Emotion Recognition with Capsule Neural Network

For human-machine communication to be as effective as human-to-human communication, research on speech emotion recognition is essential. Among the models and the classifiers used to recognize emotions, neural networks appear to be promising due to the network’s ability to learn and the diversity in configuration. Following the convolutional neural network, a capsule neural network (CapsNet) with inputs and outputs that are not scalar quantities but vectors allows the network to determine the part-whole relationships that are specific 6 for an object. This paper performs speech emotion recognition based on CapsNet. The corpora for speech emotion recognition have been augmented by adding white noise and changing voices. The feature parameters of the recognition system input are mel spectrum images along with the characteristics of the sound source, vocal tract and prosody. For the German emotional corpus EMO-DB, the average accuracy score for 4 emotions, neutral, boredom, anger and happiness, is 99.69%. For Vietnamese emotional corpus BKEmo, this score is 94.23% for 4 emotions, neutral, sadness, anger and happiness. The accuracy score is highest when combining all the above feature parameters, and this score increases significantly when combining mel spectrum images with the features directly related to the fundamental frequency.     

A reliable measure of footwear upper comfort enabled by an innovative sock equipped with textile pressure sensors

Footwear comfort is essential and pressure distribution on the foot was shown as a relevant objective measurement to assess it. However, asperities on the foot sides, especially the metatarsals and the instep, make its evaluation difficult with available equipment. Thus, a sock equipped with textile pressure sensors was designed. Results from the mechanical tests showed a high linearity of the sensor response under incremental loadings and allowed to determine the regression equation to convert voltage values into pressure measurements. The sensor response was also highly repeatable and the creep under constant loading was low. Pressure measurements on human feet associated with a perception questionnaire exhibited that significant relationships existed between pressure and comfort perceived on the first, the third and the fifth metatarsals and top of the instep.

Practitioner Summary: A sock equipped with textile sensors was validated for measuring the pressure on the foot top, medial and lateral sides to evaluate footwear comfort. This device may be relevant to help individuals with low sensitivity, such as children, elderly or neuropathic, to choose the shoes that fit the best.     

Synthesis and characterization of elastomeric,biobased, nonisocyanate polyurethane from natural rubber

Linear and crosslinked polyhydroxyurethanes (PHUs) based on natural rubber (NR) were synthesized by a polyaddition reaction without a solvent or catalyst to exploit the reactivity of diamines or triamines with dicyclic carbonate groups. Oligo‐isoprenes were obtained from the controlled oxidative degradation of NR and successive modifications of the chain ends. The syntheses of linear PHU were carried out with two approaches. The first one consisted of a reaction between amino telechelic oligo‐isoprenes and aromatic or aliphatic dicyclic carbonates. The second approach proceeded through a reaction between oligo‐isoprenes bearing cyclic carbonate chain ends and difunctional or trifunctional amines. The evolution of these reactions was studied by Fourier transform infrared spectrometry. The influence of the carbonate‐to‐amine molar ratio, the chain length of the oligo‐isoprenes, and the reaction temperatures were investigated. The thermal properties of the PHUs were studied by differential scanning calorimetry and thermogravimetric analysis. © 2017 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2017 , 134, 45427.     

Observer-based control for time-varying delay neural networks with nonlinear observation

This paper studies the problem of designing observer-based controllers for a class of delayed neural networks with nonlinear observation. The system under consideration is subject to nonlinear observation and an interval time-varying delay. The nonlinear observation output is any nonlinear Lipschitzian function and the time-varying delay is not required to be differentiable nor its lower bound be zero. By constructing a set of appropriate Lyapunov–Krasovskii functionals and utilizing the Newton–Leibniz formula, some delay-dependent stabilizability conditions which are expressed in terms of Linear Matrix Inequalities (LMIs) are derived. The derived conditions allow simultaneous computation of two bounds that characterize the exponential stability rate of the closed-loop system. The unknown observer gain and the state feedback observer-based controller are directly obtained upon the feasibility of the derived LMIs stabilizability conditions. A simulation example is presented to verify the effectiveness of the proposed result.     

