Frequency response function based damage identification using principal component analysis and pattern recognition technique

Pattern recognition is a promising approach for the identification of structural damage using measured dynamic data. Much of the research on pattern recognition has employed artificial neural networks (ANNs) and genetic algorithms as systematic ways of matching pattern features. The selection of a damage-sensitive and noise-insensitive pattern feature is important for all structural damage identification methods. Accordingly, a neural networks-based damage detection method using frequency response function (FRF) data is presented in this paper. This method can effectively consider uncertainties of measured data from which training patterns are generated. The proposed method reduces the dimension of the initial FRF data and transforms it into new damage indices and employs an ANN method for the actual damage localization and quantification using recognized damage patterns from the algorithm. In civil engineering applications, the measurement of dynamic response under field conditions always contains noise components from environmental factors. In order to evaluate the performance of the proposed strategy with noise polluted data, noise contaminated measurements are also introduced to the proposed algorithm. ANNs with optimal architecture give minimum training and testing errors and provide precise damage detection results. In order to maximize damage detection results, the optimal architecture of ANN is identified by defining the number of hidden layers and the number of neurons per hidden layer by a trial and error method. In real testing, the number of measurement points and the measurement locations to obtain the structure response are critical for damage detection. Therefore, optimal sensor placement to improve damage identification is also investigated herein. A finite element model of a two storey framed structure is used to train the neural network. It shows accurate performance and gives low error with simulated and noise-contaminated data for single and multiple damage cases. As a result, the proposed method can be used for structural health monitoring and damage detection, particularly for cases where the measurement data is very large. Furthermore, it is suggested that an optimal ANN architecture can detect damage occurrence with good accuracy and can provide damage quantification with reasonable accuracy under varying levels of damage.

On robust face recognition via sparse coding: The good, the bad and the ugly

In the field of face recognition, sparse representation (SR) has received considerable attention during the past few years, with a focus on holistic descriptors in closed-set identification applications. The underlying assumption in such SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such an assumption is easily violated in the face verification scenario, where the task is to determine if two faces (where one or both have not been seen before) belong to the same person. In this study, the authors propose an alternative approach to SR-based face verification, where SR encoding is performed on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which then form an overall face descriptor. Owing to the deliberate loss of spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment and various image deformations. Within the proposed framework, they evaluate several SR encoding techniques: l1-minimisation, Sparse Autoencoder Neural Network (SANN) and an implicit probabilistic technique based on Gaussian mixture models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, on both the traditional closed-set identification task and the more applicable face verification task. The experiments also show that l1-minimisation-based encoding has a considerably higher computational cost when compared with SANN-based and probabilistic encoding, but leads to higher recognition rates.

Fear memory reactivation after extinction activates plasticity in the lateral amygdala

Little is known about the neuronal changes that occur within the lateral amygdala (LA) following fear extinction. In fear extinction, the repeated presentation of a conditioned stimulus (CS), in the absence of a previously paired aversive unconditioned stimulus (US), reduces fear elicited by the CS. Fear extinction is an active learning process that leads to the formation of a consolidated extinction memory, however it is fragile and prone to spontaneous recovery and renewal under environmental changes such as context. Understanding the neural mechanisms underlying fear extinction is of great clinical relevance, as psychological treatments of several anxiety disorders rely largely on extinction-based procedures and relapse is major clinical problem. This study investigated plasticity in the LA following fear memory reactivation in rats with and without extinction training. Phosphorylated MAPK (p44/42 ERK/MAPK), a protein kinase required in the amygdala for fear learning and its extinction, was used as a marker for neuronal plasticity. Rats (N = 11) underwent a Pavlovian auditory fear conditioning and extinction paradigm, and later received a single conditioned stimulus presentation to reactivate the fear memory. Results showed more pMAPK+ expressing neurons in the LA following extinction-reactivation compared to control rats, with the largest number of pMAPK+ neurons counted in the ventral LA, especially including the ventro-lateral subdivision (LAvl). These findings indicate that LA subdivision specific plasticity occurs to the conditioned fear memory in the LAvl following extinction-reactivation. These findings provide important insight into the organisation of fear memories in the LA, and pave the way for future research in the memory mechanisms of fear extinction and its pathophysiology.

