Use of center of gravity with the common vector approach in isolated word recognition

In this paper, the subspace based classifier, common vector approach (CVA), with the center of gravity (COG) method is used for isolated word recognition. Since the CVA classifier is sensitive to shifts through the time axis, endpoint detection becomes extremely important for the recognition of isolated words. The COG method eliminates the need for endpoint detection. The effects of the COG method and a classical endpoint detection algorithm on the recognition rates of isolated words are investigated. The experimental results show that the COG method yields slightly higher recognition rates than the endpoint detection method in the TI-digit database when CVA is used.     

A new implementation of common matrix approach using third-order tensors for face recognition

In the classical common matrix approach (CMA), the common matrix for each individual face class is obtained using basis matrices calculated by Gram–Schmidt orthogonalization of the class covariance matrix. This common matrix represents the common or invariant properties of a given face class. The CMA idea relies on the concept of basis matrices of a face class which span the, so called, difference subspace of that class. In this paper, an alternative method to obtain the basis matrices for CMA is proposed. The basis matrices are obtained using the higher order singular value decomposition (HOSVD) of a third-order tensor constructed with face images and these basis matrices are utilized in the construction of CMA. In order to exemplify the improvements in the recognition rates, face recognition experiments are carried out via the AR face database. The original face matrices, as well as 2DPCA-, 2DSVD-, and 2DFDA-based feature matrices are applied as the input matrices for the two different implementations of CMA in the experimental studies. The results indicate that the recognition rates obtained by the proposed method are slightly higher than those obtained using the basis matrices calculated by Gram–Schmidt orthogonalization.     

Common vector approach and its combination with GMM for text-independent speaker recognition

In this paper, the common vector approach (CVA) is newly used for text-independent speaker recognition. The performance of CVA is compared with those of Fisher’s linear discriminant analysis (FLDA) and Gaussian mixture models (GMM). The recognition rates obtained for the TIMIT database indicate that CVA and GMM are superior to FLDA. However, while the recognition rates obtained from CVA and GMM are identical, CVA enjoys advantages in terms of processing power and memory requirement. In order to obtain better results than those achieved with GMM, a new method which is a combination of CVA and GMM is proposed in this paper.     

Functional Nanomaterials on 2D Surfaces and in 3D Nanocomposite Hydrogels for Biomedical Applications

An emerging approach to improve the physicobiochemical properties and the multifunctionality of biomaterials is to incorporate functional nanomaterials (NMs) onto 2D surfaces and into 3D hydrogel networks. This approach is starting to generate promising advanced functional materials such as self‐assembled monolayers (SAMs) and nanocomposite (NC) hydrogels of NMs with remarkable properties and tailored functionalities that are beneficial for a variety of biomedical applications, including tissue engineering, drug delivery, and developing biosensors. A wide range of NMs, such as carbon‐, metal‐, and silica‐based NMs, can be integrated into 2D and 3D biomaterial formulations due to their unique characteristics, such as magnetic properties, electrical properties, stimuli responsiveness, hydrophobicity/hydrophilicity, and chemical composition. The highly ordered nano‐ or microscale assemblies of NMs on surfaces alter the original properties of the NMs and add enhanced and/or synergetic and novel features to the final SAMs of the NM constructs. Furthermore, the incorporation of NMs into polymeric hydrogel networks reinforces the (soft) polymer matrix such that the formed NC hydrogels show extraordinary mechanical properties with superior biological properties.     

Electrical resistivity and thermal conductivity properties of graphene-coated woven fabrics

In this study, it was aimed to develop electrically and thermal conductive textiles surfaces. Pretreated polyester fabrics were coated with nano graphene powders at different concentration rates (50, 100, and 200 g/kg) by knife over roll technique. Electrical resistivity, thermal conductivity, thickness and mass per unit area measurements, bending rigidity, and abrasion resistance tests of coated fabrics were performed. Surface resistivity measurements of coated fabrics were made according to ASTM D 257 standard with Keithley 8009 Resistivity Test Fixture. Surface electrical resistivity values of coated fabrics decreased with increasing concentration rates. Of note, 2.53 × 10⁴ Ω/sq surface resistivity value was obtained at 200 g/kg graphene concentration rate. Thermal conductivity measurements of coated fabrics were made according to JIS R 2618 standard with Quick Thermal Conductivity Meter (QTM-710). Thermal conductivity property of fabrics improved depending on graphene concentration. The highest thermal conductivity value (0.4243 W/mK) was obtained at 200 g/kg graphene concentration rate. One of the most important results of the study was that a maximum weight loss of 0.40% was observed in the abrasion resistance test even after 100 000 cycles. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136, 48024.     

