Diagnosis of valvular heart disease through neural networks ensembles

In the last decades, several tools and various methodologies have been proposed by the researchers for developing effective medical decision support systems. Moreover, new methodologies and new tools are continued to develop and represent day by day. Diagnosing of the valvular heart disease is one of the important issue and many researchers investigated to develop intelligent medical decision support systems to improve the ability of the physicians. In this paper, we introduce a methodology which uses SAS Base Software 9.1.3 for diagnosing of the valvular heart disease. A neural networks ensemble method is in the centre of the proposed system. The ensemble-based methods creates new models by combining the posterior probabilities or the predicted values from multiple predecessor models. So, more effective models can be created. We performed experiments with proposed tool. We obtained 97.4% classification accuracy from the experiments made on data set containing 215 samples. We also obtained 100% and 96% sensitivity and specificity values, respectively, in valvular heart disease diagnosis.     

Prediction of protein cellular localization sites using a hybrid method based on artificial immune system and fuzzy k-NN algorithm

The use of artificial intelligence methods in biological data analysis has been increased recent since performance of the classification and detection systems have improved considerably to help medical experts in diagnosing. In this paper, we investigate the performance of an artificial immune system (AIS) based fuzzy k-NN algorithm with and without cross validation in a class of imbalanced problems in bioinformatics. Furthermore, we devise an unsupervised AIS algorithm in a supervised manner which contains a training stage for data reduction and a classification stage using fuzzy k-NN algorithm. The experiments show the efficacy of the proposed method with promising results. Using the Escherichia coli and yeast database, we compare the classification accuracy of the proposed method with those of other methods which have been proposed in the literature. The proposed hybrid system produced much more accurate results than the Horton and Nakai's method [P. Horton, K. Nakai, Better prediction of protein cellular localization sites with the k-nearest neighbors classifier, in: Proceedings of Intelligent Systems in Molecular Biology, Halkidiki, Greece, 1997, pp. 368–383]. Besides the improvement on the classification accuracy, one of the important aspects of the proposed method is the complexity. As the proposed AIS method incorporates data reduction in the training stage, the training complexity is considerably low comparing with the k-NN classifier.     

One-step preparation of poly(NIPAM-pyrrole) electroconductive composite hydrogel and its dielectric properties

Conductive polymers and hydrogels are two of the hot prospect polymer types that are used for new stimuli responsive materials. In this study, one-step preparation of electroconductive composite hydrogels containing polypyrrole (PPy) and N-isopropylacrylamide (NIPAM) using free radical polymerization technique was achieved with N,N-methylenebisacrylamide as a crosslinker and ammonium peroxy disulphate (APS) as initiator, in mixture of water/isopropyl alcohol. The equilibrium swelling degree of the poly(NIPAM)-pyrrole) electroconductive composite hydrogel was 9.88 g of H₂O/g dry polymer. According to TGA results, the thermal stability of the prepared composite poly(NIPAM-PPy) conductive hydrogel (700°C) hydrogel is higher than that of pure poly(NIPAM) hydrogel (600°C). Furthermore, prepared samples were characterized by FTIR, and SEM analyzes. Later, the samples were pressured into pellets so that electrical impedance spectroscopy (EIS) measurements were taken between 10 and 10 MHz at room temperature. The dielectric constant value of composite poly(NIPAM-PPy) hydrogel at 10 Hz is almost 10 times higher than that of poly(NIPAM) hydrogel. Both samples' real and imaginary parts of dielectric constant decreased with increased frequency. Samples exhibited non-Debye relaxation since experimental data fit into dielectric model of Havriliak-Negami. Moreover, low frequency data yielded d.c. conductivity of the pure and composite samples as 3.74 × 10⁻¹¹ and 1.02 × 10⁻⁸ S/cm, respectively. Real part of impedance at low frequencies also points out ~10³ times lower resistance values at 10 Hz for composite poly(NIPAM-PPy) hydrogel. Therefore, EIS results support that electroconductive composite hydrogel fabrication was achieved using free radical polymerization technique.     

Thermal and Mechanical Properties of Poly(arylene ether ketone)s Based on 5‐tert‐Butyl‐1,3‐bis(4‐fluorobenzoyl)benzene

An aromatic bishalide, 5‐tert‐butyl‐1,3‐bis(4‐fluorobenzoyl)benzene ( 2 ) was synthesized in high yield and purity by the reaction of 5‐tert‐butylisophthaloyl chloride ( 1 ) and fluorobenzene and polymerized by nucleophilic substitution reaction with commercially available aromatic bisphenols to prepare a series of high molecular weight poly(arylene ether ketone)s containing pendant tertiary butyl groups. The effect of molecular structure on the physical, thermal, mechanical and adhesion properties of the polymers was investigated.     

SILAR Controlled CdS Nanoparticles Sensitized CdO Diode Based Photodetectors

Silicon - In this research, we have produced Al/CdS nanoparticles-CdO/p-si/Al photodetetor and investigated its optical and electrical characteristics for various optoelectronic applications. The...     

