Speech emotion recognition: Features and classification models

To solve the speaker independent emotion recognition problem, a three-level speech emotion recognition model is proposed to classify six speech emotions, including sadness, anger, surprise, fear, happiness and disgust from coarse to fine. For each level, appropriate features are selected from 288 candidates by using Fisher rate which is also regarded as input parameter for Support Vector Machine (SVM). In order to evaluate the proposed system, principal component analysis (PCA) for dimension reduction and artificial neural network (ANN) for classification are adopted to design four comparative experiments, including Fisher + SVM, PCA + SVM, Fisher + ANN, PCA + ANN. The experimental results proved that Fisher is better than PCA for dimension reduction, and SVM is more expansible than ANN for speaker independent speech emotion recognition. The average recognition rates for each level are 86.5%, 68.5% and 50.2% respectively.     

A statistical model for robust integration of narrowband cues in speech

We investigate a statistical model for integrating narrowband cues in speech. The model is inspired by two ideas in human speech perception: (i) Fletcher’s hypothesis (1953) that independent detectors, working in narrow frequency bands, account for the robustness of auditory strategies, and (ii) Miller and Nicely’s analysis (1955) that perceptual confusions in noisy bandlimited speech are correlated with phonetic features. We apply the model to detecting the phonetic feature [ +  /  − sonorant] that distinguishes vowels, approximants, and nasals (sonorants) from stops, fricatives, and affricates (obstruents). The model is represented by a multilayer probabilistic network whose binary hidden variables indicate sonorant cues from different parts of the frequency spectrum. We derive the Expectation-Maximization algorithm for estimating the model’s parameters and evaluate its performance on clean and corrupted speech.     

FPGA implementation of reversible watermarking in digital images using reversible contrast mapping

Reversible contrast mapping (RCM) and its various modified versions are used extensively in reversible watermarking (RW) to embed secret information into the digital contents. RCM based RW accomplishes a simple integer transform applied on pair of pixels and their least significant bits (LSB) are used for data embedding. It is perfectly invertible even if the LSBs of the transformed pixels are lost during data embedding. RCM offers high embedding rate at relatively low visual distortion (embedding distortion). Moreover, low computation cost and ease of hardware realization make it attractive for real-time implementation. To this aim, this paper proposes a field programmable gate array (FPGA) based very large scale integration (VLSI) architecture of RCM-RW algorithm for digital images that can serve the purpose of media authentication in real-time environment. Two architectures, one for block size (8 × 8) and the other one for (32 × 32) block are developed. The proposed architecture allows a 6-stage pipelining technique to speed up the circuit operation. For a cover image of block size (32 × 32), the proposed architecture requires 9881 slices, 9347 slice flip-flops, 11291 number 4-input LUTs, 3 BRAMs and a data rate of 1.0395 Mbps at an operating frequency as high as 98.76 MHz.     

Intrinsic evolvable hardware platform for digital circuit design and repair using genetic algorithms

A hardware/software platform for intrinsic evolvable hardware is designed and evaluated for digital circuit design and repair on Xilinx Field Programmable Gate Arrays (FPGAs). Dynamic bitstream compilation for mutation and crossover operators is achieved by directly manipulating the bitstream using a layered framework. Experimental results on a case study have shown that benchmark circuit evolution from an unseeded initial population, as well as a complete recovery of a stuck-at fault is achievable using this platform. An average of 0.47 μs is required to perform the genetic mutation, 4.2 μs to perform the single point conventional crossover, 3.1 μs to perform Partial Match Crossover (PMX) as well as Order Crossover (OX), 2.8 μs to perform Cycle Crossover (CX), and 1.1 ms for one input pattern intrinsic evaluation. These represent a performance advantage of three orders of magnitude over the JBITS software framework and more than seven orders of magnitude over the Xilinx design tool driven flow for realizing intrinsic genetic operators on Xilinx Virtex Family devices.     

