An approach to statistical lip modelling for speaker identification via chromatic feature extraction

This paper presents a novel technique for the tracking of moving lips for the purpose of speaker identification. In our system, a model of the lip contour is formed directly from chromatic information in the lip region. Iterative refinement of contour point estimates is not required. Colour features are extracted from the lips via concatenated profiles taken around the lip contour. Reduction of order in lip features is obtained via principal component analysis (PCA) followed by linear discriminant analysis (LDA). Statistical speaker models are built from the lip features based on the Gaussian mixture model (GMM). Identification experiments performed on the M2VTS¹ database, show encouraging results

An examination of monotony and hypovigilance, independent of fatigue : relevance to road safety

Driving is a vigilance task, requiring sustained attention to maintain performance and avoid crashes. Hypovigilance (i.e., marked reduction in vigilance) while driving manifests as poor driving performance and is commonly attributed to fatigue (Dinges, 1995). However, poor driving performance has been found to be more frequent when driving in monotonous road environments, suggesting that monotony plays a role in generating hypovigilance (Thiffault & Bergeron, 2003b). Research to date has tended to conceptualise monotony as a uni-dimensional task characteristic, typically used over a prolonged period of time to facilitate other factors under investigation, most notably fatigue. However, more often than not, more than one exogenous factor relating to the task or operating environment is manipulated to vary or generate monotony (Mascord & Heath, 1992). Here we aimed to explore whether monotony is a multi-dimensional construct that is determined by characteristics of both the task proper and the task environment. The general assumption that monotony is a task characteristic used solely to elicit hypovigilance or poor performance related to fatigue appears to have led to there being little rigorous investigation into the exact nature of the relationship. While the two concepts are undoubtedly linked, the independent effect of monotony on hypovigilance remains largely ignored. Notwithstanding, there is evidence that monotony effects can emerge very early in vigilance tasks and are not necessarily accompanied by fatigue (see Meuter, Rakotonirainy, Johns, & Wagner, 2005). This phenomenon raises a largely untested, empirical question explored in two studies: Can hypovigilance emerge as a consequence of task and/or environmental monotony, independent of time on task and fatigue? In Study 1, using a short computerised vigilance task requiring responses to be withheld to infrequent targets, we explored the differential impacts of stimuli and task demand manipulations on the development of a monotonous context and the associated effects on vigilance performance (as indexed by respone errors and response times), independent of fatigue and time on task. The role of individual differences (sensation seeking, extroversion and cognitive failures) in moderating monotony effects was also considered. The results indicate that monotony affects sustained attention, with hypovigilance and associated performance worse in monotonous than in non-monotonous contexts. Critically, performance decrements emerged early in the task (within 4.3 minutes) and remained consistent over the course of the experiment (21.5 minutes), suggesting that monotony effects can operate independent of time on task and fatigue. A combination of low task demands and low stimulus variability form a monotonous context characterised by hypovigilance and poor task performance. Variations to task demand and stimulus variability were also found to independently affect performance, suggesting that monotony is a multi-dimensional construct relating to both task monotony (associated with the task itself) and environmental monotony (related to characteristics of the stimulus). Consequently, it can be concluded that monotony is multi-dimensional and is characterised by low variability in stimuli and/or task demands. The proposition that individual differences emerge under conditions of varying monotony with high sensation seekers and/or extroverts performing worse in monotonous contexts was only partially supported. Using a driving simulator, the findings of Study 1 were extended to a driving context to identify the behavioural and psychophysiological indices of monotony-related hypovigilance associated with variations to road design and road side scenery (Study 2). Supporting the proposition that monotony is a multi-dimensional construct, road design variability emerged as a key moderating characteristic of environmental monotony, resulting in poor driving performance indexed by decrements in steering wheel measures (mean lateral position). Sensation seeking also emerged as a moderating factor, where participants high in sensation seeking tendencies displayed worse driving behaviour in monotonous conditions. Importantly, impaired driving performance was observed within 8 minutes of commencing the driving task characterised by environmental monotony (low variability in road design) and was not accompanied by a decline in psychophysiological arousal. In addition, no subjective declines in alertness were reported. With fatigue effects associated with prolonged driving (van der Hulst, Meijman, & Rothengatter, 2001) and indexed by drowsiness, this pattern of results indicates that monotony can affect driver vigilance, independent of time on task and fatigue. Perceptual load theory (Lavie, 1995, 2005) and mindlessness theory (Robertson, Manly, Andrade, Baddley, & Yiend, 1997) provide useful theoretical frameworks for explaining and predicting monotony effects by positing that the low load (of task and/or stimuli) associated with a monotonous task results in spare attentional capacity which spills over involuntarily, resulting in the processing of task-irrelevant stimuli or task unrelated thoughts. That is, individuals – even when not fatigued - become easily distracted when performing a highly monotonous task, resulting in hypovigilance and impaired performance. The implications for road safety, including the likely effectiveness of fatigue countermeasures to mitigate monotony-related driver hypovigilance are discussed.

