Social signal processing for pain monitoring using a hidden conditional random field

utomatic pain monitoring has the potential to greatly improve patient diagnosis and outcomes by providing a continuous objective measure. One of the most promising methods is to do this via automatically detecting facial expressions. However, current approaches have failed due to their inability to: 1) integrate the rigid and non-rigid head motion into a single feature representation, and 2) incorporate the salient temporal patterns into the classification stage. In this paper, we tackle the first problem by developing a “histogram of facial action units” representation using Active Appearance Model (AAM) face features, and then utilize a Hidden Conditional Random Field (HCRF) to overcome the second issue. We show that both of these methods improve the performance on the task of pain detection in sequence level compared to current state-of-the-art-methods on the UNBC-McMaster Shoulder Pain Archive.

Speaker diarization : "who spoke when"

Speaker diarization is the process of annotating an input audio with information that attributes temporal regions of the audio signal to their respective sources, which may include both speech and non-speech events. For speech regions, the diarization system also specifies the locations of speaker boundaries and assign relative speaker labels to each homogeneous segment of speech. In short, speaker diarization systems effectively answer the question of ‘who spoke when’. There are several important applications for speaker diarization technology, such as facilitating speaker indexing systems to allow users to directly access the relevant segments of interest within a given audio, and assisting with other downstream processes such as summarizing and parsing. When combined with automatic speech recognition (ASR) systems, the metadata extracted from a speaker diarization system can provide complementary information for ASR transcripts including the location of speaker turns and relative speaker segment labels, making the transcripts more readable. Speaker diarization output can also be used to localize the instances of specific speakers to pool data for model adaptation, which in turn boosts transcription accuracies. Speaker diarization therefore plays an important role as a preliminary step in automatic transcription of audio data. The aim of this work is to improve the usefulness and practicality of speaker diarization technology, through the reduction of diarization error rates. In particular, this research is focused on the segmentation and clustering stages within a diarization system. Although particular emphasis is placed on the broadcast news audio domain and systems developed throughout this work are also trained and tested on broadcast news data, the techniques proposed in this dissertation are also applicable to other domains including telephone conversations and meetings audio. Three main research themes were pursued: heuristic rules for speaker segmentation, modelling uncertainty in speaker model estimates, and modelling uncertainty in eigenvoice speaker modelling. The use of heuristic approaches for the speaker segmentation task was first investigated, with emphasis placed on minimizing missed boundary detections. A set of heuristic rules was proposed, to govern the detection and heuristic selection of candidate speaker segment boundaries. A second pass, using the same heuristic algorithm with a smaller window, was also proposed with the aim of improving detection of boundaries around short speaker segments. Compared to single threshold based methods, the proposed heuristic approach was shown to provide improved segmentation performance, leading to a reduction in the overall diarization error rate. Methods to model the uncertainty in speaker model estimates were developed, to address the difficulties associated with making segmentation and clustering decisions with limited data in the speaker segments. The Bayes factor, derived specifically for multivariate Gaussian speaker modelling, was introduced to account for the uncertainty of the speaker model estimates. The use of the Bayes factor also enabled the incorporation of prior information regarding the audio to aid segmentation and clustering decisions. The idea of modelling uncertainty in speaker model estimates was also extended to the eigenvoice speaker modelling framework for the speaker clustering task. Building on the application of Bayesian approaches to the speaker diarization problem, the proposed approach takes into account the uncertainty associated with the explicit estimation of the speaker factors. The proposed decision criteria, based on Bayesian theory, was shown to generally outperform their non- Bayesian counterparts.

Accelerometer-based fetal movement detection

Monitoring fetal wellbeing is a compelling problem in modern obstetrics. Clinicians have become increasingly aware of the link between fetal activity (movement), well-being, and later developmental outcome. We have recently developed an ambulatory accelerometer-based fetal activity monitor (AFAM) to record 24-hour fetal movement. Using this system, we aim at developing signal processing methods to automatically detect and quantitatively characterize fetal movements. The first step in this direction is to test the performance of the accelerometer in detecting fetal movement against real-time ultrasound imaging (taken as the gold standard). This paper reports first results of this performance analysis.

