Datta Meghe College of Engineering is a private engineering college located in Airoli, Navi Mumbai, Maharashtra, India. The college is affiliated to the University of Mumbai and approved by the Directorate of Technical Education , Maharashtra State and All India Council of Technical Education , New Delhi. It is the best college in Navi Mumbai as per the survey conducted by Indian Council of Technical Education in 2007. Wikipedia.
Keshwani L.,Datta Meghe College of Engineering |
Pete D.,Datta Meghe College of Engineering
Advances in Intelligent Systems and Computing | Year: 2017
Person identification using face as a cue is one of the most prominent and robust technique. This paper presents 3D face recognition system using Radial curves and Back Propagation Neural Networks (BPNN). The face images used for experimentation are under various challenges like illumination, pose variation, expression and occlusions. The features of images are extracted using Eigen vectors. These features are compared using radial curves on the face starting from center of the face to the end of the face. Each corresponding curve is matched using Euclidean Distance classifier. The BPNN is used to train the features for face matching. The proposed algorithms are tested on ORL and DMCE database. The performance analysis is based on recognition rate accuracy of the system. The proposed radial curve system yields recognition rate accuracy of 100 % for images from the ORL database and 98 % for the images from DMCE database. © Springer Science+Business Media Singapore 2017.
Pacharaney U.,Datta Meghe College of Engineering
Proceedings of 2016 International Conference on Advanced Communication Control and Computing Technologies, ICACCCT 2016 | Year: 2016
Compressive sensing is the emerging theory in the field of wireless sensor networks which works on a Sub-Nyquist sampling theorem. Sparse representation of a few non-zero samples of the original signal will significantly reduce the number of samples. Also, reconstruction of the original signal is possible as per Sub-Nyquist sampling theorem. Internet of Things (IoT) has become an immensely popular field in wireless communication. The system an Internet of Things can be formed by thousands of independent components e.g. RFID tags, sensors, mobile phones etc. Compressive sensing theory provides a promising approach in the field of wireless sensor network. This paper investigates how compressive sensing can be applicable in an Internet of Things for energy efficiency with low computational cost. The compressive sensing based framework is proposed for Internet of Things and wireless sensor network aiming to increase the performance of a system with energy efficiency at sensor node. © 2016 IEEE.
Devane S.R.,Datta Meghe College of Engineering
ACM International Conference Proceeding Series | Year: 2016
e-Governance aims at producing citizen centric services ensuring services transparency with various government agencies. The process of approving or disapproving the application is marked by digitally signing and forwarding the edocuments. Present digital signature scheme provides the required security using identity based authentication mechanism, but in case of delegating power to third party authority for short period requires additional scheme i.e. Proxy signature system a variant of digital signature. Furthermore the identity based authentication scheme required to be changed to role base authentication using proxy signatures to protect from signature forgery attack and misuse by delegated authority. © 2016 ACM.
Kulkarni S.J.,Datta Meghe College of Engineering |
Tapre R.W.,Datta Meghe College of Engineering |
Patil S.V.,Gharda Institute of Technology |
Sawarkar M.B.,Government Polytechnic
Procedia Engineering | Year: 2013
Phenol is the major pollutants in the wastewater from various industries such as coal conversion process, fertilizers, petroleum refineries, coking plants, pharmaceutical, dye manufacturing etc. In the present study coconut shell activated carbon is used as an adsorbent. The adsorption is carried out in a fluidized bed. Coconut shell has been used for the preparation of absorbent. The effect of various parameters like concentration, fluid flow rate and adsorbent particle size has been studied. It is observed that as the concentration increases the percent saturation of adsorbent increases. Also increase in fluid flow rate gives better adsorption in case of coconut shell activated carbon. However, it is also observed that percent saturation of adsorption decreases with increases in particle size of adsorbent. In the present study particle size of 0.420 mm is found more beneficial. © 2012 Published by Elsevier Ltd.
Londhe S.,Vishwakarma Institute of Information Technology |
Charhate S.,Datta Meghe College of Engineering
Hydrological Sciences Journal | Year: 2010
Accurate forecasting of streamflow is essential for the efficient operation of water resources systems. The streamflow process is complex and highly nonlinear. Therefore, researchers try to devise alterative techniques to forecast streamflow with relative ease and reasonable accuracy, although traditional deterministic and conceptual models are available. The present work uses three data-driven techniques, namely artificial neural networks (ANN), genetic programming (GP) and model trees (MT) to forecast river flow one day in advance at two stations in the Narmada catchment of India, and the results are compared. All the models performed reasonably well as far as accuracy of prediction is concerned. It was found that the ANN and MT techniques performed almost equally well, but GP performed better than both these techniques, although only marginally in terms of prediction accuracy in normal and extreme events. © 2010 IAHS Press.
