Improved image set classification via joint sparse approximated nearest subspaces

Existing multi-model approaches for image set classification extract local models by clustering each image set individually only once, with fixed clusters used for matching with other image sets. However, this may result in the two closest clusters to represent different characteristics of an object, due to different undesirable environmental conditions (such as variations in illumination and pose). To address this problem, we propose to constrain the clustering of each query image set by forcing the clusters to have resemblance to the clusters in the gallery image sets. We first define a Frobenius norm distance between subspaces over Grassmann manifolds based on reconstruction error. We then extract local linear subspaces from a gallery image set via sparse representation. For each local linear subspace, we adaptively construct the corresponding closest subspace from the samples of a probe image set by joint sparse representation. We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold. Experiments on Honda, ETH-80 and Cambridge-Gesture datasets show that the proposed method consistently outperforms several other recent techniques, such as Affine Hull based Image Set Distance (AHISD), Sparse Approximated Nearest Points (SANP) and Manifold Discriminant Analysis (MDA).

Catchment-specific element signatures in estuarine crocodiles (Crocodylus porosus) from the Alligator Rivers Region, northern Australia

The concentrations of Na, K, Ca, Mg, Ba, Sr, Fe, Al, Mn, Zn, Pb, Cu, Ni, Cr, Co, Se, U and Ti were determined in the osteoderms and/or flesh of estuarine crocodiles (Crocodylus porosus) captured in three adjacent catchments within the Alligator Rivers Region (ARR) of northern Australia. Results from multivariate analysis of variance showed that when all metals were considered simultaneously, catchment effects were significant (P≤0.05). Despite considerable within-catchment variability, linear discriminant analysis (LDA) showed that differences in elemental signatures in the osteoderms and/or flesh of C. porosus amongst the catchments were sufficient to classify individuals accurately to their catchment of occurrence. Using cross-validation, the accuracy of classifying a crocodile to its catchment of occurrence was 76% for osteoderms and 60% for flesh. These data suggest that osteoderms provide better predictive accuracy than flesh for discriminating crocodiles amongst catchments. There was no advantage in combining the osteoderm and flesh results to increase the accuracy of classification (i.e. 67%). Based on the discriminant function coefficients for the osteoderm data, Ca, Co, Mg and U were the most important elements for discriminating amongst the three catchments. For flesh data, Ca, K, Mg, Na, Ni and Pb were the most important metals for discriminating amongst the catchments. Reasons for differences in the elemental signatures of crocodiles between catchments are generally not interpretable, due to limited data on surface water and sediment chemistry of the catchments or chemical composition of dietary items of C. porosus. From a wildlife management perspective, the provenance or source catchment(s) of 'problem' crocodiles captured at settlements or recreational areas along the ARR coastline may be established using catchment-specific elemental signatures. If the incidence of problem crocodiles can be reduced in settled or recreational areas by effective management at their source, then public safety concerns about these predators may be moderated, as well as the cost of their capture and removal. Copyright © 2002 Elsevier Science B.V.

Short utterance PLDA speaker verification using SN-WLDA and variance modelling techniques

This paper proposes a combination of source-normalized weighted linear discriminant analysis (SN-WLDA) and short utterance variance (SUV) PLDA modelling to improve the short utterance PLDA speaker verification. As short-length utterance i-vectors vary with the speaker, session variations and phonetic content of the utterance (utterance variation), a combined approach of SN-WLDA projection and SUV PLDA modelling is used to compensate the session and utterance variations. Experimental studies have found that a combination of SN-WLDA and SUV PLDA modelling approach shows an improvement over baseline system (WCCN[LDA]-projected Gaussian PLDA (GPLDA)) as this approach effectively compensates the session and utterance variations.

