Feedback systems for the quality of chest compressions during cardiopulmonary resuscitation

167 p.

Eurobalise-Train communication modelling to assess interferences in railway control signalling systems

The evolution of the railway sector depends, to a great extent, on the deployment of advanced railway signalling systems. These signalling systems are based on communication architectures that must cope with complex electromagnetical environments. This paper is outlined in the context of developing the necessary tools to allow the quick deployment of these signalling systems by contributing to an easier analysis of their behaviour under the effect of electromagnetical interferences. Specifically, this paper presents the modelling of the Eurobalise-train communication flow in a general purpose simulation tool. It is critical to guarantee this communication link since any lack of communication may lead to a stop of the train and availability problems. In order to model precisely this communication link we used real measurements done in a laboratory equipped with elements defined in the suitable subsets. Through the simulation study carried out, we obtained performance indicators of the physical layer such as the received power, SNR and BER. The modelling presented in this paper is a required step to be able to provide quality of service indicators related to perturbed scenarios.

Real time feature-based facial tracking using Lie algebras

We have developed a novel human facial tracking system that operates in real time at a video frame rate without needing any special hardware. The approach is based on the use of Lie algebra, and uses three-dimensional feature points on the targeted human face. It is assumed that the roughly estimated facial model (relative coordinates of the three-dimensional feature points) is known. First, the initial feature positions of the face are determined using a model fitting technique. Then, the tracking is operated by the following sequence: (1) capture the new video frame and render feature points to the image plane; (2) search for new positions of the feature points on the image plane; (3) get the Euclidean matrix from the moving vector and the three-dimensional information for the points; and (4) rotate and translate the feature points by using the Euclidean matrix, and render the new points on the image plane. The key algorithm of this tracker is to estimate the Euclidean matrix by using a least square technique based on Lie algebra. The resulting tracker performed very well on the task of tracking a human face.

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs

This article presents a novel algorithm for learning parameters in statistical dialogue systems which are modeled as Partially Observable Markov Decision Processes (POMDPs). The three main components of a POMDP dialogue manager are a dialogue model representing dialogue state information; a policy that selects the system's responses based on the inferred state; and a reward function that specifies the desired behavior of the system. Ideally both the model parameters and the policy would be designed to maximize the cumulative reward. However, while there are many techniques available for learning the optimal policy, no good ways of learning the optimal model parameters that scale to real-world dialogue systems have been found yet. The presented algorithm, called the Natural Actor and Belief Critic (NABC), is a policy gradient method that offers a solution to this problem. Based on observed rewards, the algorithm estimates the natural gradient of the expected cumulative reward. The resulting gradient is then used to adapt both the prior distribution of the dialogue model parameters and the policy parameters. In addition, the article presents a variant of the NABC algorithm, called the Natural Belief Critic (NBC), which assumes that the policy is fixed and only the model parameters need to be estimated. The algorithms are evaluated on a spoken dialogue system in the tourist information domain. The experiments show that model parameters estimated to maximize the expected cumulative reward result in significantly improved performance compared to the baseline hand-crafted model parameters. The algorithms are also compared to optimization techniques using plain gradients and state-of-the-art random search algorithms. In all cases, the algorithms based on the natural gradient work significantly better. © 2011 ACM.

Performance plumbing: Installing performance management systems to deliver lasting value

Purpose - The purpose of this paper is to explore the concept of performance plumbing, arguing that too often performance management systems in organisations are not correctly installed. Without the appropriate plumbing, performance management systems do not drive organisational change and improvement. Design/methodology/approach - The paper draws on the consultancy experiences of two of the authors, as well as the research of the third. Specific case examples are provided throughout the paper to illustrate the points being made. Findings - The paper argues that the key elements of a plumbed-in performance management system are: performance architecture; performance insights; performance focus; and performance action. Taken together, these four elements provide the necessary plumbing to enable performance management systems to deliver real value. Research limitations/implications - The paper draws on the experience of the authors, rather than a formally designed piece of research. The ideas presented in the paper would therefore benefit from further investigation and testing. Originality/value - The paper will be valuable to scholars and practitioners interested in ensuring that performance management systems deliver lasting value. © Emerald Group Publishing Limited.

Adaptively modulated optical OFDM modems utilizing RSOAs as intensity modulators in IMDD SMF transmission systems.

Detailed investigations of the transmission performance of adaptively modulated optical orthogonal frequency division multiplexed (AMOOFDM) signals converted using reflective semiconductor optical amplifiers (RSOAs) are undertaken over intensity-modulation and direct-detection (IMDD) single-mode fiber (SMF) transmission systems for WDM-PONs. The theoretical RSOA model adopted for modulating the AMOOFDM signals is experimentally verified rigorously in the aforementioned transmission systems incorporating recently developed real-time end-to-end OOFDM transceivers. Extensive performance comparisons are also made between RSOA and SOA intensity modulators. Optimum RSOA operating conditions are identified, which are independent of RSOA rear-facet reflectivity and very similar to those corresponding to SOAs. Under the identified optimum operating conditions, the RSOA and SOA intensity modulators support the identical AMOOFDM transmission performance of 30Gb/s over 60km SMFs. Under low-cost optical component-enabled practical operating conditions, RSOA intensity modulators with rear-facet reflectivity values of >0.3 outperform considerably SOA intensity modulators in transmission performance, which decreases significantly with reducing RSOA rear-facet reflectivity and optical input power. In addition, results also show that use can be made of the RSOA/SOA intensity modulation-induced negative frequency chirp to improve the AMOOFDM transmission performance in IMDD SMF systems.

