A framework for heading-guided recognition of human activity

A combined 2D, 3D approach is presented that allows for robust tracking of moving people and recognition of actions. It is assumed that the system observes multiple moving objects via a single, uncalibrated video camera. Low-level features are often insufficient for detection, segmentation, and tracking of non-rigid moving objects. Therefore, an improved mechanism is proposed that integrates low-level (image processing), mid-level (recursive 3D trajectory estimation), and high-level (action recognition) processes. A novel extended Kalman filter formulation is used in estimating the relative 3D motion trajectories up to a scale factor. The recursive estimation process provides a prediction and error measure that is exploited in higher-level stages of action recognition. Conversely, higher-level mechanisms provide feedback that allows the system to reliably segment and maintain the tracking of moving objects before, during, and after occlusion. Heading-guided recognition (HGR) is proposed as an efficient method for adaptive classification of activity. The HGR approach is demonstrated using “motion history images” that are then recognized via a mixture-of-Gaussians classifier. The system is tested in recognizing various dynamic human outdoor activities: running, walking, roller blading, and cycling. In addition, experiments with real and synthetic data sets are used to evaluate stability of the trajectory estimator with respect to noise.     

Two-point higher-order BVPs with singularities in phase variables

The existence of solutions for singular higher-order differential equations with the Lidstone or the (n,p) boundary conditions is proved. The right-hand sides of differential equations can have singularities in the zero value of their phase variables and so higher derivatives of solutions changing their signs can pass through these singularities. Proofs are based on the method of a priori estimates, the degree theory arguments and on Vitali's convergence theorem.     

Content-based audio classification and segmentation by using support vector machines

Content-based audio classification and segmentation is a basis for further audio/video analysis. In this paper, we present our work on audio segmentation and classification which employs support vector machines (SVMs). Five audio classes are considered in this paper: silence, music, background sound, pure speech, and non- pure speech which includes speech over music and speech over noise. A sound stream is segmented by classifying each sub-segment into one of these five classes. We have evaluated the performance of SVM on different audio type-pairs classification with testing unit of different- length and compared the performance of SVM, K-Nearest Neighbor (KNN), and Gaussian Mixture Model (GMM). We also evaluated the effectiveness of some new proposed features. Experiments on a database composed of about 4- hour audio data show that the proposed classifier is very efficient on audio classification and segmentation. It also shows the accuracy of the SVM-based method is much better than the method based on KNN and GMM.     

Parameter Estimation for Optimal Object Recognition: Theory and Application

Object recognition systems involve parameters such as thresholds, bounds and weights. These parameters have to be tuned before the system can perform successfully. A common practice is to choose such parameters manually on an ad hoc basis, which is a disadvantage. This paper presents a novel theory of parameter estimation for optimization-based object recognition where the optimal solution is defined as the global minimum of an energy function. The theory is based on supervised learning from examples. Correctness and instability are established as criteria for evaluating the estimated parameters. A correct estimate enables the labeling implied in each exemplary configuration to be encoded in a unique global energy minimum. The instability is the ease with which the minimum is replaced by a non-exemplary configuration after a perturbation. The optimal estimate minimizes the instability. Algorithms are presented for computing correct and minimal-instability estimates. The theory is applied to the parameter estimation for MRF-based recognition and promising results are obtained.     

Robust Estimation of Rotation Angles from Image Sequences Using the Annealing M-Estimator

A robust method is presented for computing rotation angles of image sequences from a set of corresponding points containing outliers. Assuming known rotation axis, a least-squares (LS) solution are derived to compute the rotation angle from a clean data set of point correspondences. Since clean data is not guaranteed, we introduce a robust solution, based on the M-estimator, to deal with outliers. Then we present an enhanced robust algorithm, called the annealing M-estimator (AM-estimator), for reliable robust estimation. The AM-estimator has several attractive advantages over the traditional M-estimator: By definition, the AM-estimator involves neither scale estimator nor free parameters and hence avoids instabilities therein. Algorithmically, it uses a deterministic annealing technique to approximate the global solution regardless of the initialization. Experimental results are presented to compare the performance of the LS, M- and AM-estimators for the angle estimation. Experiments show that in the presence of outliers, the M-estimator outperforms the LS estimator and the AM-estimator outperforms the M-estimator.     

Decoding Speech Prosody: Do Music Lessons Help?