Hormone and Metabolite Profiles in Nesting Green and Flatback Turtles: Turtle Species with Different Life Histories

Herbivorous turtle, Chelonia mydas, inhabiting the south China Sea and breeding in Peninsular Malaysia, and Natator depressus, a carnivorous turtle inhabiting the Great Barrier Reef and breeding at Curtis Island in Queensland, Australia, differ both in diet and life history. Analysis of plasma metabolites levels and six sex steroid hormones during the peak of their nesting season in both species showed hormonal and metabolite variations. When compared with results from other studies progesterone levels were the highest whereas dihydrotestosterone was the plasma steroid hormone present at the lowest concentration in both C. mydas and N. depressus plasma. Interestingly, oestrone was observed at relatively high concentrations in comparison to oestradiol levels recorded in previous studies suggesting that it plays a significant role in nesting turtles. Also, hormonal correlations between the studied species indicate unique physiological interactions during nesting. Pearson correlation analysis showed that in N. depressus the time of oviposition was associated with elevations in both plasma corticosterone and oestrone levels. Therefore, we conclude that corticosterone and oestrone may influence nesting behaviour and physiology in N. depressus. To summarise, these two nesting turtle species can be distinguished based on the hormonal profile of oestrone, progesterone, and testosterone using discriminant analysis.

Pollen image classification using the classifynder system: Algorithm comparison and a case study on New Zealand honey

We describe an investigation into how Massey University’s Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University’s pollen reference collection (2,890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set.We additionally work through a real world case study where we assess the ability of the system to determine the pollen make-up of samples of New Zealand honey. In addition to the Classifynder’s native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples.

Improving out-domain PLDA speaker verification using unsupervised inter-dataset variability compensation approach

Experimental studies have found that when the state-of-the-art probabilistic linear discriminant analysis (PLDA) speaker verification systems are trained using out-domain data, it significantly affects speaker verification performance due to the mismatch between development data and evaluation data. To overcome this problem we propose a novel unsupervised inter dataset variability (IDV) compensation approach to compensate the dataset mismatch. IDV-compensated PLDA system achieves over 10% relative improvement in EER values over out-domain PLDA system by effectively compensating the mismatch between in-domain and out-domain data.

Application of higher-order spectra for automated grading of diabetic maculopathy

Diabetic macular edema (DME) is one of the most common causes of visual loss among diabetes mellitus patients. Early detection and successive treatment may improve the visual acuity. DME is mainly graded into non-clinically significant macular edema (NCSME) and clinically significant macular edema according to the location of hard exudates in the macula region. DME can be identified by manual examination of fundus images. It is laborious and resource intensive. Hence, in this work, automated grading of DME is proposed using higher-order spectra (HOS) of Radon transform projections of the fundus images. We have used third-order cumulants and bispectrum magnitude, in this work, as features, and compared their performance. They can capture subtle changes in the fundus image. Spectral regression discriminant analysis (SRDA) reduces feature dimension, and minimum redundancy maximum relevance method is used to rank the significant SRDA components. Ranked features are fed to various supervised classifiers, viz. Naive Bayes, AdaBoost and support vector machine, to discriminate No DME, NCSME and clinically significant macular edema classes. The performance of our system is evaluated using the publicly available MESSIDOR dataset (300 images) and also verified with a local dataset (300 images). Our results show that HOS cumulants and bispectrum magnitude obtained an average accuracy of 95.56 and 94.39 % for MESSIDOR dataset and 95.93 and 93.33 % for local dataset, respectively.

Investigating in-domain data requirements for PLDA training

This paper analyzes the limitations upon the amount of in- domain (NIST SREs) data required for training a probabilistic linear discriminant analysis (PLDA) speaker verification system based on out-domain (Switchboard) total variability subspaces. By limiting the number of speakers, the number of sessions per speaker and the length of active speech per session available in the target domain for PLDA training, we investigated the relative effect of these three parameters on PLDA speaker verification performance in the NIST 2008 and NIST 2010 speaker recognition evaluation datasets. Experimental results indicate that while these parameters depend highly on each other, to beat out-domain PLDA training, more than 10 seconds of active speech should be available for at least 4 sessions/speaker for a minimum of 800 speakers. If further data is available, considerable improvement can be made over solely out-domain PLDA training.

