Human identification from video using advanced gait recognition techniques

The solutions proposed in this thesis contribute to improve gait recognition performance in practical scenarios that further enable the adoption of gait recognition into real world security and forensic applications that require identifying humans at a distance. Pioneering work has been conducted on frontal gait recognition using depth images to allow gait to be integrated with biometric walkthrough portals. The effects of gait challenging conditions including clothing, carrying goods, and viewpoint have been explored. Enhanced approaches are proposed on segmentation, feature extraction, feature optimisation and classification elements, and state-of-the-art recognition performance has been achieved. A frontal depth gait database has been developed and made available to the research community for further investigation. Solutions are explored in 2D and 3D domains using multiple images sources, and both domain-specific and independent modality gait features are proposed.

Complementary surface-enhanced resonance raman spectroscopic biodetection of mixed protein solutions by chitosan- and silica-coated plasmon-tuned silver nanoparticles

Silver nanoparticles with identical plasmonic properties but different surface functionalities are synthesized and tested as chemically selective surface-enhanced resonance Raman (SERR) amplifiers in a two-component protein solution. The surface plasmon resonances of the particles are tuned to 413 nm to match the molecular resonance of protein heme cofactors. Biocompatible functionalization of the nanoparticles with a thin film of chitosan yields selective SERR enhancement of the anionic protein cytochrome b5, whereas functionalization with SiO2 amplifies only the spectra of the cationic protein cytochrome c. As a result, subsequent addition of the two differently functionalized particles yields complementary information on the same mixed protein sample solution. Finally, the applicability of chitosan-coated Ag nanoparticles for protein separation was tested by in situ resonance Raman spectroscopy.

Electrochemical and spectral studies of self-assembled monolayer of 1,8,15,22-tetraaminophthalocyanatocobalt(II) on indium tin oxide surface

Self-assembled monolayer (SAM) of 1,8,15,22-tetraaminophthalocyanatocobalt(II) (4α-CoIITAPc) was prepared on indium tin oxide (ITO) electrode by spontaneous adsorption from dimethylformamide (DMF) solution containing 4α-CoIITAPc. The SAM of 4α-CoIITAPc formed on ITO electrode was characterized by cyclic voltammetry, Raman and UV–visible spectroscopic techniques. The cyclic voltammogram (CV) of 4α-CoIITAPc SAM shows two pairs of well-defined redox peaks corresponding to CoIII/CoII and CoIIIPc−1/CoIIIPc−2. The surface coverage (Γ) was calculated by integrating the charge under the anodic wave corresponding to CoII oxidation and it was found to be 2.25 × 10−10 mol cm−2. Raman spectrum obtained for the SAM of 4α-CoIITAPc on ITO surface shows strong stretching and breathing bands of Pc macrocycle, pyrrole ring and isoindole ring. Further, the –NH2 bending mode of vibration was absent for the SAM of 4α-CoIITAPc on ITO surface which indirectly confirmed that all the amino groups of 4α-CoIITAPc are involved in bonding with ITO surface. UV–visible spectrum for the SAM of 4α-CoIITAPc on ITO surface shows an intense B-band, Q-band and n–π∗ transition with slight broadening when compared to that of 4α-CoIITAPc in DMF.

Novel approaches for SER spectroscopic analysis of protein cofactors

Biomimetic systems employed for biotechnological applications i.e. as biosensors or bio fuel cells, require initial formation of conducting support/protein complexes with controlled properties. The specific interaction of the protein with the support determines important qualities of the device such as electrical communication, long-term stability and catalytic efficiency. In this respect the system parameters have to be chosen in a way that high protein loading on the support is achieved while protein denaturation upon adsorption is prevented. The conditions on the surface have to be adjusted in such a way that the desired surface reaction of the protein i.e. electron transfer to either the electrode or a second redox partner, is still guaranteed. Hence the choice of support, its functionlisation as well as the right adjustment of solution parameters play a crucial role in the rational design of these support/protein constructs.

Anomaly detection in online social networks : using data-mining techniques and fuzzy logic

This research is a step forward in improving the accuracy of detecting anomaly in a data graph representing connectivity between people in an online social network. The proposed hybrid methods are based on fuzzy machine learning techniques utilising different types of structural input features. The methods are presented within a multi-layered framework which provides the full requirements needed for finding anomalies in data graphs generated from online social networks, including data modelling and analysis, labelling, and evaluation.

