Classification of echolocation calls from 14 species of bat by Support Vector Machines and Ensembles of Neural Networks

Calls from 14 species of bat were classified to genus and species using discriminant function analysis (DFA), support vector machines (SVM) and ensembles of neural networks (ENN). Both SVMs and ENNs outperformed DFA for every species while ENNs (mean identification rate – 97%) consistently outperformed SVMs (mean identification rate – 87%). Correct classification rates produced by the ENNs varied from 91% to 100%; calls from six species were correctly identified with 100% accuracy. Calls from the five species of Myotis, a genus whose species are considered difficult to distinguish acoustically, had correct identification rates that varied from 91 – 100%. Five parameters were most important for classifying calls correctly while seven others contributed little to classification performance.

Reliable Fault Diagnosis for Low-Speed Bearings Using Individually Trained Support Vector Machines With Kernel Discriminative Feature Analysis

This paper proposes a highly reliable fault diagnosis approach for low-speed bearings. The proposed approach first extracts wavelet-based fault features that represent diverse symptoms of multiple low-speed bearing defects. The most useful fault features for diagnosis are then selected by utilizing a genetic algorithm (GA)-based kernel discriminative feature analysis cooperating with one-against-all multicategory support vector machines (OAA MCSVMs). Finally, each support vector machine is individually trained with its own feature vector that includes the most discriminative fault features, offering the highest classification performance. In this study, the effectiveness of the proposed GA-based kernel discriminative feature analysis and the classification ability of individually trained OAA MCSVMs are addressed in terms of average classification accuracy. In addition, the proposedGA- based kernel discriminative feature analysis is compared with four other state-of-the-art feature analysis approaches. Experimental results indicate that the proposed approach is superior to other feature analysis methodologies, yielding an average classification accuracy of 98.06% and 94.49% under rotational speeds of 50 revolutions-per-minute (RPM) and 80 RPM, respectively. Furthermore, the individually trained MCSVMs with their own optimal fault features based on the proposed GA-based kernel discriminative feature analysis outperform the standard OAA MCSVMs, showing an average accuracy of 98.66% and 95.01% for bearings under rotational speeds of 50 RPM and 80 RPM, respectively.

Flying robots to the rescue

UAVs could one day save the lives of lost civilians and those sent to find them, and a competition in outback Australia is proving how soon that day might come. We have all seen news stories of people who ventured beyond the day-to-day reach of the community and got lost: search parties are formed, aircraft drafted in, and often large sums of money expended in the quest to find them.

Using genetic algorithm in profile-based assignment of applications to virtual machines for greener data centers

The increase in data center dependent services has made energy optimization of data centers one of the most exigent challenges in today's Information Age. The necessity of green and energy-efficient measures is very high for reducing carbon footprint and exorbitant energy costs. However, inefficient application management of data centers results in high energy consumption and low resource utilization efficiency. Unfortunately, in most cases, deploying an energy-efficient application management solution inevitably degrades the resource utilization efficiency of the data centers. To address this problem, a Penalty-based Genetic Algorithm (GA) is presented in this paper to solve a defined profile-based application assignment problem whilst maintaining a trade-off between the power consumption performance and resource utilization performance. Case studies show that the penalty-based GA is highly scalable and provides 16% to 32% better solutions than a greedy algorithm.

A Strength Pareto Evolutionary Algorithm for live migration of multiple interdependent virtual machines in data centers

Although live VM migration has been intensively studied, the problem of live migration of multiple interdependent VMs has hardly been investigated. The most important problem in the live migration of multiple interdependent VMs is how to schedule VM migrations as the schedule will directly affect the total migration time and the total downtime of those VMs. Aiming at minimizing both the total migration time and the total downtime simultaneously, this paper presents a Strength Pareto Evolutionary Algorithm 2 (SPEA2) for the multi-VM migration scheduling problem. The SPEA2 has been evaluated by experiments, and the experimental results show that the SPEA2 can generate a set of VM migration schedules with a shorter total migration time and a shorter total downtime than an existing genetic algorithm, namely Random Key Genetic Algorithm (RKGA). This paper also studies the scalability of the SPEA2.

Programming an FPGA to Emulate the Dynamics of DC Machines

This paper presents the programming an FPGA (Field Programmable Gate Array) to emulate the dynamics of DC machines. FPGA allows high speed real time simulation with high precision. The described design includes block diagram representation of DC machine, which contain all arithmetic and logical operations. The real time simulation of the machine in FPGA is controlled by user interfaces they are Keypad interface, LCD display on-line and digital to analog converter. This approach provides emulation of electrical machine by changing the parameters. Separately Exited DC machine implemented and experimental results are presented.

Real-time simulation of electrical machines on FPGA platform

This paper presents real-time simulation models of electrical machines on FPGA platform. Implementation of the real-time numerical integration methods with digital logic elements is discussed. Several numerical integrations are presented. A real-time simulation of DC machine is carried out on this FPGA platform and important transient results are presented. These results are compared to simulation results obtained through a commercial off-line simulation software.

Australian Bat Lyssavirus Infection in a Captive Juvenile Black Flying Fox

The newly emerging Australian bat lyssavirus causes rabies like disease in bats and humans. A captive juvenile black flying fox exhibited progressive neurologic signs, including sudden aggression, vocalization, dysphagia, and paresis over 9 days and then died. At necropsy, lyssavirus infection was diagnosed by fluorescent antibody test, immunoperoxidase staining, polymerase chain reaction, and virus isolation. Eight human contacts received postexposure vaccination.