Consensus scoring model for the molecular docking study of mTOR kinase inhibitor

The discovery of mammalian target of rapamycin (mTOR) kinase inhibitors has always been a research hotspot of antitumor drugs. Consensus scoring used in the docking study of mTOR kinase inhibitors usually improves hit rate of virtual screening. Herein, we attempt to build a series of consensus scoring models based on a set of the common scoring functions. In this paper, twenty-five kinds of mTOR inhibitors (16 clinical candidate compounds and 9 promising preclinical compounds) are carefully collected, and selected for the molecular docking study used by the Glide docking programs within the standard precise (SP) mode. The predicted poses of these ligands are saved, and revaluated by twenty-six available scoring functions, respectively. Subsequently, consensus scoring models are trained based on the obtained rescoring results by the partial least squares (PLS) method, and validated by Leave-one-out (LOO) method. In addition, three kinds of ligand efficiency indices (BEI, SEI, and LLE) instead of pIC₅₀ as the activity could greatly improve the statistical quality of build models. Two best calculated models 10 and 22 using the same BEI indice have following statistical parameters, respectively: for model 10, training set R² = 0.767, Q² = 0.647, RMSE = 0.024, and for test set R² = 0.932, RMSE = 0.026; for model 22, raining set R² = 0.790, Q² = 0.627, RMSE = 0.023, and for test set R² = 0.955, RMSE = 0.020. These two consensus scoring model would be used for the docking virtual screening of novel mTOR inhibitors.     

An intelligent strategy for checking the annual inspection status of motorcycles based on license plate recognition

License plate recognition techniques have been successfully applied to the management of stolen cars, management of parking lots and traffic flow control. This study proposes a license plate based strategy for checking the annual inspection status of motorcycles from images taken along the roadside and at designated inspection stations. Both a UMPC (Ultra Mobile Personal Computer) with a web camera and a desktop PC are used as hardware platforms. The license plate locations in images are identified by means of integrated horizontal and vertical projections that are scanned using a search window. Moreover, a character recovery method is exploited to enhance the success rate. Character recognition is achieved using both a back propagation artificial neural network and feature matching. The identified license plate can then be compared with entries in a database to check the inspection status of the motorcycle. Experiments yield a recognition rate of 95.7% and 93.9% based on roadside and inspection station test images, respectively. It takes less than 1 s on a UMPC (Celeron 900 MHz with 256 MB memory) and about 293 ms on a PC (Intel Pentium 4 3.0 GHz with 1 GB memory) to correctly recognize a license plate. Challenges associated with recognizing license plates from roadside and designated inspection stations images are also discussed.     

Evaluation of three methodologies to estimate the VO2max in people of different ages

Aging and gender are factors that affect the variation of physical work capacity. The present paper highlights the importance of the metabolism used by ergonomics to establish the appropriate limits of loads at work. This study compares the aerobic capacity of people from 20 to 71 years old split in 5 different groups. The laboratory experiment tested 33 volunteers (19 women and 14 men). A submaximal step test was used to measure the VO₂ using a portable breath by breath metabolic system and a telemetric heart rate monitor. Three methods to estimate the VO_2max were compared: 1) a direct measurement of VO₂, 2) estimation by heart rate, and 3) a step test method using predetermined charts. Significant difference was encountered among the estimation methods as well as among the age ranges (F_2,92 = 6.43, p < 0.05 y F_4,92 = 7.18, p < 0.05 respectively). The method of direct measurement and the method of predetermined charts were different for the estimation of the VO_2max with a confidence level of 95%. The method of predetermined charts is better adapted for males and people younger than 30 years. The estimation through non invasive heart rate apparatus was a good appraiser of the maximal oxygen consumption considering both genders and all the age groups.     

Genetic programming for epileptic pattern recognition in electroencephalographic signals

This paper reports how the genetic programming paradigm, in conjunction with pattern recognition principles, can be used to evolve classifiers capable of recognizing epileptic patterns in human electroencephalographic signals. The procedure for feature extraction from the raw signal is detailed, as well as the genetic programming system that properly selects the features and evolves the classifiers. Based on the data sets used, two different epileptic patterns were detected: 3 Hz spike-and-slow-wave-complex (SASWC) and spike-or-sharp-wave (SOSW). After training, classifiers for both patterns were tested with unseen instances, and achieved sensibility = 1.00 and specificity = 0.93 for SASWC patterns, and sensibility = 0.94 and specificity = 0.89 for SOSW patterns. Results are very promising and suggest that the methodology presented can be applied to other pattern recognition tasks in complex signals.     

