Intelligent facial emotion recognition and semantic-based topic detection for a humanoid robot

Automatic perception of human affective behaviour from facial expressions and recognition of intentions and social goals from dialogue contexts would greatly enhance natural human robot interaction. This research concentrates on intelligent neural network based facial emotion recognition and Latent Semantic Analysis based topic detection for a humanoid robot. The work has first of all incorporated Facial Action Coding System describing physical cues and anatomical knowledge of facial behaviour for the detection of neutral and six basic emotions from real-time posed facial expressions. Feedforward neural networks (NN) are used to respectively implement both upper and lower facial Action Units (AU) analysers to recognise six upper and 11 lower facial actions including Inner and Outer Brow Raiser, Lid Tightener, Lip Corner Puller, Upper Lip Raiser, Nose Wrinkler, Mouth Stretch etc. An artificial neural network based facial emotion recogniser is subsequently used to accept the derived 17 Action Units as inputs to decode neutral and six basic emotions from facial expressions. Moreover, in order to advise the robot to make appropriate responses based on the detected affective facial behaviours, Latent Semantic Analysis is used to focus on underlying semantic structures of the data and go beyond linguistic restrictions to identify topics embedded in the users’ conversations. The overall development is integrated with a modern humanoid robot platform under its Linux C++ SDKs. The work presented here shows great potential in developing personalised intelligent agents/robots with emotion and social intelligence.     

Study of spray cooling of a pressure vessel head of a boiling water reactor

The present paper deals with a theoretical analysis of the spray cooling of a Reactor Pressure Vessel (RPV) head in a Boiling Water Reactor (BWR). To this end a detailed computational model has been developed. The model predicts the trajectories, diameters and temperatures of subcooled droplets moving in saturated vapor. The model has been validated through comparison with experimental data, in which droplet temperatures were measured as functions of the distance that they cover in saturated vapor from the moment they leave the sprinkler outlet to the moment they impact on the RPV head inner wall. The calculations are in very good agreement with measurements, confirming the model adequacy for the present study. The model has been used for a parametric study to investigate the influence of several parameters on the cooling efficiency of the spray system. Based on the study it has been shown that one of the main parameters that govern the temperature increase in a subcooled droplet is its initial diameter. Comparisons are also made between conclusions from the theoretical model and observations made through flow and temperature measurements in the plant (Forsmark 1 and 2). One of these observations is that the rate at which the RPV head temperature decreases on the way down from hot to cold standby is constant and independent of the sprinkling flow rate as long as the flow rate is above a certain minimum value. Accordingly, the theoretical model shows that if one assumes that the cooling of the RPV head is through a water film built on the inner wall due to sprinkling, the heat removal rate is only very weakly dependent on the sprinkling flow rate.     

Separating reflections from images by use of independent component analysis.

The image of an object can vary dramatically, depending on lighting, specularities, reflections, and shadows. It is often advantageous to separate these incidental variations from the intrinsic aspects of an image. We describe a method for photographing objects behind glass and digitally removing the reflections from the surface of the glass, leaving the image of the objects behind the glass intact. We describe the details of this method, which employs simple optical techniques and independent component analysis and show its efficacy with several examples.     

Blind inverse gamma correction

The luminance nonlinearity introduced by many imaging devices can often be described by a simple point-wise operation (gamma correction). This paper presents a technique for blindly estimating the amount of gamma correction in the absence of any calibration information or knowledge of the imaging device. The basic approach exploits the fact that gamma correction introduces specific higher-order correlations in the frequency domain. These correlations can be detected using tools from polyspectral analysis. The amount of gamma correction is then estimated by minimizing these correlations.     