Explainable,Domain-Adaptive,and Federated Artificial Intelligence in Medicine

Artificial intelligence(AI) continues to transform data analysis in many domains.Progress in each domain is driven by a growing body of annotated data,increased computational resources,and technological innovations.In medicine,the sensitivity of the data,the complexity of the tasks,the potentially high stakes,and a requirement of accountability give rise to a particular set of challenges.In this review,we focus on three key methodological approaches that address some of the particular challenges...     

One-Pot Synthesis of Poly(linoleic acid)-g-Poly(styrene)-g-Poly(ε-caprolactone) Graft Copolymers

One-pot synthesis of graft copolymers by ring-opening polymerization and free radical polymerization using polymeric linoleic acid peroxide (PLina) is reported. Graft copolymers having structures of poly(linoleic acid)-g-polystyrene-g-poly(ε-caprolactone) were synthesized from PLina, possessing peroxide groups on the main chain by the combination of free radical polymerization of styrene and ring-opening polymerization of ε-caprolactone in one-step. Principal parameters, such as monomer concentration, initiator concentration, and polymerization time, which effect the one-pot polymerization reactions were evaluated. The obtained graft copolymers were characterized by ¹H-NMR and DOSY-NMR spectroscopy, gel permeation chromatography, thermal gravimetric analysis and differential scanning calorimetry techniques.     

Effects of Mold Pressure on Mechanical, Microstructures, Oxidation Behavior, and Thermodynamic Properties of an Al-Based Alloy

In this study, the effects of mold pressure variation on the microstructure, mechanical, oxidation behavior, and thermodynamics properties of an AlSi12CuNi alloy have been investigated by means of optical microcopy, scanning electron microscopy, energy dispersive X-ray spectroscopy, X-ray diffraction, differential thermal analysis, and thermo-gravimetric analysis techniques. It is observed that hardness and tensile strength of the alloys increase as die-casting mold pressure increases due to an improvement in the distribution pattern of secondary phases and reduction in porosity. Oxidation behavior parameters and thermodynamic parameters such as formation enthalpy, heat capacity, and entropy are determined from TGA and DTA. It is found that mold pressure also has a significant effect on the oxidation behavior and thermodynamic parameters.     

Effect of nano-silica on the chemical durability and mechanical performance of fly ash based geopolymer concrete

In this study, the effect of nano silica on the short term severe durability performance of fly ash based geopolymer concrete (GPC) specimens was investigated. Four types of GPC were produced with two types of low calcium fly ashes (FAI and FAII) with and without nano silica, and ordinary Portland cement concrete (OPC) concrete was also cast for reference. For the geopolymerization process, the alkaline activator has selected a mixture of sodium silicate solution (Na₂SiO₃) and sodium hydroxide solution (NaOH) with a ratio (Na₂SiO₃/ NaOH) of 2.5. Main objectives of the study were to investigate the effect of usability or replaceability of nano silica-based low calcium fly ash based geopolymer concretes instead of OPC concrete in structural applications and make a contribution to standardization process of the fly ash based geopolymer concrete. To achieve the goals, four types of geopolymer and OPC concretes were subjected to sulfuric acid (H₂SO₄), magnesium sulfate (MgSO₄) and seawater (NaCl) solutions with concentrations of 5%, 5%, and 3.5%, respectively. Visual appearances and weight changes of the concretes under chemical environments were utilized for durability aspects. Compressive, splitting tensile and flexural strength tests were also performed on specimens to evaluate the mechanical performance under chemical environments. Results indicated that FAGPC concretes showed superior performance than OPC concrete under chemical attacks due to low calcium content. Amongst the chemical environments, sulfuric acid (H₂SO₄) was found to be the most dangerous environment for all concrete types. In addition, nano silica (NS) addition to FAGPC specimens improved both durability and residual mechanical strength due to the lower porosity and more dense structure. The FAIIGPC specimens including nano silica showed the superior mechanical performance under chemical environment.     

Hydrogen generation from sodium borohydride with Ni and Co based catalysts supported on Co3O4

Hydrogen is an alternative and clean energy carrier, but there are still some production related problems. In this aspect, it is crucial to efficiently generate hydrogen from hydrogen rich materials such as sodium borohydride. In this study, Co₃O₄ supported Ni and Co catalysts are synthesized via microwave irradiation technique for hydrogen generation from sodium borohydride. In this context, firstly, Co₃O₄ support material is synthesized by chemical method. Then, Ni and Co catalysts are decorated onto Co₃O₄ support material by microwave irradiation-polyol method. Prepared catalysts and support material are characterized by using X-ray diffraction (XRD), scanning electron microscopy (SEM), transmission electron microscopy (TEM), X-ray photoelectron spectroscopy (XPS) and inductively coupled plasma-mass spectrometer (ICP/MS). A new system is designed by our group in order to determine the activity of the prepared catalysts for hydrogen generation. The effects of different initial NaOH concentrations on hydrogen generation rate are investigated. It is observed that the rate of hydrogen generation increased with an increase in initial NaOH concentration. Co-Co₃O₄ catalyst at 10% NaOH initial concentration shows the highest hydrogen generation rate as 2823 ml/g_cat.min. In summary, Co-based catalysts are exhibited more activity than Ni-based catalysts in terms of hydrogen generation.