Fuzzy functions with LSE

“Fuzzy Functions” are proposed to be determined by the least squares estimation (LSE) technique for the development of fuzzy system models. These functions, “Fuzzy Functions with LSE” are proposed as alternate representation and reasoning schemas to the fuzzy rule base approaches. These “Fuzzy Functions” can be more easily obtained and implemented by those who are not familiar with an in-depth knowledge of fuzzy theory. Working knowledge of a fuzzy clustering algorithm such as FCM or its variations would be sufficient to obtain membership values of input vectors. The membership values together with scalar input variables are then used by the LSE technique to determine “Fuzzy Functions” for each cluster identified by FCM. These functions are different from “Fuzzy Rule Base” approaches as well as “Fuzzy Regression” approaches. Various transformations of the membership values are included as new variables in addition to original selected scalar input variables; and at times, a logistic transformation of non-scalar original selected input variables may also be included as a new variable. A comparison of “Fuzzy Functions-LSE” with Ordinary Least Squares Estimation (OLSE)” approach show that “Fuzzy Function-LSE” provide better results in the order of 10% or better with respect to RMSE measure for both training and test cases of data sets.     

Identifying plant species using mid-wave infrared (2.5–6 μm) and thermal infrared (8–14 μm) emissivity spectra

Plant species discrimination using remote sensing is generally limited by the similarity of their reflectance spectra in the visible, NIR and SWIR domains. Laboratory measured emissivity spectra in the mid infrared (MIR; 2.5 μm–6 μm) and the thermal infrared (TIR; 8 μm–14 μm) domain of different plant species, however, reveal significant differences. It is anticipated that with the advances in airborne and space borne hyperspectral thermal sensors, differentiation between plant species may improve. The laboratory emissivity spectra of thirteen common broad leaved species, comprising 3024 spectral bands in the MIR and TIR, were analyzed. For each wavelength the differences between the species were tested for significance using the one way analysis of variance (ANOVA) with the post-hoc Tukey HSD test. The emissivity spectra of the analyzed species were found to be statistically different at various wavebands. Subsequently, six spectral bands were selected (based on the histogram of separable pairs of species for each waveband) to quantify the separability between each species pair based on the Jefferies Matusita (JM) distance. Out of 78 combinations, 76 pairs had a significantly different JM distance. This means that careful selection of hyperspectral bands in the MIR and TIR (2.5 μm–14 μm) results in reliable species discrimination.     

Bacillus subtilis: As an Efficient Bacterial Strain for the Reclamation of Water Loaded with Textile Azo Dye,Orange II

The azo dye orange II is used extensively in the textile sector for coloring fabrics. High concentrations of it are released into aqueous environments through textile effluents. Therefore, its removal from textile wastewater and effluents is necessary. Herein, initially, we tested 11 bacterial strains for their capabilities in the degradation of orange II dye. It was revealed in the preliminary data that B. subtilis can more potently degrade the selected dye, which was thus used in the subsequent experiments. To achieve maximum decolorization, the experimental conditions were optimized whereby maximum degradation was achieved at: a 25 ppm dye concentration, pH 7, a temperature of 35 °C, a 1000 mg/L concentration of glucose, a 1000 mg/L urea concentration, a 666.66 mg/L NaCl concentration, an incubation period of 3 days, and with hydroquinone as a redox mediator at a concentration of 66.66 mg/L. The effects of the interaction of the operational factors were further confirmed using response surface methodology, which revealed that at optimum conditions of pH 6.45, a dye concentration of 17.07 mg/L, and an incubation time of 9.96 h at 45.38 °C, the maximum degradation of orange II can be obtained at a desirability coefficient of 1, estimated using the central composite design (CCD). To understand the underlying principles of degradation of the metabolites in the aliquot mixture at the optimized condition, the study steps were extracted and analyzed using GC-MS(Gas Chromatography Mass Spectrometry), FTIR(Fourier Transform Infrared Spectroscopy), ¹H and carbon 13 NMR(Nuclear Magnetic Resonance Spectroscopy). The GC-MS pattern revealed that the original dye was degraded into o-xylene and naphthalene. Naphthalene was even obtained in a pure state through silica gel column isolation and confirmed using ¹H and ¹³C NMR spectroscopic analysis. Phytotoxicity tests on Vigna radiata were also conducted and the results confirmed that the dye metabolites were less toxic than the parent dye. These results emphasize that B. subtilis should be used as a potential strain for the bioremediation of textile effluents containing orange II and other toxic azo dyes.     

