Search

The objective of this study was to use and compare multi- ple classifying models that can be used for classifying as- tronomical data and was tested upon data obtained from Sloan Digital Sky Survey: Data Release-16. Various Classi- fying models have been trained and tested by dividing the data into two parts- 80 per cent of the data was then used for training purposes and 20 per cent for testing. In order to achieve the task of classifying the tabular data consist- ing of spectroscopic and photometric parameters effectively, the study was not just limited to usage of indiviual models. Stacking : the combination of multiple Classifying mod- els has also been implemented. Multiple stacking models were created for the same .Stacking models have on mul- tiple occasions proven to have higher evaluation metrics , thus having significantly better performance than any individual classifier, proving that stacking is a better choice to classify data. certain Individual models such as Bagging , Hard Voting etc have been found to have comparable performance to that of Stacked Models. Box plots for indiviual classes were also plotted to compare and determine the models that were capable in identifying a single class of stellar objects. The models from this study could be used as a reliable classification tool for a wide variety of astronomical purposes to accelerate the expansion of the sample sizes of stars, galaxies, and quasars.

Arsenic is one of the heavy metals found in the environment and it is widely spread on the earth. This is due to the industrial and agricultural sectors and acts as an anthropogenic substance. This...

Research on polycystic ovarian syndrome (PCOS) remains intense due to its evolving impact on metabolism, reproduction and cardiovascular function. Changes in metabolic pathways can also significantly impact renal function including the development of Focal Segmental Glomerulosclerosis (FSGS), one of the most highly investigated renal diseases. In FSGS, scarring of the glomerulus vascular tuft damages the kidneys. Onset of FSGS may either be congenital or due to other disorders that affect the metabolism and normal kidney function. Both PCOS and FSGS appear to be associated with Transforming Growth Factor-β (TGF-β) signalling. Over-expression of TGF-β may be due to the activation of the thrombospondin 1 (TSP1) gene, which increases the probability of developing renal disorders. Higher androgen levels in PCOS may also cause podocyte damage thus directly impacting development of FSGS. This article reviews the role of TGF-β's in PCOS and FSGS and explores the inter-relationship between these two disorders.

Image denoising is an essential pre-processing step in medical image analysis. It brings about an improvement in the accuracy of disease diagnosis (done by analysis of medical images), and helps to determine the correct course of treatment plan. Over the past few years, Convolutional Neural Networks (CNNs) have been proven to be extremely effective in image processing and computer vision applications. In this work we explore efficient wide residual CNNs for denoising human brain magnetic resonance images. Many state-of-the-art CNN based image denoising methods use squared Euclidean distance for training the neural network. This causes deep networks to produce over-smoothed image outputs, losing structural or anatomical details. Also, the details of structures (found in images) are often lost in the deep hierarchy of convolution layers. Unlike such existing methods, in this paper, we use perceptual loss alongside squared Euclidean distance for training our network. This helps restoring images that are visually desirable, in the sense that they restore considerably more anatomically refined features, and are not just similar to the ground-truth pixel intensity. Our experiments show that the proposed convolutional network surpasses the state-of-the-art methods of rician MRI denoising, and obtains better quality denoised brain MR images as compared to the state-of-the-art.

Successful training of deep neural network models for Image Segmentation requires large datasets with proper ground truth annotations. In most bio-medical applications obtaining sufficiently large labelled datasets for training such networks, is a tedious task. Hence addressing this problem, we propose a simple light-weight neural network based model that generates ground truth masks of the neuronal structures of Electron Microscopy(EM) stacks training images. It is followed by image augmentation to create an extensive dataset of image-mask pairs for training the segmentation network. The proposed segmentation model is inspired by the state-of-the-art Unet++ architecture. We compare the segmentation predicts of the proposed model (unsupervised) with the manual ground truth masks to validate our results and efficiency of the model proposed. The proposed network model for unsupervised segmentation can be trained effectively with less number of train images even without the presence of proper ground truth masks. It predicts high quality segmentation outputs for the images under test with optimal time requirement(less than a second using a Google Colab Nvidia Tesla K80 GPU).

