Robustness of NIR calibrations for soluble solids in intact melon and pineapple

The soluble solids content of intact fruit can be measured non-invasively by near infrared spectroscopy, allowing “sweetness” grading of individual fruit. However, little information is available in the literature with respect to the robustness of such calibrations. We developed calibrations based on a restricted wavelength range (700–1100 nm), suitable for use with low-cost silicon detector systems, using a stepwise multiple linear regression routine. Calibrations for total soluble solids (°Brix) in intact pineapple fruit were not transferable between summer and winter growing seasons. A combined calibration (data of three harvest dates) validated reasonably well against a population set drawn from all harvest dates (r2 = 0.72, SEP = 1.84 °Brix). Calibrations for Brix in melon were transferable between two of the three varieties examined. However, a lack of robustness of calibration was indicated by poor validation within populations of fruit harvested at different times. Further work is planned to investigate the robustness of calibration across varieties, growing districts and seasons.

Assessment of internal quality attributes of mandarin fruit. 2. NIR calibration model robustness

The robustness of multivariate calibration models, based on near infrared spectroscopy, for the assessment of total soluble solids (TSS) and dry matter (DM) of intact mandarin fruit (Citrus reticulata cv. Imperial) was assessed. TSS calibration model performance was validated in terms of prediction of populations of fruit not in the original population (different harvest days from a single tree, different harvest localities, different harvest seasons). Of these, calibration performance was most affected by validation across seasons (signal to noise statistic on root mean squared error of prediction of 3.8, compared with 20 and 13 for locality and harvest day, respectively). Procedures for sample selection from the validation population for addition to the calibration population (‘model updating’) were considered for both TSS and DM models. Random selection from the validation group worked as well as more sophisticated selection procedures, with approximately 20 samples required. Models that were developed using samples at a range of temperatures were robust in validation for TSS and DM.

Robustness of NIR calibrations for assessing fruit quality

Predictive models based on near infra-red spectroscopy for the assessment of fruit internal quality attributes must exhibit a degree of robustness across the parameters of variety, district and time to be of practical use in fruit grading. At the time this thesis was initiated, while there were a number of published reports on the development of near infra-red based calibration models for the assessment of internal quality attributes of intact fruit, there were no reports of the reliability ("robustness") of such models across time, cultivars or growing regions. As existing published reports varied in instrumentation employed, a re-analysis of existing data was not possible. An instrument platform, based on partial transmittance optics, a halogen light source and (Zeiss MMS 1) detector operating in the short wavelength near infra-red region was developed for use in the assessment of intact fruit. This platform was used to assess populations of macadamia kernels, melons and mandarin fruit for total soluble solids, dry matter and oil concentration. Calibration procedures were optimised and robustness assessed across growing areas, time of harvest, season and variety. In general, global modified partial least squares regression (MPLS) calibration models based on derivatised absorbance data were better than either multiple linear regression or `local' MPLS models in the prediction of independent validation populations . Robustness was most affected by growing season, relative to the growing district or variety . Various calibration updating procedures were evaluated in terms of calibration robustness. Random selection of samples from the validation population for addition to the calibration population was equivalent to or better than other methods of sample addition (methods based on the Mahalanobis distance of samples from either the centroid of the population or neighbourhood samples). In these exercises the global Mahalanobis distance (GH) was calculated using the scores and loadings from the calibration population on the independent validation population. In practice, it is recommended that model predictive performance be monitored in terms of predicted sample GH, with model updating using as few as 10 samples from the new population undertaken when the average GH value exceeds 1 .0 .

Society by Numbers : Studies on Model-Based Explanations in the Social Sciences

The aim of this dissertation is to provide conceptual tools for the social scientist for clarifying, evaluating and comparing explanations of social phenomena based on formal mathematical models. The focus is on relatively simple theoretical models and simulations, not statistical models. These studies apply a theory of explanation according to which explanation is about tracing objective relations of dependence, knowledge of which enables answers to contrastive why and how-questions. This theory is developed further by delineating criteria for evaluating competing explanations and by applying the theory to social scientific modelling practices and to the key concepts of equilibrium and mechanism. The dissertation is comprised of an introductory essay and six published original research articles. The main theses about model-based explanations in the social sciences argued for in the articles are the following. 1) The concept of explanatory power, often used to argue for the superiority of one explanation over another, compasses five dimensions which are partially independent and involve some systematic trade-offs. 2) All equilibrium explanations do not causally explain the obtaining of the end equilibrium state with the multiple possible initial states. Instead, they often constitutively explain the macro property of the system with the micro properties of the parts (together with their organization). 3) There is an important ambivalence in the concept mechanism used in many model-based explanations and this difference corresponds to a difference between two alternative research heuristics. 4) Whether unrealistic assumptions in a model (such as a rational choice model) are detrimental to an explanation provided by the model depends on whether the representation of the explanatory dependency in the model is itself dependent on the particular unrealistic assumptions. Thus evaluating whether a literally false assumption in a model is problematic requires specifying exactly what is supposed to be explained and by what. 5) The question of whether an explanatory relationship depends on particular false assumptions can be explored with the process of derivational robustness analysis and the importance of robustness analysis accounts for some of the puzzling features of the tradition of model-building in economics. 6) The fact that economists have been relatively reluctant to use true agent-based simulations to formulate explanations can partially be explained by the specific ideal of scientific understanding implicit in the practise of orthodox economics.

