Robust video stabilisation algorithm using feature point selection and delta optical flow

In this study, the authors propose a novel video stabilisation algorithm for mobile platforms with moving objects in the scene. The quality of videos obtained from mobile platforms, such as unmanned airborne vehicles, suffers from jitter caused by several factors. In order to remove this undesired jitter, the accurate estimation of global motion is essential. However it is difficult to estimate global motions accurately from mobile platforms due to increased estimation errors and noises. Additionally, large moving objects in the video scenes contribute to the estimation errors. Currently, only very few motion estimation algorithms have been developed for video scenes collected from mobile platforms, and this paper shows that these algorithms fail when there are large moving objects in the scene. In this study, a theoretical proof is provided which demonstrates that the use of delta optical flow can improve the robustness of video stabilisation in the presence of large moving objects in the scene. The authors also propose to use sorted arrays of local motions and the selection of feature points to separate outliers from inliers. The proposed algorithm is tested over six video sequences, collected from one fixed platform, four mobile platforms and one synthetic video, of which three contain large moving objects. Experiments show our proposed algorithm performs well to all these video sequences.

The effect of language models on phonetic decoding for spoken term detection

Spoken term detection (STD) popularly involves performing word or sub-word level speech recognition and indexing the result. This work challenges the assumption that improved speech recognition accuracy implies better indexing for STD. Using an index derived from phone lattices, this paper examines the effect of language model selection on the relationship between phone recognition accuracy and STD accuracy. Results suggest that language models usually improve phone recognition accuracy but their inclusion does not always translate to improved STD accuracy. The findings suggest that using phone recognition accuracy to measure the quality of an STD index can be problematic, and highlight the need for an alternative that is more closely aligned with the goals of the specific detection task.

Spoken term detection using fast phonetic decoding

While spoken term detection (STD) systems based on word indices provide good accuracy, there are several practical applications where it is infeasible or too costly to employ an LVCSR engine. An STD system is presented, which is designed to incorporate a fast phonetic decoding front-end and be robust to decoding errors whilst still allowing for rapid search speeds. This goal is achieved through mono-phone open-loop decoding coupled with fast hierarchical phone lattice search. Results demonstrate that an STD system that is designed with the constraint of a fast and simple phonetic decoding front-end requires a compromise to be made between search speed and search accuracy.

Unsupervised speaker adaptation for telephone call transcription

The use of the PC and Internet for placing telephone calls will present new opportunities to capture vast amounts of un-transcribed speech for a particular speaker. This paper investigates how to best exploit this data for speaker-dependent speech recognition. Supervised and unsupervised experiments in acoustic model and language model adaptation are presented. Using one hour of automatically transcribed speech per speaker with a word error rate of 36.0%, unsupervised adaptation resulted in an absolute gain of 6.3%, equivalent to 70% of the gain from the supervised case, with additional adaptation data likely to yield further improvements. LM adaptation experiments suggested that although there seems to be a small degree of speaker idiolect, adaptation to the speaker alone, without considering the topic of the conversation, is in itself unlikely to improve transcription accuracy.

Early outcomes of patella resurfacing in total knee arthroplasty

Background Patella resurfacing in total knee arthroplasty is a contentious issue. The literature suggests that resurfacing of the patella is based on surgeon preference, and little is known about the role and timing of resurfacing and how this affects outcomes. Methods We analyzed 134,799 total knee arthroplasties using data from the Australian Orthopaedic Association National Joint Replacement Registry. Hazards ratios (HRs) were used to compare rates of early revision between patella resurfacing at the primary procedure (the resurfacing group, R) and primary arthroplasty without resurfacing (no-resurfacing group, NR). We also analyzed the outcomes of NR that were revised for isolated patella addition. Results At 5 years, the R group showed a lower revision rate than the NR group: cumulative per cent revision (CPR) 3.1% and 4.0%, respectively (HR = 0.75, p < 0.001). Revisions for patellofemoral pain were more common in the NR group (17%) than in the R group (1%), and “patella only” revisions were more common in the NR group (29%) than in the R group (6%). Non-resurfaced knees revised for isolated patella addition had a higher revision rate than patella resurfacing at the primary procedure, with a 4-year CPR of 15% and 2.8%, respectively (HR = 4.1, p < 0.001). Interpretation Rates of early revision of primary total knees were higher when the patella was not resurfaced, and suggest that surgeons may be inclined to resurface later if there is patellofemoral pain. However, 15% of non-resurfaced knees revised for patella addition are re-revised by 4 years. Our results suggest an early beneficial outcome for patella resurfacing at primary arthroplasty based on revision rates up to 5 years.