Three experiments revealed that music lessons promote sensitivity to emotions conveyed by speech prosody. After hearing semantically neutral utterances spoken with emotional (i.e., happy, sad, fearful, or angry) prosody, or tone sequences that mimicked the utterances' prosody, participants identified the emotion conveyed. In Experiment 1 (n=20), musically trained adults performed better than untrained adults. In Experiment 2 (n=56), musically trained adults outperformed untrained adults at identifying sadness, fear, or neutral emotion. In Experiment 3 (n=43), 6-year-olds were tested after being randomly assigned to 1 year of keyboard, vocal, drama, or no lessons. The keyboard group performed equivalently to the drama group and better than the no-lessons group at identifying anger or fear. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Synthesis and testing of cellulose acetate nicotinate as adsorbent for rhodamine B dye

The esterification of cellulose hydroxyl groups with natural carboxylic acids in mild conditions represents an adequate pathway in obtaining cellulose derivatives with different useful properties. In this article, authors report the synthesis of new mixed ester of cellulose and cellulose acetate nicotinate (CAN) , in a homogenous medium using DMF as solvent, cellulose acetate (CA) as starting cellulosic material, and nicotinic acid as an esterification agent in the presence of p-toluenesulfonyl chloride and pyridine. FTIR and NMR techniques were used to prove the binding of nicotinoyl group at free hydroxyl groups of CA. The obtained CAN was electrospun by electrospinning technique to obtain adsorbent ultrafine fibers, evidenced by SEM images, with high specific surface area. Monolayer Langmuir and empirical Leundrich isotherms were used to assess the adsorption capacity for rhodamine B dye of electrospun CAN in comparison with that of electrospun CA used as starting material. Langmuir isotherm led to a better assessment of experimental data suggesting that the adsorption is mainly determined by hydrogen bonds formed between carboxylic OH hydrogen bonding donor and pyridine N hydrogen bonding acceptor. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136, 47772.     

Extraction,optimisation and characterisation of phenolics from Thymus vulgaris L.: phenolic content and profiles in relation to antioxidant,antidiabetic and antihypertensive properties

The objectives of this study were to examine varying extraction conditions of Thymus vulgaris L. as related to phenolic content and profiles of the extracts and their antioxidant, antihypertensive and antidiabetic properties. Phenolics were extracted under various conditions pertaining to free and bound phenolics, solvent type and combination of extraction time and temperature, and these extracts were evaluated in terms of their antioxidant activities and inhibitory activities of angiotensin‐converting enzyme (ACE), α‐glucosidase and α‐amylase. The acetone–water solvent mixture (1:1; v/v) produced the extract with the greatest phenolic content, antioxidant activity and inhibitory activities of ACE and α‐glucosidase. The optimal extraction temperature for maximum phenolic content and antioxidant activity associated with methanol extraction was 60 °C, whereas a lower temperature at 40 °C was required to maximise inhibitory activities for ACE, α‐glucosidase and α‐amylase. An inverse relationship was seen between antioxidant and glucosidase inhibitory activities vs. the ACE and α‐amylase inhibitory activities, which suggests the need for extractions to be directed to specific bioactivities of thyme extracts. Generally, the results indicate major differences in phenolic profiles among the tested extraction conditions with thymol as the predominant phenolic seen in most extractions, while gallic acid, rosmarinic acid or diosmin also predominated in other extracts. Extracts with the same predominant phenolic compound and similar phenolic content showed major disparities in their ACE, glucosidase and α‐amylase inhibitory activities, indicating that the major phenolic profiles of thyme extracts may not be necessarily related to the degree of inhibition of ACE, glucosidase and α‐amylase enzymes.     

Prediction of Transport Properties of Liquid Ammonia and Its Binary Mixture with Methanol by Molecular Simulation

Transport properties of ammonia and of the binary mixture ammonia + methanol are predicted for a broad range of liquid states by molecular dynamics (MD) simulation on the basis of rigid, non-polarizable molecular models of the united-atom type. These models were parameterized in preceding work using only experimental vapor-liquid equilibrium data. The self- and the Maxwell-Stefan (MS) diffusion coefficients as well as the shear viscosity are obtained by equilibrium MD and the Green-Kubo formalism. Non-equilibrium MD is used for the thermal conductivity. The transport properties of liquid ammonia are predicted for temperatures between 223 K and 473 K up to pressures of 200 MPa and are compared to experimental data and correlations thereof. Generally, good agreement is achieved. The predicted self-diffusion coefficient as well as the shear viscosity deviates on average by less than 15 % from the experiment and the thermal conductivity by less than 6 %. Furthermore, the self- and the MS transport diffusion coefficients as well as the shear viscosity of the liquid mixture ammonia + methanol are studied at different compositions and compared to the available experimental data.