Observing the relevance of an information systems success model

This paper contributes to the rigor vs. relevance debate in the Information Systems (IS) discipline. Using the Action Research methodology, this study evaluates the relevance of a rigorously validated IS evaluation model in practice. The study captures observations of operational end-users employing a market leading Enterprise System application for procurement and order fulfillment in an organization. The analysis of the observations demonstrates the broad relevance of the measurement instrument. More importantly, the study identifies several improvements and possible confusions in applying the instrument in the practice.

User-representative feature selection for keystroke dynamics

Continuous user authentication with keystroke dynamics uses characters sequences as features. Since users can type characters in any order, it is imperative to find character sequences (n-graphs) that are representative of user typing behavior. The contemporary feature selection approaches do not guarantee selecting frequently-typed features which may cause less accurate statistical user-representation. Furthermore, the selected features do not inherently reflect user typing behavior. We propose four statistical based feature selection techniques that mitigate limitations of existing approaches. The first technique selects the most frequently occurring features. The other three consider different user typing behaviors by selecting: n-graphs that are typed quickly; n-graphs that are typed with consistent time; and n-graphs that have large time variance among users. We use Gunetti’s keystroke dataset and k-means clustering algorithm for our experiments. The results show that among the proposed techniques, the most-frequent feature selection technique can effectively find user representative features. We further substantiate our results by comparing the most-frequent feature selection technique with three existing approaches (popular Italian words, common n-graphs, and least frequent ngraphs). We find that it performs better than the existing approaches after selecting a certain number of most-frequent n-graphs.

Me and my body : the relevance of the difference for the distinction between withdrawing life support and euthanasia

In this paper I discuss David Shaw’s claim that the body of a terminally ill person can be conceived as a kind of life-support, akin to an artificial ventilator. I claim that this position rests upon an untenable dualism between the mind and the body. Given that dualism continues to be attractive to some thinkers, I attempt to diagnose the reasons why it continues to be attractive, as well as to demonstrate its incoherence, drawing on some recent work in the philosophy of psychology. I conclude that, if my criticisms are sound, Shaw’s attempt to deny the distinction between withdrawal and euthanasia fails.

Toward automated power line corridor monitoring using advanced aircraft control and multisource feature fusion

The conventional manual power line corridor inspection processes that are used by most energy utilities are labor-intensive, time consuming and expensive. Remote sensing technologies represent an attractive and cost-effective alternative approach to these monitoring activities. This paper presents a comprehensive investigation into automated remote sensing based power line corridor monitoring, focusing on recent innovations in the area of increased automation of fixed-wing platforms for aerial data collection, and automated data processing for object recognition using a feature fusion process. Airborne automation is achieved by using a novel approach that provides improved lateral control for tracking corridors and automatic real-time dynamic turning for flying between corridor segments, we call this approach PTAGS. Improved object recognition is achieved by fusing information from multi-sensor (LiDAR and imagery) data and multiple visual feature descriptors (color and texture). The results from our experiments and field survey illustrate the effectiveness of the proposed aircraft control and feature fusion approaches.

