A Cascade Visual Front End for Speaker Independent Automatic Speechreading

We propose a three-stage pixel-based visual front end for automatic speechreading (lipreading) that results in significantly improved recognition performance of spoken words or phonemes. The proposed algorithm is a cascade of three transforms applied on a three-dimensional video region-of-interest that contains the speaker's mouth area. The first stage is a typical image compression transform that achieves a high-energy, reduced-dimensionality representation of the video data. The second stage is a linear discriminant analysis-based data projection, which is applied on a concatenation of a small amount of consecutive image transformed video data. The third stage is a data rotation by means of a maximum likelihood linear transform that optimizes the likelihood of the observed data under the assumption of their class-conditional multivariate normal distribution with diagonal covariance. We applied the algorithm to visual-only 52-class phonetic and 27-class visemic classification on a 162-subject, 8-hour long, large vocabulary, continuous speech audio-visual database. We demonstrated significant classification accuracy gains by each added stage of the proposed algorithm which, when combined, can achieve up to 27% improvement. Overall, we achieved a 60% (49%) visual-only frame-level visemic classification accuracy with (without) use of test set viseme boundaries. In addition, we report improved audio-visual phonetic classification over the use of a single-stage image transform visual front end. Finally, we discuss preliminary speech recognition results.     

A derivative-free distributed filtering approach for sensorless control of nonlinear systems

This article examines the problem of sensorless control for nonlinear dynamical systems with the use of derivative-free Extended Information Filtering (EIF). The system is first subject to a linearisation transformation and next state estimation is performed by applying the standard Kalman Filter to the linearised model. At a second level, the standard Information Filter is used to fuse the state estimates obtained from local derivative-free Kalman filters running at the local information processing nodes. This approach has significant advantages because unlike the EIF (i) is not based on local linearisation of the nonlinear dynamics (ii) does not assume truncation of higher order Taylor expansion terms thus preserving the accuracy and robustness of the performed estimation and (iii) does not require the computation of Jacobian matrices. As a case study a robotic manipulator is considered and a cameras network consisting of multiple vision nodes is assumed to provide the visual information to be used in the control loop. A derivative-free implementation of the EIF is used to produce the aggregate state vector of the robot by processing local state estimates coming from the distributed vision nodes. The performance of the considered sensorless control scheme is evaluated through simulation experiments.     

A model-driven software engineering workflow and tool architecture for servitised manufacturing

Modern manufacturing businesses increasingly engage in servitisation, by offering advanced services along with physical products, and creating “product–service systems”. Information Technology infrastructures, and especially software, are a critical part of modern service provision. However, software development in this context has not been investigated and there are no development methods or tools specifically adapted to the task of creating software for servitised businesses in general, or manufacturing in particular. In this paper, we define the requirements for software engineering in servitised manufacturing. Based on these, we describe a model-driven software engineering workflow for servitised manufacturing, supporting both structural and behavioural modelling of the service system. Furthermore, we elaborate on the architecture of an appropriate model-driven Integrated Development Environment (IDE). The proposed workflow and a prototype implementation of the IDE were evaluated in a set of industrial pilots, demonstrating improved communication and collaboration between participants in the software engineering process.     

The Role of Exosomal Non-Coding RNAs in Colorectal Cancer Drug Resistance

Background: Colorectal cancer (CRC) is one of the most common types of cancer diagnosed worldwide with high morbidity; drug resistance is often responsible for treatment failure in CRC. Non-coding RNAs (ncRNAs) play distinct regulatory roles in tumorigenesis, cancer progression and chemoresistance. Methods: A literature search was conducted in PubMed database in order to sum up and discuss the role of exosomal ncRNAs (ex-ncRNAs) in CRC drug resistance/response and their possible mechanisms. Results: Thirty-six (36) original research articles were identified; these included exosome or extracellular vesicle (EV)-containing microRNAs (miRNAs), long non-coding RNAs (lncRNAs), circular RNAs (circRNAs) and small-interfering (siRNAs). No studies were found for piwi-interacting RNAs. Conclusions: Exosomal transfer of ncRNAs has been documented as a new mechanism of CRC drug resistance. Despite being in its infancy, it has emerged as a promising field for research in order to (i) discover novel biomarkers for therapy monitoring and/or (ii) reverse drug desensitization.     

Particle and Kalman filtering for state estimation and control of DC motors

State estimation is a major problem in industrial systems. To this end, Gaussian and nonparametric filters have been developed. In this paper the Kalman Filter, which assumes Gaussian measurement noise, is compared to the Particle Filter, which does not make any assumption on the measurement noise distribution. As a case study the estimation of the state vector of a DC motor is used. The reconstructed state vector is used in a feedback control loop to generate the control input of the DC motor. In simulation tests it was observed that for a large number of particles the Particle Filter could succeed in accurately estimating the motor’s state vector, but at the same time it required higher computational effort.     

The stabilizing role of higher-order strain gradients in non-linear thermoviscoplasticity

Summary The stabilizing role of higher order strain gradients incorporated in the constitutive equation for the stress is illustrated. It is shown, in particular, that these gradients smooth out possible non-uniformities in strain and temperature that may develop in a thermoviscoplastic slab sheared by a constant boundary force. Moreover, it is demonstrated that the occurrence and nature of instability is qualitatively different than the localized catastrophic shear banding instability of the classical analysis where higher order strain gradients are not included.     

Neural network-based approach for early detection of cascading events in electric power systems

This study proposes neural modelling and fault diagnosis methods for the early detection of cascading events in electric power systems. A neural-fuzzy network is used to model the dynamics of the power transmission system in fault-free conditions. The output of the neural-fuzzy network is compared to measurements from the power system and the obtained residuals undergo statistical processing according to a fault detection and isolation algorithm. If a fault threshold, defined by the fault detection and isolation (FDI) algorithm, is exceeded then deviation from normal operation can be detected at its early stages and an alarm can be launched. In several cases fault isolation can be also performed, that is the sources of fault in the power transmission system can be also identified. The performance of the proposed methodology is tested through simulation experiments