Subiramoniyan S.,Satyabama University
Research Journal of Applied Sciences, Engineering and Technology | Year: 2015
In this study, a simple PI controller is presented for regulation of the output voltage of the DC to DC fly back converter driven DC Servo motor with constant frequency. Here a new PI control algorithm implemented in FPGA has been proposed for optimizing the PI parameters using PSO and ABC optimization techniques. A comparison has been made between the two optimization algorithms across different load and voltage variations and their effectiveness in reduction of overshoot and settling time of fly back converter in DC Servo motor drive have been evaluated. © Maxwell Scientific Organization, 2015.
Lakshmi D.,Satyabama University
2016 International Conference on Advances in Human Machine Interaction, HMI 2016 | Year: 2016
An increasingly large amount of multimodal content is posted on social media websites such as YouTube and Face book every day. In order to cope with the growth of such so much multimodal data, there is very urgent need to develop an intelligent multi-modal analysis framework that can effectively extract information from multiple modalities. In this research work, here propose a novel multimodal information extraction agent, which infers and aggregates the semantic and affective information associated with user generated multimodal data in contexts such as e-learning, e-health, automatic video content tagging and human-computer interaction(HCI). In particular, the developed intelligent agent adopts an ensemble feature extraction approach by exploiting the joint use of tri-modal (text, audio and video data) features to enhance the multimodal information extraction process. In preliminary experiments using the INTERFACE and SEMINE dataset, our proposed multi-modal system is shown to achieve an accuracy of 88.75%, outperforming the best state-of-the-art system by more than 10%, or in relative terms, a 46% reduction in error rate. © 2016 IEEE.
Austin N.,Satyabama University
ARPN Journal of Engineering and Applied Sciences | Year: 2012
This paper presents an artificial neural network approach with back propagation algorithm (BPA) to find an alternative to Chloroflurocarbon (CFC) by considering the mixture of Hydro fluorocarbon (HFC) and Hydrocarbon (HC). The thermodynamic properties of refrigerants are obtained using REFPROP 9. Correspondingly, the Coefficients of Performances (COPs) of the mixed refrigerants have been obtained. The testing of the ANN shows high performance in estimating the closest COP. © 2006-2012 Asian Research Publishing Network (ARPN).
Krishnaveni S.,Satyabama University |
Ravi S.,Dr. M.G.R. Educational and Research Institute
Journal of Computational and Theoretical Nanoscience | Year: 2017
In this work, the electromechanical is implemented to design a resonant DC/AC power inverter. This approach is used two-port electrodynamics transformer to provide with lower component count compared to electrical design is proposed. The system consists of permanent magnet, two coils and a cantilever beam. With addition, a MOSFET and an output capacitor act like a resonant DC/AC inverter is also demonstrated. This macro system exhibits very low power density and high efficiency, where improved performance is expected with miniaturization of the components. This work is focused on miniaturizing the components and maximizing the power density of the power converter systems also. To observe MEMS technique, it is used mechanical structures to realize electrical functionalities. The macroscale (9.6 cm3) electrodynamic transformer consists of a permanent magnet, two coils and a cantilever beam emulates an electrical transformer, three inductors, and one capacitor at the same time. The results demonstrated the power inverter functionality with tunable output AC voltage amplitude (15 dB dynamic range) when the MOSFET switching frequency is adjusted within 360±3 Hz which is experimented in MatLab. Copyright © 2017 American Scientific Publishers All right reserved.
Dhiravidachelvi E.,Satyabama University |
Rajamani V.,Veltech Multi Technology Engineering College
Journal of Computer Science | Year: 2015
In recent years the medical profession has seen an ever increasing demand for diagnosis and a permanent cure for illnesses caused by climatic-changes, unwholesome food and environmental pollution. Also the appearances of hitherto unknown viral diseases have caused eye diseases, which have prompted surgeons to monitor the health of the eyes. Potential new therapies that may help in preserving sight in the growing population of diabetic patients into the 21st Century. Early detection of diseases affecting the eyes reduces the risk of permanent damage. Some of the serious conditions which warrant early diagnosis are: Glaucoma, floaters, macula degradation and diabetic retinopathy. In the early stages, a choice of treatment options exist, which dwindles as the disease spreads. A visual inspection of the optic disc, macula and the blood vessels of the eye requires to be done routinely. Diabetic patients run the risk of damage to retinal vessels, which are referred to as diabetic retinopathy. This may further be classified as: Non-proliferative diabetic retinopathy and proliferative diabetic retinopathy. In scientific literatures, feature extraction method has been reported for diagnosis and classification. In this study a systematic Decide, Detect, Determine and Do approach for analyzing diabetic retinopathy images has been taken up. The proposed approach gives a clearer picture of the abnormality, its type (NPDR or PDR), its status (viz., mild, moderate or severe) and finally the appropriate treatment. © 2015 The Dhiravidachelvi, E. and V. Rajamani.
