A forensic investigation of single human hair fibres using FTIR-ATR spectroscopy and chemometrics

Human hair fibres are ubiquitous in nature and are found frequently at crime scenes often as a result of exchange between the perpetrator, victim and/or the surroundings according to Locard's Principle. Therefore, hair fibre evidence can provide important information for crime investigation. For human hair evidence, the current forensic methods of analysis rely on comparisons of either hair morphology by microscopic examination or nuclear and mitochondrial DNA analyses. Unfortunately in some instances the utilisation of microscopy and DNA analyses are difficult and often not feasible. This dissertation is arguably the first comprehensive investigation aimed to compare, classify and identify the single human scalp hair fibres with the aid of FTIR-ATR spectroscopy in a forensic context. Spectra were collected from the hair of 66 subjects of Asian, Caucasian and African (i.e. African-type). The fibres ranged from untreated to variously mildly and heavily cosmetically treated hairs. The collected spectra reflected the physical and chemical nature of a hair from the near-surface particularly, the cuticle layer. In total, 550 spectra were acquired and processed to construct a relatively large database. To assist with the interpretation of the complex spectra from various types of human hair, Derivative Spectroscopy and Chemometric methods such as Principal Component Analysis (PCA), Fuzzy Clustering (FC) and Multi-Criteria Decision Making (MCDM) program; Preference Ranking Organisation Method for Enrichment Evaluation (PROMETHEE) and Geometrical Analysis for Interactive Aid (GAIA); were utilised. FTIR-ATR spectroscopy had two important advantages over to previous methods: (i) sample throughput and spectral collection were significantly improved (no physical flattening or microscope manipulations), and (ii) given the recent advances in FTIR-ATR instrument portability, there is real potential to transfer this work.s findings seamlessly to on-field applications. The "raw" spectra, spectral subtractions and second derivative spectra were compared to demonstrate the subtle differences in human hair. SEM images were used as corroborative evidence to demonstrate the surface topography of hair. It indicated that the condition of the cuticle surface could be of three types: untreated, mildly treated and treated hair. Extensive studies of potential spectral band regions responsible for matching and discrimination of various types of hair samples suggested the 1690-1500 cm^-1 IR spectral region was to be preferred in comparison with the commonly used 1750-800 cm^-1. The principal reason was the presence of the highly variable spectral profiles of cystine oxidation products (1200-1000 cm^-1), which contributed significantly to spectral scatter and hence, poor hair sample matching. In the preferred 1690-1500 cm^-1 region, conformational changes in the keratin protein attributed to the α-helical to β-sheet transitions in the Amide I and Amide II vibrations and played a significant role in matching and discrimination of the spectra and hence, the hair fibre samples. For gender comparison, the Amide II band is significant for differentiation. The results illustrated that the male hair spectra exhibit a more intense β-sheet vibration in the Amide II band at approximately 1511 cm^-1 whilst the female hair spectra displayed more intense α-helical vibration at 1520-1515cm^-1. In terms of chemical composition, female hair spectra exhibit greater intensity of the amino acid tryptophan (1554 cm^-1), aspartic and glutamic acid (1577 cm^-1). It was also observed that for the separation of samples based on racial differences, untreated Caucasian hair was discriminated from Asian hair as a result of having higher levels of the amino acid cystine and cysteic acid. However, when mildly or chemically treated, Asian and Caucasian hair fibres are similar, whereas African-type hair fibres are different. In terms of the investigation's novel contribution to the field of forensic science, it has allowed for the development of a novel, multifaceted, methodical protocol where previously none had existed. The protocol is a systematic method to rapidly investigate unknown or questioned single human hair FTIR-ATR spectra from different genders and racial origin, including fibres of different cosmetic treatments. Unknown or questioned spectra are first separated on the basis of chemical treatment i.e. untreated, mildly treated or chemically treated, genders, and racial origin i.e. Asian, Caucasian and African-type. The methodology has the potential to complement the current forensic analysis methods of fibre evidence (i.e. Microscopy and DNA), providing information on the morphological, genetic and structural levels.

