College of Engineering, Pune

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

Statistical Study of Machine Learning Algorithms Using Parametric and Non-Parametric Tests: A Comparative Analysis and Recommendations

Abstract: The emerging area of the internet of things (IoT) generates a large amount of data from IoT applications such as health care, smart cities, etc. This data needs to be analyzed in order to derive us...

One touch multi-banking transaction ATM system using biometric and GSM authentication

Abstract: Every individuals has multiple bank accounts in different banks, people's need to carry multiple ATM cards for transaction, there may be different PINs for every account. In traditional system, ATM terminal customer recognition systems only rely on bank cards, security pin number, and such identity verification methods which measures are not perfect and functions are too single and at times there are incidents where we forget ours security PIN number, lose our cards, cards get stolen, stolen PIN numbers. To overcome the bugs in traditional ATM system, introducing a new ATM terminal customer recognition system, “One touch Multi-banking Transaction system using Biometric and GSM Authentication”. Biometric based fingerprint authentication technique is one of the most secure systems, unauthorized accesses are restricted, as this makes fingerprint a unique identification for everyone. This system also assures a secure GSM (OTP-One time Password) based transaction. Here the proposed system has no risk overhead in managing multiple account transactions and achieves high security as compare to the traditional ATM system.

Parametric design analysis of meridional deflection stresses in metal expansion bellows using gray relational grade

Abstract: Unpredictable and uncertain failure of the bellows needs the attention of the designer toward maximum meridional deflection stresses generated on the U-shaped convolutions. Evaluation of these maximum stress points on the flexible convolutions is multifaceted. This paper deals with the identification of these stresses induced on the bellows convolutions by analytical and experimental methods. Further, the influence of the pivotal design parameters on meridional deflection stresses is studied mainly in two aspects: (1) effect of number of convolutions (N) and pitch diameter (dp) on the meridional deflection stresses and (2) the determination of the optimized design parameters to reduce the stress levels using effective multi-response gray relational grade (GRG) optimization technique. Three bellows of stainless steel material (Grade SS321) are used for the experimentation with a different number of convolutions (N) and pitch diameters (dp). The optimal design parameter setting is found by using GRG analysis through ANOVA and regression mathematical model. The effect of design factors on GRG is analyzed. Besides, using GRG, the regression model enhances to give alternative optimal solutions; in turn, it increases the designer’s choice for the selection of the parametric levels. In the confirmation test, it is seen that the average improvement in GRG for all selected Taguchi orthogonal runs is 23%.

Online hand gesture recognition & classification for deaf & dumb

Abstract: Sign language is widely used by individuals with hearing impairment to communicate with each other conveniently using hand gestures. However, non-sign-language speakers find it very difficult to communicate with those with speech or hearing impairment since it interpreters are not readily available at all times. Many countries have their own sign language, such as American Sign Language (ASL) which is mainly used in the United States and the English-speaking part of Canada. The proposed system helps non-sign-language speakers in recognising gestures used in American Sign Language. The system described in this paper is implemented using MATLAB. In this approach, firstly, the signs are captured using a webcam. The images captured are then processed further and the features are extracted from the captured images using PCA. Comparison of the features is done using Euclidean Distance with the training sets. Minimum Euclidean distance helps to recognise the character. This system will enable non-sign-language speakers to better understand and communicate with those with impaired hearing.

Synthesis of nanosized barium titanate/epoxy resin composites and measurement of microwave absorption

Abstract: Barium titanate/epoxy resin composites have been synthesized and tested for microwave absorption/transmission. Nanocrystalline barium titanate (BaTiO3 or BT) was synthesized by the hydrothermal method and the composites of BT/epoxy resin were fabricated as thin solid slabs of four different weight ratios. BT was obtained in the cubic phase with an average particle size of 21 nm, deduced from the X-ray diffraction data. The reflection loss (RL) and transmission loss (TL) of the composite materials were measured by the reflection/transmission method using a vector network analyser R&S: ZVA40, in the frequency range 8·0–18·5 GHz (X and Ku-bands). The RL was found to be better than −10 dB over wide frequency bands. The higher RL for lower concentration of BT could be due to increase in impedance matching effects. Low TL values indicate that the absorption by BT is quite low. This could be due to formation of BT in the cubic paraelectric phase.