Experimental demonstration of colourless real-time end-to-end optical OFDM transmission at 7.5Gb/s over 25km SSMF using a 1GHz RSOA

7.5Gb/s real-time end-to-end optical OFDM (OOFDM) transceivers incorporating variable power loading on each individual subcarrier are demonstrated experimentally, for the first time, using a live-optimized RSOA intensity modulator having a modulation bandwidth as narrow as 1GHz. Colourless real-time 16-QAM-encoded OOFDM signal transmission at 7.5Gb/s over 25km SSMF is achieved across the C-band in simple IMDD systems without in-line optical amplification and dispersion compensation. Copyright © 2010 The authors.

First experimental demonstration of low-cost VCSEL-intensity modulated end-to-end real-time optical OFDM signal transmission at 11.25Gb/s over 25km SSMFs

Low-cost, narrow modulation bandwidth, un-cooled VCSELs can be utilized to directly modulate 64-QAM-encoded 11.25Gb/s signals for end-to-end real-time optical OFDM transmission over 25km SSMF IMDD systems with excellent performance robustness. © 2011 Optical Society of America.

Experimental demonstration of real-time optical OFDM Transmission at 7.5 Gb/s over 25-km SSMF using a 1-GHz RSOA

The 7.5-Gb/s real-time end-to-end optical orthogonal frequency-division- multiplexing (OOFDM) transceivers incorporating variable power loading on each individual subcarrier are demonstrated experimentally using a live-optimized reflective semiconductor optical amplifier intensity modulator having a modulation bandwidth as narrow as 1 GHz. Real-time OOFDM signal transmission at 7.5 Gb/s over 25-km standard single-mode fiber is achieved across the $C$-band in simple intensity modulation and direct detection systems without in-line optical amplification and dispersion compensation. © 2006 IEEE.

Building more sustainable solutions in production-consumption systems: the case of food for people with reduced access

In new product development, the ability to integrate different dimensions of sustainability at a value chain level is still a complex, problematic goal. As product-service approaches are increasingly enabling the introduction of more sustainable paths, this paper describes the authors' experience thus far when building insights into conditions for the implementation of integrated solutions in a process of co-development and testing in real life conditions, which are driven by a social need focusing on food for people with reduced access. Throughout this process, which brought together producers, consumers and other stakeholders to design and test industrialised, sustainable solutions, empirical evidence demonstrates feasibility and usefulness of the approach and insight into the conditions for implementing interactive, comprehensive multi-stakeholder processes in real life situations. In addition, results show that the delivery of innovative solutions enabled to offer social added value, economic profits and environmental improvements under specific experimental conditions. © 2006 Elsevier Ltd. All rights reserved.

Reinforcement learning for parameter estimation in statistical spoken dialogue systems

Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters. © 2011 Elsevier Ltd. All rights reserved.

Towards real-time profiling of sprints using wearable pressure sensors

On-body sensor systems for sport are challenging since the sensors must be lightweight and small to avoid discomfort, and yet robust and highly accurate to withstand and capture the fast movements associated with sport. In this work, we detail our experience of building such an on-body system for track athletes. The paper describes the design, implementation and deployment of an on-body sensor system for sprint training sessions. We autonomously profile sprints to derive quantitative metrics to improve training sessions. Inexpensive Force Sensitive Resistors (FSRs) are used to capture foot events that are subsequently analysed and presented back to the coach. We show how to identify periods of sprinting from the FSR data and how to compute metrics such as ground contact time. We evaluate our system using force plates and show that millisecond-level accuracy is achievable when estimating contact times. © 2012 Elsevier B.V. All rights reserved.

On-line policy optimisation of spoken dialogue systems via live interaction with human subjects

Statistical dialogue models have required a large number of dialogues to optimise the dialogue policy, relying on the use of a simulated user. This results in a mismatch between training and live conditions, and significant development costs for the simulator thereby mitigating many of the claimed benefits of such models. Recent work on Gaussian process reinforcement learning, has shown that learning can be substantially accelerated. This paper reports on an experiment to learn a policy for a real-world task directly from human interaction using rewards provided by users. It shows that a usable policy can be learnt in just a few hundred dialogues without needing a user simulator and, using a learning strategy that reduces the risk of taking bad actions. The paper also investigates adaptation behaviour when the system continues learning for several thousand dialogues and highlights the need for robustness to noisy rewards. © 2011 IEEE.

Compression techniques applied to multiple speech recognition systems

Speech recognition systems typically contain many Gaussian distributions, and hence a large number of parameters. This makes them both slow to decode speech, and large to store. Techniques have been proposed to decrease the number of parameters. One approach is to share parameters between multiple Gaussians, thus reducing the total number of parameters and allowing for shared likelihood calculation. Gaussian tying and subspace clustering are two related techniques which take this approach to system compression. These techniques can decrease the number of parameters with no noticeable drop in performance for single systems. However, multiple acoustic models are often used in real speech recognition systems. This paper considers the application of Gaussian tying and subspace compression to multiple systems. Results show that two speech recognition systems can be modelled using the same number of Gaussians as just one system, with little effect on individual system performance. Copyright © 2009 ISCA.