Reduced complexity on-line estimation of hidden Markov model parameters

In this paper we propose and study low complexity algorithms for on-line estimation of hidden Markov model (HMM) parameters. The estimates approach the true model parameters as the measurement noise approaches zero, but otherwise give improved estimates, albeit with bias. On a nite data set in the high noise case, the bias may not be signi cantly more severe than for a higher complexity asymptotically optimal scheme. Our algorithms require O(N3) calculations per time instant, where N is the number of states. Previous algorithms based on earlier hidden Markov model signal processing methods, including the expectation-maximumisation (EM) algorithm require O(N4) calculations per time instant.

Echolocation calls of the long tailed bat: a quantitative analysis of types of calls

The echolocation calls of long-tailed bats (Chalinolobus tuberculatus) were recorded in the Eglinton Valley, Fjordland, New Zealand, and digitized for analysis with the signal-processing software. Univariate and multivariate analyses of measure features facilitated a quantitative classification of the calls. Cluster analysis was used to categorize calls into two groups equating to search and terminal buzz calls described qualitatively for other species. When moving from search to terminal phases, the calls decrease in bandwidth, maximum and minimum frequency of call, and duration. Search calls begin with a steep-downward FM sweep followed by a short, less-modulated component. Buzz calls are FM sweeps. Although not found quantitatively, a broad pre-buzz group of calls also was identified. Ambiguity analysis of calls from the three groups shows that search-phrase calls are well suited to resolving the velocity of targets, and hence, identifying moving targets in a stationary clutter. Pre-buzz and buzz calls are better suited to resolving range, a feature that may aid the bats in capture of evasive prey after it has been identified.

Using upper bounds on attainable discrimination to select discrete valued features

Selection of features that will permit accurate pattern classification is a difficult task. However, if a particular data set is represented by discrete valued features, it becomes possible to determine empirically the contribution that each feature makes to the discrimination between classes. This paper extends the discrimination bound method so that both the maximum and average discrimination expected on unseen test data can be estimated. These estimation techniques are the basis of a backwards elimination algorithm that can be use to rank features in order of their discriminative power. Two problems are used to demonstrate this feature selection process: classification of the Mushroom Database, and a real-world, pregnancy related medical risk prediction task - assessment of risk of perinatal death.

A Likelihood-Maximizing Framework for Enhanced In-Car Speech Recognition Based on Speech Dialog System Interaction

Speech recognition in car environments has been identified as a valuable means for reducing driver distraction when operating noncritical in-car systems. Under such conditions, however, speech recognition accuracy degrades significantly, and techniques such as speech enhancement are required to improve these accuracies. Likelihood-maximizing (LIMA) frameworks optimize speech enhancement algorithms based on recognized state sequences rather than traditional signal-level criteria such as maximizing signal-to-noise ratio. LIMA frameworks typically require calibration utterances to generate optimized enhancement parameters that are used for all subsequent utterances. Under such a scheme, suboptimal recognition performance occurs in noise conditions that are significantly different from that present during the calibration session – a serious problem in rapidly changing noise environments out on the open road. In this chapter, we propose a dialog-based design that allows regular optimization iterations in order to track the ever-changing noise conditions. Experiments using Mel-filterbank noise subtraction (MFNS) are performed to determine the optimization requirements for vehicular environments and show that minimal optimization is required to improve speech recognition, avoid over-optimization, and ultimately assist with semireal-time operation. It is also shown that the proposed design is able to provide improved recognition performance over frameworks incorporating a calibration session only.

A communication model and partitioning algorithm for streaming applications for an embedded MPSoC

Energy efficient embedded computing enables new application scenarios in mobile devices like software-defined radio and video processing. The hierarchical multiprocessor considered in this work may contain dozens or hundreds of resource efficient VLIW CPUs. Programming this number of CPU cores is a complex task requiring compiler support. The stream programming paradigm provides beneficial properties that help to support automatic partitioning. This work describes a compiler for streaming applications targeting the self-build hierarchical CoreVA-MPSoC multiprocessor platform. The compiler is supported by a programming model that is tailored to fit the streaming programming paradigm. We present a novel simulated-annealing (SA) based partitioning algorithm, called Smart SA. The overall speedup of Smart SA is 12.84 for an MPSoC with 16 CPU cores compared to a single CPU implementation. Comparison with a state of the art partitioning algorithm shows an average performance improvement of 34.07%.

