Human vs. machine : identification of bat species from their echolocation calls by humans and by artificial neural networks

Automated remote ultrasound detectors allow large amounts of data on bat presence and activity to be collected. Processing of such data involves identifying bat species from their echolocation calls. Automated species identification has the potential to provide more consistent, predictable, and potentially higher levels of accuracy than identification by humans. In contrast, identification by humans permits flexibility and intelligence in identification, as well as the incorporation of features and patterns that may be difficult to quantify. We compared humans with artificial neural networks (ANNs) in their ability to classify short recordings of bat echolocation calls of variable signal to noise ratios; these sequences are typical of those obtained from remote automated recording systems that are often used in large-scale ecological studies. We presented 45 recordings (1–4 calls) produced by known species of bats to ANNs and to 26 human participants with 1 month to 23 years of experience in acoustic identification of bats. Humans correctly classified 86% of recordings to genus and 56% to species; ANNs correctly identified 92% and 62%, respectively. There was no significant difference between the performance of ANNs and that of humans, but ANNs performed better than about 75% of humans. There was little relationship between the experience of the human participants and their classification rate. However, humans with <1 year of experience performed worse than others. Currently, identification of bat echolocation calls by humans is suitable for ecological research, after careful consideration of biases. However, improvements to ANNs and the data that they are trained on may in future increase their performance to beyond those demonstrated by humans.

Identification of New Zealand bats in flight from analysis of echolocation calls by artificial neural networks.

Time-expanded and heterodyned echolocation calls of the New Zealand long-tailed Chalinolobus tuberculatus and lesser short-tailed bat Mystacina tuberculata were recorded and digitally analysed. Temporal and spectral parameters were measured from time-expanded calls and power spectra generated for both time-expanded and heterodyned calls. Artificial neural networks were trained to classify the calls of both species using temporal and spectral parameters and power spectra as input data. Networks were then tested using data not previously seen. Calls could be unambiguously identified using parameters and power spectra from time-expanded calls. A neural network, trained and tested using power spectra of calls from both species recorded using a heterodyne detector set to 40 kHz (the frequency with the most energy of the fundamental of C. tuberculatus call), could identify 99% and 84% of calls of C. tuberculatus and M. tuberculata, respectively. A second network, trained and tested using power spectra of calls from both species recorded using a heterodyne detector set to 27 kHz (the frequency with the most energy of the fundamental of M. tuberculata call), could identify 34% and 100% of calls of C. tuberculatus and M. tuberculata, respectively. This study represents the first use of neural networks for the identification of bats from their echolocation calls. It is also the first study to use power spectra of time-expanded and heterodyned calls for identification of chiropteran species. The ability of neural networks to identify bats from their echolocation calls is discussed, as is the ecology of both species in relation to the design of their echolocation calls.

Acoustic identification of 12 species of echolocating bat by discriminant function analysis and artificial neural networks

We recorded echolocation calls from 14 sympatric species of bat in Britain. Once digitised, one temporal and four spectral features were measured from each call. The frequency-time course of each call was approximated by fitting eight mathematical functions, and the goodness of fit, represented by the mean-squared error, was calculated. Measurements were taken using an automated process that extracted a single call from background noise and measured all variables without intervention. Two species of Rhinolophus were easily identified from call duration and spectral measurements. For the remaining 12 species, discriminant function analysis and multilayer back-propagation perceptrons were used to classify calls to species level. Analyses were carried out with and without the inclusion of curve-fitting data to evaluate its usefulness in distinguishing among species. Discriminant function analysis achieved an overall correct classification rate of 79% with curve-fitting data included, while an artificial neural network achieved 87%. The removal of curve-fitting data improved the performance of the discriminant function analysis by 2 %, while the performance of a perceptron decreased by 2 %. However, an increase in correct identification rates when curve-fitting information was included was not found for all species. The use of a hierarchical classification system, whereby calls were first classified to genus level and then to species level, had little effect on correct classification rates by discriminant function analysis but did improve rates achieved by perceptrons. This is the first published study to use artificial neural networks to classify the echolocation calls of bats to species level. Our findings are discussed in terms of recent advances in recording and analysis technologies, and are related to factors causing convergence and divergence of echolocation call design in bats.

Acoustic identification of twelve species of echolocating bat by discriminant function analysis and artificial neural networks

We recorded echolocation calls from 14 sympatric species of bat in Britain. Once digitised, one temporal and four spectral features were measured from each call. The frequency-time course of each call was approximated by fitting eight mathematical functions, and the goodness of fit, represented by the mean-squared error, was calculated. Measurements were taken using an automated process that extracted a single call from background noise and measured all variables without intervention. Two species of Rhinolophus were easily identified from call duration and spectral measurements. For the remaining 12 species, discriminant function analysis and multilayer back-propagation perceptrons were used to classify calls to species level. Analyses were carried out with and without the inclusion of curve-fitting data to evaluate its usefulness in distinguishing among species. Discriminant function analysis achieved an overall correct classification rate of 79% with curve-fitting data included, while an artificial neural network achieved 87%. The removal of curve-fitting data improved the performance of the discriminant function analysis by 2 %, while the performance of a perceptron decreased by 2 %. However, an increase in correct identification rates when curve-fitting information was included was not found for all species. The use of a hierarchical classification system, whereby calls were first classified to genus level and then to species level, had little effect on correct classification rates by discriminant function analysis but did improve rates achieved by perceptrons. This is the first published study to use artificial neural networks to classify the echolocation calls of bats to species level. Our findings are discussed in terms of recent advances in recording and analysis technologies, and are related to factors causing convergence and divergence of echolocation call design in bats.

