Automation of underground truck haulage

This paper reviews the state-of-the-art in the automation of underground truck haulage. Past attempts at automating LHDs and haul trucks are described and their particular strengths and weaknesses are listed. We argue that the simple auto-tramming systems currently being commercialised, that follow rail-type guides placed along the back, cannot match the performance, flexibility and reliability of systems based on modern mobile robotic principles. In addition, the lack of collision detection research in the underground environment is highlighted.

Statistical, electrical and mathematical analysis of water treed cross-linked polyethylene cable insulation

This work examined a new method of detecting small water filled cracks in underground insulation ('water trees') using data from commecially available non-destructive testing equipment. A testing facility was constructed and a computer simulation of the insulation designed in order to test the proposed ageing factor - the degree of non-linearity. This was a large industry-backed project involving an ARC linkage grant, Ergon Energy and the University of Queensland, as well as the Queensland University of Technology.

The QUT-NOISE-SRE protocol for the evaluation of noisy speaker recognition

The QUT-NOISE-SRE protocol is designed to mix the large QUT-NOISE database, consisting of over 10 hours of back- ground noise, collected across 10 unique locations covering 5 common noise scenarios, with commonly used speaker recognition datasets such as Switchboard, Mixer and the speaker recognition evaluation (SRE) datasets provided by NIST. By allowing common, clean, speech corpora to be mixed with a wide variety of noise conditions, environmental reverberant responses, and signal-to-noise ratios, this protocol provides a solid basis for the development, evaluation and benchmarking of robust speaker recognition algorithms, and is freely available to download alongside the QUT-NOISE database. In this work, we use the QUT-NOISE-SRE protocol to evaluate a state-of-the-art PLDA i-vector speaker recognition system, demonstrating the importance of designing voice-activity-detection front-ends specifically for speaker recognition, rather than aiming for perfect coherence with the true speech/non-speech boundaries.

A nonconservative Lagrangian framework for statistical fluid registration - SAFIRA

In this paper, we used a nonconservative Lagrangian mechanics approach to formulate a new statistical algorithm for fluid registration of 3-D brain images. This algorithm is named SAFIRA, acronym for statistically-assisted fluid image registration algorithm. A nonstatistical version of this algorithm was implemented, where the deformation was regularized by penalizing deviations from a zero rate of strain. In, the terms regularizing the deformation included the covariance of the deformation matrices Σ and the vector fields (q). Here, we used a Lagrangian framework to reformulate this algorithm, showing that the regularizing terms essentially allow nonconservative work to occur during the flow. Given 3-D brain images from a group of subjects, vector fields and their corresponding deformation matrices are computed in a first round of registrations using the nonstatistical implementation. Covariance matrices for both the deformation matrices and the vector fields are then obtained and incorporated (separately or jointly) in the nonconservative terms, creating four versions of SAFIRA. We evaluated and compared our algorithms' performance on 92 3-D brain scans from healthy monozygotic and dizygotic twins; 2-D validations are also shown for corpus callosum shapes delineated at midline in the same subjects. After preliminary tests to demonstrate each method, we compared their detection power using tensor-based morphometry (TBM), a technique to analyze local volumetric differences in brain structure. We compared the accuracy of each algorithm variant using various statistical metrics derived from the images and deformation fields. All these tests were also run with a traditional fluid method, which has been quite widely used in TBM studies. The versions incorporating vector-based empirical statistics on brain variation were consistently more accurate than their counterparts, when used for automated volumetric quantification in new brain images. This suggests the advantages of this approach for large-scale neuroimaging studies.

Eye-safe UV stand-off Raman spectroscopy for the ranged detection of explosives in the field

Increasing worldwide terrorist attacks involving explosives presents a growing need for a rapid and ranged explosive detection method that can safely be deployed in the field. Stand-off Raman spectroscopy shows great promise; however, the radiant exposures of lasers required for adequate signal generation are often much greater than what is safe for the eye or the skin, restricting use of the technique to un-populated areas. Here, by determining the safe exposure levels for lasers typically used in Raman spectroscopy, optimal parameter values are identified, which produce the largest possible detection range using power densities that do not exceed the eye-safe limit. It is shown that safe ultraviolet pulse energies can be more than three orders of magnitude greater than equivalent safe visible pulse energies. Coupling this to the 16-fold increase in Raman signal obtained in the ultraviolet at 266 nm over that at 532 nm results in a 131 times larger detection range for the eye-safe 266-nm system over an equivalent eye-safe 532-nm laser system. For the Raman system described here, this translates to a maximum range of 42 m for detecting Teflon with a 266-nm laser emitting a 100-mm diameter beam of 23.5-mJ nanosecond pulses.