Intelligent prognostics of machinery health utilising suspended condition monitoring data

The ability to forecast machinery failure is vital to reducing maintenance costs, operation downtime and safety hazards. Recent advances in condition monitoring technologies have given rise to a number of prognostic models for forecasting machinery health based on condition data. Although these models have aided the advancement of the discipline, they have made only a limited contribution to developing an effective machinery health prognostic system. The literature review indicates that there is not yet a prognostic model that directly models and fully utilises suspended condition histories (which are very common in practice since organisations rarely allow their assets to run to failure); that effectively integrates population characteristics into prognostics for longer-range prediction in a probabilistic sense; which deduces the non-linear relationship between measured condition data and actual asset health; and which involves minimal assumptions and requirements. This work presents a novel approach to addressing the above-mentioned challenges. The proposed model consists of a feed-forward neural network, the training targets of which are asset survival probabilities estimated using a variation of the Kaplan-Meier estimator and a degradation-based failure probability density estimator. The adapted Kaplan-Meier estimator is able to model the actual survival status of individual failed units and estimate the survival probability of individual suspended units. The degradation-based failure probability density estimator, on the other hand, extracts population characteristics and computes conditional reliability from available condition histories instead of from reliability data. The estimated survival probability and the relevant condition histories are respectively presented as “training target” and “training input” to the neural network. The trained network is capable of estimating the future survival curve of a unit when a series of condition indices are inputted. Although the concept proposed may be applied to the prognosis of various machine components, rolling element bearings were chosen as the research object because rolling element bearing failure is one of the foremost causes of machinery breakdowns. Computer simulated and industry case study data were used to compare the prognostic performance of the proposed model and four control models, namely: two feed-forward neural networks with the same training function and structure as the proposed model, but neglected suspended histories; a time series prediction recurrent neural network; and a traditional Weibull distribution model. The results support the assertion that the proposed model performs better than the other four models and that it produces adaptive prediction outputs with useful representation of survival probabilities. This work presents a compelling concept for non-parametric data-driven prognosis, and for utilising available asset condition information more fully and accurately. It demonstrates that machinery health can indeed be forecasted. The proposed prognostic technique, together with ongoing advances in sensors and data-fusion techniques, and increasingly comprehensive databases of asset condition data, holds the promise for increased asset availability, maintenance cost effectiveness, operational safety and – ultimately – organisation competitiveness.

Creating an asset registry for railway electrical traction equipment with open standards

An asset registry arguably forms the core system that needs to be in place before other systems can operate or interoperate. Most systems have rudimentary asset registry functionality that store assets, relationships, or characteristics, and this leads to different asset management systems storing similar sets of data in multiple locations in an organisation. As organisations have been slowly moving their information architecture toward a service-oriented architecture, they have also been consolidating their multiple data stores, to form a “single point of truth”. As part of a strategy to integrate several asset management systems in an Australian railway organisation, a case study for developing a consolidated asset registry was conducted. A decision was made to use the MIMOSA OSA-EAI CRIS data model as well as the OSA-EAI Reference Data in building the platform due to the standard’s relative maturity and completeness. A pilot study of electrical traction equipment was selected, and the data sources feeding into the asset registry were primarily diagrammatic based. This paper presents the pitfalls encountered, approaches taken, and lessons learned during the development of the asset registry.

End-winding effect on shalft voltage in AC generators

This paper presents effects of end-winding on shaft voltage in AC generators. A variety of design parameters have been considered to calculate the parasitic capacitive couplings in the machine structure with Finite Elements simulations and mathematical calculations. End-winding capacitances have also been calculated to have a precise estimation of shaft voltage and its relationship with design parameters in AC generators.

Corrosion studies on the plasma-sprayed nanostructured titanium dioxide coating

Purpose: The purpose of this paper is to report the resistance of plasma-sprayed titanium dioxide (TiO2) nanostructured coatings in a corrosive environment.----- Design/methodology/approach: Weight loss studies are performed according to ASTM G31 specifications in 3.5?wt% NaCl. Electrochemical polarization resistance measurements are made according to ASTM G59-91 specifications. Corrosion resistance in a humid and corrosive environment is determined by exposing the samples in a salt spray chamber for 100?h. Microstructural studies are carried out using an atomic force microscope and scanning electron microscope.----- Findings: The nanostructured TiO2 coatings offer good resistance to corrosion, as shown by the results of immersion, electrochemical and salt spray studies. The corrosion resistance of the coating is dictated primarily by the geometry of splat lamellae, density of unmelted nanoparticles, magnitude of porosity and surface homogeneity.----- Practical implications: The TiO2 nanostructured coatings show promising potential for use as abrasion, wear-resistant and thermal barrier coatings for service in harsh environments.----- Originality/value: The paper relates the corrosion resistance of nanostructured TiO2 coatings to their structure and surface morphology.