Improving PLDA speaker verification using WMFD and linear-weighted approaches in limited microphone data conditions

This paper proposes the addition of a weighted median Fisher discriminator (WMFD) projection prior to length-normalised Gaussian probabilistic linear discriminant analysis (GPLDA) modelling in order to compensate the additional session variation. In limited microphone data conditions, a linear-weighted approach is introduced to increase the influence of microphone speech dataset. The linear-weighted WMFD-projected GPLDA system shows improvements in EER and DCF values over the pooled LDA- and WMFD-projected GPLDA systems in inter-view-interview condition as WMFD projection extracts more speaker discriminant information with limited number of sessions/ speaker data, and linear-weighted GPLDA approach estimates reliable model parameters with limited microphone data.

Detecting the attributes of a wheat crop using digital imagery acquired from a low-altitude platform

A low-altitude platform utilising a 1.8-m diameter tethered helium balloon was used to position a multispectral sensor, consisting of two digital cameras, above a fertiliser trial plot where wheat (Triticum spp.) was being grown. Located in Cecil Plains, Queensland, Australia, the plot was a long-term fertiliser trial being conducted by a fertiliser company to monitor the response of crops to various levels of nutrition. The different levels of nutrition were achieved by varying nitrogen application rates between 0 and 120 units of N at 40 unit increments. Each plot had received the same application rate for 10 years. Colour and near-infrared images were acquired that captured the whole 2 ha plot. These images were examined and relationships sought between the captured digital information and the crop parameters imaged at anthesis and the at-harvest quality and quantity parameters. The statistical analysis techniques used were correlation analysis, discriminant analysis and partial least squares regression. A high correlation was found between the image and yield (R2 = 0.91) and a moderate correlation between the image and grain protein content (R2 = 0.66). The utility of the system could be extended by choosing a more mobile platform. This would increase the potential for the system to be used to diagnose the causes of the variability and allow remediation, and/or to segregate the crop at harvest to meet certain quality parameters.

Identifying major contributing sources to odour annoyance using a non-specific gas sensor array

Identification of major contributors to odour annoyance in areas with multiple emission sources is necessary to address and resolve odour disputes. In an effort to develop an appropriate tool for this task, odour samples were collected on-site at a piggery and an abattoir (the major odour sources in the area) and at surrounding off-site areas, then analysed using a commercial non-specific chemical sensor array to develop an odour fingerprint database. The developed odour fingerprint database was analysed using two pattern recognition algorithms including a partial least squares-discriminant analysis (PLS-DA) and a Kohonen self-organising map (KSOM). The KSOM model could identify odour samples sourced from the piggery shed 15, piggery pond 8, piggery pond 9, abattoir, motel and others with mean percentage values of 77.5, 65.0, 90.2, 75.7, 44.8 and 64.6%, respectively.

Marker selection by Akaike information criterion and Bayesian information criterion

We carried out a discriminant analysis with identity by descent (IBD) at each marker as inputs, and the sib pair type (affected-affected versus affected-unaffected) as the output. Using simple logistic regression for this discriminant analysis, we illustrate the importance of comparing models with different number of parameters. Such model comparisons are best carried out using either the Akaike information criterion (AIC) or the Bayesian information criterion (BIC). When AIC (or BIC) stepwise variable selection was applied to the German Asthma data set, a group of markers were selected which provide the best fit to the data (assuming an additive effect). Interestingly, these 25-26 markers were not identical to those with the highest (in magnitude) single-locus lod scores.