SERS based detection of barcoded gold nanoparticle assemblies from within animal tissue

We have explored the potential of deep Raman spectroscopy, specifically surface enhanced spatially offset Raman spectroscopy (SESORS), for non-invasive detection from within animal tissue, by employing SERS-barcoded nanoparticle (NP) assemblies as the diagnostic agent. This concept has been experimentally verified in a clinic-relevant backscattered Raman system with an excitation line of 785 nm under ex vivo conditions. We have shown that our SORS system, with a fixed offset of 2-3 mm, offered sensitive probing of injected QTH-barcoded NP assemblies through animal tissue containing both protein and lipid. In comparison to that of non-aggregated SERS-barcoded gold NPs, we have demonstrated that the tailored SERS-barcoded aggregated NP assemblies have significantly higher detection sensitivity. We report that these NP assemblies can be readily detected at depths of 7-8 mm from within animal proteinaceous tissue with high signal-to-noise (S/N) ratio. In addition they could also be detected from beneath 1-2 mm of animal tissue with high lipid content, which generally poses a challenge due to high absorption of lipids in the near-infrared region. We have also shown that the signal intensity and S/N ratio at a particular depth is a function of the SERS tag concentration used and that our SORS system has a QTH detection limit of 10-6 M. Higher detection depths may possibly be obtained with optimization of the NP assemblies, along with improvements in the instrumentation. Such NP assemblies offer prospects for in vivo, non-invasive detection of tumours along with scope for incorporation of drugs and their targeted and controlled release at tumour sites. These diagnostic agents combined with drug delivery systems could serve as a “theranostic agent”, an integration of diagnostics and therapeutics into a single platform.

IS-RT-PCR assay detection of MT-MMP in a human breast cancer cell line

The in situ-reverse transcription-polymerase chain reaction (IS-RT-PCR) is a method that allows the direct localisation of gene expression. The method utilises the dual buffer mediated activity of the enzyme rTth DNA polymerase enabling both reverse transcription and DNA amplification. Labelled nucleoside triphosphates allow the site of expression to be labelled, rather than the PCR primers themselves, giving a more accurate localisation of transcript expression and decreased background than standard in situ hybridisation (ISH) assays. The MDA-MB-231 human breast carcinoma (HBC) cell line was assayed via the IS-RT-PCR technique, using primers encoding MT-MMP (membrane-type matrix metalloproteinase) and human β-actin. Our results clearly indicate baseline expression of MT-MMP in the relatively invasive MDA-MB-231 cell line at a signal intensity similar to the housekeeping gene β-actin, and results following induction with Concanavalin A (Con A) are consistent with our previous results obtained via Northern blotting.

An efficient algorithm for the detection of Eden

In this paper, a polynomial time algorithm is presented for solving the Eden problem for graph cellular automata. The algorithm is based on our neighborhood elimination operation which removes local neighborhood configurations which cannot be used in a pre-image of a given configuration. This paper presents a detailed derivation of our algorithm from first principles, and a detailed complexity and accuracy analysis is also given. In the case of time complexity, it is shown that the average case time complexity of the algorithm is \Theta(n^2), and the best and worst cases are \Omega(n) and O(n^3) respectively. This represents a vast improvement in the upper bound over current methods, without compromising average case performance.

The detection of incipient faults in small multi-cylinder diesel engines using multiple acoustic emission sensors

This thesis investigates condition monitoring (CM) of diesel engines using acoustic emission (AE) techniques. The AE signals recorded from a small size diesel engine are mixtures of multiple sources from multiple cylinders. Thus, it is difficult to interpret the information conveyed in the signals for CM purposes. This thesis develops a series of practical signal processing techniques to overcome this problem. Various experimental studies conducted to assess the CM capabilities of AE analysis for diesel engines. A series of modified signal processing techniques were proposed. These techniques showed promising results of capability for CM of multiple cylinders diesel engine using multiple AE sensors.

