An automated decision-support system for non-proliferative diabetic retinopathy disease based on MAs and HAs detection

Diabetic retinopathy (DR) has become a serious threat in our society, which causes 45% of the legal blindness in diabetes patients. Early detection as well as the periodic screening of DR helps in reducing the progress of this disease and in preventing the subsequent loss of visual capability. This paper provides an automated diagnosis system for DR integrated with a user-friendly interface. The grading of the severity level of DR is based on detecting and analyzing the early clinical signs associated with the disease, such as microaneurysms (MAs) and hemorrhages (HAs). The system extracts some retinal features, such as optic disc, fovea, and retinal tissue for easier segmentation of dark spot lesions in the fundus images. That is followed by the classification of the correctly segmented spots into MAs and HAs. Based on the number and location of MAs and HAs, the system quantifies the severity level of DR. A database of 98 color images is used in order to evaluate the performance of the developed system. From the experimental results, it is found that the proposed system achieves 84.31% and 87.53% values in terms of sensitivity for the detection of MAs and HAs respectively. In terms of specificity, the system achieves 93.63% and 95.08% values for the detection of MAs and HAs respectively. Also, the proposed system achieves 68.98% and 74.91% values in terms of kappa coefficient for the detection of MAs and HAs respectively. Moreover, the system yields sensitivity and specificity values of 89.47% and 95.65% for the classification of DR versus normal.     

An intelligent IoT with cloud centric medical decision support system for chronic kidney disease prediction

At present days, Internet of Things (IoT) and cloud platforms become widely used in various healthcare applications. The enormous quantity of data produced by the IoT devices in the healthcare sector can be examined on the cloud platform instead of dependent on restricted storage and computation resources exist in the mobile gadgets. For offering effective medicinal services, in this article, an online medical decision support system (OMDSS) is introduced for chronic kidney disease (CKD) prediction. The presented model involves a set of stages namely data gathering, preprocessing, and classification of medical data for the prediction of CKD. For classification, logistic regression (LR) model is applied for classifying the data instances into CKD and non-CKD. In addition, for tuning the parameters of LR, Adaptive Moment Estimation (Adam), and adaptive learning rate optimization algorithm is applied. The performance of the introduced model is examined using a benchmark CKD dataset. The experimental outcome observed the superior characteristics of the presented model on the applied dataset.     

Drag on ensembles of fluid spheres translating in a power-law liquid at moderate Reynolds numbers

This work elucidates the role of power-law rheology on the sedimentation velocity of an ensemble of mono-size spherical Newtonian droplets (free from surfactants) translating in a power-law continuous phase numerically by solving the momentum equations of both phases. A simple sphere-in-sphere cell model has been used to account for inter-drop interactions. In particular, in this study, the effects of the Reynolds number (Re_o), the internal to external fluid characteristic viscosity ratio (k), the volume fraction of the dispersed phase (Φ) and the power-law index of the continuous phase (n_o) on the external flow field, pressure drag (C_dp), friction drag (C_df) and total drag (C_d) coefficients have been analyzed over wide ranges of parameters as follows: 1 ≤ Re_o ≤ 200, 0.1 ≤ k ≤ 50, 0.2 ≤ Φ ≤ 0.6 and 0.6 ≤ n_o ≤ 1.6. Based on the extensive numerical results obtained in this work, a simple predictive correlation has been proposed for the total drag coefficient, which can be used to predict the rate of sedimentation of ensembles of Newtonian fluid spheres in power-law liquids in a new application.     

Mass transfer from a single fluid sphere to power-law liquids at moderate Reynolds numbers

The steady-state convective inter-phase mass transfer from a single Newtonian fluid sphere (free from surfactants) to a continuous phase with power-law viscosity has been studied at moderate Reynolds and Schmidt numbers under the conditions when the resistance to mass transfer in the dispersed phase is negligible. The species continuity equation, segregated from the momentum equations of both phases, has been numerically solved using a finite difference method. The effects of the Reynolds number (Re_o), power-law index (n_o), internal to external fluid characteristic viscosity ratio (k) and Schmidt number (Sc) on the local and average Sherwood number (Sh) have been analysed over the following ranges of conditions: 5?Re_o?200, 0.6?n_o?1.6, 0.1?k?50 and 1?Sc?1000. It has been observed that irrespective of the values of the Reynolds number and of the power-law index, as the value of k increases the average Sherwood number decreases for intermediate to large values of the Peclet number. As the value of the power-law index increases, the rate of mass transfer decreases for all values of the Reynolds number and the characteristic viscosity ratio thereby suggesting that shear-thinning behaviour facilitates mass transfer, whereas shear-thickening behaviour impedes it. Based on the present numerical results, a simple predictive correlation is proposed which can be used to estimate the rate of inter-phase mass transfer of a fluid sphere sedimenting in power-law liquids.     