Design of high speed gate driver employing IZO TFTs

This paper presents a new bi-side gate driver integrated by indium-zinc-oxide thin film transistors (IZO TFTs). Our optimized operate method can achieve high speed performance by employing a lower duty ratio (25%) CK2 with its pulse located in the middle of the pulse of CK2L to fully use the bootstrapped high voltage of node Q. In addition, the size of devices is optimized by calculation and simulation, and the function of the proposed gate driver is predicted by the circuit simulation. Furthermore, the proposed gate driver with 20 stages is fabricated by the IZO TFTs process. It is shown that a 2.6 μs width pulse with good noise-suppressed characteristic can be successfully output at the condition of R_load = 6 kΩ and C_load = 150 pF. The power consumption of the proposed gate driver with 20 stages is measured as 1 mW. Hence, the proposed gate driver may be applied to the display of 4K resolution (4096 × 2160) at a frame rate of 120 Hz. Moreover, there is a good stability for the proposed gate driver under 48 h operation.     

Realization strategies of dedicated path protection: A bandwidth cost perspective

Communication networks have to provide a high level of availability and instantaneous recovery after failures in order to ensure sufficient survivability for mission-critical services. Currently, dedicated path protection (or 1 + 1) is implemented in backbone networks to provide the necessary resilience and instantaneous recovery against single link failures with remarkable simplicity. However, in order to satisfy strict availability requirements, connections also have to be resilient against Shared Risk Link Group (SRLG) failures. In addition, switching matrix reconfigurations have to be avoided after a failure in order to guarantee instantaneous recovery. For this purpose, there are several possible realization strategies improving the characteristics of traditional 1 + 1 path protection by lowering reserved bandwidth while conserving all its favorable properties. These methods either utilize diversity coding, network coding, or generalize the disjoint-path constraint of 1 + 1.In this paper, we consider the cost aspect of the traditional and the alternative 1 + 1 realization strategies. We evaluate the bandwidth cost of different schemes both analytically and empirically in realistic network topologies. As the more complex realizations lead to NP-complete problems even in the single link failure case, we propose both Integer Linear Programming (ILP) based optimal methods, as well as heuristic and meta-heuristic approaches to solve them. Our findings provide a tool and guidelines for service providers for selecting the path protection method with the lowest bandwidth cost for their network corresponding to a given level of reliability.     

Language identification using multi-core processors

Graphics processing units (GPUs) provide substantial processing power for little cost. We explore the application of GPUs to speech pattern processing, using language identification (LID) to demonstrate their benefits. Realization of the full potential of GPUs requires both effective coding of predetermined algorithms, and, if there is a choice, selection of the algorithm or technique for a specific function that is most able to exploit the GPU. We demonstrate these principles using the NIST LRE 2003 standard LID task, a batch processing task which involves the analysis of over 600 h of speech. We focus on two parts of the system, namely the acoustic classifier, which is based on a 2048 component Gaussian Mixture Model (GMM), and acoustic feature extraction. In the case of the latter we compare a conventional FFT-based analysis with IIR and FIR filter banks, both in terms of their ability to exploit the GPU architecture and LID performance. With no increase in error rate our GPU based system, with an FIR-based front-end, completes the NIST LRE 2003 task in 16 h, compared with 180 h for the conventional FFT-based system on a standard CPU (a speed up factor of more than 11). This includes a 61% decrease in front-end processing time. In the GPU implementation, front-end processing accounts for 8% and 10% of the total computing times during training and recognition, respectively. Hence the reduction in front-end processing achieved in the GPU implementation is significant.     

Buffered DDA command generation in a CNC

In a computerized numerical controller (CNC), interpolating more than one block in a sampling interval, increases the feed rate. Some commands skipped by the generator are pre-saved in a circular buffer, to provide faster operation than that of a conventional digital differential analyzer. The feed rate can be increased when programmed distances are short. The high feed rate is confirmed by installing the buffered command generation algorithm in the motion board that includes a digital signal processor. The feed rate can reach 11.6 m/min, when minimal (1 μm) distance is programmed in all blocks.     

Ferroelectric properties of direct-patterned half-micron thick PZT film

Ferroelectric properties of direct-patterned PZT(PbZr_0.52Ti_0.48O₃) films with 460 μm × 460 μm size and 510 nm thick were analyzed for applying to micro-detecting devices. A photosensitive solution containing ortho-nitrobenzaldehyde was used for the preparation of direct-patterned PZT film. PZT solution was coated on Pt(1 1 1)/Ti/SiO₂/Si(1 0 0) substrate for three times to obtain half-micron thick film and three times of direct-patterning process were repeated to define a pattern on multi-layer PZT film. Through intermediate and final anneal procedure of direct-patterned PZT film, any shrinkage along horizontal direction was not observed within this experimental condition, i.e., the size of the pattern was preserved after annealing, only a thickness reduction was observed after each annealing treatment. Ferroelectric properties of direct-patterned PZT film with 460 μm × 460 μm size and 510 nm thick were compared with those of un-patterned conventional PZT film and shown to be almost the same. Through this work, the high potentiality of direct-patternable PZT film for applying to micro-devices without the introduction of physical damages from dry-etching could be confirmed.     