Statistical Optimization of Iron Electrodes for Alkaline Storage Batteries

A pressed-plate Fe electrode for alkalines storage batteries, designed using a statistical method (fractional factorial technique), is described. Parameters such as the configuration of the base grid, electrode compaction temperature and pressure, binder composition, mixing time, etc. have been optimised using this method. The optimised electrodes have a capacity of 300 plus /minus 5 mA h/g of active material (mixture of Fe and magnetite) at 7 h rate to a cut-off voltage of 8.86V vs. Hg/HgO, OH exp 17 ref.

Domain Adaptation on the Statistical Manifold

In this paper, we tackle the problem of unsupervised domain adaptation for classification. In the unsupervised scenario where no labeled samples from the target domain are provided, a popular approach consists in transforming the data such that the source and target distributions be- come similar. To compare the two distributions, existing approaches make use of the Maximum Mean Discrepancy (MMD). However, this does not exploit the fact that prob- ability distributions lie on a Riemannian manifold. Here, we propose to make better use of the structure of this man- ifold and rely on the distance on the manifold to compare the source and target distributions. In this framework, we introduce a sample selection method and a subspace-based method for unsupervised domain adaptation, and show that both these manifold-based techniques outperform the cor- responding approaches based on the MMD. Furthermore, we show that our subspace-based approach yields state-of- the-art results on a standard object recognition benchmark.

Comparison Of If Estimation Methods For Noise Robustness

Non-stationary signal modeling is a well addressed problem in the literature. Many methods have been proposed to model non-stationary signals such as time varying linear prediction and AM-FM modeling, the later being more popular. Estimation techniques to determine the AM-FM components of narrow-band signal, such as Hilbert transform, DESA1, DESA2, auditory processing approach, ZC approach, etc., are prevalent but their robustness to noise is not clearly addressed in the literature. This is critical for most practical applications, such as in communications. We explore the robustness of different AM-FM estimators in the presence of white Gaussian noise. Also, we have proposed three new methods for IF estimation based on non-uniform samples of the signal and multi-resolution analysis. Experimental results show that ZC based methods give better results than the popular methods such as DESA in clean condition as well as noisy condition.

Annual forecasting of the Australian macadamia crop - integrating tree census data with statistical climate-adjustment models

To facilitate marketing and export, the Australian macadamia industry requires accurate crop forecasts. Each year, two levels of crop predictions are produced for this industry. The first is an overall longer-term forecast based on tree census data of growers in the Australian Macadamia Society (AMS). This data set currently accounts for around 70% of total production, and is supplemented by our best estimates of non-AMS orchards. Given these total tree numbers, average yields per tree are needed to complete the long-term forecasts. Yields from regional variety trials were initially used, but were found to be consistently higher than the average yields that growers were obtaining. Hence, a statistical model was developed using growers' historical yields, also taken from the AMS database. This model accounted for the effects of tree age, variety, year, region and tree spacing, and explained 65% of the total variation in the yield per tree data. The second level of crop prediction is an annual climate adjustment of these overall long-term estimates, taking into account the expected effects on production of the previous year's climate. This adjustment is based on relative historical yields, measured as the percentage deviance between expected and actual production. The dominant climatic variables are observed temperature, evaporation, solar radiation and modelled water stress. Initially, a number of alternate statistical models showed good agreement within the historical data, with jack-knife cross-validation R2 values of 96% or better. However, forecasts varied quite widely between these alternate models. Exploratory multivariate analyses and nearest-neighbour methods were used to investigate these differences. For 2001-2003, the overall forecasts were in the right direction (when compared with the long-term expected values), but were over-estimates. In 2004 the forecast was well under the observed production, and in 2005 the revised models produced a forecast within 5.1% of the actual production. Over the first five years of forecasting, the absolute deviance for the climate-adjustment models averaged 10.1%, just outside the targeted objective of 10%.

