Time filter

Source Type

Dongre S.,Sinhgad Institute of Technology
2010 International Conference on Computer and Communication Technology, ICCCT-2010 | Year: 2010

The medical diagnosis process can be interpreted as a decision making process, during which the physician induces the diagnosis of a new and unknown case from an available set of clinical data and from his/her clinical experience. This process can be computerized in order to present medical diagnostic procedures in a rational, objective, accurate and fast way. This paper presents a decision support system for heart disease classification based on support vector machine (SVM) and Artificial Neural Network (ANN). A multilayer perceptron neural network (MLPNN) with three layers is employed to develop a decision support system for the diagnosis of heart disease. The multilayer perceptron neural network is trained by back-propagation algorithm which is computationally efficient method. Results obtained show that a MLPNN with backpropagation can be successfully used for diagnosing heart disease than support vector machine. ©2010 IEEE.


Karande Kailash J.,NBN Sinhgad Technical Institute Campus | Talbar Sanjay N.,Shri Guru Gobind Singhji Institute of Engineering and Technology | Inamdar Sandeep S.,Sinhgad Institute of Technology
2012 2nd International Conference on Digital Information and Communication Technology and its Applications, DICTAP 2012 | Year: 2012

The problem of face recognition using Laplacian pyramids with different orientations and independent components is addressed in this paper. The edginess like information is obtained by using Oriented Laplacian of Gaussian (OLOG) methods with four different orientations (0°, 45°, 90°, and 135°) then preprocessing is done by using Principle Component analysis (PCA) before obtaining the Independent Components. The independent components obtained by ICA algorithms are used as feature vectors for classification. The Euclidean distance (L2) classifier is used for testing of images. The algorithm is tested on two different databases of face images for variation in illumination, facial expressions and facial poses up to 180° rotation angle. © 2012 IEEE.


Bhowte Y.W.,Sinhgad Institute of Technology
2016 International Conference on Computation of Power, Energy, Information and Communication, ICCPEIC 2016 | Year: 2016

Electrical Energy is one of the most fundamental parts of our universe. Energy has come to be known as a 'strategic commodity' and any uncertainty about its supply can threaten the functioning of the economy, particularly in developing economies. Achieving Electric energy security in this strategic sense is of fundamental importance not only to India's economic growth but also for the human development objectives that aim at alleviation of poverty and unemployment and meeting the Millennium Development Goals Holistic planning for achieving these objectives requires quality energy statistics that is able to address the issues related to energy demand, energy supply and environmental effects of energy growth. In this paper, the Garch model is used to determine the market volatility in the demand and supplychains of electricity in Nigeria for 36 years, i.e. from 1970 to 2005 from the historic data obtained from the National Bureau of Statistics. The Harvey logistic model is used to predict the demand and supply of electricity in the country from 2005 to 2026. © 2016 IEEE.


Chaudhary D.D.,Sinhgad Institute of Technology | Waghmare L.M.,Shri Guru Gobind Singhji Institute of Engineering and Technology
Proceedings of the 2013 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2013 | Year: 2013

In delay sensitive applications of wireless sensor network, it is required to monitor the situation continuously with the sensors. The continuous monitoring operation results in more energy consumption of the sensor nodes. If the delay in data processing and it's communication from one node to other is more, then energy requirement may increase. In most of the situations, it is difficult to replace the battery of a sensor node, after the deployment of node in the network. The efficient energy management and low latency are the important issue in such applications as they affect the life of network. Many protocols are suggested by various researchers for energy efficient data process and minimum latency in sensor networks. There are limitations in existing protocols as they are particularly designed either for energy efficiency or minimum latency or for both. This paper presents the new protocol to overcome some of the existing protocol's limitations. In this paper, a concept of distance metric based routing protocol approach is explored, for 'high energy efficiency' and 'shortest path selection' for latency improvement. The proposed new protocol is 'Dynamic Energy Efficient Latency Improving Protocol (DEELIP)'. The simulation results are compared with 'AODV' routing protocol. It is observed that in proposed protocol; the overhead of the network traffic is reduced, resulting in improvement of energy efficiency and latency than existing routing protocols. © 2013 IEEE.


Barde S.I.,Sinhgad Institute of Technology | Walke G.R.,Sinhgad Institute of Technology
2016 - Biennial International Conference on Power and Energy Systems: Towards Sustainable Energy, PESTSE 2016 | Year: 2016

Maintaining synchronous and stable operation in interconnected power system at minimum cost is complex problem. To ensure the continuous supply of electricity all synchronous generators must remain in synchronism during abnormal conditions also. In this work, Distributed Static Series Compensator (DSSC) is used to maintain required transient stability in power system during severe three-phase to ground fault and, it is found that DSSC is capable of maintaining synchronous operation in a considered two machine power system along with power system stabilizer as a supplementary controller. © 2016 IEEE.


