With over 172 Million people infected with the novel coronavirus (COVID-19) globally and with the numbers increasing exponentially, the dire need of a fast diagnostic system keeps on surging. With shortage of kits, and deadly underlying disease due to its vastly mutating and contagious properties, the tired physicians need a fast diagnostic method to cater the requirements of the soaring number of infected patients. Laboratory testing has turned out to be an arduous, cost-ineffective and requiring a well-equipped laboratory for analysis. This paper proposes a convolutional neural network (CNN) based model for analysis/detection of COVID-19, dubbed as CovCNN, which uses the patient’s chest X-ray images for the diagnosis of COVID-19 with an aim to assist the medical practitioners to expedite the diagnostic process amongst high workload conditions. In the proposed CovCNN model, a novel deep-CNN based architecture has been incorporated with multiple folds of CNN. These models utilize depth wise convolution with varying dilation rates for efficiently extracting diversified features from chest X-rays. 657 chest X-rays of which 219 were X-ray images of patients infected from COVID-19 and the remaining were the images of non-COVID-19 (i.e. normal or COVID-19 negative) patients. Further, performance evaluation on the dataset using different pre-trained models has been analyzed based on the loss and accuracy curve. The experimental results show that the highest classification accuracy (98.4%) is achieved using the proposed CovCNN model.

No abstract

Machine learning facilitates predictive maintenance due to the advantages it holds over traditional methods of maintaining semi-conductor devices such as preventive and breakdown maintenance. Several predictive models using machine learning on the Semiconductor Manufacturing process dataset (SECOM) will be applied in this paper. The dataset contains the information related to semiconductor manufacturing process, with the attributes corresponding to signals collected from semiconductor devices. Due to the high-dimensionality of the data and class imbalance problem in the SECOM dataset, it poses several challenges related to data pre-processing, which is an essential step incorporated in this work while applying various machine learning models. Comparison and analysis of various predictive machine learning classification models were carried out based on the performance metrics like, accuracy and Receiver Operating Characteristic (ROC) curve.

No abstract

No abstract