Similarity-based birdcall retrieval from environmental audio

Automated digital recordings are useful for large-scale temporal and spatial environmental monitoring. An important research effort has been the automated classification of calling bird species. In this paper we examine a related task, retrieval of birdcalls from a database of audio recordings, similar to a user supplied query call. Such a retrieval task can sometimes be more useful than an automated classifier. We compare three approaches to similarity-based birdcall retrieval using spectral ridge features and two kinds of gradient features, structure tensor and the histogram of oriented gradients. The retrieval accuracy of our spectral ridge method is 94% compared to 82% for the structure tensor method and 90% for the histogram of gradients method. Additionally, this approach potentially offers a more compact representation and is more computationally efficient.

Learned ultra-wideband RADAR sensor model for augmented LIDAR-based traversability mapping in vegetated environments

In vegetated environments, reliable obstacle detection remains a challenge for state-of-the-art methods, which are usually based on geometrical representations of the environment built from LIDAR and/or visual data. In many cases, in practice field robots could safely traverse through vegetation, thereby avoiding costly detours. However, it is often mistakenly interpreted as an obstacle. Classifying vegetation is insufficient since there might be an obstacle hidden behind or within it. Some Ultra-wide band (UWB) radars can penetrate through vegetation to help distinguish actual obstacles from obstacle-free vegetation. However, these sensors provide noisy and low-accuracy data. Therefore, in this work we address the problem of reliable traversability estimation in vegetation by augmenting LIDAR-based traversability mapping with UWB radar data. A sensor model is learned from experimental data using a support vector machine to convert the radar data into occupancy probabilities. These are then fused with LIDAR-based traversability data. The resulting augmented traversability maps capture the fine resolution of LIDAR-based maps but clear safely traversable foliage from being interpreted as obstacle. We validate the approach experimentally using sensors mounted on two different mobile robots, navigating in two different environments.

Generalised features for bird vocalisation retrieval in acoustic recordings

Bioacoustic monitoring has become a significant research topic for species diversity conservation. Due to the development of sensing techniques, acoustic sensors are widely deployed in the field to record animal sounds over a large spatial and temporal scale. With large volumes of collected audio data, it is essential to develop semi-automatic or automatic techniques to analyse the data. This can help ecologists make decisions on how to protect and promote the species diversity. This paper presents generic features to characterize a range of bird species for vocalisation retrieval. In the implementation, audio recordings are first converted to spectrograms using short-time Fourier transform, then a ridge detection method is applied to the spectrogram for detecting points of interest. Based on the detected points, a new region representation are explored for describing various bird vocalisations and a local descriptor including temporal entropy, frequency bin entropy and histogram of counts of four ridge directions is calculated for each sub-region. To speed up the retrieval process, indexing is carried out and the retrieved results are ranked according to similarity scores. The experiment results show that our proposed feature set can achieve 0.71 in term of retrieval success rate which outperforms spectral ridge features alone (0.55) and Mel frequency cepstral coefficients (0.36).

Clustering acoustic events in environmental recordings for species richness surveys

Environmental acoustic recordings can be used to perform avian species richness surveys, whereby a trained ornithologist can observe the species present by listening to the recording. This could be made more efficient by using computational methods for iteratively selecting the richest parts of a long recording for the human observer to listen to, a process known as “smart sampling”. This allows scaling up to much larger ecological datasets. In this paper we explore computational approaches based on information and diversity of selected samples. We propose to use an event detection algorithm to estimate the amount of information present in each sample. We further propose to cluster the detected events for a better estimate of this amount of information. Additionally, we present a time dispersal approach to estimating diversity between iteratively selected samples. Combinations of approaches were evaluated on seven 24-hour recordings that have been manually labeled by bird watchers. The results show that on average all the methods we have explored would allow annotators to observe more new species in fewer minutes compared to a baseline of random sampling at dawn.