Robust iris recognition using decision fusion and degradation modelling

This thesis investigates the use of fusion techniques and mathematical modelling to increase the robustness of iris recognition systems against iris image quality degradation, pupil size changes and partial occlusion. The proposed techniques improve recognition accuracy and enhance security. They can be further developed for better iris recognition in less constrained environments that do not require user cooperation. A framework to analyse the consistency of different regions of the iris is also developed. This can be applied to improve recognition systems using partial iris images, and cancelable biometric signatures or biometric based cryptography for privacy protection.

Conceptualising recognition of prior learning processes in the age of open learning

This chapter interrogates what recognition of prior learning (RPL) can and does mean in the higher education sector—a sector in the grip of the widening participation agenda and an open access age. The chapter discusses how open learning is making inroads into recognition processes and examines two studies in open learning recognition. A case study relating to e-portfolio-style RPL for entry into a Graduate Certificate in Policy and Governance at a metropolitan university in Queensland is described. In the first instance, candidates who do not possess a relevant Bachelor degree need to demonstrate skills in governmental policy work in order to be eligible to gain entry to a Graduate Certificate (at Australian Qualifications Framework Level 8) (Australian Qualifications Framework Council, 2013, p. 53). The chapter acknowledges the benefits and limitations of recognition in open learning and those of more traditional RPL, anticipating future developments in both (or their convergence).

Memory of past random wave conditions in submarine groundwater discharge

Submarine groundwater discharge (SGD) is an integral part of the hydrological cycle and represents an important aspect of land-ocean interactions. We used a numerical model to simulate flow and salt transport in a nearshore groundwater aquifer under varying wave conditions based on yearlong random wave data sets, including storm surge events. The results showed significant flow asymmetry with rapid response of influxes and retarded response of effluxes across the seabed to the irregular wave conditions. While a storm surge immediately intensified seawater influx to the aquifer, the subsequent return of intruded seawater to the sea, as part of an increased SGD, was gradual. Using functional data analysis, we revealed and quantified retarded, cumulative effects of past wave conditions on SGD including the fresh groundwater and recirculating seawater discharge components. The retardation was characterized well by a gamma distribution function regardless of wave conditions. The relationships between discharge rates and wave parameters were quantifiable by a regression model in a functional form independent of the actual irregular wave conditions. This statistical model provides a useful method for analyzing and predicting SGD from nearshore unconfined aquifers affected by random waves

Repeatable Condition-Invariant Visual Odometry for Sequence-Based Place Recognition

This paper describes a vision-only system for place recognition in environments that are tra- versed at different times of day, when chang- ing conditions drastically affect visual appear- ance, and at different speeds, where places aren’t visited at a consistent linear rate. The ma- jor contribution is the removal of wheel-based odometry from the previously presented algo- rithm (SMART), allowing the technique to op- erate on any camera-based device; in our case a mobile phone. While we show that the di- rect application of visual odometry to our night- time datasets does not achieve a level of perfor- mance typically needed, the VO requirements of SMART are orthogonal to typical usage: firstly only the magnitude of the velocity is required, and secondly the calculated velocity signal only needs to be repeatable in any one part of the environment over day and night cycles, but not necessarily globally consistent. Our results show that the smoothing effect of motion constraints is highly beneficial for achieving a locally consis- tent, lighting-independent velocity estimate. We also show that the advantage of our patch-based technique used previously for frame recogni- tion, surprisingly, does not transfer to VO, where SIFT demonstrates equally good performance. Nevertheless, we present the SMART system us- ing only vision, which performs sequence-base place recognition in extreme low-light condi- tions where standard 6-DOF VO fails and that improves place recognition performance over odometry-less benchmarks, approaching that of wheel odometry.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

The con-stitutional re-cognition (s)cam-pain: The campaign for the hidden recognition of first nations peoples' racial inferiority

The constitutional recognition campaign has received party-wide support and its efforts have been promoted by Prime Minister Tony Abbott as being something that would ‘complete our Constitution.’ The broader rhetoric surrounding this campaign suggests that it will result in a just, albeit delayed, recognition of indigenous peoples in the Australian legal system. However, beneath the surface of this seemingly benevolent gesture, is a reaffirmation of the colonial subordination and erasure of the several hundred original nations’ peoples and ways of being.

Recognition and enforcement in cross-border insolvency law: A proposal for judicial gap-filling

This Article analyzes the recognition and enforcement of cross-border insolvency judgments from the United States, United Kingdom, and Australia to determine whether the UNCITRAL Model Law’s goal of modified universalism is currently being practiced, and subjects the Model Law to analysis through the lens of international relations theories to elaborate a way forward. We posit that courts could use the express language of the Model Law text to confer recognition and enforcement of foreign insolvency judgments. The adoption of our proposal will reduce costs, maximize recovery for creditors, and ensure predictability for all parties.