Rapid Proteomic Characterization of Bacteriocin-Producing Enterococcus faecium Strains from Foodstuffs

Enterococcus belongs to a group of microorganisms known as lactic acid bacteria (LAB), which constitute a broad heterogeneous group of generally food-grade microorganisms historically used in food preservation. Enterococci live as commensals of the gastrointestinal tract of warm-blooded animals, although they also are present in food of animal origin (milk, cheese, fermented sausages), vegetables, and plant materials because of their ability to survive heat treatments and adverse environmental conditions. The biotechnological traits of enterococci can be applied in the food industry; however, the emergence of enterococci as a cause of nosocomial infections makes their food status uncertain. Recent advances in high-throughput sequencing allow the subtyping of bacterial pathogens, but it cannot reflect the temporal dynamics and functional activities of microbiomes or bacterial isolates. Moreover, genetic analysis is based on sequence homologies, inferring functions from databases. Here, we used an end-to-end proteomic workflow to rapidly characterize two bacteriocin-producing Enterococcus faecium (Efm) strains. The proteome analysis was performed with liquid chromatography coupled to a trapped ion mobility spectrometry-time-of-flight mass spectrometry instrument (TimsTOF) for high-throughput and high-resolution characterization of bacterial proteins. Thus, we identified almost half of the proteins predicted in the bacterial genomes (>1100 unique proteins per isolate), including quantifying proteins conferring resistance to antibiotics, heavy metals, virulence factors, and bacteriocins. The obtained proteomes were annotated according to function, resulting in 22 complete KEGG metabolic pathway modules for both strains. The workflow used here successfully characterized these bacterial isolates and showed great promise for determining and optimizing the bioengineering and biotechnology properties of other LAB strains in the food industry.     

Deep features-based speech emotion recognition for smart affective services

Emotion recognition from speech signals is an interesting research with several applications like smart healthcare, autonomous voice response systems, assessing situational seriousness by caller affective state analysis in emergency centers, and other smart affective services. In this paper, we present a study of speech emotion recognition based on the features extracted from spectrograms using a deep convolutional neural network (CNN) with rectangular kernels. Typically, CNNs have square shaped kernels and pooling operators at various layers, which are suited for 2D image data. However, in case of spectrograms, the information is encoded in a slightly different manner. Time is represented along the x-axis and y-axis shows frequency of the speech signal, whereas, the amplitude is indicated by the intensity value in the spectrogram at a particular position. To analyze speech through spectrograms, we propose rectangular kernels of varying shapes and sizes, along with max pooling in rectangular neighborhoods, to extract discriminative features. The proposed scheme effectively learns discriminative features from speech spectrograms and performs better than many state-of-the-art techniques when evaluated its performance on Emo-DB and Korean speech dataset.

     

Isolation,purification, and antioxidant activities of polysaccharides from Ziziphus Jujuba cv. Muzao

In the present study, crude polysaccharides from Ziziphus Jujuba cv. Muzao were isolated and purified using DEAE cellulose-52 and Sephadex G-100 size-exclusion chromatography; four fractions were collected, namely GZMP-1, GZMP-2, GZMP-3, and GZMP-4. The molecular weights of these four fractions were measured to be 111.2, 95.1, 84.2, and 571.4 kDa, respectively, using high-performance gel permeation chromatography. Gas chromatography analysis of the monosaccharide composition confirmed that GZMP-1 was composed of rhamnose, arabinose, glucose, and galactose. Rhamnose, arabinose, and galactose were the main components present in GZMP-2 and GZMP-3, whereas GZMP-4 was composed of only rhamnose and arabinose. Scanning electron microscopy showed relatively smooth surfaces for GZMP-1 and GZMP-4, whereas GZMP-2 and GZMP-3 had more folds on their surfaces. Fourier transform infrared spectroscopy analyses indicated that GZMP-1 and ZMP mainly had α-type glycosidic linkages. The in vitro antioxidant activities of the polysaccharides revealed that jujube polysaccharides exhibit remarkable antioxidant activity, and can scavenge DPPH radical and OH radical in a concentration-dependent manner. The results of this work suggest that polysaccharides from Z. Jujuba cv. Muzao have potential to be used as functional food and in the development of natural antioxidant drug carriers.     

Radiation crosslinked polyvinyl alcohol/polyvinyl pyrrolidone/acrylic acid hydrogels: swelling,crosslinking and dye adsorption study

Iranian Polymer Journal - Hydrogels were produced from mixtures of polyvinyl alcohol (PVA), polyvinyl pyrrolidone (PVP), and acrylic acid (AAc) using γ-radiation at doses of 3, 7, and...