ARE ARTIFICIAL NEURAL NETS AS SMART AS A RAT

The origins of artificial neural networks are related to animal conditioning theory: both are forms of connectionist theory, which in turn derives from the empiricist philosophers' principle of association. The parallel between animal learning and neural nets suggests that interaction between them should benefit both sides.

Determining propeller induced erosion alongside quay walls in harbours using Artificial Neural Networks

In shallow waters, such as those found close to berth structures, the wash from a manoeuvring ship’s propeller can cause erosion of the seabed. This erosion can be increased if the wash intersects a berth structure. A number of researchers have undertaken model studies and used regression analysis to develop predictive relationships for the scouring action. This paper presents an experimental investigation with Artificial Neural Networks (ANN’s), used to analyse the results. The purpose of using ANN’s was to examine the prediction accuracy of the Networks in comparison with previous regression analysis methods. ANN’s were found to provide a more accurate method of predicting propeller wash scour than the equations presented by previous investigators.

Demo: Have a Chat with Sensitive Artificial Listeners

Sensitive Artificial Listeners (SAL) are virtual dialogue partners based on audiovisual analysis and synthesis. Despite their very limited verbal understanding, they intend to engage the user in a conversation by paying attention to the user’s emotions and non- verbal expressions. The SAL characters have their own emotionally defined personality, and attempt to drag the user towards their dom- inant emotion through a combination of verbal and non-verbal ex- pression. The demonstrator shows the publicly available, fully au- tonomous SAL system.

Application of artificial neural network techniques to low bit-rate speech coding

Research has been undertaken to investigate the use of artificial neural network (ANN) techniques to improve the performance of a low bit-rate vector transform coder. Considerable improvements in the perceptual quality of the coded speech have been obtained. New ANN-based methods for vector quantiser (VQ) design and for the adaptive updating of VQ codebook are introduced for use in speech coding applications.

Fasciola hepatica:Histological demonstration of apoptosis in the reproductive organs of flukes of triclabendazole-sensitive and triclabendazole-resistant isolates, and in field-derived flukes from triclabendazole-treated hosts, using in situ hybridisation to visualise endonuclease-generated DNA strand breaks

Investigation of the triclabendazole (TCBZ) resistance status of populations of Fasciola hepatica in field cases of fasciolosis, where treatment failure has been reported, can be supported by histological examination of flukes collected from recently treated hosts. In TCBZ-sensitive flukes (TCBZ-S) exposed to TCBZ metabolites for 1-4. days in vivo, but not in TCBZ-resistant flukes (TCBZ-R), morphological changes suggestive of apoptosis occur in cells undergoing meiosis or mitosis in the testis, ovary and vitelline follicles. In order to verify or refute the contention that efficacy of TCBZ treatment is associated with apoptosis in the reproductive organs of flukes, histological sections of TCBZ-S (Cullompton isolate) flukes and TCBZ-R (Sligo isolate) flukes were subjected to the TdT-mediated dUDP nick end labelling (TUNEL) in situ hybridisation method, a commercially available test specifically designed to label endonuclease-induced DNA strand breaks associated with apoptosis. Additionally, sections of in vivo-treated and untreated flukes originating from field outbreaks of suspected TCBZ-S and TCBZ-R fasciolosis were labelled by the TUNEL method. It was found that in treated TCBZ-S flukes, strong positive labelling indicating apoptosis was associated with morphologically abnormal cells undergoing mitosis or meiosis in the testis, ovary and vitelline follicles. Background labelling in the positive testis sections was attributed to heterophagy of cell debris by the sustentacular tissue. The triggering of apoptosis was probably related to failure of spindle formation at cell division, supporting the contention that TCBZ inhibits microtubule formation. In treated TCBZ-R (Sligo Type 1) flukes, and in treated flukes from field outbreaks of suspected TCBZ-R fasciolosis, no significant labelling was observed, while sections of fluke derived from a field case of fasciolosis where TCBZ resistance was not suspected were heavily labelled. Light labelling was associated with the testis of untreated Cullompton (TCBZ-S) and Sligo Type 2 (TCBZ-R) flukes, which exhibit abnormal spermatogenesis and spermiogenesis, respectively. This was attributed to apoptosis and to heterophagy of effete germ line cells by the sustentacular tissue. It is concluded that demonstration of apoptosis by in situ hybridisation using the TUNEL method on sections of 1-4. days in vivo TCBZ-treated F. hepatica can contribute to the diagnosis of TCBZ resistance in field outbreaks of fasciolosis. © 2012 Elsevier B.V.

Community convergence and recruitment of keystone species as performance indicators of artificial reefs

An experimental artificial reefwas constructed in Strangford Lough, Northern Ireland as part of trials to regenerate damaged biogenic reefs formed by the horse mussel Modiolus modiolus. Experimental reef plots were constructed using Pecten maximus shell as cultch. Clumps of live adult M. modiolus were translocated from nearby natural reefs into cultchwith a high profile (elevated cultch), cultch with a lowprofile (flattened cultch), as well as directly into the seafloor. The aim of the study was to test the hypothesis that translocated mussel clumps would increase habitat complexity thus accelerating community succession and enhancing natural recruitment of M. modiolus spat. These effects were predicted to be greater on elevated cultch due to greater protection from
predators and increased accessibility to food resources. Within the artificial reef array the translocated clumps had a significant positive effect on recruitment compared to cultch without mussels with average densities of spat settled on the translocated M. modiolus clumps ranging from 100 to 200 individuals m-2 compared to 4 to 52 spat m-2 on cultch without mussels. Recruitment of M. modiolus spat was also significantly higher on translocated horse mussels when compared to natural reefs where densities of 8–36 spat m-2 were recorded.
Reef elevation appeared to provide some degree of protection from predators but differences in translocated M. modiolus survival on the different elevation treatments were not significant. In total, 223 taxa were recorded 12 months after reef construction. The presence of translocated clumps ofM. modiolus was the main driver of the increases in faunal diversity and species abundance. Application of objective criteria to assess the performance of artificial reefs suggested that translocation of M. modiolus clumps alone achieved most of the restoration objectives. Consequently this pilot study demonstrates a straightforward and realistic intervention technique that could be used to kick start the regeneration and expansion of impacted mussel and similar biogenic reefs elsewhere.