Development of wireless compressive/relaxation-stress measurement system integrated with pressure-sensitive carbon black-filled silicone rubber-based sensors

In order to detect the installation compressive stress and monitor the stress relaxation between two bending surfaces on a defensive furnishment, a wireless compressive-stress/relaxation-stress measurement system based on pressure-sensitive sensors is developed. The flexible pressure-sensitive stress sensor array is fabricated by using carbon black-filled silicone rubber-based composite. The wireless stress measurement system integrated with this sensor array is tested with compressive stress in the range from 0 MPa to 3 MPa for performance evaluation. Experimental results indicate that the fractional change in electrical resistance of the pressure-sensitive stress sensor changes linearly and reversibly with the compressive stress, and its fractional change goes up to 355% under uniaxial compression; the change rate of the electrical resistance can track the relaxation stress and give out a credible measurement in the process of stress relaxation. The relationship between input (compressive stress) and output (the fractional change in electrical resistance) of the pressure-sensitive sensor is ΔR/R₀ = σ × 1.2 MPa^?1. The wireless compressive stress measurement system can be used to achieve sensitivity of 1.33 V/MPa to the stress at stress resolution of 920.3 Pa. The newly developed wireless stress measurement system integrated with pressure-sensitive carbon black-filled silicone rubber-based sensors has advantages such as high sensitivity to stress, high stress resolution, simple circuit and low energy consumption.     

Automated delineation of thyroid nodules in ultrasound images using spatial neutrosophic clustering and level set

An accurate contour estimation plays a significant role in classification and estimation of shape, size, and position of thyroid nodule. This helps to reduce the number of false positives, improves the accurate detection and efficient diagnosis of thyroid nodules. This paper introduces an automated delineation method that integrates spatial information with neutrosophic clustering and level-sets for accurate and effective segmentation of thyroid nodules in ultrasound images. The proposed delineation method named as Spatial Neutrosophic Distance Regularized Level Set (SNDRLS) is based on Neutrosophic L-Means (NLM) clustering which incorporates spatial information for Level Set evolution. The SNDRLS takes rough estimation of region of interest (ROI) as input provided by Spatial NLM (SNLM) clustering for precise delineation of one or more nodules. The performance of the proposed method is compared with level set, NLM clustering, Active Contour Without Edges (ACWE), Fuzzy C-Means (FCM) clustering and Neutrosophic based Watershed segmentation methods using the same image dataset. To validate the SNDRLS method, the manual demarcations from three expert radiologists are employed as ground truth. The SNDRLS yields the closest boundaries to the ground truth compared to other methods as revealed by six assessment measures (true positive rate is 95.45 ± 3.5%, false positive rate is 7.32 ± 5.3% and overlap is 93.15 ± 5. 2%, mean absolute distance is 1.8 ± 1.4 pixels, Hausdorff distance is 0.7 ± 0.4 pixels and Dice metric is 94.25 ± 4.6%). The experimental results show that the SNDRLS is able to delineate multiple nodules in thyroid ultrasound images accurately and effectively. The proposed method achieves the automated nodule boundary even for low-contrast, blurred, and noisy thyroid ultrasound images without any human intervention. Additionally, the SNDRLS has the ability to determine the controlling parameters adaptively from SNLM clustering.     