Roller compacted concrete with contaminated recycled aggregates

Recycling waste building materials from construction and demolition (C&D) sites is increasingly investigated for economical and environmental reasons. Roller compacted concrete (RCC) is a special dry concrete mix; laid down and compacted like a soil, it is especially used for the construction of massive structures like dams or large horizontal surfaces like road foundation. In this paper, natural concrete slabs were cured in water, sea water, chloride solutions or sulphate solutions and then crushed to obtain virgin and contaminated (polluted) recycled aggregates. The aim of this research is the total replacement (100% coarse and fine) of natural aggregates (NA) by recycled concrete aggregates (RA) in the composition of a roller compacted concrete. The natural and recycled aggregates are characterised and compared. The mechanical properties and durability performances of concrete with contaminated RA are analysed. The experimental results showed that the polluted RA are much richer in chlorides than in sulphates and are leached if they are soaked in water. Significant differences were observed between the properties of original and new concrete and the results demonstrated the need of taking these contaminations into account.     

Modelling and performance comparison of optimal AIGaAs/GaAs DMTs and multichannel HEMTs for power amplification

We present two detailed studies concerning thedmt and the multichannelhemt for power amplifications. Each work comprises a first theoretical part where the structure is optimized by simulating the device. Technological realizations are hence performed at the laboratory. The following measurements give results very encouraging and permit to foresee the superior performance relatively to that of GaAs powermesfet.     

Feasibility and performance evaluation of a 6LoWPAN‐enabled platform for ubiquitous healthcare monitoring

Technology has revolutionized medical practices by enabling more convenient and non‐intrusive monitoring of patient's health, leading to next generation ubiquitous healthcare (u‐healthcare). The exploitation of the Internet protocol version 6 addressing space along with the miniaturization of electronic devices has fostered providing interoperability and connectivity of wearable sensor devices in wireless body area networks to the Internet of Things. In this paper, we propose to integrate the IPv6 over low power wireless personal area network (6LoWPAN) to the u‐healthcare monitoring system architecture. The main objective is to study the feasibility of the 6LoWPAN‐enabled platform in real‐world scenarios dealing with medical data. The performance evaluation of this platform is carried out initially through simulations using OMNet++ and then supported by an experimental study using sensor motes and a customized micro‐computing unit. Performance metrics such as throughput, end‐to‐end delay, packet error rate, and energy consumption are investigated under acute health conditions, where patient's health information has to be sent continuously and at maximum rate to the care provider. The obtained results show that the proposed 6LoWPAN solution fulfills the main quality of service requirements of u‐healthcare applications. Copyright © 2015 John Wiley & Sons, Ltd.     

Ultrasonic synthesis of Zn-doped CdO nanostructures and their optoelectronic properties

The effect of Zn dopant on the growth of cadmium oxide (CdO) nanostructures through a sonochemical method was investigated. The X-ray diffraction (XRD) patterns of the nanoparticles show CdO cubic structures for the produced samples. Field emission scanning electron microscope (FESEM) images reveal that morphologies of the samples change, when they are doped with Zn atoms, and their sizes reduce. Room temperature photoluminescence (PL) and UV-Vis spectrometers were used to study optical properties of the samples. Evaluation of optical properties indicates that different emission bands result from different transitions and the value of CdO energy band gap increases due to doping. Studies of electrical properties of the nanostructures demonstrate that Zn dopant enhances electrical conductivity and photocurrent generation as the result of light illumination on the nanostructures due to improved density of photo-generated carriers. Considering the obtained outcomes, Zn dopant can alter the physical property of the CdO nanostructures.     

RADAR: A reputation-driven anomaly detection system for wireless mesh networks

As one of the backup measures of intrusion prevention techniques, intrusion detection plays a paramount role in the second defense line of computer networks. Intrusion detection in wireless mesh networks (WMNs) is especially challenging and requires particular design concerns due to their special infrastructure and communication mode. In this paper, we propose a novel anomaly detection system, termed RADAR, to detect and handle anomalous mesh nodes in wireless mesh networks. Specifically, reputation is introduced to characterize and quantify a node’s behavior in terms of fine-grained performance metrics of interest. The dual-core detection engine of RADAR then explores spatio-temporal property of such behavior to manifest the deviation between that of normal and anomalous nodes. Although the current RADAR prototype is only implemented with routing protocols, the design architecture allows it to be easily extended to cross-layer anomaly detection where anomalous events occur at different layers and can be resulted by either intentional intrusion or accidental network failure. The simulation results demonstrate that RADAR can achieve high detection accuracy, low computational complexity, and low false positive rate.