Neuro-angiostrongylosis in wild Black and Grey-headed flying foxes (Pteropus spp)

Objective: To identify nematodes seen in histological sections of brains of flying foxes (fruit bats) and describe the associated clinical disease and pathology. Proceedures: Gross and histological examination of brains from 86 free-living flying foxes with neurological disease was done as part of an ongoing surveillance program for Australian bat lyssavirus. Worms were recovered, or if seen in histological sections, extracted by maceration of half the brain and identified by microscopic examination. Histological archives were also reviewed. Results: There was histological evidence of angiostrongylosis in 16 of 86 recently submitted flying foxes with neurological disease and in one archival case from 1992. In 10 flying foxes, worms were definitively identified as Angiostrongylus cantonensis fifth-stage larvae. A worm fragment and third stage larvae were identified as Angiostrongylus sp, presumably A cantonensis, in a further three cases. The clinical picture was dominated by paresis, particularly of the hindlimbs, and depression, with flying foxes surviving up to 22 days in the care of wildlife volunteers. Brains containing fifthstage larvae showed a moderate to severe eosinophilic and granulomatous meningoencephalitis (n = 14), whereas there was virtually no inflammation of the brains of bats which died when infected with only smaller, third-stage larvae (n = 3). There was no histological evidence of pulmonary involvement. Conclusion: This is the first report of the recovery and identification of A cantonensis from free-living Australian wildlife. While angiostrongylosis is a common cause of paresis in flying foxes, the initial clinical course cannot be differentiated from Australian bat lyssavirus infection, and wildlife carers should be urged not to attempt to rehabilitate flying foxes with neurological disease.

Emerging henipaviruses and flying foxes - Conservation and management perspectives

Wildlife populations are affected by a series of emerging diseases, some of which pose a significant threat to their conservation. They can also be reservoirs of pathogens that threaten domestic animal and human health. In this paper, we review the ecology of two viruses that have caused significant disease in domestic animals and humans and are carried by wild fruit bats in Asia and Australia. The first, Hendra virus, has caused disease in horses and/or humans in Australia every five years since it first emerged in 1994. Nipah virus has caused a major outbreak of disease in pigs and humans in Malaysia in the late 1990s and has also caused human mortalities in Bangladesh annually since 2001. Increased knowledge of fruit bat population dynamics and disease ecology will help improve our understanding of processes driving the emergence of diseases from bats. For this, a transdisciplinary approach is required to develop appropriate host management strategies that both maximise the conservation of bat populations as well as minimise the risk of disease outbreaks in domestic animals and humans.

Infection with Menangle virus in flying foxes (Pteropus spp.) in Australia

Objective: To examine flying foxes (Pteropus spp.) for evidence of infection with Menangle virus. Design: Clustered non-random sampling for serology, virus isolation and electron microscopy (EM). Procedure: Serum samples were collected from 306 Pteropus spp. in northern and eastern Australia and tested for antibodies against Menangle virus (MenV) using a virus neutralisation test (VNT). Virus isolation was attempted from tissues and faeces collected from 215 Pteropus spp. in New South Wales. Faecal samples from 68 individual Pteropus spp. and four pools of faeces were examined by transmission EM following routine negative staining and immunogold labelling. Results: Neutralising antibodies (VNT titres ≥ 8) against MenV were detected in 46% of black flying foxes (P. alecto), 41% of grey-headed flying foxes (P. poliocephalus), 25% of spectacled flying foxes (P. conspicillatus) and 1% of little red flying foxes (P. scapulatus) in Australia. Positive sera included samples collected from P. poliocephalus in a colony adjacent to a piggery that had experienced reproductive disease caused by MenV. Virus-like particles were observed by EM in faeces from Pteropus spp. and reactivity was detected in pooled faeces and urine by immunogold EM using sera from sows that had been exposed to MenV. Attempts to isolate the virus from the faeces and tissues from Pteropus spp. were unsuccessful. Conclusion: Serological evidence of infection with MenV was detected in Pteropus spp. in Australia. Although virus-like particles were detected in faeces, no viruses were isolated from faeces, urine or tissues of Pteropus spp.

Plasma biochemistry and hematologic values for wild-caught flying foxes (Pteropus giganteus) in India

Although bats of the genus Pteropus are important ecologically as pollinators and natural hosts for zoonotic pathogens, little is known about their basic physiology. Hematology and plasma biochemistries were determined from wild-caught flying foxes (Pteropus giganteus) in northern India (n = 41). Mean lymphocyte differential count was higher for juveniles than adults. Mean platelet count was lower than previously reported. No hemoparasites were observed. No differences were observed between plasma biochemistry values of male and female bats, juveniles and adults, or lactating and nonlactating females. Variation in aspartate aminotransferase (AST) was seen based on body condition score. Blood urea nitrogen and cholesterol concentrations were lower in P. giganteus than other mammalian groups, but were consistent with those reported from other Pteropus species. Alanine aminotransferase and AST concentrations were higher than those reported for Pteropus vampyrus, a closely related species. This study provides basic physiologic information that can be used in future health and disease studies of Indian flying foxes.