Ganesh S.,Satyabama University |
Amutha R.,SSN College of Engineering
European Journal of Scientific Research | Year: 2011
Wireless Sensor Networks (WSN) is becoming a viable tool for many applications. In many cases these applications may be of critical nature, where the transmitting of vital information from sensors to base station or sink is crucial, and data loss cannot be tolerated. In a Wireless Sensor Network, the sensor nodes rely upon a multi-hop routing protocol to relay their data to the base station. However, most WSN routing protocols are vulnerable to attacks in which a malicious node can disrupt the routes, drop, modify or divert data away from the base station. Triple Umpiring System (TUS) has already been proved its better performance on mobile ad hoc network (MANET) in which each node in the path from source to destination has dual roles to perform: packet forwarding and umpiring. In the umpiring role, each node in the path closely monitors the behavior of its succeeding node and if any misbehavior is noticed immediately flags off the guilty node. In this paper, we investigate how well this ad hoc routing protocol works on WSN. For demonstration, we have implemented the umpiring system by modifying the popular Ad hoc on- demand Distance Vector routing protocol (AODV). We focus on their (TUS and AODV) performances in terms of Packet delivery ratio (PDR), average end to end delay and Communication overheads. Extensive investigation studies using QualNet 5.0.2 simulator show that TUS significantly improves the PDR by 28.3% and decreases end to end delay by 20% in the presence 40% malicious nodes with varying network load.© EuroJournals Publishing, Inc. 2011.
Bottu B.,Sathyabama University |
Srilatha K.,Satyabama University
International Journal of Applied Engineering Research | Year: 2015
Accurate parenchymal lung tumor delineation with PET-CT can be problematic given the inherent tumor heterogeneity and proximity/involvement of extra-parenchymal tissue. In this proposed method, we propose a tumor delineation approach that is based on new tumor–Ground truth method models for a given image. The ground truth method givesmore efficient results compared to other methods. Then this method extends to segmentation, region based graph methods and other segmentation model is k-means algorithm is used. After the tumor detection part move on to classification part, this classification done by neural network based implementation has been used. The result computation is very fast the more efficiency. In background likelihood method not efficient compare other methods. The above model is processed in MATLAB tool and achieve high efficiency in the detection and classification model compared to previous one. © Research India Publications.
Dhiravidachelvi E.,Satyabama University |
Rajamani V.,Veltech Multi Technology
2014 International Conference on Circuits, Power and Computing Technologies, ICCPCT 2014 | Year: 2014
Recently, most of the people working in Medical field need a CAD system to investigate and analyze the diseases to provide appropriate treatment and prevent from diseases in the earlier stage itself In this paper an automatic Optic Disc detection for analyzing and diagnosing the disease level in the fundus images has been introduced The retina has the features like optic disc, macula, fovea, micro aneurysms, exudates. The optic disc is detected and removed, since it has the homogeneity with the abnormal feature like exudates. This CAD system helps the ophthalmologist to do further investigation and prior knowledge about the disease. The proposed approach contains a sequence of steps where the fundus image has been preprocessed by histogram equalization and the optic disc is detected by using background subtraction and contour detection method. © 2014 IEEE.
Sathishkumar R.,Satyabama University |
Ramesh C.,Ericsson AB
Journal of Engineering and Applied Sciences | Year: 2016
Black hole attack is a serious security problem to be solved for active delivery of packets of data in Mobile Ad-Hoc networks. In this problem, a malicious node uses routing protocol to promote itself as having the shortest path to the node whose packets it wants to snatch. In flooding based protocol, if the malicious node reply reaches the requesting node before the reply from the actual node, a fake route is created and try to send the packets of data. This research study deals with the presentation of preventing black hole attack in Mobile Ad Hoc Network (MANET). Various prevention techniques have been discussed in the study that are used to prevent black hole attack. Mobile Ad Hoc networks are susceptible to various attacks, so attacks have to be mitigated in initial setup. © Medwell Journals, 2016.
Stalin R.,Satyabama University |
Senthil Kumar S.,Satyabama University |
Rani Fathima K.A.,Satyabama University
2016 2nd International Conference on Science Technology Engineering and Management, ICONSTEM 2016 | Year: 2016
System stability and protection from any disturbances are significant problems in power system especially in a distribution system with dispersed generation. Superconductivity is expected to be a powerful controller to stabilize and protect the power systems. SMES is effective to damp the power swing Improvement transient stability SMES not able to absorb enough energy during fault. In order to enhance the control effect of SMES resistive type SFCL is installed appropriately. The optimal parameter of SFCL & SMES can be automatically obtained. UPFC is used to smooth out the power output. UPFC (Unified Power Flow Controller) is the most powerful FACTS devices, it can vary the parameter values independent so that it can control the power flow. Superconducting Magnetic Energy Storage (SMES) is effective to damp the power swing after the occurrence of faults. To enhance the SMES control effect and transient stability, this project proposes the coordinated control of the optimized resistive type superconducting fault current limiter (SFCL) inconpereted with active part UPFC, SMES acts as the storage device. Since the stored energy of the capacitor is limited, it can only continuously inject into the system or absorb reactive power from the system, but to provide active power compensation for a long time Super conductor magnetic storage system (SMES) was applied. The system are simulated in Matlab Simulink platform and appreciable results are obtained. © 2016 IEEE.