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 line start permanent magnet synchronous motor using two-part rotor

Abstract: Line Start Permanent Magnet Synchronous Motor (LSPMSM) has been proved as an economically feasible, high efficiency alternative to an induction motor where constant speed is desirable. These motors are having the properties of an induction motor during starting and synchronous motor during steady state period. The need of line starting, calls for a cage winding in addition to permanent magnets in the rotor, which increases the complications in rotor design, and restricts the choice of rotor geometries. There is always conflict in the rotor design of this machine. This conflict is in between synchronous and asynchronous performance of the machine which in turn is a conflict between cage and magnet placement in the rotor. This paper reports an attempt in the direction of removing this conflict and optimizes both synchronous and asynchronous performances of the machine. A new two-part rotor geometry is suggested and analyzed using the dynamic model of LSPMSM prepared in Simulink.

Use of Multiple Classifier System for Gender Driven Speech Emotion Recognition

Abstract: This paper proposes a system that allows recognizing a person's emotional state with the help of recording audio signals. This system is able to recognize four emotions (anger, happiness, sadness and neutral) This emotion recognition technique is mainly composed of two subsystems as - 1) gender recognition (GR) and 2) emotion recognition (ER). It has been proved experimentally that the performance of emotion recognition increases because of the apriori knowledge about gender of the speaker. Traditional approach shows that selection of proper and unique features of speech signals reduces the unnecessary calculation complexity. Recently use of combination of two or more different classifiers is emerging trend in the classification field. As HMM is the best training algorithm and SVM is the best classification algorithm, proposed technique makes use of hybrid of HMM and SVM classifiers to get best results.

Facial image based security system using PCA

Abstract: Security is one of the utmost requirements of homes and businesses which requires biometric identification. This paper aims to identify a person through face recognition. Face recognition is very complex and multidimensional problem. A MATLAB based Principal Component Analysis is used for face matching decision. The system is designed in MATLAB which converts facial images to feature characteristics of initial training database images. Facial features are extracted from the face and eigenvalues are calculated and represented as a eigen vector. Comparison of unknown face image and database image is done using Euclidian distance method. The recognized facial image has minimum Euclidian distance with the database images. When face is recognized by MATLAB Code it will provide the signal to ARM7 to open Gate and System will send SMS to the authorized person using GSM module. Security system using MATLAB and Embedded system design is cost effective, reliable and highly accurate.