Detecting rare events using Kullback-Leibler divergence

One main challenge in developing a system for visual surveillance event detection is the annotation of target events in the training data. By making use of the assumption that events with security interest are often rare compared to regular behaviours, this paper presents a novel approach by using Kullback-Leibler (KL) divergence for rare event detection in a weakly supervised learning setting, where only clip-level annotation is available. It will be shown that this approach outperforms state-of-the-art methods on a popular real-world dataset, while preserving real time performance.

Searching for semantic person queries using channel representations

It is not uncommon to hear a person of interest described by their height, build, and clothing (i.e. type and colour). These semantic descriptions are commonly used by people to describe others, as they are quick to relate and easy to understand. However such queries are not easily utilised within intelligent surveillance systems as they are difficult to transform into a representation that can be searched for automatically in large camera networks. In this paper we propose a novel approach that transforms such a semantic query into an avatar that is searchable within a video stream, and demonstrate state-of-the-art performance for locating a subject in video based on a description.

MIMO enhanced slotted cooperation in urban vehicular networks

The requirement of isolated relays is one of the prime obstacles in utilizing sequential slotted cooperative protocols for Vehicular Ad-hoc Networks (VANET). Significant research advancement has taken place to improve the diversity multiplexing trade-off (DMT) of cooperative protocols in conventional mobile networks without much attention on vehicular ad-hoc networks. We have extended the concept of sequential slotted amplify and forward (SAF) protocols in the context of urban vehicular ad-hoc networks. Multiple Input Multiple Output (MIMO) reception is used at relaying vehicular nodes to isolate the relays effectively. The proposed approach adds a pragmatic value to the sequential slotted cooperative protocols while achieving attractive performance gains in urban VANETs. We have analysed the DMT bounds and the outage probabilities of the proposed scheme. The results suggest that the proposed scheme can achieve an optimal DMT similar to the DMT upper bound of the sequential SAF. Furthermore, the outage performance of the proposed scheme outperforms the SAF protocol by 2.5 dB at a target outage probability of 10-4.

Computational analysis of epigenetic information in human DNA sequences

Over the last few years, investigations of human epigenetic profiles have identified key elements of change to be Histone Modifications, stable and heritable DNA methylation and Chromatin remodeling. These factors determine gene expression levels and characterise conditions leading to disease. In order to extract information embedded in long DNA sequences, data mining and pattern recognition tools are widely used, but efforts have been limited to date with respect to analyzing epigenetic changes, and their role as catalysts in disease onset. Useful insight, however, can be gained by investigation of associated dinucleotide distributions. The focus of this paper is to explore specific dinucleotides frequencies across defined regions within the human genome, and to identify new patterns between epigenetic mechanisms and DNA content. Signal processing methods, including Fourier and Wavelet Transformations, are employed and principal results are reported.

A statistical model for combustion resonance from a DI diesel engine with applications

Introduced in this paper is a Bayesian model for isolating the resonant frequency from combustion chamber resonance. The model shown in this paper focused on characterising the initial rise in the resonant frequency to investigate the rise of in-cylinder bulk temperature associated with combustion. By resolving the model parameters, it is possible to determine: the start of pre-mixed combustion, the start of diffusion combustion, the initial resonant frequency, the resonant frequency as a function of crank angle, the in-cylinder bulk temperature as a function of crank angle and the trapped mass as a function of crank angle. The Bayesian method allows for individual cycles to be examined without cycle-averaging|allowing inter-cycle variability studies. Results are shown for a turbo-charged, common-rail compression ignition engine run at 2000 rpm and full load.

Estimating link-dependent origin-destination matrices from sample trajectories and traffic counts

In transport networks, Origin-Destination matrices (ODM) are classically estimated from road traffic counts whereas recent technologies grant also access to sample car trajectories. One example is the deployment in cities of Bluetooth scanners that measure the trajectories of Bluetooth equipped cars. Exploiting such sample trajectory information, the classical ODM estimation problem is here extended into a link-dependent ODM (LODM) one. This much larger size estimation problem is formulated here in a variational form as an inverse problem. We develop a convex optimization resolution algorithm that incorporates network constraints. We study the result of the proposed algorithm on simulated network traffic.

Dragline swing automation

Draglines are very large machines that are used to remove overburden in open-cut coal mines. This paper outlines the design of a computer control system to implement an automated swing cycle on a production dragline. Subsystems and sensors have been developed to satisfy the constraints imposed by the task, the harsh operating environment and the mine's production requirements.