Sectional analysis of stormwater treatment performance of a constructed wetland

Constructed wetlands are among the most common Water Sensitive Urban Design (WSUD) measures for stormwater treatment. These systems have been extensively studied to understand their performance and influential treatment processes. Unfortunately, most past studies have been undertaken considering a wetland system as a lumped system with a primary focus on the reduction of the event mean concentration (EMC) values of specific pollutant species or total pollutant load removal. This research study adopted an innovative approach by partitioning the inflow runoff hydrograph and then investigating treatment performance in each partition and their relationships with a range of hydraulic factors. The study outcomes confirmed that influenced by rainfall characteristics, the constructed wetland displays different treatment characteristics for the initial and later sectors of the runoff hydrograph. The treatment of small rainfall events (<15 mm) is comparatively better at the beginning of runoff events while the trends in pollutant load reductions for large rainfall events (>15 mm) are generally lower at the beginning and gradually increase towards the end of rainfall events. This highlights the importance of ensuring that the inflow into a constructed wetland has low turbulence in order to achieve consistent treatment performance for both, small and large rainfall events.

Analysing governance of Australia's system of landscape-based greenhouse gas abatement

Healthy governance systems are key to delivering effective outcomes in any broad domain of natural resource management (NRM). One of Australia's emerging NRM governance domains is our national framework for greenhouse gas abatement (GGA), as delivered through a wide range of management practices in the Australian landscape. The emerging Landscape-Based GGA Domain represents an innovative governance space that straddles both the nation's broader NRM Policy and Delivery Domain and Australia's GGA Domain. As a point-in-time benchmark, we assess the health of this hybrid domain as it stood at the end of 2013. At that time, the domain was being progressed through the Australian government's Clean Energy Package and, more particularly, its Carbon Farming Initiative (CFI). While significant changes are currently under development by a new Australian government, this paper explores key areas of risk within the governance system underpinning this emerging hybrid domain at that point in time. We then map some potential reform or continuous improvement pathways required (from national to paddock scale) with the view to securing improved landscape outcomes over time through widespread GGA activities.

Prediction of GMA welding characteristic parameter by artificial neural network system

Nowadays, demand for automated Gas metal arc welding (GMAW) is growing and consequently need for intelligent systems is increased to ensure the accuracy of the procedure. To date, welding pool geometry has been the most used factor in quality assessment of intelligent welding systems. But, it has recently been found that Mahalanobis Distance (MD) not only can be used for this purpose but also is more efficient. In the present paper, Artificial Neural Networks (ANN) has been used for prediction of MD parameter. However, advantages and disadvantages of other methods have been discussed. The Levenberg–Marquardt algorithm was found to be the most effective algorithm for GMAW process. It is known that the number of neurons plays an important role in optimal network design. In this work, using trial and error method, it has been found that 30 is the optimal number of neurons. The model has been investigated with different number of layers in Multilayer Perceptron (MLP) architecture and has been shown that for the aim of this work the optimal result is obtained when using MLP with one layer. Robustness of the system has been evaluated by adding noise into the input data and studying the effect of the noise in prediction capability of the network. The experiments for this study were conducted in an automated GMAW setup that was integrated with data acquisition system and prepared in a laboratory for welding of steel plate with 12 mm in thickness. The accuracy of the network was evaluated by Root Mean Squared (RMS) error between the measured and the estimated values. The low error value (about 0.008) reflects the good accuracy of the model. Also the comparison of the predicted results by ANN and the test data set showed very good agreement that reveals the predictive power of the model. Therefore, the ANN model offered in here for GMA welding process can be used effectively for prediction goals.

Autonomous helicopter hover using an artificial neural network

Details the developments to date of an unmanned air vehicle (UAV) based on a standard size 60 model helicopter. The design goal is to have the helicopter achieve stable hover with the aid of an INS and stereo vision. The focus of the paper is on the development of an artificial neural network (ANN) that makes use of only the INS data to generate hover commands, which are used to directly manipulate the flight servos. Current results show that networks incorporating some form of recurrency (state history) offer little advantage over those without. At this stage, the ANN has partially maintained periods of hover even with misaligned sensors.