Biomethane production kinetics of rumen pretreated lignocellulosic wastes

Clean Technologies and Environmental Policy - Bioenergy production from lignocellulosic biomass is challenging due to its complex structure. Therefore, a pretreatment is required before methane...     

Reactive compatibilization of PLA/PBS bio-blends via a new generation of hybrid nanoparticles

Poly(butylene succinate) (PBS) is a worthy biodegradable thermoplastic polyester for blending along with other biopolymers, especially with poly (lactic acid) (PLA), to overcome its inadequacies in mechanical and thermal characteristics. Since binary blends of PLA and PBS showed that they are incompatible, compatibilization is required. In this work, multi-epoxide polyhedral oligomeric silsesquioxane (Glycidyl POSS) was added to PLA and PBS using the melt blending method to make them compatible. The blends were prepared at different weight ratios having different amounts of compatibilizer. SEM analysis showed that the Glycidyl POSS impacted the interfacial adhesion and other properties of PLA and PBS blends. Noticeable improvements in mechanical properties were revealed by tensile and impact test results. Tensile strength and Young's modulus were improved when epoxy-POSS was added up to 1 and 3 wt% into ternary blends, but further increasing POSS concentrations resulted in lower values. FTIR analysis showed a strong interaction between the epoxide group of POSS and the end groups of PBS or PLA. The thermal properties of samples were analyzed using differential scanning calorimetry (DSC) and thermogravimetric analysis (TGA), respectively. The shifts in glass transition temperatures of the PLA phase towards lower values appeared in DSC, confirming the enhanced compatibility of PLA and PBS. Also, the reinforcing ability of the POSS inorganic core structure impacted the thermal stability of the blends.     

Biocomposite scaffolds for 3D cell culture: Propolis enriched polyvinyl alcohol nanofibers favoring cell adhesion

The objective of this work is generation of propolis/polyvinyl alcohol (PVA) scaffold by electrospinning for 3D cell culture. Here, PVA used as co-spinning agent since propolis alone cannot be easily processed by electrospinning methodology. Propolis takes charge in maximizing biological aspect of scaffold to facilitate cell attachment and proliferation. Morphological analysis showed size of the electrospun nanofibers varied between 172–523 nm and 345–687 nm in diameter, for non-crosslinked and crosslinked scaffolds, respectively. Incorporation of propolis resulted in desired surface properties of hybrid matrix, where hybrid scaffolds highly favored protein adsorption. To examine cell compatibility, NIH-3T3 and HeLa cells were seeded on propolis/PVA hybrid scaffold. Results confirmed that integration of propolis supported cell adhesion and cell proliferation. Also, results indicated electrospun propolis/PVA hybrid scaffold provide suitable microenvironment for cell culturing. Therefore, developed hybrid scaffold could be considered as potential candidate for 3D cell culture and tissue engineering.     

Automatic writer identification from text line images

In the present article, new techniques have been introduced for revealing the individual features of a person??s handwriting pattern from the scanned images of handwritten text lines to facilitate text-independent writer identification. These techniques are aimed at designing a dynamic model which can be formalized according to any handwritten text line. Various combinations of the extracted features are applied to three well known classifiers for evaluating the contribution of features to define the correct identification rate. The K-NN, GMM, and Normal Density Discriminant Function Bayes classifiers are used in the present identification model. The experimental studies are conducted using two datasets obtained from the IAM database. The first dataset has already been proposed and used in the literature, whereas the second dataset is an expanded version of the first dataset and has been constituted for the first time in this study to analyze the performance of the extracted features under conditions such as an increased number of writers to discriminate in the database and a decreased number of text lines per writer. The remarkable identification rates obtained from the three classifiers on both datasets clearly indicate that the proposed feature extraction techniques can be effectively used in writer identification systems.