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.

A novel training algorithm for convolutional neural network

Abstract: Many machine learning softwares are available which help the researchers to accomplish various tasks. These software packages have various conventional algorithms which perform well if the training and test data are independent and identically distributed. However, this might not be the case in the real world. The training data may not be available at one time. In the case of neural networks, the architecture has to be retrained with new data that are made available subsequently. In this paper, we present a novel training algorithm which can avoid complete retraining of any neural network architecture meant for visual pattern recognition. To show the utility of the algorithm, we have investigated the performance of convolutional neural network (CNN) architecture for a face recognition task under transfer learning. The proposed training algorithm may be used for enhancing the utility of machine learning software by providing researchers with an approach that can reduce the training time under transfer learning.

Sentiments analysis of Twitter data using data mining

Abstract: With rapid growth in user of Social Media in recent years, the researcher get attracted towords the use of social media data for sentiments analysis of people or particular product or person or event. Twitter is one of the widely used social media platform to express the thoughts. This Paper presents approch for analysing the sentiments of users using data mining classifiers. It also compares the performance of single classifiers for sentiments analysis over ensemble of classifier. Expermental results obtained demonstrates that k-nearest neighbour classifier gives very high predictive accuracy. Result also demonstrate that single classifiers outperforms ensemble of classifier approch.

Delta-Operator-Based Extended Disturbance Observer and Its Applications

Abstract: In this paper, a delta-operator-based discrete-time disturbance observer (DO) is proposed for a class of uncertain systems. The proposed observer not only estimates disturbances but also their derivatives, enabling improvement in the accuracy of the estimation of disturbances. The scheme seamlessly unifies the design of continuous-time and discrete-time DOs. The proposed observer is combined with a discrete-time sliding-mode controller with application to mismatched systems. The stability of the overall system is proved. The efficacy of the scheme is illustrated by the simulation of numerical examples and by implementation on a 2-degree-of-freedom serial flexible joint manipulator setup in a laboratory.

Automated system for malaria parasite identification

Abstract: Malaria is a serious worldwide health issue which causes globally an expected 3.4 billion individuals in danger of malaria in 2013. Malaria is an entirely preventable and treatable disease [1]. For fast diagnosis and acute treatment of Malaria is important to reduce the death rate. As the parasite changes morphology in its different life stages and its types varies, an experienced technician is required to identify types of malaria parasites in laboratory diagnosis. Current malaria analysis depends essentially on microscopic examination of Giemsa-stained thick and thin blood films, this method is time consuming and routine. According to the World Health Organization, it causes more than 1 million deaths arising from approximately 300 to 500 million infections every year [2]. For the proper medication of patient it is important to identify the species. For acute diagnosis of malaria, numerous analysts have proposed automated malaria detection devices using digital image processing. In this paper, we provide an approach to identify the species of malaria. The system describes image acquisition, preprocessing, segmentation algorithms, and classifier.

Estimation of blood glucose by non-invasive method using photoplethysmography

Abstract: This paper presents a system which estimates blood glucose level (BGL) by non-invasive method using Photoplethysmography (PPG). Previous studies have shown better estimation of blood glucose level using an optical sensor. An optical sensor based data acquisition system is built and the PPG signal of the subjects is recorded. The main contribution of this paper is exploring various features of a PPG signal using Single Pulse Analysis technique for effective estimation of BGL values. A PPG data of 611 individuals is recorded over duration of 3 minutes each. BGL value estimation is performed using two types of feature sets, (i) Time and frequency domain features and (ii) Single Pulse Analysis (SPA). Neural network is trained using above mentioned proposed feature sets and BGL value estimation is performed. First we validate our methodology using the same features used by Monte Moreno in his earlier work. The experimentation is performed on our own dataset. We obtained comparable results of BGL value estimation as compared with Monte Moreno, with maximum R2 = 0.81. Further, BGL estimation using (i) Time and frequency domain features and (ii) Single Pulse Analysis (SPA) is performed and the resulting coefficient of determination (i.e., R2) obtained for reference vs. prediction are 0.84 and 0.91, respectively. Clarke Error Grid analysis for BGL estimation is clinically accepted, so we performed similar analysis. Using Time and frequency domain feature set, the distributions of data samples is obtained as 80.6% in class A and 17.4% in class B. 1% samples in zone C and Zone D. For Single Pulse Analysis technique (SPA) the distribution of data samples are 83% in class A and 17% in class B. The proposed features in SPA have shown significant improvement in R2 and Clarke Error grid analysis. SPA technique with the proposed feature set is a good choice for the implementation of system for measurement of non-invasive glucometer.