Multi-step ahead direct prediction for the machine condition prognosis using regression trees and neuro-fuzzy systems

This paper presents an approach to predict the operating conditions of machine based on classification and regression trees (CART) and adaptive neuro-fuzzy inference system (ANFIS) in association with direct prediction strategy for multi-step ahead prediction of time series techniques. In this study, the number of available observations and the number of predicted steps are initially determined by using false nearest neighbor method and auto mutual information technique, respectively. These values are subsequently utilized as inputs for prediction models to forecast the future values of the machines’ operating conditions. The performance of the proposed approach is then evaluated by using real trending data of low methane compressor. A comparative study of the predicted results obtained from CART and ANFIS models is also carried out to appraise the prediction capability of these models. The results show that the ANFIS prediction model can track the change in machine conditions and has the potential for using as a tool to machine fault prognosis.

Fault diagnosis of induction motor based on decision trees and adaptive neuro-fuzzy inference

This paper presents a fault diagnosis method based on adaptive neuro-fuzzy inference system (ANFIS) in combination with decision trees. Classification and regression tree (CART) which is one of the decision tree methods is used as a feature selection procedure to select pertinent features from data set. The crisp rules obtained from the decision tree are then converted to fuzzy if-then rules that are employed to identify the structure of ANFIS classifier. The hybrid of back-propagation and least squares algorithm are utilized to tune the parameters of the membership functions. In order to evaluate the proposed algorithm, the data sets obtained from vibration signals and current signals of the induction motors are used. The results indicate that the CART–ANFIS model has potential for fault diagnosis of induction motors.

Practical stability of approximating discrete-time filters with respect to model mismatch using relative entropy concepts

This paper establishes practical stability results for an important range of approximate discrete-time filtering problems involving mismatch between the true system and the approximating filter model. Using local consistency assumption, the practical stability established is in the sense of an asymptotic bound on the amount of bias introduced by the model approximation. Significantly, these practical stability results do not require the approximating model to be of the same model type as the true system. Our analysis applies to a wide range of estimation problems and justifies the common practice of approximating intractable infinite dimensional nonlinear filters by simpler computationally tractable filters.

The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

Sample complexity results from computational learning theory, when applied to neural network learning for pattern classification problems, suggest that for good generalization performance the number of training examples should grow at least linearly with the number of adjustable parameters in the network. Results in this paper show that if a large neural network is used for a pattern classification problem and the learning algorithm finds a network with small weights that has small squared error on the training patterns, then the generalization performance depends on the size of the weights rather than the number of weights. For example, consider a two-layer feedforward network of sigmoid units, in which the sum of the magnitudes of the weights associated with each unit is bounded by A and the input dimension is n. We show that the misclassification probability is no more than a certain error estimate (that is related to squared error on the training set) plus A3 √((log n)/m) (ignoring log A and log m factors), where m is the number of training patterns. This may explain the generalization performance of neural networks, particularly when the number of training examples is considerably smaller than the number of weights. It also supports heuristics (such as weight decay and early stopping) that attempt to keep the weights small during training. The proof techniques appear to be useful for the analysis of other pattern classifiers: when the input domain is a totally bounded metric space, we use the same approach to give upper bounds on misclassification probability for classifiers with decision boundaries that are far from the training examples.

Shifting : one-inclusion mistake bounds and sample compression

We present new expected risk bounds for binary and multiclass prediction, and resolve several recent conjectures on sample compressibility due to Kuzmin and Warmuth. By exploiting the combinatorial structure of concept class F, Haussler et al. achieved a VC(F)/n bound for the natural one-inclusion prediction strategy. The key step in their proof is a d = VC(F) bound on the graph density of a subgraph of the hypercube—oneinclusion graph. The first main result of this paper is a density bound of n [n−1 <=d-1]/[n <=d] < d, which positively resolves a conjecture of Kuzmin and Warmuth relating to their unlabeled Peeling compression scheme and also leads to an improved one-inclusion mistake bound. The proof uses a new form of VC-invariant shifting and a group-theoretic symmetrization. Our second main result is an algebraic topological property of maximum classes of VC-dimension d as being d contractible simplicial complexes, extending the well-known characterization that d = 1 maximum classes are trees. We negatively resolve a minimum degree conjecture of Kuzmin and Warmuth—the second part to a conjectured proof of correctness for Peeling—that every class has one-inclusion minimum degree at most its VCdimension. Our final main result is a k-class analogue of the d/n mistake bound, replacing the VC-dimension by the Pollard pseudo-dimension and the one-inclusion strategy by its natural hypergraph generalization. This result improves on known PAC-based expected risk bounds by a factor of O(logn) and is shown to be optimal up to an O(logk) factor. The combinatorial technique of shifting takes a central role in understanding the one-inclusion (hyper)graph and is a running theme throughout.