HMM relative entropy rate concepts for vision-based aircraft manoeuvre detection

Machine vision is emerging as a viable sensing approach for mid-air collision avoidance (particularly for small to medium aircraft such as unmanned aerial vehicles). In this paper, using relative entropy rate concepts, we propose and investigate a new change detection approach that uses hidden Markov model filters to sequentially detect aircraft manoeuvres from morphologically processed image sequences. Experiments using simulated and airborne image sequences illustrate the performance of our proposed algorithm in comparison to other sequential change detection approaches applied to this application.

Hydraulic instability onset detection in Kaplan turbines by monitoring shaft vibrations

Design of hydraulic turbines has often to deal with hydraulic instability. It is well-known that Francis and Kaplan types present hydraulic instability in their design power range. Even if modern CFD tools may help to define these dangerous operating conditions and optimize runner design, hydraulic instabilities may fortuitously arise during the turbine life and should be timely detected in order to assure a long-lasting operating life. In a previous paper, the authors have considered the phenomenon of helical vortex rope, which happens at low flow rates when a swirling flow, in the draft tube conical inlet, occupies a large portion of the inlet. In this condition, a strong helical vortex rope appears. The vortex rope causes mechanical effects on the runner, on the whole turbine and on the draft tube, which may eventually produce severe damages on the turbine unit and whose most evident symptoms are vibrations. The authors have already shown that vibration analysis is suitable for detecting vortex rope onset, thanks to an experimental test campaign performed during the commissioning of a 23 MW Kaplan hydraulic turbine unit. In this paper, the authors propose a sophisticated data driven approach to detect vortex rope onset at different power load, based on the analysis of the vibration signals in the order domain and introducing the so-called "residual order spectrogram", i.e. an order-rotation representation of the vibration signal. Some experimental test runs are presented and the possibility to detect instability onset, especially in real-time, is discussed.

Second harmonic generation and multiphoton microscopic detection of collagen without the need for species specific antibodies

High-resolution, high-contrast, three-dimensional images of live cell and tissue architecture can be obtained using second harmonic generation (SHG), which comprises non-absorptive frequency changes in an excitation laser line. SHG does not require any exogenous antibody or fluorophore labeling, and can generate images from unstained sections of several key endogenous biomolecules, in a wide variety of species and from different types of processed tissue. Here, we examined normal control human skin sections and human burn scar tissues using SHG on a multi-photon microscope (MPM). Examination and comparison of normal human skin and burn scar tissue demonstrated a clear arrangement of fibers in the dermis, similar to dermal collagen fiber signals. Fluorescence-staining confirmed the MPM-SHG collagen colocalization with antibody staining for dermal collagen type-I but not fibronectin or elastin. Furthermore, we were able to detect collagen MPM-SHG signal in human frozen sections as well as in unstained paraffin embedded tissue sections that were then compared with hematoxylin and eosin staining in the identical sections. This same approach was also successful in localizing collagen in porcine and ovine skin samples, and may be particularly important when species-specific antibodies may not be available. Collectively, our results demonstrate that MPM SHG-detection is a useful tool for high resolution examination of collagen architecture in both normal and wounded human, porcine and ovine dermal tissue.

Acoustic emission condition monitoring : an application for wind turbine fault detection

Low speed rotating machines which are the most critical components in drive train of wind turbines are often menaced by several technical and environmental defects. These factors contribute to mount the economic requirement for Health Monitoring and Condition Monitoring of the systems. When a defect is happened in such system result in reduced energy loss rates from related process and due to it Condition Monitoring techniques that detecting energy loss are very difficult if not possible to use. However, in the case of Acoustic Emission (AE) technique this issue is partly overcome and is well suited for detecting very small energy release rates. Acoustic Emission (AE) as a technique is more than 50 years old and in this new technology the sounds associated with the failure of materials were detected. Acoustic wave is a non-stationary signal which can discover elastic stress waves in a failure component, capable of online monitoring, and is very sensitive to the fault diagnosis. In this paper the history and background of discovering and developing AE is discussed, different ages of developing AE which include Age of Enlightenment (1950-1967), Golden Age of AE (1967-1980), Period of Transition (1980-Present). In the next section the application of AE condition monitoring in machinery process and various systems that applied AE technique in their health monitoring is discussed. In the end an experimental result is proposed by QUT test rig which an outer race bearing fault was simulated to depict the sensitivity of AE for detecting incipient faults in low speed high frequency machine.