Nirmal A.J.,Datta Meghe College of Engineering |
Gaikwad V.B.,University of Mumbai
International Conference and Workshop on Emerging Trends in Technology 2011, ICWET 2011 - Conference Proceedings | Year: 2011
Content Based Image Retrieval System retrieves images using color, texture and shape properties of the image. Different methods which are implemented in this paper are Discrete wavelet transform (DWT), Gabor wavelet transform (GWT), Color histogram (CH), color autocorrelogram (CA). Integration of color and texture features is done using different methods and their comparison is done using precision and recall as performance measures.. DWT (D) method is implemented using the combination of statistical mean and standard deviation features and perceptual feature directionality. The best results are obtained with GWT (A) + CH method as compared to all other ten methods as phase information from the Gabor transformed coefficients is taken into consideration. Copyright © 2011 ACM.
Sawarkar S.,Datta Meghe College of Engineering
ICWET 2010 - International Conference and Workshop on Emerging Trends in Technology 2010, Conference Proceedings | Year: 2010
The proposed method detects the exact location of masses and circumscribed masses in mammograms based on RBFNN (Redial Basis Function Neural Network) with accuracy of 62% and 50% respectively for mammograms containing masses. The recognition rate for the normal one reaches 94.89% in MIAS (Mammography Image Analysis Society) database. Also the results are independent of preprocessing. This procedure is implemented by performing sub-image windowing analysis. The evaluation of the proposed mass and circumscribed mass detection was carried out in the MIAS database, giving reliable detection. Copyright 2010 ACM.
Ashraf K.N.,Ramrao Adik Institute of Technology |
Amarsinh V.,Ramrao Adik Institute of Technology |
Satish D.,Datta Meghe College of Engineering
Proceedings of the 2013 3rd IEEE International Advance Computing Conference, IACC 2013 | Year: 2013
Mobile devices often change their location which triggers the handover from one access router to another. Mobility management provides a way to retain the ongoing session of the mobile node. It is crucial to provide efficient handoff mechanism support for mobile devices. Mobile IPv6 (MIPv6) and its extensions have been proposed for this purpose. Fast Mobile IPv6 (FMIPv6) and Hierarchical Mobile IPv6 (HMIPv6) have been developed as host-based mobility management protocols whereas Proxy Mobile IPv6 (PMIPv6) and Fast Proxy Mobile IPv6 (FPMIPv6) have been proposed as network-based mobility management protocols. In this paper, survey and detailed signaling of each protocol is presented followed by analysis of these protocols based on handover latency and signaling cost. Finally numerical results are presented and commented. © 2013 IEEE.
Amarsinh V.,Ramrao Adik Institute of Technology |
Devane S.,Datta Meghe College of Engineering
Communications in Computer and Information Science | Year: 2013
Uses of multimedia, video and audio oriented applications are increasing day by day on mobile devices. The growth of these applications is hampered because of limitation in MIPv6 during handover, as MIPv6 is not designed for continuous streaming. Limitations to support QoS parameters like variable jitter, delays in addition to loss of packets for streaming video during handoff. This paper makes an attempt to improve the latency in handover by modifying the signals related to handover, which has resulted in reducing the signaling cost and latency. © 2013 Springer-Verlag Berlin Heidelberg.
Patil R.V.,Datta Meghe College of Engineering |
Pete D.J.,Datta Meghe College of Engineering
Proceedings - IEEE International Conference on Information Processing, ICIP 2015 | Year: 2015
The image change detection is been used in various applications like map updating, building change detection, disaster assessment, military application etc. In recent years image matching algorithm from computer vision have been introduced and used in satellite imagery. One of the important application of image change detection such as building change detection is discuss in this paper. When we are dealing with building change due to different imaging conditions 2D information obtain for different dates is not sufficient. It has been become difficult to distinguish the building changes from various man made construction such as roads and bridges due to similarity. So for to obtain the 3D building changes, stereo imagery is of importance. Therefore Digital Surface Model (DSM) and stereo imagery is used for building change detection. To detect the similarity information between two original images the Kullback Leibler Divergence(KLD) is preferred. Whereas Dempster Shafer Fusion theory (DS fusion) is used to combine the result of DSM and K L divergence, in order to improve accuracy. Image change detection can be used in both rural and urban area, image obtain from digital camera, satellite, Google earth, USGS etc. Detecting and monitoring urban area changes are of great relevance for city planning, environmental monitoring. In this we have shown an example of image change detection. Change detection by information measure using radio metric information at the level of pixel is not sufficient to discriminate the ground structure. So object based or structural based image descriptions are used to resolve the problem of radio metric information. If resolution of image is decreases than transform produce a non-linear temporal behavior which cannot be capture by linear transform change detection method. The image capture from satellite a DSM co-registration and refinement a pre processing is required. © 2015 IEEE.