The automated segmentation of biomedical images is being used increasingly for the clinical practices. Deep learning techniques and networks demonstrate promising results in applications of computer vision. However, the behaviour of different networks are effectively influenced by the choice of architecture and training parameter settings. Ensembles of neural networks are known to be much more efficient and accurate than individual networks. We explore stacking ensemble and snapshot ensembles of different neural network models and architectures for robust performance through the aggregation of predictions for effective biomedical image segmentation tasks. The network models used are inspired from the Fully Convolutional Network(FCN) architectures. The proposed approach is a generic and unbiased deep learning approach that reduces the risk of over fitting the network configuration to a particular dataset. We evaluated our approach on the Boston University-Biomedical Image Library(BU-BIL) Dataset 1. The predicted image segmentation masks were compared to the gold standard ground truth annotations of the dataset to validate the effectiveness of our proposed ensemble architectures.

Now-a-days agile software development process has become famous in industries and substituting the traditional methods of software development. However, an accurate estimation of effort in this paradigm still remains a dispute in industries. Hence, the industry must be able to estimate the effort necessary for software development using agile methodology efficiently. For this, different techniques like expert opinion, analogy, disaggregation etc. are adopted by researchers and practitioners. But no proper mathematical model exists for this. The existing techniques are ad-hoc and are thus prone to be incorrect. One popular approach of calculating effort of agile projects mathematically is the Story Point Approach (SPA). In this study, an effort has been made to enhance the prediction accuracy of agile software effort estimation process using SPA. For doing this, different types of neural networks (General Regression Neural Network (GRNN), Probabilistic Neural Network (PNN), Group Method of Data Handling (GMDH) Polynomial Neural Network and Cascade-Correlation Neural Network) are used. Finally performance of the models generated using various neural networks are compared and analyzed.

Steels are alloys of iron and carbon, widely used in construction and other applications. The evolution of steel microstructure through various heat treatment processes is an important factor in controlling properties and performance of steel. Extensive experimentations have been performed to enhance the properties of steel by customizing heat treatment processes. However, experimental analyses are always associated with high resource requirements in terms of cost and time. As an alternative solution, we propose an image processing-based technique for refinement of raw plain carbon steel microstructure images, into a digital form, usable in experiments related to heat treatment processes of steel in diverse applications. The proposed work follows the conventional steps practiced by materials engineers in manual refinement of steel images; and it appropriately utilizes basic image processing techniques (including filtering, segmentation, opening, and clustering) to automate the whole process. The proposed refinement of steel microstructure images is aimed to enable computer-aided simulations of heat treatment of plain carbon steel, in a timely and cost-efficient manner; hence it is beneficial for the materials and metallurgy industry. Our experimental results prove the efficiency and effectiveness of the proposed technique.

Agile software development is now accepted as a superior alternative to conventional methods of software development, because of its inherent benefits like iterative development, rapid delivery and reduced risk. Hence, the industry must be able to efficiently estimate the effort necessary to develop projects using agile methodology. For this, different techniques like expert opinion, analogy, disaggregation etc. are adopted by researchers and practitioners. But no proper mathematical model exists for this. The existing techniques are ad-hoc and are thus prone to be incorrect. One popular approach of calculating effort of agile projects mathematically is the Story Point Approach (SPA). In this study, an effort has been made to improve the prediction accuracy of estimation done using SPA. For doing this, different types of neural networks (General Regression Neural Network (GRNN), Group Method of Data Handling (GMDH) Polynomial Neural Network and Cascade- Correlation Neural Network) are used. Finally, performance of models generated using these neural networks are compared and analyzed. using story points. The team defines the relationship between story point and effort. Usually 1 story point is equal to 1 ideal working day. Total no. of story points that a team can convey in a sprint (an iteration in agile software development) is called as ``team velocity" or story points per sprint. In the SPA, aggregate number of story points alongside velocity of the project are considered to determine agile software development effort. Now for obtaining better prediction accuracy, three types of neural networks are used in this study. The results obtained by applying these networks are compared and their performance is accessed