A rule-based hybrid method for anomaly detection in online-social-network graphs

Detecting anomalies in the online social network is a significant task as it assists in revealing the useful and interesting information about the user behavior on the network. This paper proposes a rule-based hybrid method using graph theory, Fuzzy clustering and Fuzzy rules for modeling user relationships inherent in online-social-network and for identifying anomalies. Fuzzy C-Means clustering is used to cluster the data and Fuzzy inference engine is used to generate rules based on the cluster behavior. The proposed method is able to achieve improved accuracy for identifying anomalies in comparison to existing methods.

Characterising an ECG signal using statistical modelling : a feasibility study

For clinical use, in electrocardiogram (ECG) signal analysis it is important to detect not only the centre of the P wave, the QRS complex and the T wave, but also the time intervals, such as the ST segment. Much research focused entirely on qrs complex detection, via methods such as wavelet transforms, spline fitting and neural networks. However, drawbacks include the false classification of a severe noise spike as a QRS complex, possibly requiring manual editing, or the omission of information contained in other regions of the ECG signal. While some attempts were made to develop algorithms to detect additional signal characteristics, such as P and T waves, the reported success rates are subject to change from person-to-person and beat-to-beat. To address this variability we propose the use of Markov-chain Monte Carlo statistical modelling to extract the key features of an ECG signal and we report on a feasibility study to investigate the utility of the approach. The modelling approach is examined with reference to a realistic computer generated ECG signal, where details such as wave morphology and noise levels are variable.

Fault detection of slow speed rolling element bearing with noise removal techniques

Rolling Element Bearings (REBs) are vital components in rotating machineries for providing rotating motion. In slow speed rotating machines, bearings are normally subjected to heavy static loads and a catastrophic failure can cause enormous disruption to production and human safety. Due to its low operating speed the impact energy generated by the rotating elements on the defective components is not sufficient to produce a detectable vibration response. This is further aggravated by the inability of general measuring instruments to detect and process the weak signals at the initiation of the defect accurately. Furthermore, the weak signals are often corrupted by background noise. This is a serious problem faced by maintenance engineers today and the inability to detect an incipient failure of the machine can significantly increases the risk of functional failure and costly downtime. This paper presents the application of noise removal techniques for enhancing the detection capability for slow speed REB condition monitoring. Blind deconvolution (BD) and adaptive line enhancer (ALE) are compared to evaluate their performance in enhancing the source signal with consequential removal of background noise. In the experimental study, incipient defects were seeded on a number of roller bearings and the signals were acquired using acoustic emission (AE) sensor. Kurtosis and modified peak ratio (mPR) were used to determine the detectability of signal corrupted by noise.

Ultra sensitive label free surface enhanced Raman spectroscopy method for the detection of biomolecules

We present a proof of concept for a novel nanosensor for the detection of ultra-trace amounts of bio-active molecules in complex matrices. The nanosensor is comprised of gold nanoparticles with an ultra-thin silica shell and antibody surface attachment, which allows for the immobilization and direct detection of bio-active molecules by surface enhanced Raman spectroscopy (SERS) without requiring a Raman label. The ultra-thin passive layer (~1.3 nm thickness) prevents competing molecules from binding non-selectively to the gold surface without compromising the signal enhancement. The antibodies attached on the surface of the nanoparticles selectively bind to the target molecule with high affinity. The interaction between the nanosensor and the target analyte result in conformational rearrangements of the antibody binding sites, leading to significant changes in the surface enhanced Raman spectra of the nanoparticles when compared to the spectra of the un-reacted nanoparticles. Nanosensors of this design targeting the bio-active compounds erythropoietin and caffeine were able to detect ultra-trace amounts the analyte to the lower quantification limits of 3.5×10−13 M and 1×10−9 M, respectively.