Ultrasonic welding of thermoplastics in the near-field

Ultrasonic welding is one of the most popular techniques for joining thermoplastics because it is fast, economical, and easily automated. In near-field ultrasonic welding, the distance between the horn and the joint interface is 6 mm or less. This study investigated the near-field ultrasonic welding of amorphous (acrylonitrile-butadiene-styrene and polystyrene) and semicrystalline (polyethylene and polypropylene) polymers. High frequency ultrasonic wave propagation and attenuation measurements were made in order to estimate the dynamic mechanical moduli of the polymers. The estimated moduli were entered into a lumped parameter model in order to predict heating rates and energy dissipation. Experimental results showed that variations in the welding pressure had little effect on energy dissipation or joint strength; Increasing the amplitude of vibration increased the energy dissipation and the weld strength. For the semicrystalline polymers, increasing the weld time improved strength up to weld times greater than 1.5 s, where strength leveled off. For the amorphous polymers, the weld strength increased with Increasing weld time up to times of 0.8 s; for longer weld times, the power required was too high, causing overloading of the welder. Monitoring of the energy dissipation and static displacement or collapse provided valuable information on weld quality.     

Effect of baffles on a partially filled cubic tank: Numerical simulation and experimental validation

In this paper, sloshing waves have been analyzed for baffled and un-baffled tanks. Numerical simulations were carried out based on volume of fluid (VOF) techniques with arbitrary-Lagrangian–Eulerian (ALE) formulation which adopts the displacement of solid, the pressure and displacement in the fluid as variables to model the coupled system. The response of the coupled system is obtained by using the well-known software ADINA, which offers efficient fully coupled fluid–structure interaction capabilities by finite element method. The results obtained are compared with the available experimental data to demonstrate the reduction of sloshing effects in fluid model.     

Performance Optimization of Video Coding Process on Multi-Core Platform Using Gop Level Parallelism

High definition video applications often require heavy computation, high bandwidth and high memory requirements which make their real-time implementation difficult. Multi-core architecture with parallelism provides new solutions to implementing complex multimedia applications in real-time. It is well-known that the speed of the H.264 encoder can be increased on a multi-core architecture using the parallelism concept. Most of the parallelization methods proposed earlier for these purposes suffer from the drawbacks of limited scalability and data dependency. In this paper, we present a result obtained using data-level parallelism at the Group-Of-Pictures (GOP) level for the video encoder. The proposed technique involves each GOP being encoded independently and implemented on JM 18.0 using advanced data structures and OpenMP programming techniques. The performance of the parallelized video encoder is evaluated for various resolutions based on the parameters such as encoding speed, bit rate, memory requirements and PSNR. The results show that with GOP level parallelism, very high speed up values can be achieved without much degradation in the video quality.     

Vibration analysis of steam turbine discsSchwingungsanalyse von dampfturbinenräder

A knowledge of the vibration characteristics of discs of steam turbines is a prerequisite for a successful design of the turbine. As a matter of fact, considerable research effort, both theoretical and experimental, has been directed towards understanding the dynamic behaviour of blades and discs taken singly and jointly. This paper presents a theoretical analysis of the vibration characteristics of a steam turbine disc. In particular, the Runge—Kutta method has been used to solve the differential equation governing the flexural oscillations of the disc. Numerical results evaluated for a typical disc are presented.     

Performance evaluation of a small scale indirect solar dryer with static reflectors during non-summer months in the Saurashtra region of western India

This paper reports the design and development of an indirect, natural convection batch-type solar dryer fitted with North–South reflectors. With the help of the reflectors the collector efficiency without load was enhanced from 40.0% to 58.5% under peak solar irradiation conditions during a typical day in January in Bhavnagar, Gujarat, India. The corresponding computed values based on heat transfer equations were 36.5% and 50.3%. The desired extent of drying (ca. 12%, wet basis) of ‘papad’ – a popular Indian wafer – could be achieved within 5 h in this static dryer having 1.8 m² area of the collector and computed loading capacity of 3.46 kg. The initial and average values of the drying efficiency were 16.3% and 4.1%, respectively. The drying performance data could be fitted to the diffusivity equation with effective diffusivity value of 3.9 × 10⁻⁹ m² s⁻¹. Despite the high collector efficiency achieved, the average drying efficiency was low on account of under-loading of the dryer, as evident from the increase in drying efficiency to 13% in a smaller dryer loaded with the same amount of wet papad.