Tensor query expansion : a cognitively motivated relevance model

In information retrieval, a user's query is often not a complete representation of their real information need. The user's information need is a cognitive construction, however the use of cognitive models to perform query expansion have had little study. In this paper, we present a cognitively motivated query expansion technique that uses semantic features for use in ad hoc retrieval. This model is evaluated against a state-of-the-art query expansion technique. The results show our approach provides significant improvements in retrieval effectiveness for the TREC data sets tested.

Feature-based visual odometry and featureless place recognition for SLAM in 2.5D environments

In this paper we present a novel algorithm for localization during navigation that performs matching over local image sequences. Instead of calculating the single location most likely to correspond to a current visual scene, the approach finds candidate matching locations within every section (subroute) of all learned routes. Through this approach, we reduce the demands upon the image processing front-end, requiring it to only be able to correctly pick the best matching image from within a short local image sequence, rather than globally. We applied this algorithm to a challenging downhill mountain biking visual dataset where there was significant perceptual or environment change between repeated traverses of the environment, and compared performance to applying the feature-based algorithm FAB-MAP. The results demonstrate the potential for localization using visual sequences, even when there are no visual features that can be reliably detected.

Acoustic hazard detection for pedestrians with obscured hearing

Pedestrians’ use of mp3 players or mobile phones can pose the risk of being hit by motor vehicles. We present an approach for detecting a crash risk level using the computing power and the microphone of mobile devices that can be used to alert the user in advance of an approaching vehicle so as to avoid a crash. A single feature extractor classifier is not usually able to deal with the diversity of risky acoustic scenarios. In this paper, we address the problem of detection of vehicles approaching a pedestrian by a novel, simple, non resource intensive acoustic method. The method uses a set of existing statistical tools to mine signal features. Audio features are adaptively thresholded for relevance and classified with a three component heuristic. The resulting Acoustic Hazard Detection (AHD) system has a very low false positive detection rate. The results of this study could help mobile device manufacturers to embed the presented features into future potable devices and contribute to road safety.

An exploration of feature detector performance in the thermal-infrared modality

Thermal-infrared images have superior statistical properties compared with visible-spectrum images in many low-light or no-light scenarios. However, a detailed understanding of feature detector performance in the thermal modality lags behind that of the visible modality. To address this, the first comprehensive study on feature detector performance on thermal-infrared images is conducted. A dataset is presented which explores a total of ten different environments with a range of statistical properties. An investigation is conducted into the effects of several digital and physical image transformations on detector repeatability in these environments. The effect of non-uniformity noise, unique to the thermal modality, is analyzed. The accumulation of sensor non-uniformities beyond the minimum possible level was found to have only a small negative effect. A limiting of feature counts was found to improve the repeatability performance of several detectors. Most other image transformations had predictable effects on feature stability. The best-performing detector varied considerably depending on the nature of the scene and the test.

