College of Engineering, Pune

About: College of Engineering, Pune is a based out in . It is known for research contribution in the topics: Sliding mode control & Control theory. The organization has 4264 authors who have published 3492 publications receiving 19371 citations. The organization is also known as: COEP.

Disease Risk Prediction by Using Convolutional Neural Network

Abstract: Data analysis plays a significant role in handling a large amount of data in the healthcare. The previous medical researches based on handling and assimilate a huge amount of hospital data instead of prediction. Due to an enormous amount of data growth in the biomedical and healthcare field the accurate analysis of medical data becomes propitious for earlier detection of disease and patient care. However, the accuracy decreases when the medical data is partially missing. To overcome the problem of missing medical data, we perform data cleaning and imputation to transform the incomplete data to complete data. We are working on heart disease prediction on the basis of the dataset with help of Naive bayes and KNN algorithm. To extend this work, we propose the disease risk prediction using structured data. We use convolutional neural network based unimodel disease risk prediction algorithm. The prediction accuracy of CNN-UDRP algorithm reaches more than 65%. Moreover, this system answers the question related to disease which people face in their life.

Pack-Boronizing of AISI 4140 Steel: Boronizing Mechanism and the Role of Container Design

Abstract: In this study, pack-boronizing of AISI 4140 steel was done. Three mild-steel containers with different size, namely, small-size container (SC), medium-size container (MC), and big-size container (BC) were used. Steel specimens were boronized at 950°C for 2 or 3 h. Preconditioning of the containers was observed to be essential before doing final pack-boronizing of steel. MC was found suitable for the formation of monophase Fe2B layer while BC produced unwanted FeB phase along with Fe2B layer. Fe2B phase showed the columnar morphology. Continuous decrease in the hardness from surface to nonboronized core was observed. Maximum surface hardness of about 1367 HV0.1 was obtained (hardness of nonboronized core was about 252 HV0.1) for the boronized steel. As compared to the normalized and hardened–tempered (HT) AISI 4140 steel pins, boronized steel pin showed the lowest “specific wear rate” (0.89 × 10−6 mm3/Nm) and coefficient of friction (COF) (0.55).

Detection of leukemia in microscopic white blood cell images

Abstract: Leukemia means blood cancer which is featured by the uncontrolled and abnormal production of white blood cells (leukocytes) by the bone marrow in the blood. Analyzing microscopic blood cell images, diseases can be identified and diagnosed early. Hematologist are using technique of image processing to analyze, detect and identify leukemia types in patients recently. Detection through images is fast and cheap method as there is no special need of equipment for lab testing. In this paper, we proposed a method of detection of leukemia in patients from microscopic white blood cell images. We have focused on the changes in the geometry of cells and statistical parameters like mean and standard deviation which separates white blood cells from other blood components using processing tools like MATLAB and LabVIEW. Images processing steps like image enhancement, image segmentation and feature extraction are applied on microscopic images.

NegBERT: A Transfer Learning Approach for Negation Detection and Scope Resolution

Abstract: Negation is an important characteristic of language, and a major component of information extraction from text. This subtask is of considerable importance to the biomedical domain. Over the years, multiple approaches have been explored to address this problem: Rule-based systems, Machine Learning classifiers, Conditional Random Field Models, CNNs and more recently BiLSTMs. In this paper, we look at applying Transfer Learning to this problem. First, we extensively review previous literature addressing Negation Detection and Scope Resolution across the 3 datasets that have gained popularity over the years: the BioScope Corpus, the Sherlock dataset, and the SFU Review Corpus. We then explore the decision choices involved with using BERT, a popular transfer learning model, for this task, and report state-of-the-art results for scope resolution across all 3 datasets. Our model, referred to as NegBERT, achieves a token level F1 score on scope resolution of 92.36 on the Sherlock dataset, 95.68 on the BioScope Abstracts subcorpus, 91.24 on the BioScope Full Papers subcorpus, 90.95 on the SFU Review Corpus, outperforming the previous state-of-the-art systems by a significant margin. We also analyze the model's generalizability to datasets on which it is not trained.

Slip regulation for anti-lock braking systems using multiple surface sliding controller combined with inertial delay control

Abstract: In this paper, a multiple surface sliding controller is designed for an anti-lock braking system to maintain the slip ratio at a desired level. Various types of uncertainties coming from unknown road surface conditions, the variations in normal force and the mass of the vehicle are estimated using an uncertainty estimation technique called the inertial delay control and then the estimate is used in the design of the multiple surface sliding controller. The proposed scheme does not require the bounds of uncertainties. The ultimate boundedness of the overall system is proved. The proposed scheme is validated by simulation under various scenarios of road friction, road gradient and vehicle loading followed by experimentation on a laboratory anti-lock braking set-up for different friction conditions.