An effective deep learning model for grading abnormalities in retinal fundus images using variational auto-encoders

Diabetic retinopathy (DR) and Diabetic Macular Edema (DME) are severe diseases that affect the eyes due to damage in blood vessels. Computer-aided automated grading will help clinicians conduct disease diagnoses at ease. Experiments of automated image processing with deep learning techniques using CNN produce promising results, especially in the medical imaging domain. However, the disease grading tasks in retinal images using CNN struggle to retain high-quality information at the output. A novel deep learning model based on variational auto-encoder to grade DR and DME abnormalities in retinal images is proposed. The objective of the proposed model is to extract the most relevant retinal image features efficiently. It focuses on addressing less relevant candidate region generation and translational invariance present in images. The experiments are conducted in IDRID dataset and evaluated using accuracy, U-kappa, sensitivity, specificity and precision metrics. The results outperform compared with other state-of-art techniques.     

A new robust reference watermarking scheme based on DWT-SVD

This paper presents a new semi-blind reference watermarking scheme based on discrete wavelet transform(DWT) and singular value decomposition(SVD) for copyright protection and authenticity. We are using a gray scale logo image as watermark instead of randomly generated Gaussian noise type watermark. For watermark embedding, the original image is transformed into wavelet domain and a reference sub-image is formed using directive contrast and wavelet coefficients. We embed watermark into reference image by modifying the singular values of reference image using the singular values of the watermark. A reliable watermark extraction scheme is developed for the extraction of watermark from distorted image. Experimental evaluation demonstrates that the proposed scheme is able to withstand a variety of attacks. We show that the proposed scheme also stands with the ambiguity attack also.     

A constrained non-linear optimization model for fuzzy pairwise comparison matrices using teaching learning based optimization

Non-linear optimization models have been recently proposed to derive crisp weights from fuzzy pairwise comparison matrices. In this paper, a TLBO (Teaching Learning Based Optimization) based solution is presented for solving an optimization model as a system of non-linear equations to derive crisp weights from fuzzy pairwise comparison matrices in AHP (Analytic Hierarchy Process). This fuzzy-AHP method is named as TLBO-1. It has been found that TLBO-1 can lead to inconsistent or less consistent weights. To solve the problem of inconsistent weights, a new constrained non-linear optimization model is proposed in this paper. This model is based on the min-max approach for fuzzy pairwise comparison ratios of weights. TLBO is again used to solve this optimization model, and crisp weights are derived. This fuzzy AHP method is named as TLBO-2. The effectiveness of the proposed model is illustrated by three examples. For each example, the consistency of the derived crisp weights is compared with other optimization models. The results show that the TLBO-2 method can derive more consistent weights for the fuzzy AHP based Multi-Criteria Decision Making (MCDM) systems as compared to the other optimization models.     

Routing on Meshes with Buses

We consider the problem of routing packets on an MIMD mesh-connected array of processors augmented with row and column buses. We give lower bounds and randomized algorithms for the problem of routing k-permutations (where each processor is the source and destination of exactly k packets) on a d-dimensional mesh with buses, which we call the (k,d)-routing problem. We give a general class of ``hard' permutations which we use to prove lower bounds for the (k,d)-routing problem, for all k,d≥ 1. For the (1,1)- and (1,2)-routing problems the worst-case permutations from this class are identical to ones published by other authors, as are the resulting lower bounds. However, we further show that the (1,d)-routing problem requires 0.72 ... n steps for d=3, 0.76 ... n steps for d=4, and slightly more than steps for all d≥ 5. We also obtain new lower bounds for the (k,d)-routing problem for k,d > 1, which improve on the bisection lower bound in some cases. These lower bounds hold for off-line routing as well. We develop efficient algorithms for the (k,1)-routing problem and for the problem of routing k-randomizations (where each processor has k packets initially and each packet is routed to a random destination) on the one-dimensional mesh and use them in a general (k,d)-routing algorithm which improves considerably on previous results. In particular, the routing time for the (1,d)-routing problem is bounded by steps with high probability (whp), whenever for some constant ε > 0, and the routing time for the (k,d)-routing problem is steps whp whenever for some constant ε > 0 and k≥ 3.6 ... d, matching the bisection lower bound. We then present a simple algorithm for the (2,2)-routing problem running in 1.39 ... n+o(n) steps whp. Finally, for the important special case of routing permutations on two-dimensional meshes with buses, the (1,2)-routing problem, we give a more sophisticated algorithm that runs in 0.78 ... n+o(n) steps whp. Received May 18, 1994; revised June 23, 1995.     