Raloxifene for improving attention and memory in schizophrenia?

Schizophrenia can affect people's thoughts, feelings, and behaviour, and it can be as if your brain was playing tricks on you.

BIFF to BAPFF: considering 'festival memory' in the face of innovation and change

As an art form, film has arguably always functioned as a stronghold for memory. Memories unfold in the stories told on screen, and remain preserved in the experiences of the audience viewing the film, at a particular time and place. The environment of a film festival further alters the viewing experience and its relationship to memory. The Brisbane International Film Festival (BIFF) was founded in 1992. After considerable disruption due to economic and socio-political changes, it took place for the last time in 2013. The change in BIFF’s leadership and programming agenda significantly impacted the festival’s image and its position on the wider festival circuit. Through an examination of cinema and memory) it will be argued that film festivals operate as (temporary) sites of memory, through the programming and screening of films, engagement with local audiences, and promotion of film culture. This specific and unique ‘festival memory’ inextricably links to the audience and the venue, and is curated by the festival programmers and staff, who carry a wealth of knowledge (not necessarily recorded), of past festivals, successes, and failures. The people involved, the festival staff and audience, act as caretakers of this ‘festival memory.’ This essay will therefore examine how the BIFF and its home, the Regent Theatre, have functioned as crucial ‘sites of memory’ for film and film culture in Brisbane, Australia.

Farewelling the regent: Considering 'festival memory' in the face of innovation and change

The rapid expansion of the international film festival circuit has included the loss of smaller, but well established festivals, often due to the perceived need for constant innovation and change. The Brisbane International Film Festival was founded in 1992. After considerable disruption to the festival’s leadership, programme and location due to economic and socio-political changes, it was held for the last time in 2013. Nafus and Anderson cite the term ‘lieux de memoire’, meaning ‘sites of memory’, as a place of “remembrance that exist(s) in a social world that constantly seeks to get ahead of itself, to “innovate” (Nafus and Anderson in Cefkin 2009, 141). The concept of ‘festival memory’ has not yet been explored in any depth, but such significant shifts in festivals such as BIFF are arguably sites where festival histories and identities, and film knowledge itself, can be irretrievably lost.

Evoking poetics of memory through performing site: Naik Naik, a Malaysian Australian collaboration in the world heritage setting of Melaka

Memory, time and metaphor are central triggers for artists in exploring and shaping their creative work. This paper examines the place of artists as ‘memory-keepers’, and ‘memory-makers’, in particular through engagement with the time-based art of site-specific performance. Naik Naik (Ascent) was a multi-site performance project in the historic setting of Melaka, Malaysia, and is partially recaptured through the presence and voices of its collaborating artists. Distilled from moments recalled, this paper seeks to uncover the poetics of memory to emerge from the project; one steeped in metaphor rather than narrative. It elicits some of the complex and interdependent layers of experience revealed by the artists in Naik Naik; cultural, ancestral, historical, personal, instinctual and embodied memories connected to sound, smell, touch, sensation and light, in a spatiotemporal context for which site is the catalyst. The liminal nature of memory at the heart of Naik Naik, provides a shared experience of past and present and future, performatively interwoven.

Activity recognition using binary tree SVM

This paper presents an effective classification method based on Support Vector Machines (SVM) in the context of activity recognition. Local features that capture both spatial and temporal information in activity videos have made significant progress recently. Efficient and effective features, feature representation and classification plays a crucial role in activity recognition. For classification, SVMs are popularly used because of their simplicity and efficiency; however the common multi-class SVM approaches applied suffer from limitations including having easily confused classes and been computationally inefficient. We propose using a binary tree SVM to address the shortcomings of multi-class SVMs in activity recognition. We proposed constructing a binary tree using Gaussian Mixture Models (GMM), where activities are repeatedly allocated to subnodes until every new created node contains only one activity. Then, for each internal node a separate SVM is learned to classify activities, which significantly reduces the training time and increases the speed of testing compared to popular the `one-against-the-rest' multi-class SVM classifier. Experiments carried out on the challenging and complex Hollywood dataset demonstrates comparable performance over the baseline bag-of-features method.