Deviant near-infrared spectra identifies Corymbia hybrids

The study examined the potential of Near Infrared Reflectance (NIR) spectroscopy for field diagnosis of hybrids between Corymbia (formerly Eucalyptus) species. NIR profiles were generated by scanning foliage from a total of 383 hybrid and 533 parental seedlings grown in a common garden and partial least squares discriminant analysis was used to test three-way model power to assign individuals to their appropriate taxon; either a parental or F1 hybrid class. Using the optimised conditions, fresh foliage from eight-month-old seedlings and a handheld NIR instrument (950–1800 nm), the mean assignment rates for the three hybrid groups ranged from 76% to 90%. Hybrid-parent contrast of NIR spectra deviated more so than parent–parent contrast. The F1 taxon assignment rates were usually higher than those for parents at 100% and 72%, respectively. Hybrid resolution was even greater for 2nd generation backcross hybrids. Similar to studies of morphology, taxon assignments tended to be more accurate for hybrid groups in which the parental taxa were more divergent. The practical application of this technique for hybrid diagnosis of seedlings in the nursery will require careful attention to control environmental factors because seedling age and storage effects influenced the ability of NIR to identify hybrids. The technique may also necessitate the generation of comparable reference populations, although exclusions approaches to analysis may circumvent the need for reference populations. The application of NIR in field diagnosis will be further complicated by the need to generate global models across environments but such models have been obtained for reliable prediction of chemistries in other situations.

Otolith morphology of four mackerel species (Scomberomorus spp.) in Australia: Species differentiation and prediction for fisheries monitoring and assessment

Four species of large mackerels (Scomberomorus spp.) co-occur in the waters off northern Australia and are important to fisheries in the region. State fisheries agencies monitor these species for fisheries assessment; however, data inaccuracies may exist due to difficulties with identification of these closely related species, particularly when specimens are incomplete from fish processing. This study examined the efficacy of using otolith morphometrics to differentiate and predict among the four mackerel species off northeastern Australia. Seven otolith measurements and five shape indices were recorded from 555 mackerel specimens. Multivariate modelling including linear discriminant analysis (LDA) and support vector machines, successfully differentiated among the four species based on otolith morphometrics. Cross validation determined a predictive accuracy of at least 96% for both models. An optimum predictive model for the four mackerel species was an LDA model that included fork length, feret length, feret width, perimeter, area, roundness, form factor and rectangularity as explanatory variables. This analysis may improve the accuracy of fisheries monitoring, the estimates based on this monitoring (i.e. mortality rate) and the overall management of mackerel species in Australia.

Större frihet - bättre lokalt anpassad service? : Förvaltningsreformer och kommunernas service för utvecklingsstörda 1994-2000

In the beginning of the 1990s the legislation regarding the municipalities and the system of central government transfers were reformed in Finland. This resulted in a move from detailed governmental control to increased municipal autonomy. The purpose of this decentralization was to enable the municipalities to better adapt their administration and service supply to local needs. The aim of this study was to explore the effects of the increased municipal autonomy on the organization of services for people with intellectual disabilities. Did the increased autonomy cause the municipalities to alter their service supply and production and did the services become more adapted to local needs? The data consists of statistical information on service use and production, and also of background data such as demographics, economics and political elections on 452 municipalities in Finland from the years 1994 and 2000. The methods used are cluster analysis, discriminant analysis and factor analysis. The municipalities could be grouped in two categories: those which offered mainly one kind of residential services and others which had more varied mixes of services. The use of institutional care had decreased and municipalities which used institutional care as their primary form of service were mostly very small municipalities in 2000. The situation had changed from 1994, when institutional care was the primary service for municipalities of all sizes. Also the service production had become more differentiated and the municipalities had started using more varied ways of production. More municipalities had started producing their own services and private production had increased as well. Furthermore, the increase in local autonomy had opened up possibilities for local politics to influence both the service selection and methods of production. The most significant motive for changes in the service structure was high unemployment and an increasing share of elderly people in the population, particularly in sparsely populated areas. Municipalities with a low level of resources had made more changes in their service organization while those with more resources had been able to carry on as before. Key words: service structure, service for people with intellectual disabilities, municipalities, contingency theory, New Public Management