Generalized pencils of rays in statistical wave optics

The recently introduced generalized pencil of Sudarshan which gives an exact ray picture of wave optics is analysed in some situations of interest to wave optics. A relationship between ray dispersion and statistical inhomogeneity of the field is obtained. A paraxial approximation which preserves the rectilinear propagation character of the generalized pencils is presented. Under this approximation the pencils can be computed directly from the field conditions on a plane, without the necessity to compute the cross-spectral density function in the entire space as an intermediate quantity. The paraxial results are illustrated with examples. The pencils are shown to exhibit an interesting scaling behaviour in the far-zone. This scaling leads to a natural generalization of the Fraunhofer range criterion and of the classical van Cittert-Zernike theorem to planar sources of arbitrary state of coherence. The recently derived results of radiometry with partially coherent sources are shown to be simple consequences of this scaling.

Learning with symmetric label noise: The importance of being unhinged

Convex potential minimisation is the de facto approach to binary classification. However, Long and Servedio [2008] proved that under symmetric label noise (SLN), minimisation of any convex potential over a linear function class can result in classification performance equivalent to random guessing. This ostensibly shows that convex losses are not SLN-robust. In this paper, we propose a convex, classification-calibrated loss and prove that it is SLN-robust. The loss avoids the Long and Servedio [2008] result by virtue of being negatively unbounded. The loss is a modification of the hinge loss, where one does not clamp at zero; hence, we call it the unhinged loss. We show that the optimal unhinged solution is equivalent to that of a strongly regularised SVM, and is the limiting solution for any convex potential; this implies that strong l2 regularisation makes most standard learners SLN-robust. Experiments confirm the unhinged loss’ SLN-robustness.

Development of commercial application of an avocado fruit robustness test

Fruit quality is one of the major factors limiting growth in avocado retail sales. Avocado growers are often unaware of their end-use fruit quality since quality problems only manifest upon fruit ripening and growers receive limited feedback from the supply chain. If growers were aware of their expected fruit quality they would be equipped to make better marketing decisions and if necessary to take remedial actions to improve their fruit quality. Avotest is being developed as a quick and easy method of determining expected end-use fruit quality before the start of the commercial fruit harvest. The test aims at distinguishing between blocks with robust fruit and those with less robust fruit. The test could also be used to predict the resulting fruit quality after the implementation of new farming practices.

Statistical analysis of the associations of hereditary factors with the risk of Type 1 diabetes and Diabetic Nephropathy based on the familial data collected through ascertaiment from population-based registers

In genetic epidemiology, population-based disease registries are commonly used to collect genotype or other risk factor information concerning affected subjects and their relatives. This work presents two new approaches for the statistical inference of ascertained data: a conditional and full likelihood approaches for the disease with variable age at onset phenotype using familial data obtained from population-based registry of incident cases. The aim is to obtain statistically reliable estimates of the general population parameters. The statistical analysis of familial data with variable age at onset becomes more complicated when some of the study subjects are non-susceptible, that is to say these subjects never get the disease. A statistical model for a variable age at onset with long-term survivors is proposed for studies of familial aggregation, using latent variable approach, as well as for prospective studies of genetic association studies with candidate genes. In addition, we explore the possibility of a genetic explanation of the observed increase in the incidence of Type 1 diabetes (T1D) in Finland in recent decades and the hypothesis of non-Mendelian transmission of T1D associated genes. Both classical and Bayesian statistical inference were used in the modelling and estimation. Despite the fact that this work contains five studies with different statistical models, they all concern data obtained from nationwide registries of T1D and genetics of T1D. In the analyses of T1D data, non-Mendelian transmission of T1D susceptibility alleles was not observed. In addition, non-Mendelian transmission of T1D susceptibility genes did not make a plausible explanation for the increase in T1D incidence in Finland. Instead, the Human Leucocyte Antigen associations with T1D were confirmed in the population-based analysis, which combines T1D registry information, reference sample of healthy subjects and birth cohort information of the Finnish population. Finally, a substantial familial variation in the susceptibility of T1D nephropathy was observed. The presented studies show the benefits of sophisticated statistical modelling to explore risk factors for complex diseases.

Robustness of the partitions in grouping multi-item inventories

A recent work obtained closed-form solutions to the.problem of optimally grouping a multi-item inventory into subgroups with a common order cycle per group, when the distribution by value of the inventory could be described by a Pareto function. This paper studies the sensitivity of the optimal subgroup boundaries so obtained. Closed-form expressions have been developed to find intervals for the subgroup boundaries for any given level of suboptimality. Graphs have been provided to aid the user in selecting a cost-effective level of aggregation and choosing appropriate subgroup boundaries for a whole range of inventory distributions. The results of sensitivity analyses demonstrate the availability of flexibility in the partition boundaries and the cost-effectiveness of any stock control system through three groups, and thus also provide a theoretical support to the intuitive ABC system of classifying the items.

Statistical properties of turbulence: An overview

We present an introductory overview of several challenging problems in the statistical characterization of turbulence. We provide examples from fluid turbulence in three and two dimensions, from the turbulent advection of passive scalars, turbulence in the one-dimensional Burgers equation, and fluid turbulence in the presence of polymer additives.