Birdcall retrieval from environmental acoustic recordings using image processing

Acoustic recordings of the environment provide an effective means to monitor bird species diversity. To facilitate exploration of acoustic recordings, we describe a content-based birdcall retrieval algorithm. A query birdcall is a region of spectrogram bounded by frequency and time. Retrieval depends on a similarity measure derived from the orientation and distribution of spectral ridges. The spectral ridge detection method caters for a broad range of birdcall structures. In this paper, we extend previous work by incorporating a spectrogram scaling step in order to improve the detection of spectral ridges. Compared to an existing approach based on MFCC features, our feature representation achieves better retrieval performance for multiple bird species in noisy recordings.

Characteristics of the first pre-discharge current pulse in SF6 under a steep fronted impulse voltage

An improved understanding of the characteristics of the pre-discharge current pulses in GIS will lead to improved analyses of the results from the UHF partial discharge detection method. This paper presents the characteristics of the first pre-discharge current pulses from a point-to-plain geometry at 1 bar absolute under both polarities of a 1.1/80 us lightning impulse. The analysis has shown that the pre-discharge current wave shape, peak current magnitude and charge is effected by the instantaneous voltage at which the pre- discharge took place as well as the polarity of the active electrode. The measured results show that protrusions on the electrodes have slower wave shape parameters than those reported for free conducting particles.

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.

Damage detection in suspension bridges using vibration characteristics

This research developed a method to detect damage in suspension bridges using vibration characteristics. These bridges exhibit complex vibration and hence it is difficult to use traditional vibration based methods to detect damage in them. This research therefore proposed component specific damage indices and verified their capability to detect and locate damage in the main cables and hangers of suspension bridges.

Letter: Brain natriuretic peptide is a potentially useful screening tool for the detection of cardiovascular disease in patients with rheumatoid arthritis

Patients with rheumatoid arthritis (RA) have a significantly higher risk of coronary heart disease, despite being less likely to report symptoms of angina, and are more likely to experience unrecognised myocardial infarction and sudden cardiac death than non-RA controls.1 Furthermore, left ventricular diastolic dysfunction has been described in up to 40% of patients with RA.2...

Whole exome sequencing is an efficient and sensitive method for detection of germline mutations in patients with phaeochromcytomas and paragangliomas

Background Genetic testing is recommended when the probability of a disease-associated germline mutation exceeds 10%. Germline mutations are found in approximately 25% of individuals with phaeochromcytoma (PCC) or paraganglioma (PGL); however, genetic heterogeneity for PCC/PGL means many genes may require sequencing. A phenotype-directed iterative approach may limit costs but may also delay diagnosis, and will not detect mutations in genes not previously associated with PCC/PGL. Objective To assess whether whole exome sequencing (WES) was efficient and sensitive for mutation detection in PCC/PGL. Methods Whole exome sequencing was performed on blinded samples from eleven individuals with PCC/PGL and known mutations. Illumina TruSeq™ (Illumina Inc, San Diego, CA, USA) was used for exome capture of seven samples, and NimbleGen SeqCap EZ v3.0 (Roche NimbleGen Inc, Basel, Switzerland) for five samples (one sample was repeated). Massive parallel sequencing was performed on multiplexed samples. Sequencing data were called using Genome Analysis Toolkit and annotated using annovar. Data were assessed for coding variants in RET, NF1, VHL, SDHD, SDHB, SDHC, SDHA, SDHAF2, KIF1B, TMEM127, EGLN1 and MAX. Target capture of five exome capture platforms was compared. Results Six of seven mutations were detected using Illumina TruSeq™ exome capture. All five mutations were detected using NimbleGen SeqCap EZ v3.0 platform, including the mutation missed using Illumina TruSeq™ capture. Target capture for exons in known PCC/PGL genes differs substantially between platforms. Exome sequencing was inexpensive (<$A800 per sample for reagents) and rapid (results <5 weeks from sample reception). Conclusion Whole exome sequencing is sensitive, rapid and efficient for detection of PCC/PGL germline mutations. However, capture platform selection is critical to maximize sensitivity.