Speaker verification using I-vector features

This PhD research has provided novel solutions to three major challenges which have prevented the wide spread deployment of speaker recognition technology: (1) combating enrolment/ verification mismatch, (2) reducing the large amount of development and training data that is required and (3) reducing the duration of speech required to verify a speaker. A range of applications of speaker recognition technology from forensics in criminal investigations to secure access in banking will benefit from the research outcomes.

Highly sensitive electrochemical sensor for nitric oxide using the self-assembled monolayer of 1,8,15,22-tetraaminophthalo-cyanatocobalt(II) on glassy carbon electrode

Glassy carbon (GC) electrode modified with a self-assembled monolayer (SAM) of 1,8,15,22-tetraaminophthalocyanatocobalt(II) (4α-CoIITAPc) was used for the selective and highly sensitive determination of nitric oxide (NO). The SAM of 4α-CoIITAPc was formed on GC electrode by spontaneous adsorption from DMF containing 1 mM 4α-CoIITAPc. The SAM showed two pairs of well-defined redox peaks corresponding to CoIII/CoII and CoIIIPc−1/CoIIIPc−2 in 0.2 M phosphate buffer (PB) solution (pH 2.5). The SAM modified electrode showed excellent electrocatalytic activity towards the oxidation of nitric oxide (NO) by enhancing its oxidation current with 310 mV less positive potential shift when compared to bare GC electrode. In amperometric measurements, the current response for NO oxidation was linearly increased in the concentration range of 3×10−9 to 30×10−9 M with a detection limit of 1.4×10−10 M (S/N=3). The proposed method showed a better recovery for NO in human blood serum samples.

Selective electrochemical epinephrine sensor using self-assembled monomolecular film of 1,8,15,22-tetraaminophthalocyanatonickel(II) on gold electrode

This article describes the highly sensitive and selective determination of epinephrine (EP) using self-assembled monomolecular film (SAMF) of 1,8,15,22-tetraamino-phthalocyanatonickel(II) (4α-NiIITAPc) on Au electrode. The 4α-NiIITAPc SAMF modified electrode was prepared by spontaneous adsorption of 4α-NiIITAPc from dimethylformamide solution. The modified electrode oxidizes EP at less over potential with enhanced current response in contrast to the bare Au electrode. The standard heterogeneous rate constant (k°) for the oxidation of EP at 4α-NiIITAPc SAMF modified electrode was found to be 1.94×10−2 cm s−1 which was much higher than that at the bare Au electrode. Further, it was found that 4α-NiIITAPc SAMF modified electrode separates the voltammetric signals of ascorbic acid (AA) and EP with a peak separation of 250 mV. Using amperometric method the lowest detection limit of 50 nM of EP was achieved at SAMF modified electrode. Simultaneous amperometric determination of AA and EP was also achieved at the SAMF modified electrode. Common physiological interferents such as uric acid, glucose, urea and NaCl do not interfere within the potential window of EP oxidation. The present 4α-NiIITAPc SAMF modified electrode was also successfully applied to determine the concentration of EP in commercially available injection.

Higher order spectra based support vector machine for arrhythmia classification

Heart rate variability (HRV) refers to the regulation of the sinoatrial node, the natural pacemaker of the heart by the sympathetic and parasympathetic branches of the autonomic nervous system. HRV analysis is an important tool to observe the heart’s ability to respond to normal regulatory impulses that affect its rhythm. Like many bio-signals, HRV signals are non-linear in nature. Higher order spectral analysis (HOS) is known to be a good tool for the analysis of non-linear systems and provides good noise immunity. A computer-based arrhythmia detection system of cardiac states is very useful in diagnostics and disease management. In this work, we studied the identification of the HRV signals using features derived from HOS. These features were fed to the support vector machine (SVM) for classification. Our proposed system can classify the normal and other four classes of arrhythmia with an average accuracy of more than 85%.

Practical analysis of big acoustic sensor data for environmental monitoring

Monitoring the environment with acoustic sensors is an effective method for understanding changes in ecosystems. Through extensive monitoring, large-scale, ecologically relevant, datasets can be produced that can inform environmental policy. The collection of acoustic sensor data is a solved problem; the current challenge is the management and analysis of raw audio data to produce useful datasets for ecologists. This paper presents the applied research we use to analyze big acoustic datasets. Its core contribution is the presentation of practical large-scale acoustic data analysis methodologies. We describe details of the data workflows we use to provide both citizen scientists and researchers practical access to large volumes of ecoacoustic data. Finally, we propose a work in progress large-scale architecture for analysis driven by a hybrid cloud-and-local production-grade website.

Classification of echolocation calls from 14 species of bat by Support Vector Machines and Ensembles of Neural Networks

Calls from 14 species of bat were classified to genus and species using discriminant function analysis (DFA), support vector machines (SVM) and ensembles of neural networks (ENN). Both SVMs and ENNs outperformed DFA for every species while ENNs (mean identification rate – 97%) consistently outperformed SVMs (mean identification rate – 87%). Correct classification rates produced by the ENNs varied from 91% to 100%; calls from six species were correctly identified with 100% accuracy. Calls from the five species of Myotis, a genus whose species are considered difficult to distinguish acoustically, had correct identification rates that varied from 91 – 100%. Five parameters were most important for classifying calls correctly while seven others contributed little to classification performance.

Modeling kinect sensor noise for improved 3D reconstruction and tracking

We contribute an empirically derived noise model for the Kinect sensor. We systematically measure both lateral and axial noise distributions, as a function of both distance and angle of the Kinect to an observed surface. The derived noise model can be used to filter Kinect depth maps for a variety of applications. Our second contribution applies our derived noise model to the KinectFusion system to extend filtering, volumetric fusion, and pose estimation within the pipeline. Qualitative results show our method allows reconstruction of finer details and the ability to reconstruct smaller objects and thinner surfaces. Quantitative results also show our method improves pose estimation accuracy. © 2012 IEEE.

Reliable Fault Diagnosis for Low-Speed Bearings Using Individually Trained Support Vector Machines With Kernel Discriminative Feature Analysis

This paper proposes a highly reliable fault diagnosis approach for low-speed bearings. The proposed approach first extracts wavelet-based fault features that represent diverse symptoms of multiple low-speed bearing defects. The most useful fault features for diagnosis are then selected by utilizing a genetic algorithm (GA)-based kernel discriminative feature analysis cooperating with one-against-all multicategory support vector machines (OAA MCSVMs). Finally, each support vector machine is individually trained with its own feature vector that includes the most discriminative fault features, offering the highest classification performance. In this study, the effectiveness of the proposed GA-based kernel discriminative feature analysis and the classification ability of individually trained OAA MCSVMs are addressed in terms of average classification accuracy. In addition, the proposedGA- based kernel discriminative feature analysis is compared with four other state-of-the-art feature analysis approaches. Experimental results indicate that the proposed approach is superior to other feature analysis methodologies, yielding an average classification accuracy of 98.06% and 94.49% under rotational speeds of 50 revolutions-per-minute (RPM) and 80 RPM, respectively. Furthermore, the individually trained MCSVMs with their own optimal fault features based on the proposed GA-based kernel discriminative feature analysis outperform the standard OAA MCSVMs, showing an average accuracy of 98.66% and 95.01% for bearings under rotational speeds of 50 RPM and 80 RPM, respectively.