Type 2 Diabetes Risk Prediction Using Deep Convolutional Neural Network Based-Bayesian Optimization

Diabetes mellitus is a long-term condition characterized by hyperglycemia. It could lead to plenty of difficulties. According to rising morbidity in recent years, the world’s diabetic patients will exceed 642 million by 2040, implying that one out of every ten persons will be diabetic. There is no doubt that this startling figure requires immediate attention from industry and academia to promote innovation and growth in diabetes risk prediction to save individuals’ lives. Due to its rapid development, deep learning (DL) was used to predict numerous diseases. However, DL methods still suffer from their limited prediction performance due to the hyperparameters selection and parameters optimization. Therefore, the selection of hyper-parameters is critical in improving classification performance. This study presents Convolutional Neural Network (CNN) that has achieved remarkable results in many medical domains where the Bayesian optimization algorithm (BOA) has been employed for hyperparameters selection and parameters optimization. Two issues have been investigated and solved during the experiment to enhance the results. The first is the dataset class imbalance, which is solved using Synthetic Minority Oversampling Technique (SMOTE) technique. The second issue is the model's poor performance, which has been solved using the Bayesian optimization algorithm. The findings indicate that the Bayesian based-CNN model superbases all the state-of-the-art models in the literature with an accuracy of 89.36%, F1-score of 0.88.6, and Matthews Correlation Coefficient (MCC) of 0.88.6.     

Rheological properties of poly(vinyl chloride) / epoxidized natural rubber blends. Part II: The effect of processing variables

The effect of processing variables on the rheological properties of PVC/ENR blends was investigated. The role of crosslinking in determining the flow behavior of blends was also examined by means of dynamically cured blends. It was found that PVC/ENR blends yield melts that are power law fluids. The flow of the melts improves with an increase in temperature and shear rate. However, the introduction of crosslinks reverses this trend, although under more rigorous conditions, the influence of crosslinks is superseded, and subsequently, flow becomes shear rate and temperature dependent. PVC/ENR systems also manifested elastic phenomena. The dependence of the elastic phenomena such as die swell and melt fracture on L/D ratio of the die was demonstrated.     

Nanovesicles Based on Mixtures of a Biantennary Glycolipid with Ionic Co‐Surfactants

A biantennary surfactant based on a synthetic C₁₆‐maltoside was chosen to prepare vesicles for a potential vesicular drug delivery system. The synthesis comprised of three stages: Initial synthesis of β‐d ‐maltose octaacetate was followed by glycosidation of 2‐hexyl‐decanol and final glycolipid deacetylation. Both α‐ and β‐anomers were prepared and their anomeric purity was evaluated by ¹H NMR. Owing to the low water solubility of the glycolipid, addition of ionic co‐surfactants was believed to promote the surfactant distribution, thus leading to smaller and more uniform vesicles. The assembly behavior of the surfactant systems was studied by contact penetration under an optical polarizing microscope, while interfacial properties were determined by surface tension measurements. Vesicles were prepared by injection of an ethanolic solution into bulk water and investigated by dynamic light scattering and field emission scanning electron microscopy. Contact of the surfactant mixtures with water indicated a high tendency to exhibit the lamellar phase and confirmed the expected low molecular solubility. These findings suggest a potential of the surfactant to form stable vesicles. Injection of an ethanolic surfactant solution into bulk water gave sub‐micrometer sized vesicles with a narrow size distribution. Application of ionic co‐surfactants reduced the vesicle size. In particular ～20 % of anionic SDS proved highly effective, lowering the vesicle size by nearly one decade, thus accessing nano‐sized vesicles. Encapsulation of a water‐soluble drug was achieved in a 76 ± 10 % efficiency.     

Growth mechanisms of MgO nanocrystals via a sol-gel synthesis using different complexing agents

In the preparation of nanostructured materials, it is important to optimize synthesis parameters in order to obtain the desired material. This work investigates the role of complexing agents, oxalic acid and tartaric acid, in the production of MgO nanocrystals. Results from simultaneous thermogravimetric analysis (STA) show that the two different synthesis routes yield precursors with different thermal profiles. It is found that the thermal profiles of the precursors can reveal the effects of crystal growth during thermal annealing. X-ray diffraction confirms that the final products are pure, single phase and of cubic shape. It is also found that complexing agents can affect the rate of crystal growth. The structures of the oxalic acid and tartaric acid as well as the complexation sites play very important roles in the formation of the nanocrystals. The complexing agents influence the rate of growth which affects the final crystallite size of the materials. Surprisingly, it is also found that oxalic acid and tartaric acid act as surfactants inhibiting crystal growth even at a high temperature of 950°C and a long annealing time of 36 h. The crystallite formation routes are proposed to be via linear and branched polymer networks due to the different structures of the complexing agents.     

Inverted organic photovoltaic device with a new electron transport layer

We demonstrate that there is a new solution-processed electron transport layer, lithium-doped zinc oxide (LZO), with high-performance inverted organic photovoltaic device. The device exhibits a fill factor of 68.58%, an open circuit voltage of 0.86 V, a short-circuit current density of −9.35 cm/mA² along with 5.49% power conversion efficiency. In addition, we studied the performance of blend ratio dependence on inverted organic photovoltaics. Our device also demonstrates a long stability shelf life over 4 weeks in air.     