Multifractal characterisation and analysis of complex networks

Complex networks have been studied extensively due to their relevance to many real-world systems such as the world-wide web, the internet, biological and social systems. During the past two decades, studies of such networks in different fields have produced many significant results concerning their structures, topological properties, and dynamics. Three well-known properties of complex networks are scale-free degree distribution, small-world effect and self-similarity. The search for additional meaningful properties and the relationships among these properties is an active area of current research. This thesis investigates a newer aspect of complex networks, namely their multifractality, which is an extension of the concept of selfsimilarity. The first part of the thesis aims to confirm that the study of properties of complex networks can be expanded to a wider field including more complex weighted networks. Those real networks that have been shown to possess the self-similarity property in the existing literature are all unweighted networks. We use the proteinprotein interaction (PPI) networks as a key example to show that their weighted networks inherit the self-similarity from the original unweighted networks. Firstly, we confirm that the random sequential box-covering algorithm is an effective tool to compute the fractal dimension of complex networks. This is demonstrated on the Homo sapiens and E. coli PPI networks as well as their skeletons. Our results verify that the fractal dimension of the skeleton is smaller than that of the original network due to the shortest distance between nodes is larger in the skeleton, hence for a fixed box-size more boxes will be needed to cover the skeleton. Then we adopt the iterative scoring method to generate weighted PPI networks of five species, namely Homo sapiens, E. coli, yeast, C. elegans and Arabidopsis Thaliana. By using the random sequential box-covering algorithm, we calculate the fractal dimensions for both the original unweighted PPI networks and the generated weighted networks. The results show that self-similarity is still present in generated weighted PPI networks. This implication will be useful for our treatment of the networks in the third part of the thesis. The second part of the thesis aims to explore the multifractal behavior of different complex networks. Fractals such as the Cantor set, the Koch curve and the Sierspinski gasket are homogeneous since these fractals consist of a geometrical figure which repeats on an ever-reduced scale. Fractal analysis is a useful method for their study. However, real-world fractals are not homogeneous; there is rarely an identical motif repeated on all scales. Their singularity may vary on different subsets; implying that these objects are multifractal. Multifractal analysis is a useful way to systematically characterize the spatial heterogeneity of both theoretical and experimental fractal patterns. However, the tools for multifractal analysis of objects in Euclidean space are not suitable for complex networks. In this thesis, we propose a new box covering algorithm for multifractal analysis of complex networks. This algorithm is demonstrated in the computation of the generalized fractal dimensions of some theoretical networks, namely scale-free networks, small-world networks, random networks, and a kind of real networks, namely PPI networks of different species. Our main finding is the existence of multifractality in scale-free networks and PPI networks, while the multifractal behaviour is not confirmed for small-world networks and random networks. As another application, we generate gene interactions networks for patients and healthy people using the correlation coefficients between microarrays of different genes. Our results confirm the existence of multifractality in gene interactions networks. This multifractal analysis then provides a potentially useful tool for gene clustering and identification. The third part of the thesis aims to investigate the topological properties of networks constructed from time series. Characterizing complicated dynamics from time series is a fundamental problem of continuing interest in a wide variety of fields. Recent works indicate that complex network theory can be a powerful tool to analyse time series. Many existing methods for transforming time series into complex networks share a common feature: they define the connectivity of a complex network by the mutual proximity of different parts (e.g., individual states, state vectors, or cycles) of a single trajectory. In this thesis, we propose a new method to construct networks of time series: we define nodes by vectors of a certain length in the time series, and weight of edges between any two nodes by the Euclidean distance between the corresponding two vectors. We apply this method to build networks for fractional Brownian motions, whose long-range dependence is characterised by their Hurst exponent. We verify the validity of this method by showing that time series with stronger correlation, hence larger Hurst exponent, tend to have smaller fractal dimension, hence smoother sample paths. We then construct networks via the technique of horizontal visibility graph (HVG), which has been widely used recently. We confirm a known linear relationship between the Hurst exponent of fractional Brownian motion and the fractal dimension of the corresponding HVG network. In the first application, we apply our newly developed box-covering algorithm to calculate the generalized fractal dimensions of the HVG networks of fractional Brownian motions as well as those for binomial cascades and five bacterial genomes. The results confirm the monoscaling of fractional Brownian motion and the multifractality of the rest. As an additional application, we discuss the resilience of networks constructed from time series via two different approaches: visibility graph and horizontal visibility graph. Our finding is that the degree distribution of VG networks of fractional Brownian motions is scale-free (i.e., having a power law) meaning that one needs to destroy a large percentage of nodes before the network collapses into isolated parts; while for HVG networks of fractional Brownian motions, the degree distribution has exponential tails, implying that HVG networks would not survive the same kind of attack.