Abatement of aqueous anionic contaminants by thermo-responsive nanocomposites: (Poly(N-isopropylacrylamide))-co-silylanized Magnesium/Aluminun layered double hydroxides

A series of novel thermo-responsive composite sorbents, were prepared by free-radical co-polymerization of N-isopropylacrylamide (NIPAm) and the silylanized Mg/Al layered double hydroxides (SiLDHs), named as PNIPAm-co-SiLDHs. For keeping the high affinity of Mg/Al layered double hydroxides towards anions, the layered structure of LDHs was assumed to be reserved in PNIPAm-co-SiLDHs by the silanization of the wet LDH plates as evidenced by the X-ray powder diffraction. The sorption capacity of PNIPAm-co-SiLDH (13.5 mg/g) for Orange-II from water was found to be seven times higher than that of PNIPAm (2.0 mg/g), and the sorption capacities of arsenate onto PNIPAm-co-SiLDH are also greater than that onto PNIPAm, for both As(III) and As(V). These sorption results suggest that reserved LDH structure played a significant role in enhancing the sorption capacities. NO3− intercalated LDHs composite showed the stronger sorption capacity for Orange-II than that of CO32−. After sorption, the PNIPAm-co-SiLDH may be removed from water because of its gel-like nature, and may be easily regenerated contributing to the accelerated desorption of anionic contaminants from PNIPAm-co-SiLDHs by the unique phase-transfer feature through slightly heating (to 40 °C). These recyclable and regeneratable properties of thermo-responsive nanocomposites facilitate its potential application in the in-situ remediation of organic and inorganic anions from contaminated water.

Wastewater pollution abatement in China: A comparative study of fifteen industrial sectors from 1998 to 2010

This study analyzes the management of wastewater pollutants in a number of Chinese industrial sectors from 1998 to 2010. We use decomposition analysis to calculate changes in wastewater pollutant emissions that result from cleaner production processes, end-of-pipe treatment, structural changes in industry, and changes in the scale of production. We focus on one indicator of water quality and three pollutants: chemical oxygen demand (COD), petroleum, cyanide, and volatile phenols. We find that until 2002, COD emissions were mainly reduced through end-of-pipe treatments. Cleaner production processes didn’t begin contributing to COD emissions reductions until the introduction of a 2003 law that enforced their implementation. Petroleum emissions were primarily lowered through cleaner production mechanisms, which have the added benefit of reducing the input cost of intermediate petroleum. Diverse and effective pollution abatement strategies for cyanide and volatile phenols are emerging among industries in China. It will be important for the government to consider differences between industries should they choose to regulate the emissions of specific chemical substances.

Artificial Neural Network Based Automatic Emergency Landing Site Selection for UAVs and Highly Automated Aircraft

In this report an artificial neural network (ANN) based automated emergency landing site selection system for unmanned aerial vehicle (UAV) and general aviation (GA) is described. The system aims increase safety of UAV operation by emulating pilot decision making in emergency landing scenarios using an ANN to select a safe landing site from available candidates. The strength of an ANN to model complex input relationships makes it a perfect system to handle the multicriteria decision making (MCDM) process of emergency landing site selection. The ANN operates by identifying the more favorable of two landing sites when provided with an input vector derived from both landing site's parameters, the aircraft's current state and wind measurements. The system consists of a feed forward ANN, a pre-processor class which produces ANN input vectors and a class in charge of creating a ranking of landing site candidates using the ANN. The system was successfully implemented in C++ using the FANN C++ library and ROS. Results obtained from ANN training and simulations using randomly generated landing sites by a site detection simulator data verify the feasibility of an ANN based automated emergency landing site selection system.

An economic approach towards estimating health impacts of major transport investments and transport policies: A case study of transport emission abatement policy

The PhD thesis developed an economic model as an integral part of the current Health Impact Assessment (HIA) framework. Based on a Health Production Function approach, the model showed how to estimate economic benefits of positive health gains generated by transport investment programs and transport policies. Using Australian mortality and morbidity statistics and applying econometric analysis, the case study quantified health benefits induced by transport emission abatement policies in dollar terms for the Australian households. Finally, the thesis demonstrated transferability of the economic model through two example case studies, establishing a wider application capacity of the model.

Threats and Promises: The Promotion of Artificial Lighting to Women Consumers in the United States, 1880s – 1960s

This article examines the development of a specific gendered discourse in the United States in the first half of the twentieth century that united key beliefs about feminine beauty, identity, and the domestic interior with particular electric lighting technologies and effects. Largely driven by the electrical industry’s marketing rhetoric, American women were encouraged to adopt electric lighting as a beauty aid and ally in a host of domestic tasks. Drawing evidence from a number of primary texts, including women’s magazines, lighting and electrical industry trade journals, manufacturer-generated marketing materials, and popular home decoration and beauty advice literature, this study shifts the focus away from lighting as a basic utility, demonstrating the ways in which modern electric illumination was culturally constructed as a desirable personal and environmental beautifier as well as a means of harmonizing the domestic interior.