Sungheetha A.,Karpagam College of Engineering
Proceedings of 2017 11th International Conference on Intelligent Systems and Control, ISCO 2017 | Year: 2017
Over the years, the growth in medical image processing is increasing in a tremendous manner. The rate of increasing diseases with respect to various types of cancer and other related human problems paves the way for the development in biomedical research. Thus processing and analyzing these medical images is of high importance for clinical diagnosis. This work focuses on performing effective classification of brain tumor images and segmentation of live disease images employing the proposed hybrid intelligent techniques. The challenges and objectives on design of feature extraction, image classification and segmentation for medical images are discussed. © 2017 IEEE.
Rajarajeswari P.L.,Sri Krishna College of Engineering And Technology |
Karthikeyan N.K.,Karpagam College of Engineering
Journal of Intelligent and Fuzzy Systems | Year: 2017
The lifetime of a Wireless Sensor Network (WSN) depends on the efficiency of the Cluster Head (CH) selection techniques that address most of the significant issues related to network management. The existing energy based CH selection mechanisms consider that all the participating sensors are trustworthy. Conversely, the trust-based CH selection schemes assume that the sensor nodes are energy efficient. But, these assumptions of energy factor or trust assessment made by the CH selection mechanisms may not be true and the Residual Energy (RE) of the sensors may not be the sole factor to identify an effective CH in a WSN. Hence, this paper presents hybrid integrated energy and trust assessment based forecasting model known as Hyper-geometric Energy Factor based Semi-Markov Prediction Mechanism (HEFSPM) for effective CH election so as to improve the lifetime of the network. From the simulation results, it is inferred that HEFSPM is superior in improving the lifetime of the network to a maximum extent of 22 than the existing CH election mechanisms considered for investigation. © 2017-IOS Press and the authors. All rights reserved.
Shanmughasundaram P.,Karpagam College of Engineering |
Subramanian R.,PSG College of Technology
Advances in Materials Science and Engineering | Year: 2013
Dry sliding wear behaviour of eutectic Al-Si alloy-graphite composites was investigated employing a pin-on-disc wear test rig. Results revealed that the wear and friction coefficients decreased linearly with increasing weight percentage of graphite particles. Wear resistance of the composite increased considerably with increasing sliding velocity at constant load. In contrast, the friction coefficient of Al-7.5 wt.% Gr composite increased when the sliding velocity was increased from 1 m/s to 2 m/s at 49 N. Worn-out surfaces of wear specimens after the test were examined by scanning electron microscopy to study the morphology of worn surfaces. EDS analysis was carried out to investigate the influence of mechanically mixed layer (MML) which comprises oxides and iron, and this acted as an effective tribolayer in enhancing the wear resistance at higher sliding velocity. © 2013 P. Shanmughasundaram and R. Subramanian.
Shanmughasundaram P.,Karpagam College of Engineering |
Subramanian R.,PSG College of Technology
Journal of Mechanical Science and Technology | Year: 2013
This paper presents an experimental investigation on the surface roughness of pure commercial Al, Al-15 wt% fly ash, and Al-15 wt% fly ash/1.5 wt% graphite (Gr) composites produced by modified two-step stir casting. The effect of reinforcements and machining parameters such as cutting speed, feed rate, and depth of cut on surface roughness, which greatly influence the performance of the machined product, were analyzed during turning operation. The optimum machining parameters were found in minimizing the surface roughness of the materials by using the Taguchi and ANOVA approach. Results show that the presence of the fly ash particles reduces the surface roughness of composites compared with pure Al. The inclusion of 1.5 wt% Gr in the Al-fly ash composite reduces the surface roughness considerably. A scanning electron microscopy investigation was carried out on the machined surfaces of the tested materials. Confirmation tests were performed to validate the regression models. © 2013 The Korean Society of Mechanical Engineers and Springer-Verlag Berlin Heidelberg.
Kathirvel P.,Karpagam College of Engineering |
Ravi S.,Karpagam University
Natural Product Research | Year: 2012
This study examines the chemical composition and in vitro anticancer activity of the essential oil from Ocimum basilicum Linn. (Lamiaceae), cultivated in the Western Ghats of South India. The chemical compositions of basil fresh leaves were identified by GC-MS: 11 components were identified. The major constituents were found to be methyl cinnamate (70.1%), linalool (17.5%), β-elemene (2.6%) and camphor (1.52%). The results revealed that this plant may belong to the methyl cinnamate and linalool chemotype. A methyl thiazol tetrazolium assay was used for in vitro cytotoxicity screening against the human cervical cancer cell line (HeLa), human laryngeal epithelial carcinoma cell line (HEp-2) and NIH 3T3 mouse embryonic fibroblasts. The IC50 values obtained were 90.5 and 96.3 μgmL -1, respectively, and the results revealed that basil oil has potent cytotoxicity. © 2012 Taylor & Francis.