Chaudhary D.D.,Sinhgad Institute of Technology | Waghmare L.M.,Shri Guru Gobind Singhji Institute of Engineering and Technology
Proceedings of the 2012 7th IEEE Conference on Industrial Electronics and Applications, ICIEA 2012 | Year: 2012

The delay sensitive industrial control applications like Industrial process control, Environmental control, Gas leakage monitoring, etc. in this a reliable communication between sensor and base station are highly essential. Wireless Sensor Networks (WSN) becomes an immensely popular technology in such application as it offers low latency and high energy-efficiency in message transmission. Life span of the network can be extended by using appropriate energy efficient routing protocol. The three standard routing protocols, namely Ad-hoc On-Demand Distance Vector, Destination Sequence Distance Vector and Ad-hoc On-demand Multipath Distance Vector have been analyzed. In this work we have proposed multi-sink model to compare with conventional single sink model. We have designed probabilistic model to compare transmission delay in these two models. They are also compared with IEEE802.11 and IEEE802.15.4 MAC protocol. The proposed WSN model is analyzed by estimating end-to-end delay, energy consumption and packet drop ratio of both models. NS-2 simulator is used for result analysis in different traffic conditions. The Quality of Service can be improved by minimizing delay in packet delivery of the network. It has been observed that overall delay can be minimized significantly in proposed model. © 2012 IEEE.


Kumbhar V.S.,Shivaji University | Lokhande A.C.,Sinhgad Institute of Technology | Gaikwad N.S.,Yashavantrao Chavan Institute of Science | Lokhande C.D.,Shivaji University
Materials Science in Semiconductor Processing | Year: 2015

In the present letter, a novel aqueous chemical method is employed to prepare thin film of Sm2S3 material containing porous network of interconnected nanoparticles for super-capacitive application. The orthorhombic phase formation of Sm2S3 film is concluded from X-ray diffraction study. The chemical states of samarium and sulfur are determined using X-ray photoelectron spectroscopy study. The pseudocapacitive behavior of Sm2S3 showed a maximum specific capacitance of 248 F g-1 in 1.5 M LiClO4 electrolyte prepared in propylene carbonate electrolyte. The nature of charge and discharge curves confirmed pseudocapacitive behavior of film electrode. The highest power and energy densities of 15.6 kWh kg-1 and 54.6 Wh kg-1, respectively are obtained. An electrochemical stability of 94% is retained after 1500 cycles. © 2015 Elsevier Ltd. All rights reserved.


Nawale S.D.,Sinhgad Institute of Technology | Sarawade N.P.,Veermata Jijabai Technological Institute
Proceedings of the International Conference on Sensing Technology, ICST | Year: 2012

Since RFID is wireless technology, it enables the identification from a distance, depending upon the read range of the tag. There is a vast requirement of RFID technology in security, military, health-care, airline, library, sports, farming and other applications, not only for identification but as a sensor to monitor different parameters related to these fields. RFID based environmental sensor can be designed with the integration of sensing material in a microstrip antenna. The properties of the sensing material are responsible for converting a passive tag as a sensor. Here, RFID based passive chemical vapor sensor is presented doped with the conducting polymer. A sensitive Polystyrene Sulfonate is used as sensing material to integrate in H-shaped slot of PIFA like tag. The designed tag working at 870 MHz is characterized by turn-on and back-scattered power measurements. The experimental results are also presented by considering known and unknown percentage of water vapor and the moisture levels. © 2012 IEEE.


Chaudhary D.D.,Sinhgad Institute of Technology | Waghmare L.M.,Shri Guru Gobind Singhji Institute of Engineering and Technology
Wireless Personal Communications | Year: 2014

In delay sensitive applications of wireless sensor network, it is required to monitor the situation continuously with the sensors. The continuous operation and processing delay, may contribute latency in data communication. This results in more energy consumption of the sensor nodes. It is difficult to replace the battery of a sensor node, after the deployment in the network. The efficient energy management and low latency are the important issues in delay sensitive applications as they affect the life of network. There are some limitations in existing routing protocols as they are particularly designed either for energy efficiency or minimum latency. This paper presents the new protocol to overcome some drawbacks of the existing protocols. A concept of distance metric based routing is explored for shortest routing path selection. This helps to reduce the overhead of the network traffic, which results in improvement of energy efficiency and latency. The simulation results are compared with standard 'AODV' routing protocol. It is observed that, this 'Dynamic Energy Efficient and Latency Improving Protocol' will be very much suitable for wireless sensor networks in industrial control applications. © 2014 Springer Science+Business Media New York.


Borawake M.P.,University of Pune | Rameshwar K.,Sinhgad Institute of Technology
International Conference on Electrical, Electronics, Signals, Communication and Optimization, EESCO 2015 | Year: 2015

My research work address dilemma of categorization of uninterrupted general aural data for content based recovery. This research article deals with scheme for classifying aural data Segmentation is also done on same data so that processing rate is faster. Aural data is able to classify into eight categories simple speech, noise, silence, music, single speech with music, double speech with music, speech without music, instrument sound. There are so many features are there, among that linear prediction coefficient, Mel-frequency campestral coefficients etc. We studied all possible features. Depending upon Campestral based features which provide accurate classification. To reduce errors aural segmentation is done. So that processing rate is faster & to get more accuracy. There are so many features are there, among that linear prediction coefficient, Mel-frequency Cepstral coefficients etc. We studied all possible features. Depending upon Cepstral based features which provide accurate classification. To reduce errors aural segmentation is done. So that processing rate is faster & to get more accuracy. © 2015 IEEE.

Loading Sinhgad Institute of Technology collaborators
Loading Sinhgad Institute of Technology collaborators