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.

Primary and secondary neural networks of auditory prepulse inhibition: a functional magnetic resonance imaging study of sensorimotor gating of the human acoustic startle response

Feedforward inhibition deficits have been consistently demonstrated in a range of neuropsychiatric conditions using prepulse inhibition (PPI) of the acoustic startle eye-blink reflex when assessing sensorimotor gating. While PPI can be recorded in acutely decerebrated rats, behavioural, pharmacological and psychophysiological studies suggest the involvement of a complex neural network extending from brainstem nuclei to higher order cortical areas. The current functional magnetic resonance imaging study investigated the neural network underlying PPI and its association with electromyographically (EMG) recorded PPI of the acoustic startle eye-blink reflex in 16 healthy volunteers. A sparse imaging design was employed to model signal changes in blood oxygenation level-dependent (BOLD) responses to acoustic startle probes that were preceded by a prepulse at 120 ms or 480 ms stimulus onset asynchrony or without prepulse. Sensorimotor gating was EMG confirmed for the 120-ms prepulse condition, while startle responses in the 480-ms prepulse condition did not differ from startle alone. Multiple regression analysis of BOLD contrasts identified activation in pons, thalamus, caudate nuclei, left angular gyrus and bilaterally in anterior cingulate, associated with EMGrecorded sensorimotor gating. Planned contrasts confirmed increased pons activation for startle alone vs 120-ms prepulse condition, while increased anterior superior frontal gyrus activation was confirmed for the reverse contrast. Our findings are consistent with a primary pontine circuitry of sensorimotor gating that interconnects with inferior parietal, superior temporal, frontal and prefrontal cortices via thalamus and striatum. PPI processes in the prefrontal, frontal and superior temporal cortex were functionally distinct from sensorimotor gating.

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.

Fine-grained plant classification using convolutional neural networks for feature extraction

We present an overview of the QUT plant classification system submitted to LifeCLEF 2014. This system uses generic features extracted from a convolutional neural network previously used to perform general object classification. We examine the effectiveness of these features to perform plant classification when used in combination with an extremely randomised forest. Using this system, with minimal tuning, we obtained relatively good results with a score of 0:249 on the test set of LifeCLEF 2014.

Improving deep convultional neural networks with unsupervised feature learning

The latest generation of Deep Convolutional Neural Networks (DCNN) have dramatically advanced challenging computer vision tasks, especially in object detection and object classification, achieving state-of-the-art performance in several computer vision tasks including text recognition, sign recognition, face recognition and scene understanding. The depth of these supervised networks has enabled learning deeper and hierarchical representation of features. In parallel, unsupervised deep learning such as Convolutional Deep Belief Network (CDBN) has also achieved state-of-the-art in many computer vision tasks. However, there is very limited research on jointly exploiting the strength of these two approaches. In this paper, we investigate the learning capability of both methods. We compare the output of individual layers and show that many learnt filters and outputs of the corresponding level layer are almost similar for both approaches. Stacking the DCNN on top of unsupervised layers or replacing layers in the DCNN with the corresponding learnt layers in the CDBN can improve the recognition/classification accuracy and training computational expense. We demonstrate the validity of the proposal on ImageNet dataset.

Implementation of Art1 and Art2 Artificial Neural Networks on Ring and Mesh Architectures

The Artificial Neural Networks (ANNs) are being used to solve a variety of problems in pattern recognition, robotic control, VLSI CAD and other areas. In most of these applications, a speedy response from the ANNs is imperative. However, ANNs comprise a large number of artificial neurons, and a massive interconnection network among them. Hence, implementation of these ANNs involves execution of computer-intensive operations. The usage of multiprocessor systems therefore becomes necessary. In this article, we have presented the implementation of ART1 and ART2 ANNs on ring and mesh architectures. The overall system design and implementation aspects are presented. The performance of the algorithm on ring, 2-dimensional mesh and n-dimensional mesh topologies is presented. The parallel algorithm presented for implementation of ART1 is not specific to any particular architecture. The parallel algorithm for ARTE is more suitable for a ring architecture.

An adaptive drug delivery design using neural networks for effective treatment of infectious diseases: A simulation study

An adaptive drug delivery design is presented in this paper using neural networks for effective treatment of infectious diseases. The generic mathematical model used describes the coupled evolution of concentration of pathogens, plasma cells, antibodies and a numerical value that indicates the relative characteristic of a damaged organ due to the disease under the influence of external drugs. From a system theoretic point of view, the external drugs can be interpreted as control inputs, which can be designed based on control theoretic concepts. In this study, assuming a set of nominal parameters in the mathematical model, first a nonlinear controller (drug administration) is designed based on the principle of dynamic inversion. This nominal drug administration plan was found to be effective in curing "nominal model patients" (patients whose immunological dynamics conform to the mathematical model used for the control design exactly. However, it was found to be ineffective in curing "realistic model patients" (patients whose immunological dynamics may have off-nominal parameter values and possibly unwanted inputs) in general. Hence, to make the drug delivery dosage design more effective for realistic model patients, a model-following adaptive control design is carried out next by taking the help of neural networks, that are trained online. Simulation studies indicate that the adaptive controller proposed in this paper holds promise in killing the invading pathogens and healing the damaged organ even in the presence of parameter uncertainties and continued pathogen attack. Note that the computational requirements for computing the control are very minimal and all associated computations (including the training of neural networks) can be carried out online. However it assumes that the required diagnosis process can be carried out at a sufficient faster rate so that all the states are available for control computation.

