Deep Neural Networks Regularization Using a Combination of Sparsity Inducing Feature Selection Methods

Neural Processing Letters - Deep learning is an important subcategory of machine learning approaches in which there is a hope of replacing man-made features with fully automatic extracted features....     

Enhancing spatial and temporal utilities in differentially private moving objects database release

International Journal of Information Security - The pervasive use of mobile technologies and GPS-equipped vehicles has resulted in a large number of moving objects databases. Privacy protection is...     

Application of thermal ultrasound-assisted liquid–liquid micro-extraction coupled with HPLC-UV for rapid determination of synthetic phenolic antioxidants in edible oils

A simple, fast, and reliable liquid–liquid micro-extraction (LLME) method assisted by thermal ultrasound approach was developed for simultaneous determination of synthetic phenolic antioxidants (SPAs) in edible oils by high-performance liquid chromatography equipped with ultraviolet detector (HPLC-UV). The synthetic antioxidants were propyl gallate (PG), butylated hydroxyanisole (BHA), tert-butylhydroquinone (TBHQ), and butylated hydroxyltoluene (BHT). The best extraction conditions were observed were methanol/acetonitrile (1:1, v/v) as the solvent, ultrasound at 4 min, and a temperature of 40°C. The linearity of the calibration curves for the optimum conditions were R² > 0.989 for all of the SPAs in a range from 1–200 μg ml⁻¹. Relative standard deviation (RSD %) for five analysis was in range of 2.83% to 4.21%. Limit of detection (LOD) and limit of quantification (LOQ) were obtained in range of 0.012–0.06 and 0.04–0.2 μg g⁻¹, respectively. With regard to recovery, a range of 91%–116% was calculated for the spiked edible oils.     

Determination of stability constants of mercury(II) by garlic organosulfur ligands with differential pulse voltammetry

Journal of Applied Electrochemistry - In this work, interactions of mercury with di allyl disulfide (DADS), dimethyl disulfide (DMDS), and diallyl sulfide (DAS) were studied by differential pulse...     

MC-MLAS: Multi-channel Minimum Latency Aggregation Scheduling in Wireless Sensor Networks

Data aggregation is a key, yet time-consuming functionality in wireless sensor networks (WSNs). Multi-channel design is a promising technique to alleviate interference as a primary reason for long latency of TDMA aggregation scheduling. Indeed, it provides more potential of parallel transmissions over different frequency channels, thus minimizing time latency. In this paper, we focus on designing a multi-channel minimum latency aggregation scheduling protocol, named MC-MLAS, using a new joint approach for tree construction, channel assignment, and transmission scheduling. To our best knowledge, this is the first work in the literature which combines orthogonal channels and partially overlapping channels to consider the total latency involved in data aggregation. Extensive simulations verify the superiority of MC-MLAS in WSNs.     

Embedding linear arrays of the maximum length in O-shaped meshes

The Journal of Supercomputing - Embedding an interconnection network into another network is one of the important problems in parallel processing. In this paper, we study embedding of linear arrays...     

Adaptive neuro-fuzzy inference system multi-objective optimization using the genetic algorithm/singular value decomposition method for modelling the discharge coefficient in rectangular sharp-crested side weirs

In the present article, the adaptive neuro-fuzzy inference system (ANFIS) is employed to model the discharge coefficient in rectangular sharp-crested side weirs. The genetic algorithm (GA) is used for the optimum selection of membership functions, while the singular value decomposition (SVD) method helps in computing the linear parameters of the ANFIS results section (GA/SVD-ANFIS). The effect of each dimensionless parameter on discharge coefficient prediction is examined in five different models to conduct sensitivity analysis by applying the above-mentioned dimensionless parameters. Two different sets of experimental data are utilized to examine the models and obtain the best model. The study results indicate that the model designed through GA/SVD-ANFIS predicts the discharge coefficient with a good level of accuracy (mean absolute percentage error?=?3.362 and root mean square error?=?0.027). Moreover, comparing this method with existing equations and the multi-layer perceptron–artificial neural network (MLP-ANN) indicates that the GA/SVD-ANFIS method has superior performance in simulating the discharge coefficient of side weirs.     

Effects of Fe/SDS and Au nanoparticles on P. aeruginosa bacterial growth and biosurfactant production

The aim of this study was to evaluate the effects of iron (Fe)/SDS and gold (Au) nanoparticles on growth and biosurfactant production of Pseudomonas aeruginosa PBCC5. The concentrations of the nanoparticles used were 1, 500 and 1000 mg/l. In this research, the surface tension of biosurfactant, dry weight of biosurfactant and biomass, emulsification indexes (E₂₄) were measured and transmission electron microscopy analysis was used to monitor the nanoparticles. The test results showed that the effect of nanoparticles on the bacterial growth and biosurfactant production varied corresponding to the type and concentration of nanoparticles. Fe/SDS nanoparticles showed no bacterial toxicity when the concentration of nanoparticles was 1 mg/ml and increased the growth and biosurfactant production, 23.21 and 20.73%, respectively. While at higher concentrations (500, 1000 mg/l), the nanoparticles suppressed bacterial growth as well as biosurfactant production. Similarly, Au nanoparticles had no bacterial toxicity and also increased bacterial growth and biosurfactant production. The surface tensions of all samples decreased from 72 of distiled water to 32–35 mN/m.Inspec keywords: nanoparticles, iron, gold, nanofabrication, nanomedicine, surfactants, biomedical materials, surface tension, renewable materials, transmission electron microscopy, microorganismsOther keywords: Au nanoparticles, P. aeruginosa bacterial growth, biosurfactant production, Pseudomonas aeruginosa PBCC5, surface tension, biomass, emulsification indexes, dry weight, transmission electron microscopy, Fe‐SDS nanoparticles, distiled water, Fe, Au     

Vocal-based emotion recognition using random forests and decision tree

This paper proposes a new vocal-based emotion recognition method using random forests, where pairs of the features on the whole speech signal, namely, pitch, intensity, the first four formants, the first four formants bandwidths, mean autocorrelation, mean noise-to-harmonics ratio and standard deviation, are used in order to recognize the emotional state of a speaker. The proposed technique adopts random forests to represent the speech signals, along with the decision-trees approach, in order to classify them into different categories. The emotions are broadly categorised into the six groups, which are happiness, fear, sadness, neutral, surprise, and disgust. The Surrey Audio-Visual Expressed Emotion database is used. According to the experimental results using leave-one-out cross-validation, by means of combining the most significant prosodic features, the proposed method has an average recognition rate of \(66.28\%\), and at the highest level, the recognition rate of \(78\%\) has been obtained, which belongs to the happiness voice signals. The proposed method has \(13.78\%\) higher average recognition rate and \(28.1\%\) higher best recognition rate compared to the linear discriminant analysis as well as \(6.58\%\) higher average recognition rate than the deep neural networks results, both of which have been implemented on the same database.