Wear mechanisms and scale effects in two-body abrasion

The ‘particle size effect’ and its manifestation in abrasion still attracts considerable debate as to its origins and the ranking of its likely causes. Experiments have been conducted to study the important contribution that the formation of wear debris can have on the progression of wear. The experiments consist of unlubricated (dry) pin-on-disk tests with silicon carbide coated paper of varying particle size, with different pin material, diameter and loads. It has been observed that the influence of debris formation on wear rate is more pronounced for fine abrasives and soft-wearing materials. Consequently, it is proposed that the particle size effect can be explained in terms of geometrical scaling and the evolution of third-body effects with diminishing particle diameter.

Characteristic analysis for multisampled digital implementation of fixed-switching-frequency closed-loop modulation of voltage-source inverter

In this paper, a fixed-switching-frequency closed-loop modulation of a voltage-source inverter (VSI), upon the digital implementation of the modulation process, is analyzed and characterized. The sampling frequency of the digital processor is considered as an integer multiple of the modulation switching frequency. An expression for the determination of the modulation design parameter is developed for smooth modulation at a fixed switching frequency. The variation of the sampling frequency, switching frequency, and modulation index has been analyzed for the determination of the switching condition under closed loop. It is shown that the switching condition determined based on the continuous-time analysis of the closed-loop modulation will ensure smooth modulation upon the digital implementation of the modulation process. However, the stability properties need to be tested prior to digital implementation as they get deteriorated at smaller sampling frequencies. The closed-loop modulation index needs to be considered maximum while determining the design parameters for smooth modulation. In particular, a detailed analysis has been carried out by varying the control gain in the sliding-mode control of a two-level VSI. The proposed analysis of the closed-loop modulation of the VSI has been verified for the operation of a distribution static compensator. The theoretical results are validated experimentally on both single- and three-phase systems.

Design of self-turning controllers for two terminal HVDC link

This paper presents the design of self-tuning controllers for a two terminal HVDC link. The controllers are designed utilizing a novel discrete-time converter model based on multirate sampling. The nature of converter firing system necessitates the development of a two-step ahead self-tuning control strategy. A two terminal HVDC system study has been carried out to show the effectiveness of the control strategies proposed which include the design of minimum variance controller, pole assigned controller and PLQG controller. The coordinated control of a two terminal HVDC system has been established deriving the signal from inverter end current and voltage which has been estimated based on the measurements of rectifier end quantities only realized through the robust reduced order observer. A well known scaled down sample system data has been selected for studies and the controllers designed have been tested for worst conditions. The performance of self-tuning controllers has been evaluated through digital simulation.

Determination of elastic modulus of thin coating materials using nanoindentation and finite element analysis

A deconvolution method that combines nanoindentation and finite element analysis was developed to determine elastic modulus of thin coating layer in a coating-substrate bilayer system. In this method, the nanoindentation experiments were conducted to obtain the modulus of both the bilayer system and the substrate. The finite element analysis was then applied to deconvolve the elastic modulus of the coating. The results demonstrated that the elastic modulus obtained using the developed method was in good agreement with that reported in literature.

Biometric template security using higher order spectra

A method of improving the security of biometric templates which satisfies desirable properties such as (a) irreversibility of the template, (b) revocability and assignment of a new template to the same biometric input, (c) matching in the secure transformed domain is presented. It makes use of an iterative procedure based on the bispectrum that serves as an irreversible transformation for biometric features because signal phase is discarded each iteration. Unlike the usual hash function, this transformation preserves closeness in the transformed domain for similar biometric inputs. A number of such templates can be generated from the same input. These properties are illustrated using synthetic data and applied to images from the FRGC 3D database with Gabor features. Verification can be successfully performed using these secure templates with an EER of 5.85%

Control and protection of a microgrid with converter interfaced micro sources

This paper describes protection and control of a microgrid with converter interfaced micro sources. The proposed protection and control scheme consider both grid connected and autonomous operation of the microgrid. A protection scheme, capable of detecting faults effectively in both grid connected and islanded operations is proposed. The main challenge of the protection, due to current limiting state of the converters is overcome by using admittance relays. The relays operate according to the inverse time characteristic based on measured admittance of the line. The proposed scheme isolates the fault from both sides, while downstream side of the microgrid operates in islanding condition. Moreover faults can be detected in autonomous operation. In grid connected mode distributed generators (DG) supply the rated power while in absence of the grid, DGs share the entire power requirement proportional to rating based on output voltage angle droop control. The protection scheme ensures minimum load shedding with isolating the faulted network and DG control provides a smooth islanding and resynchronization operation. The efficacy of coordinated control and protection scheme has been validated through simulation for various operating conditions.