Classification of Indian meteorological stations using cluster and fuzzy cluster analysis, and Kohonen artificial neural networks

The present study deals with the application of cluster analysis, Fuzzy Cluster Analysis (FCA) and Kohonen Artificial Neural Networks (KANN) methods for classification of 159 meteorological stations in India into meteorologically homogeneous groups. Eight parameters, namely latitude, longitude, elevation, average temperature, humidity, wind speed, sunshine hours and solar radiation, are considered as the classification criteria for grouping. The optimal number of groups is determined as 14 based on the Davies-Bouldin index approach. It is observed that the FCA approach performed better than the other two methodologies for the present study.

Search for the Higgs Boson Using Neural Networks in Events with Missing Energy and b-Quark Jets in pp̅ Collisions at √s=1.96 TeV

We report on a search for the standard model Higgs boson produced in association with a $W$ or $Z$ boson in $p\bar{p}$ collisions at $\sqrt{s} = 1.96$ TeV recorded by the CDF II experiment at the Tevatron in a data sample corresponding to an integrated luminosity of 2.1 fb$^{-1}$. We consider events which have no identified charged leptons, an imbalance in transverse momentum, and two or three jets where at least one jet is consistent with originating from the decay of a $b$ hadron. We find good agreement between data and predictions. We place 95% confidence level upper limits on the production cross section for several Higgs boson masses ranging from 110$\gevm$ to 150$\gevm$. For a mass of 115$\gevm$ the observed (expected) limit is 6.9 (5.6) times the standard model prediction.

Detecting Earnings Management Using Neural Networks

Detecting Earnings Management Using Neural Networks. Trying to balance between relevant and reliable accounting data, generally accepted accounting principles (GAAP) allow, to some extent, the company management to use their judgment and to make subjective assessments when preparing financial statements. The opportunistic use of the discretion in financial reporting is called earnings management. There have been a considerable number of suggestions of methods for detecting accrual based earnings management. A majority of these methods are based on linear regression. The problem with using linear regression is that a linear relationship between the dependent variable and the independent variables must be assumed. However, previous research has shown that the relationship between accruals and some of the explanatory variables, such as company performance, is non-linear. An alternative to linear regression, which can handle non-linear relationships, is neural networks. The type of neural network used in this study is the feed-forward back-propagation neural network. Three neural network-based models are compared with four commonly used linear regression-based earnings management detection models. All seven models are based on the earnings management detection model presented by Jones (1991). The performance of the models is assessed in three steps. First, a random data set of companies is used. Second, the discretionary accruals from the random data set are ranked according to six different variables. The discretionary accruals in the highest and lowest quartiles for these six variables are then compared. Third, a data set containing simulated earnings management is used. Both expense and revenue manipulation ranging between -5% and 5% of lagged total assets is simulated. Furthermore, two neural network-based models and two linear regression-based models are used with a data set containing financial statement data from 110 failed companies. Overall, the results show that the linear regression-based models, except for the model using a piecewise linear approach, produce biased estimates of discretionary accruals. The neural network-based model with the original Jones model variables and the neural network-based model augmented with ROA as an independent variable, however, perform well in all three steps. Especially in the second step, where the highest and lowest quartiles of ranked discretionary accruals are examined, the neural network-based model augmented with ROA as an independent variable outperforms the other models.

Robust/optimal temperature profile control using neural networks

An approximate dynamic programming (ADP) based neurocontroller is developed for a heat transfer application. Heat transfer problem for a fin in a car's electronic module is modeled as a nonlinear distributed parameter (infinite-dimensional) system by taking into account heat loss and generation due to conduction, convection and radiation. A low-order, finite-dimensional lumped parameter model for this problem is obtained by using Galerkin projection and basis functions designed through the 'Proper Orthogonal Decomposition' technique (POD) and the 'snap-shot' solutions. A suboptimal neurocontroller is obtained with a single-network-adaptive-critic (SNAC). Further contribution of this paper is to develop an online robust controller to account for unmodeled dynamics and parametric uncertainties. A weight update rule is presented that guarantees boundedness of the weights and eliminates the need for persistence of excitation (PE) condition to be satisfied. Since, the ADP and neural network based controllers are of fairly general structure, they appear to have the potential to be controller synthesis tools for nonlinear distributed parameter systems especially where it is difficult to obtain an accurate model.

Design of a FIR filter for image restoration using principal component neural networks

The neural network finds its application in many image denoising applications because of its inherent characteristics such as nonlinear mapping and self-adaptiveness. The design of filters largely depends on the a-priori knowledge about the type of noise. Due to this, standard filters are application and image specific. Widely used filtering algorithms reduce noisy artifacts by smoothing. However, this operation normally results in smoothing of the edges as well. On the other hand, sharpening filters enhance the high frequency details making the image non-smooth. An integrated general approach to design a finite impulse response filter based on principal component neural network (PCNN) is proposed in this study for image filtering, optimized in the sense of visual inspection and error metric. This algorithm exploits the inter-pixel correlation by iteratively updating the filter coefficients using PCNN. This algorithm performs optimal smoothing of the noisy image by preserving high and low frequency features. Evaluation results show that the proposed filter is robust under various noise distributions. Further, the number of unknown parameters is very few and most of these parameters are adaptively obtained from the processed image.