptual basis of bimanual coordination. Nature, 414, 69-73] suggested that the basis of rhythmic coordination is purely spatial/perceptual in nature, and independent of the neuro-anatomical constraints of the motor system. To investigate this issue further, we employed a four finger tapping task similar to that used by F. Mechsner and G. Knoblich (2004) [Do muscle matter in bimanual coordination? Journal of Experimental Psychology: Human Perception and Performance, 30, 490-503] in which six male participants were required to alternately tap combinations of adjacent pairs of index (1), middle (M) and ring (R) fingers of each hand in time with an auditory metronome. The metronome pace increased continuously from 1 Hz to 3 Hz over the course of a 30-s trial. Each participant performed three blocks of trials in which finger combination for each hand (IM or MR) and mode of coordination (mirror or parallel) were presented in random order. Within each block, the right hand was placed in one of three orientations; prone, neutral and supine. The order of blocks was counterbalanced across the six participants. The left hand maintained a prone position throughout the experiment. On the basis of discrete relative phase analyses between synchronised taps, the time at which the initial mode of coordination was lost was determined for each trial. When the right hand was prone, transitions occurred only from parallel symmetry to mirror symmetry, regardless of finger combination. In contrast, when the right hand was supine, transitions occurred only from mirror symmetry to parallel but no transitions were observed in the opposite direction. In the right hand neutral condition, mirror and parallel symmetry are insufficient to describe the modes of coordination since the hands are oriented orthogonally. When defined anatomically, however, the results in each of the three right hand orientations are consistent. That is, synchronisation of finger tapping is deter-mined by a hierarchy of control of individual fingers based on their intrinsic neuro-mechanical properties rather than on the basis of their spatial orientation. (c) 2005 Elsevier B.V. All rights reserved.

Application and evaluation of classification trees for screening unwanted plants

Risk assessment systems for introduced species are being developed and applied globally, but methods for rigorously evaluating them are still in their infancy. We explore classification and regression tree models as an alternative to the current Australian Weed Risk Assessment system, and demonstrate how the performance of screening tests for unwanted alien species may be quantitatively compared using receiver operating characteristic (ROC) curve analysis. The optimal classification tree model for predicting weediness included just four out of a possible 44 attributes of introduced plants examined, namely: (i) intentional human dispersal of propagules; (ii) evidence of naturalization beyond native range; (iii) evidence of being a weed elsewhere; and (iv) a high level of domestication. Intentional human dispersal of propagules in combination with evidence of naturalization beyond a plants native range led to the strongest prediction of weediness. A high level of domestication in combination with no evidence of naturalization mitigated the likelihood of an introduced plant becoming a weed resulting from intentional human dispersal of propagules. Unlikely intentional human dispersal of propagules combined with no evidence of being a weed elsewhere led to the lowest predicted probability of weediness. The failure to include intrinsic plant attributes in the model suggests that either these attributes are not useful general predictors of weediness, or data and analysis were inadequate to elucidate the underlying relationship(s). This concurs with the historical pessimism that we will ever be able to accurately predict invasive plants. Given the apparent importance of propagule pressure (the number of individuals of an species released), future attempts at evaluating screening model performance for identifying unwanted plants need to account for propagule pressure when collating and/or analysing datasets. The classification tree had a cross-validated sensitivity of 93.6% and specificity of 36.7%. Based on the area under the ROC curve, the performance of the classification tree in correctly classifying plants as weeds or non-weeds was slightly inferior (Area under ROC curve = 0.83 +/- 0.021 (+/- SE)) to that of the current risk assessment system in use (Area under ROC curve = 0.89 +/- 0.018 (+/- SE)), although requires many fewer questions to be answered.

Using machine vision classification to control access of animals to water

Invasive vertebrate pests together with overabundant native species cause significant economic and environmental damage in the Australian rangelands. Access to artificial watering points, created for the pastoral industry, has been a major factor in the spread and survival of these pests. Existing methods of controlling watering points are mechanical and cannot discriminate between target species. This paper describes an intelligent system of controlling watering points based on machine vision technology. Initial test results clearly demonstrate proof of concept for machine vision in this application. These initial experiments were carried out as part of a 3-year project using machine vision software to manage all large vertebrates in the Australian rangelands. Concurrent work is testing the use of automated gates and innovative laneway and enclosure design. The system will have application in any habitat throughout the world where a resource is limited and can be enclosed for the management of livestock or wildlife.

Real-Time Gene-Expression Extraction with Fast Classification (FC) Networks

Fast Classification (FC) networks were inspired by a biologically plausible mechanism for short term memory where learning occurs instantaneously. Both weights and the topology for an FC network are mapped directly from the training samples by using a prescriptive training scheme. Only two presentations of the training data are required to train an FC network. Compared with iterative learning algorithms such as Back-propagation (which may require many hundreds of presentations of the training data), the training of FC networks is extremely fast and learning convergence is always guaranteed. Thus FC networks may be suitable for applications where real-time classification is needed. In this paper, the FC networks are applied for the real-time extraction of gene expressions for Chlamydia microarray data. Both the classification performance and learning time of the FC networks are compared with the Multi-Layer Proceptron (MLP) networks and support-vector-machines (SVM) in the same classification task. The FC networks are shown to have extremely fast learning time and comparable classification accuracy.

Towards a standards-based autonomic context management system

Pervasive computing applications must be sufficiently autonomous to adapt their behaviour to changes in computing resources and user requirements. This capability is known as context-awareness. In some cases, context-aware applications must be implemented as autonomic systems which are capable of dynamically discovering and replacing context sources (sensors) at run-time. Unlike other types of application autonomy, this kind of dynamic reconfiguration has not been sufficiently investigated yet by the research community. However, application-level context models are becoming common, in order to ease programming of context-aware applications and support evolution by decoupling applications from context sources. We can leverage these context models to develop general (i.e., application-independent) solutions for dynamic, run-time discovery of context sources (i.e., context management). This paper presents a model and architecture for a reconfigurable context management system that supports interoperability by building on emerging standards for sensor description and classification.