Kannappan A.,Karpagam College of Engineering |
Tamilarasi A.,Kongu Engineering College |
Papageorgiou E.I.,Technological Educational Institute of Lamia
Expert Systems with Applications | Year: 2011
The soft computing technique of fuzzy cognitive maps (FCM) for modeling and predicting autistic spectrum disorder has been proposed. The FCM models the behavior of a complex system and is used to develop new knowledge based system applications. FCM combines the robust properties of fuzzy logic and neural networks. To overwhelm the limitations and to improve the efficiency of FCM, a good learning method of unsupervised training could be applied. A decision system based on human knowledge and experience with a FCM trained using unsupervised non-linear hebbian learning algorithm is proposed here. Through this work the hebbian algorithm on non-linear units is used for training FCMs for the autistic disorder prediction problem. The investigated approach serves as a guide in determining the prognosis and in planning the appropriate therapies to special children. © 2010 Elsevier Ltd. All rights reserved.
Joe C.V.,Karpagam College of Engineering
2014 International Conference on Science Engineering and Management Research, ICSEMR 2014 | Year: 2014
Finding the user's emotion it can be used for business development and psychological analysis. The motivation of this paper is to build the Tamil emotional corpus for being base for the emotional analysis based on the acoustic variations present and to make Tamil emotional corpus available in public domain. Tamil Play will be used as main resource for building the emotional corpus. Basically, emotions like Happy, Neural, Sad, Fear and Anger are taken for this analysis purpose. And also for the accuracy purpose from the play both Male and Female Speakers emotional speech have been considered. The observer's perception test result will be used to evaluate annotation of emotion. Tamil emotional speech corpus have been built and Emotion Recognition engine has been constructed using Support Vector Machine (SVM) classifier with the features like MFCC and Energy. © 2014 IEEE.
Rajaram A.,Karpagam College of Engineering |
Gopinath S.,Anna University
Journal of Theoretical and Applied Information Technology | Year: 2014
Mobile Ad hoc Network is the indivisible part of wireless network. In the past few years, the popularity of MANET grows unlimitedly. Due to the presence of mobility and infrastructure less topology, the vulnerability of ad hoc networks is introduced unconditionally. So the failures of link, path and node may occur which leads to lack of communication between the users. Sometimes the malicious attackers arise to make more damage to network connectivity and produce false information among the mobile nodes. To overcome this issue, several approaches are developed to make more efficient routing. But they have not focused on failures of node, link and path as well as malicious activities at a time. We proposed Optimized Multicast Routing Scheme (OMRS) to attain balance between the above said issues. In first phase of this scheme, we develop the detection and avoidance of malicious attacks is implemented with the predetermined trust value of node characteristics. We have also introduced the characteristics of malicious attacks in linear network systems. In second phase, stability ratio of link, path and node is determined to maintain threshold value which ensures the resilience to the path failures. By implementing these solutions, we have achieved better stability and node connectivity towards the ultimate goal of multicast routing scheme. We implement our proposed scheme within Network Simulator (NS2.34) tool environment. By using the extensive simulation results, the proposed scheme achieves better delivery ratio, detection ratio, probability of failure occurrence and less communication overhead, end to end delay than the ODMRP, BDP. © 2005 - 2014 JATIT & LLS. All rights reserved.
Sathesh K.,Karpagam College of Engineering
Microsystem Technologies | Year: 2011
Components like passive electronically scanned (sub) arrays, T/R modules, reconfigurable antennas etc., in RF applications are in need of MEMS switches for its re-configurability and polarization. This paper presents the analysis, design and simulation of a MEMS switch. The switch proposed in this paper is intended to work in the frequency range of 4-8 GHz. The proposed switch fulfills the switching characteristics concerning the five requirements loss, linearity, high switching speed, small size/power consumption, low pull down voltage following a relatively simple design, which ensures reliability, robustness and high fabrication yield. The switch implemented in this paper is based on the integration mode of operation and widely used in RF applications. © 2010 Springer-Verlag.
Velmyl P.,Karpagam College of Engineering
Proceedings of International Conference on Electronics Communication and Computing Technologies 2011, ICECCT'11 | Year: 2011
Cloud computing is the emerging computing technology platform which resolves for a single platform for diversive applications. The paper takes up the issues of security, migration of applications from an internal data centre into cloud, scalability, billing and security. The paper thus points out the hardware incongruence for the cloud computing and presents key concepts for fabrication of VLSI chips. For example, the bills for cloud storage access is based on I/0 count. This metric is inaccurate since the cost of handling the bits varies from disk to disk. This arises due to variance of random access and sequential access used in disk. In sequential access, data is written to or read from one portion of the disk in a continual stream of bits. In random access, the disk head must jump around to different parts of the disk to read or write data. This disparity is immense since, sequential access can achieve a throughput on an average disk of up to 63.5MB/s (megabits per second), whereas random access can only be executed at 1.5MB/s. Techniques for reducing the random access and unnecessary metadata lookups are analyzed. The external threats for cloud from hardware hacking is attended and key alternatives are suggested for networking environment. © 2011 IEEE.