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.

Face recognition based on PCA on wavelet subband

Abstract: Many recent events, such as terrorist attacks, exposed serious weaknesses in most sophisticated security systems, it is necessary to improve security data systems based on the body or behavioral characteristics, often called biometrics. Together with the growing interest in the development of human and computer interface and biometric identification, human face recognition has become an active research area. Face recognition appears to offer several advantages over other biometric methods. Nowadays Principal Component Analysis (PCA) has been widely adopted for the face recognition algorithm. Yet still, PCA has its limitations such as poor discriminatory power and large computational load. In this paper to improve the performance of PCA, it is applied on Daubechies wavelet subbands. Results are compared using City Block distance and Euclidean distance measures. The best recognition rate is obtained using PCA on subband A3 of db2 wavelet using City block distance measure.

Dot matrix text recognition for industrial carton classification

Abstract: Automatic classification of packaging cartons according to their contents is an industrial need. In this paper we present an Optical Character Recognition (OCR) system to segment and recognize the sparse dot matrix text printed on the cartons in order to classify them based on the contents. Proposed solution is robust to non-uniformities in background illumination, shadow artifacts, inclined text, degraded text due to missing dots etc. We propose efficient segmentation technique using simple morphological operations which makes use of the discrete nature of the dot matrix text in distinguishing it from other information. The dot matrix characters can be uniquely characterized by analyzing the pattern of dots. We retrieve this pattern, and feed it as feature vector to the trained Support Vector Machine (SVM) classifier. The combination of the unique patterns and SVM classifier results into high character recognition accuracy, in turn leading to efficient carton classification. Finally, we discuss the result statistics of character recognition and carton classification.

Role of Interface on Dynamic Modulus of High-Performance Poly(etheretherketone)/Ceramic Composites

Abstract: High-performance printed circuit board or electronic packaging substrate with low warping particularly at high frequency is the key demand of manufacturers. In the present work, poly(etheretherketone) (PEEK) matrix composites reinforced with untreated micron size aluminum nitride (AlN) and alumina (Al2O3) particles have been studied for dynamic modulus in the temperature range varying from 30 to 250°C. At 48 vol % particles, the room temperature modulus of the PEEK/AlN composites increased by approximately fivefold (∼ 23 GPa), whereas it increased by twofold for PEEK/Al2O3 composite. The reinforcing efficiency is more pronounced at higher temperatures. The significant improvement in modulus was attributed to the better adhesion between the matrix and the AlN particles. Scanning electron microscope (SEM) and Kubat parameter showed that the poor adhesion between the matrix and the Al2O3 particles resulted in comparatively smaller increase in modulus of PEEK/Al2O3, despite higher intrinsic modulus of Al2O3 than that of AlN. SEM showed almost uniform distribution of particles in the matrix. The experimental data were correlated with several theoretical models. The Halpin–Tsai model with ξ (xi) is equal to four correlates well up to 48 vol % AlN composites while ξ is equal to two correlates only up to 18 vol % Al2O3 composites. Guth–Smallwood model also correlates well up to 28 vol % AlN and 18 vol % Al2O3-filled composites. Thereafter, data deviated from it due to the particles tendency to aggregate formation. © 2011 Wiley Periodicals, Inc. J Appl Polym Sci, 2011

Designing of dual-axis Solar tracking system with remote monitoring

Abstract: The use of renewable energy resources like solar energy is the need of time in countries like India, where energy demand is increasing very rapidly with population. Solar panels are the transducers which convert solar energy into electrical energy. The conventional, i.e. fixed installation of these solar panels on a flat surface is very inefficient and less cost effective solution. This paper comes with an engineering solution to enhance efficiency of solar panel in a very cost effective way. This engineering solution is the dual axis solar tracking of solar panel. The dual axis Solar tracking system for solar panel is the most appropriate way to increase efficiency of solar panel by tracking the sun completely. The proposed system comprises of ARM processor BeagleBone Black - BBB which has Linux OS, Light dependent Resistors (LDRs), Servo motors. The internet facility provided by BBB takes this system to the next level by allowing users to monitor real time solar tracking of solar panels with total amount of electricity generated by these solar panels from anywhere in the world.

Optimization of Vehicle Suspension Parameters for Ride Comfort Based on RSM

Abstract: Vehicle suspension design requires an investigation to determine the spring and damper settings that assure optimal ride comfort (RC) of vehicle. In the present work response surface methodology (RSM), one of the methods of design of experiment has been successfully implemented for the purpose of finding optimal setting. Design of experiment sometimes requires accurate representation of the independent variables which are usually difficult to measure or else unavailable for experimentation. This paper proposes a simulation model to analyze the ride comfort with accurate independent variables as per Box–Behnken design of RSM. A prediction model of response variable, RC is developed using regression analysis which leads to a good agreement with simulated model (R 2 = 99.74 %). The fitted model can be effectively used to evaluate optimal setting of spring stiffness and damping coefficient with the help of response optimization of a high desirability value.