Prediction of activity type in preschool children using machine learning techniques

Objectives Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. Design Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. Methods Eleven children aged 3–6 years (mean age = 4.8 ± 0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). Results Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. Conclusions Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.

Deterrence of drug driving : the impact of the ACT drug driving legislation and detection techniques

Overarching Research Questions Are ACT motorists aware of roadside saliva based drug testing operations? What is the perceived deterrent impact of the operations? What factors are predictive of future intentions to drug drive? What are the differences between key subgroups

Identifying product families using data mining techniques in manufacturing paradigm

Identifying product families has been considered as an effective way to accommodate the increasing product varieties across the diverse market niches. In this paper, we propose a novel framework to identifying product families by using a similarity measure for a common product design data BOM (Bill of Materials) based on data mining techniques such as frequent mining and clus-tering. For calculating the similarity between BOMs, a novel Extended Augmented Adjacency Matrix (EAAM) representation is introduced that consists of information not only of the content and topology but also of the fre-quent structural dependency among the various parts of a product design. These EAAM representations of BOMs are compared to calculate the similarity between products and used as a clustering input to group the product fami-lies. When applied on a real-life manufacturing data, the proposed framework outperforms a current baseline that uses orthogonal Procrustes for grouping product families.

An SEM, EDS and vibrational spectroscopic study of the silicate mineral meliphanite (Ca,Na)2Be[(Si,Al)2O6(F,OH)]

The mineral meliphanite (Ca,Na)2Be[(Si,Al)2O6(F,OH)] is a crystalline sodium calcium beryllium silicate which has the potential to be used as piezoelectric material and for other ferroelectric applications. The mineral has been characterized by a combination of scanning electron microscopy (SEM) with energy dispersive spectroscopy (EDS) and vibrational spectroscopy. EDS analysis shows a material with high concentrations of Si and Ca and low amounts of Na, Al and F. Beryllium was not detected. Raman bands at 1016 and 1050 cm−1 are assigned to the SiO and AlOH stretching vibrations of three dimensional siloxane units. The infrared spectrum of meliphanite is very broad in comparison with the Raman spectrum. Raman bands at 472 and 510 cm−1 are assigned to OSiO bending modes. Raman spectroscopy identifies bands in the OH stretching region. Raman spectroscopy with complimentary infrared spectroscopy enables the characterization of the silicate mineral meliphanite.

SEM, EDX and vibrational spectroscopic study of the mineral tunisite NaCa2Al4(CO3)4Cl(OH)8

The mineral tunisite has been studied by using a combination of scanning electron microscopy with energy dispersive X-ray fluorescence and vibrational spectroscopy. Chemical analysis shows the presence of Na, Ca, Al and Cl. SEM shows a pure single phase. An intense Raman band at 1127 cm−1 is assigned to the carbonate ν1 symmetric stretching vibration and the Raman band at 1522 cm−1 is assigned to the ν3 carbonate antisymmetric stretching vibration. Infrared bands are observed in similar positions. Multiple carbonate bending modes are found. Raman bands attributable to AlO stretching and bending vibrations are observed. Two Raman bands at 3419 and 3482 cm−1 are assigned to the OH stretching vibrations of the OH units. Vibrational spectroscopy enables aspects of the molecular structure of the carbonate mineral tunisite to be assessed.

SEM, EDS and vibrational spectroscopic study of dawsonite NaAl(CO3)(OH)2

In this work we have studied the mineral dawsonite by using a combination of scanning electron microscopy with EDS and vibrational spectroscopy. Single crystals show an acicular habitus forming aggregates with a rosette shape. The chemical analysis shows a phase composed of C, Al, and Na. Two distinct Raman bands at 1091 and 1068 cm−1 are assigned to the CO32− ν1 symmetric stretching mode. Multiple bands are observed in both the Raman and infrared spectra in the antisymmetric stretching and bending regions showing that the symmetry of the carbonate anion is reduced and in all probability the carbonate anions are not equivalent in the dawsonite structure. Multiple OH deformation vibrations centred upon 950 cm−1 in both the Raman and infrared spectra show that the OH units in the dawsonite structure are non-equivalent. Raman bands observed at 3250, 3283 and 3295 cm−1 are assigned to OH stretching vibrations. The position of these bands indicates strong hydrogen bonding of the OH units in the dawsonite structure. The formation of the mineral dawsonite has the potential to offer a mechanism for the geosequestration of greenhouse gases.