No abstract

1. The stag beetle, Lucanus cervus is Nationally Scarce in the UK, yet no methods exist for monitoring the abundance of adults or presence of the subterranean larvae.2. Here, we describe the design of an aerial flight interception trap that can be used to catch adults. Various lures were tested and ginger root was found to attract both sexes in equal numbers.3. Road transect surveys of adults killed by vehicles were found to produce reliable estimates of the total abundance of both sexes in areas up to about 12 km from the survey. 4. A novel use of radial diffusive samplers is described to infer the presence of larvae. Both larvae and adult females produce longifolene, which is highly attractive to males.5. Larvae produce a characteristic stridulation pattern, which can be recorded and distinguished from sounds produced by other saproxylic beetles that may co-occur with L. cervus.6. We conclude that aerial traps baited with ginger, combined with road transect surveys can be used to monitor population abundance of adults, while detection of longifolene and the characteristic stridulation pattern can be used to reveal larval presence, without destroying their fragile habitat.

Research into the automated identification of animals by bioacoustics is becoming more widespread mainly due to difficulties in carrying out manual surveys. This paper describes automated recognition of insects (Orthoptera) using time domain signal coding and artificial neural networks. Results of field recordings made in the UK in 2002 are presented which show that it is possible to accurately recognize 4 British Orthoptera species in natural conditions under high levels of interference. Work is under way to increase the number of species recognized.

We present the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) 1 designed for temporal signal recognition. The CLNN takes into consideration the temporal nature of the sound signal and the MCLNN extends upon the CLNN through a binary mask to preserve the spatial locality of the features and allows an automated exploration of the features combination analogous to hand-crafting the most relevant features for the recognition task. MCLNN has achieved competitive recognition accuracies on the GTZAN and the ISMIR2004 music datasets that surpass several state-of-theart neural network based architectures and hand-crafted methods applied on both datasets.

Wireless sensor networks (WSNs) consist of multiple, distributed nodes each with limited resources. With their strict resource constraints and application-specific characteristics, WSNs contain many challenging tradeoffs. This paper proposes a bioinspired load balancing approach, based on pheromone signalling mechanisms, to solve the tradeoff between service availability and energy consumption. We explore the performance consequences of the pheromone-based load balancing approach using (1) a system-level simulator, (2) deployment of real sensor testbeds to provide a competitive analysis of these evaluation methodologies. The effectiveness of the proposed algorithm is evaluated with different scenario parameters and the required performance evaluation techniques are investigated on case studies based on sound sensors.