MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

Engineering and Technology

School of Computer Engineering & Technology

World University root node

Annual UB Conference, Ballarat, Australia

The Integration of Image and Text Retrieval to Support Radiological Diagnosis

Facial Expression recognition and its relation with Human health

School of Electronics & Communication Engineering

Computer Engineering and Applications Journal

Improvement and Comparison of Mean Shift Tracker using Convex Kernel Function and Motion Information

Noise removal and image enhancement are the important tasks addressed by many Image Processing algorithms, especially, when the images are corrupted by high noise level e.g. in the case of remote imaging, thermal imaging, night vision etc. The noise makes the image recognition more difficult as it gives a grainy, snowy or textured appearance to the image. So there exists a need for efficient image de-noising method without introducing any artifacts in the original image. The Images with a Noise Standard Deviation (Sigma) greater than 25 are considered as high noise images. The dark images, e.g. night shoots, have very low dynamic range of brightness. The darkness and the high noise needs to be carefully tackled by the image processing algorithm for acceptable visual quality e.g. surveillance applications. Furthermore, de-noising is often necessary as a pre-processing step in image compression, segmentation, recognition etc. Basically, the image de-noising methods are divided into two types: local and non-local. A non local method called as Non-Local Means [4] estimates a noise-free pixel intensity as a weighted average of all pixel intensities in the image, and the weights are proportional to the similarity between the local neighbourhood of the pixel being processed and local neighbourhoods of surrounding pixels. The method is quite spontaneous that results in PSNR and visual quality comparable with other de-noising methods. © 2013 IEEE.

Proceedings of IEEE International Conference on Circuit, Power and Computing Technologies, ICCPCT 2013

De-noising of Gaussian noise affected images by Non-Local Means algorithm

Azo-bridged azole derivatives were designed and investigated in order to find comprehensive relationship between the structure and performance of nitrogen-rich energetic compounds. Density functional theory (DFT) was used to predict the optimized structures, heat of formation, and detonation properties. Introduction of the azido group greatly enhances the heat of formation of these derivatives due to the high energy contribution from the -N 3 group. The crystal density was predicted by using the DREIDING force field. The nitroazoles show higher densities than amino and azido derivatives and hence better detonation performance. Thermal stability was analyzed using bond dissociation energies of C-NO 2, C-NH 2, and C-N 3 bonds. Nucleus-independent chemical shifts (NICS) were calculated at the ring centers to find the stability via aromaticity. The sensitivity of the designed compounds were predicted on the basis of band gap between the highest occupied molecular orbital and lowest unoccupied molecular orbital. The amino derivatives were found to be more stable and less sensitive than the designed compounds. © 2012 Copyright Taylor and Francis Group, LLC.

School of Polymer Engineering

Journal of Energetic Materials

Quantum Chemical Studies on Energetic Azo-Bridged Azoles

For real time multimedia signal transmission in wireless channel, the effect of packets lost due to error and due to congestion, end-to-end delay during the transmission which in-turn will affect the parameters of wireless channel like reliability, quality of service (QoS); transmission rate, transmission delay etc. are required to be considered. Most of the real-time applications uses user datagram protocol (UDP) as their transport protocol. For better end-to-end performance of wireless network, improvements are required in the existing protocol of physical (PHY) layer. This paper surveys the literature on real time communication over wireless and suggests adaptive error control mechanism for reliable transmission. The suggested adaptive forward error control (AFEC) method results in achieving the desired recovery rate at the receiver without using any retransmission mechanism. The network simulator NS-2 is used to evaluate the same. The simulation results indicate that the suggested method improves end-to-end performance by increased packet delivery ratio (PDR) by reducing end to end delay for real time multimedia signal in the wireless network. © 2013 Springer Science+Business Media.

Computer Networks &amp; Communications (NetCom)

PHY Layer Considerations for Real Time Multimedia Signal Transmission in Wireless Medium

Real time video transmission in wireless environment considers various parameters of wireless channel like information rate, error resiliency, security, end-to-end latency, quality of service etc. The available internet protocols are transmission control protocol and user datagram protocol (UDP). But most of the real-time applications uses UDP as their transport protocol. UDP is a fast protocol suitable for delay sensitive applications like video and audio transmission as it does not provide flow control or error recovery and does not require connection management. Due to the tremendous growth in wired and wireless real-time applications, some improvements should be made in the existing systems or protocols. Various techniques to improve end-to-end performance of system for real time video transmission over wireless channel are available in literature. Authors claim that the solution suggested in the paper provide more reliability in wireless video transmission. In the proposed solution, adaptive redundant packets are added in every block (or datagram) transmitted in order to achieve a desired recovery rate at the receiver. The suggested method dose not use any retransmission mechanism. The network simulator NS-2 is used to evaluate the method and the simulation results indicate that the proposed method can guarantee satisfied end-to-end performance by increased packet delivery ratio, reduced end-to-end delay and hence increased network throughput for video transmission in wireless network. © 2013 Springer Science+Business Media New York.

Wireless personal communications

End-to-end performance improvement of the wireless channel for video transmission

Document image analysis analyzes the document images to extract the text and graphics information from image. Printed character recognition is important in the context of document image analysis. Machine learning Approach such as pattern recognition and matching can be applied to document image based printed character recognition. In this paper we discussed the Template Matching approach to printed character recognition. Template matching is found to be an effective technique to recognize printed character as compared to neural network and other classification techniques. © 2013 Springer.

Advances in Intelligent Systems and Computing

An approach for document image based printed character recognition

Random Forest is an Ensemble Supervised Machine Learning technique. Research work in the area of Random Forest aims at either improving accuracy or improving performance. In this paper we are presenting our research towards improvement in learning time of Random Forest by proposing a new approach called Disjoint Partitioning. In this approach, we are using disjoint partitions of training dataset to train individual base decision trees. This helps in creating diversity in base decision trees. Also different subsets of attributes are used at each node of decision tree to increase diversity. This approach generates Random Forest classifier which is trained efficiently and gives classification accuracy comparable to the original Random Forest approach.

Lecture Notes in Engineering and Computer Science

Efficient learning of random forest classifier using disjoint partitioning approach

To improve market value, any horticulture product should meet quality standards. Abnormality in fruit shape represents a defective fruit which can be rejected while exporting. This study was conducted to evaluate applicability of mother wavelet for mango shape sorting. A database of images was first formulated from mangoes with different shapes and sizes. The methodology consists of two phases. During the first phase, deformed mango fruits were separated out from well formed one using Wavelet based shape features and Support Vector Machines. The average correct classification was 86.36% for a testing set composed of 220 mangoes. The second phase involves extraction of size characteristics of well formed mangoes using statistical method. Experimental results showed that well-formed mangoes are classified by statistical size estimation method achieves 93.963% accuracy indicating that developed sorting algorithm has potential in detection and sorting of deformed mango fruits. © 2013 IEEE.