Analgesic Effect of Tranilast in an Animal Model of Neuropathic Pain and Its Role in the Regulation of Tetrahydrobiopterin Synthesis

Trigeminal neuralgia is unilateral, lancinating, episodic pain that can be provoked by routine activities. Anticonvulsants, such as carbamazepine, are the drugs of choice; however, these possess side-effects. Microvascular decompression is the most effective surgical technique with a higher success rate, although occasionally causes adverse effects. The potential treatment for this type of pain remains unmet. Increased tetrahydrobiopterin (BH4) levels have been reported in association with axonal injury. This study aimed to evaluate the effect of tranilast on relieving neuropathic pain in animal models and analyze the changes in BH4 synthesis. Neuropathic pain was induced via infraorbital nerve constriction. Tranilast, carbamazepine, or saline was injected intraperitoneally to assess the rat’s post-intervention pain response. In the von Frey’s test, the tranilast and carbamazepine groups showed significant changes in the head withdrawal threshold in the ipsilateral whisker pad area. The motor coordination test showed no changes in the tranilast group, whereas the carbamazepine group showed decreased performance, indicating impaired motor coordination. Trigeminal ganglion tissues were used for the PCR array analysis of genes that regulate the BH4 pathway. Downregulation of the sepiapterin reductase (Spr) and aldoketo reductase (Akr) genes after tranilast injection was observed compared to the pain model. These findings suggest that tranilast effectively treats neuropathic pain.     

Revisiting Stress Corrosion Cracking of Steel in Caustic Solutions for Developing Cracking Susceptibility Diagrams for Improved Applicability

Stress corrosion cracking tests were conducted using Bayer solutions of different chemistry at different temperatures for extraction of alumina from bauxite ores. The validity of the commonly used caustic cracking susceptibility (CS) diagram for steels exposed to plain caustic solutions was assessed by testing the notched and precracked specimens. This study presents first results toward the development of a model susceptibility diagram for actual Bayer solutions, and for improved applicability of the traditional plain caustic diagram. For mechanistic understanding of caustic cracking, tests were also carried out under imposed electrochemical conditions.     

How do the plants used in phytoremediation in constructed wetlands,a sustainable remediation strategy,perform in heavy‐metal‐contaminated mine sites?

This review draws on knowledge for the treatment of heavy‐metal leachate in contaminated mine sites. Mine waste rock dumps and tailings generate a continuous stream of metalliferous and saline leachate over the long term. The mining industry has many legacy sites, which have compromised aquatic ecosystems and groundwater because of heavy‐metal contamination. Chemical and engineering methods are available and have been extensively utilised. However, these methods require intensive energy and often produce substantial volumes of secondary waste. We therefore argue in favour of phytoremediation as a sustainable remediation strategy leading towards efficient and sustainable metal removal and immobilisation through constructed wetlands.     

On the computer simulation of the P–C isotherms of ZrFe2 type hydrogen storage materials

This paper deals with computer simulation of the P–C isotherms of some ZrFe₂ type (Zr(Fe_1−xCr_x)₂, Zr_1−xTi_xFe_1.4Cr_0.6, Zr_1−2xMm_xTi_xFe_1.4Cr_0.6 : x00.4) of hydrogen storage materials. A feasible mathematical model has been developed to simulate the P–C isotherms. The randomized variables in the model applied for simulating the P–C isotherms of the above-mentioned ZrFe₂ type hydrogen storage materials correspond to change in enthalpy (ΔH) and entropy (ΔS) of hydride formation. Several ZrFe₂ type materials as in above have been synthesized and their P–C isotherms, enthalpy and entropy change has been evaluated experimentally in order to have input data for simulation. A special software was developed to simulate the P–C isotherms using the said model. A close match between the experimentally observed and simulated P–C isotherms for the above said ZrFe₂ type alloys has been obtained.     

Emissivity of substrate supported films

Results of experimental measurements of emissivity carried out on cobalt oxide and nickel sulphide films deposited on aluminum substrates are reported in this paper. Experimental results supported the general behaviour of variation of emissivity with film thickness as reported theoretically. The theoretical model is based on the interaction and attenuation of the emitted wavelengths from the substrate and film materials.