Molecular Characterization of α- and β-Thalassaemia among Malay Patients

Both α- and β-thalassaemia syndromes are public health problems in the multi-ethnic population of Malaysia. To molecularly characterise the α- and β-thalassaemia deletions and mutations among Malays from Penang, Gap-PCR and multiplexed amplification refractory mutation systems were used to study 13 α-thalassaemia determinants and 20 β-thalassaemia mutations in 28 and 40 unrelated Malays, respectively. Four α-thalassaemia deletions and mutations were demonstrated. −−^SEA deletion and α^CSα accounted for more than 70% of the α-thalassaemia alleles. Out of the 20 β-thalassaemia alleles studied, nine different β-thalassaemia mutations were identified of which β^E accounted for more than 40%. We concluded that the highest prevalence of (α- and β-thalassaemia alleles in the Malays from Penang are −−^SEA deletion and β^E mutation, respectively.     

Toxicity and Metabolism of Layered Double Hydroxide Intercalated with Levodopa in a Parkinson’s Disease Model

Layered hydroxide nanoparticles are generally biocompatible, and less toxic than most inorganic nanoparticles, making them an acceptable alternative drug delivery system. Due to growing concern over animal welfare and the expense of in vivo experiments both the public and the government are interested to find alternatives to animal testing. The toxicity potential of zinc aluminum layered hydroxide (ZAL) nanocomposite containing anti-Parkinsonian agent may be determined using a PC 12 cell model. ZAL nanocomposite demonstrated a decreased cytotoxic effect when compared to levodopa on PC12 cells with more than 80% cell viability at 100 μg/mL compared to less than 20% cell viability in a direct levodopa exposure. Neither levodopa-loaded nanocomposite nor the un-intercalated nanocomposite disturbed the cytoskeletal structure of the neurogenic cells at their IC₅₀ concentration. Levodopa metabolite (HVA) released from the nanocomposite demonstrated the slow sustained and controlled release character of layered hydroxide nanoparticles unlike the burst uptake and release system shown with pure levodopa treatment.     

An Insight View on Synthetic Protocol,Surface Activity,and Biological Aspects of Novel Biocompatible Quaternary Ammonium Cationic Gemini Surfactants

In this study, we prepared a novel series of diester-functionalized cationic gemini surfactants (C_m-E2O2-C_m) containing ethylene oxide as a spacer with varying alkyl chain lengths and characterized by ¹H NMR, FT-IR, elemental analysis, and ESI-MS. The physicochemical properties of the geminis were explored by tensiometry, fluorescence, dye solubilization, and Krafft point. These geminis acquire superior surface activity than the conventional surfactants. Fluorescence spectroscopy analysis affirmed that the micropolarity and aggregation number of micelles diminished with increase in the alkyl chain length. These geminis represent a new group of amphiphiles of considerably high biodegradability, better cleavability, and low toxicity as assessed by BOD test, FT-IR analysis, and HC₅₀ analysis, respectively. They also showed significant level of antimicrobial activity toward some specified bacterial strains of Gram-positive and Gram-negative by using agar well diffusion method. Furthermore, the thermogravimetric analysis provided information regarding thermal stabilities of the newly synthesized gemini surfactants.     

Peak‐to‐average power ratio reduction and digital predistortion effects in power amplifiers in OFDM system

In this paper, the effects of peak‐to‐average power ratio reduction in nonlinear power amplifiers (PAs) by considering memory effects and of digital predistortion are investigated. A new predistortion technique is proposed, which is called the complex gain memory predistortion (CGMP) method. The CGMP is applied to compensate the dynamic memory effects of PAs. The conventional partial transmit sequence method is applied for peak‐to‐average power ratio reduction, and combining it with the CGMP results in efficiency enhancement and spectrum efficiency improvement. Simulation and results are examined with the two types of PAs and with an OFDM signal with quadrature phase‐shift keying modulation. Copyright © 2011 John Wiley & Sons, Ltd.     

Proton exchange membranes prepared by simultaneous radiation grafting of styrene onto poly(tetrafluoroethylene‐co‐hexafluoropropylene) films. I. Effect of grafting conditions

The simultaneous radiation grafting of styrene onto poly(tetrafluoroethylene‐co‐hexafluoropropylene) (FEP) films was studied at room temperature. The effects of grafting conditions (type of solvent, irradiation dose, dose rate, and monomer concentration) were investigated. The degree of grafting was found to be dependent on the investigated grafting conditions. The dependence of the initial rate of grafting on the dose rate and the monomer concentration was found to be of 0.5 and 1.3 orders, respectively. The results suggest that grafting proceeds by the so‐called front mechanism in which the grafting front starts at the surface of the film and moves internally toward the middle of the film by successive diffusion of styrene through the grafted layers. Some selected properties of the grafted films were evaluated in correlation with the degree of grafting. We found that the grafted FEP films possess good mechanical stability, which encourages their use for the preparation of proton exchange membranes. © 2000 John Wiley & Sons, Inc. J Appl Polym Sci 76: 220–227, 2000