SimSelect: Similarity‐based selection for 3D surfaces

Surface selection is one of the fundamental interactions in shape modeling. In the case of complex models, this task is often tedious for at least two reasons: firstly the local geometry of a given region may be hard to manually select and needs great accuracy; secondly the selection process may have to be repeated a large number of times for similar regions requiring similar subsequent editing. We propose SimSelect, a new system for interactive selection on 3D surfaces addressing these two issues. We cope with the accuracy issue by classifying selections in different types, namely components, parts and patches for which we independently optimize the selection process. Second, we address the repetitiveness issue by introducing an expansion process based on shape recognition which automatically retrieves potential selections similar to the user‐defined one. As a result, our system provides the user with a compact set of simple interaction primitives providing a smooth select‐and‐edit workflow.     

Compact Saloplastic Poly(Acrylic Acid)/Poly(Allylamine) Complexes: Kinetic Control Over Composition,Microstructure, and Mechanical Properties

Durable compact polyelectrolyte complexes (CoPECs) with controlled porosity and mechanical properties are prepared by ultracentrifugation. Because the starting materials, poly(allylamine hydrochloride) (PAH) and poly(acrylic acid sodium salt) (PAA), are weak acids/bases, both composition and morphology are controlled by solution pH. In addition, the nonequilibrium nature of polyelectrolyte complexation can be exploited to provide a range of compositions and porosities under the influence of polyelectrolyte addition order and speed, and concentration. Confocal microscopy shows these “saloplastic” materials to be highly porous, where pore formation is attributed to a combination of deswelling of the polyelectrolyte matrix and expansion of small inhomogenities by osmotic pressure. The porosity (15–70%) and the pore size (<5 μm to >70 μm) of these materials can be tuned by adjusting the PAA to PAH ratio, the salt concentration, and the pH. The modulus of these CoPECs depends on the ratio of the two polyelectrolytes, with stoichiometric complexes being the stiffest due to optimized charge pairing, which correlates with maximized crosslinking density. Mechanical properties, pore sizes, and pore density of these materials make them well suited to three dimensional supports for tissue engineering applications.     

A study of depth/texture bit-rate allocation in multi-view video plus depth compression

Multi-view video plus depth (MVD) data offer a reliable representation of three-dimensional (3D) scenes for 3D video applications. This is a huge amount of data whose compression is an important challenge for researchers at the current time. Consisting of texture and depth video sequences, the question of the relationship between these two types of data regarding bit-rate allocation often raises. This paper questions the required ratio between texture and depth when encoding MVD data. In particular, the paper investigates the elements impacting on the best bit-rate ratio between depth and color: total bit-rate budget, input data features, encoding strategy, and assessed view.     

Generation behavior of elctricity in a microbial fuel cell

Electricity generation using a microbial fuel cell (MFC) was investigated with acetate as the fuel and Geobacter sulfurreducens as the biocatalyst on the anode electrode. The voltage and power density behaviors at various external resistances were observed, as were the coulombic efficiency and energy recovery behaviors at various acetate concentrations. A high voltage production was obtained when the pH in the cathode chamber was maintained in the range of 7–8, which is similar to that used in other MFC studies. After 72 hours of operation, the voltage production was decreased by 11.5% with 30 mM tris-HCl and by 33.7% with 10 mM tris-HCl.     

Stability of rare earth oxides in a moist environment at high temperatures—Experimental and thermodynamic studies. Part I: The way to assess thermodynamic parameters from volatilisation rates

A methodology based on a weight loss measurement was used to quantify the volatility of yttria in high temperature water vapor. This method was first assessed on silica. Sintered materials with a shape of pellets were exposed at temperatures between 1000 and 1400 °C in air with 50 kPa of water at atmospheric pressure, under a flowing gas velocity of 5 cm s^?1. Besides the volatilisation rate, the nature of the volatile gaseous species was determined using a kinetic study. Knowing the nature of flows in the furnace, partial pressures of yttrium (oxy-)hydroxide in equilibrium over Y₂O₃ were calculated, and used to assess the enthalpies of formation of YO(OH) and Y(OH)₃.