A lidar-based hierarchical approach for assessing MODIS fPAR

The purpose of this study was to estimate the fraction of photosynthetically active radiation absorbed by the canopy (fPAR) from point measurements to airborne lidar for hierarchical scaling up and assessment of the Moderate Resolution Imaging Spectroradiometer (MODIS) fPAR product within a “medium-sized” (7 km × 18 km) watershed. Nine sites across Canada, containing one or more (of 11) distinct species types and age classes at varying stages of regeneration and seasonal phenology were examined using a combination of discrete pulse airborne scanning Light Detection And Ranging (lidar) and coincident analog and digital hemispherical photography (HP). Estimates of fPAR were first compared using three methods: PAR radiation sensors, HP, and airborne lidar. HP provided reasonable estimates of fPAR when compared with radiation sensors. A simplified fractional canopy cover ratio from lidar based on the number of within canopy returns to the total number of returns was then compared with fPAR estimated from HP at 486 geographically registered measurement locations. The return ratio fractional cover method from lidar compared well with HP-derived fPAR (coefficient of determination = 0.72, RMSE = 0.11), despite varying the lidar survey configurations, canopy structural characteristics, seasonal phenologies, and possible slight inaccuracies in location using handheld GPS at some sites. Lidar-derived fractional cover estimates of fPAR were ～ 10% larger than those obtained using HP (after removing wood components), indicating that lidar likely provides a more realistic estimate of fPAR than HP when compared with radiation sensors. Finally, fPAR derived from lidar fractional cover was modelled at 1 m resolution and averaged over 99 1 km areas for comparison with MODIS fPAR. The following study is one of the first to scale between plot measurements and MODIS pixels using airborne lidar.     

Structural study of carboxylesterase from hyperthermophilic bacteria Geobacillus stearothermophilus by molecular dynamics simulation

Carboxylesterases are ubiquitous enzymes with important physiological, industrial and medical applications such as synthesis and hydrolysis of stereo specific compounds, including the metabolic processing of drugs, and antimicrobial agents. Here, we have performed molecular dynamics simulations of carboxylesterase from hyperthermophilic bacterium Geobacillus stearothermophilus (GsEst) for 10 ns each at five different temperatures namely at 300 K, 343 K, 373 K, 473 K and 500 K. Profiles of root mean square fluctuation (RMSF) identify thermostable and thermosensitive regions of GsEst. Unfolding of GsEst initiates at the thermosensitive α-helices and proceeds to the thermostable β-sheets. Five ion-pairs have been identified as critical ion-pairs for thermostability and are maintained stably throughout the higher temperature simulations. A detailed investigation of the active site residues of this enzyme suggests that the geometry of this site is well preserved up to 373 K. Furthermore, the hydrogen bonds between Asp188 and His218 of the active site are stably maintained at higher temperatures imparting stability of this site. Radial distribution functions (RDFs) show similar pattern of solvent ordering and water penetration around active site residues up to 373 K. Principal component analysis suggests that the motion of the entire protein as well as the active site is similar at 300 K, 343 K and 373 K. Our study may help to identify the factors responsible for thermostability of GsEst that may endeavor to design enzymes with enhanced thermostability.     

Fuzzy logic and statistical-based modelling of the Marshall Stability of asphalt concrete under varying temperatures and exposure times

In this study, the Marshall Stability (MS) of asphalt concrete under varying temperature and exposure times was modelled by using fuzzy logic and statistical method. This is an experimental study conducted using statistics and fuzzy logic methods. In order to investigate the Marshall Stability of asphalt concrete based on exposure time and environment temperature, exposure times of 1.5, 3, 4.5 and 6 h and temperatures of 30, 40 and 50 °C were selected. The MS of the asphalt concrete at 17 °C (in laboratory environment temperature) was used as reference. The results showed that the MS of the asphalt core samples decreased 40.16% at 30 °C after 1.5 h and 62.39% after 6 h. At 40 °C the decrease was 74.31% after 1.5 h, and 78.10% after 6 h. At 50 °C the stability of the asphalt decreased 83.22% after 1.5 h, 88.66% after 6 h. The relationships between experimental results, fuzzy logic model and statistical results exhibited good correlation. The correlation coefficient was R = 0.99 for fuzzy logic model and R² = 0.9 for statistical method. Based on the results of the study, it could be said that both the fuzzy logic method and statistical methods could be used for modelling of the stability of asphalt concrete under varying temperature and exposure time.     

Tautomeric transformation of temozolomide,their proton affinities and chemical reactivities: A theoretical approach

The gas-phase geometry optimizations of bare, mono- and dihydrated complexes of temozolomide isomers were carried out using density functional calculation at the M06 − 2X/6 − 31 + G(d,p) level of the theory. The structures and protonation energies of protonated species of temozolomide are reported. Chemical indices of all isomers and protonated species are also reported. Energies, thermodynamic quantities, rate constants and equilibrium constants of tautomeric and rotameric transformations of all isomers I1 ↔ TZM ↔ HIa ↔ HIb ↔ I2 ↔ I3 in bare and hydrated systems were obtained.