Corrigendum to “Shifting : one-inclusion mistake bounds and sample compression” [J. Comput. System Sci. 75 (1) (2009) 37–59]

H. Simon and B. Szörényi have found an error in the proof of Theorem 52 of “Shifting: One-inclusion mistake bounds and sample compression”, Rubinstein et al. (2009). In this note we provide a corrected proof of a slightly weakened version of this theorem. Our new bound on the density of one-inclusion hypergraphs is again in terms of the capacity of the multilabel concept class. Simon and Szörényi have recently proved an alternate result in Simon and Szörényi (2009).

On the optimality of sample-based estimates of the expectation of the empirical minimizer

We study sample-based estimates of the expectation of the function produced by the empirical minimization algorithm. We investigate the extent to which one can estimate the rate of convergence of the empirical minimizer in a data dependent manner. We establish three main results. First, we provide an algorithm that upper bounds the expectation of the empirical minimizer in a completely data-dependent manner. This bound is based on a structural result due to Bartlett and Mendelson, which relates expectations to sample averages. Second, we show that these structural upper bounds can be loose, compared to previous bounds. In particular, we demonstrate a class for which the expectation of the empirical minimizer decreases as O(1/n) for sample size n, although the upper bound based on structural properties is Ω(1). Third, we show that this looseness of the bound is inevitable: we present an example that shows that a sharp bound cannot be universally recovered from empirical data.

Shifting : one-inclusion mistake bounds and sample compression

We present new expected risk bounds for binary and multiclass prediction, and resolve several recent conjectures on sample compressibility due to Kuzmin and Warmuth. By exploiting the combinatorial structure of concept class F, Haussler et al. achieved a VC(F)/n bound for the natural one-inclusion prediction strategy. The key step in their proof is a d=VC(F) bound on the graph density of a subgraph of the hypercube—one-inclusion graph. The first main result of this report is a density bound of n∙choose(n-1,≤d-1)/choose(n,≤d) < d, which positively resolves a conjecture of Kuzmin and Warmuth relating to their unlabeled Peeling compression scheme and also leads to an improved one-inclusion mistake bound. The proof uses a new form of VC-invariant shifting and a group-theoretic symmetrization. Our second main result is an algebraic topological property of maximum classes of VC-dimension d as being d-contractible simplicial complexes, extending the well-known characterization that d=1 maximum classes are trees. We negatively resolve a minimum degree conjecture of Kuzmin and Warmuth—the second part to a conjectured proof of correctness for Peeling—that every class has one-inclusion minimum degree at most its VC-dimension. Our final main result is a k-class analogue of the d/n mistake bound, replacing the VC-dimension by the Pollard pseudo-dimension and the one-inclusion strategy by its natural hypergraph generalization. This result improves on known PAC-based expected risk bounds by a factor of O(log n) and is shown to be optimal up to a O(log k) factor. The combinatorial technique of shifting takes a central role in understanding the one-inclusion (hyper)graph and is a running theme throughout

Relative entropy rate based design for linear hybrid system models

Hybrid system representations have been applied to many challenging modeling situations. In these hybrid system representations, a mixture of continuous and discrete states is used to capture the dominating behavioural features of a nonlinear, possible uncertain, model under approximation. Unfortunately, the problem of how to best design a suitable hybrid system model has not yet been fully addressed. This paper proposes a new joint state measurement relative entropy rate based approach for this design purpose. Design examples and simulation studies are presented which highlight the benefits of our proposed design approaches.