Sheejakumari V.,Rajaas Engineering College |
Sankara Gomathi B.,National Engineering College
Computational and Mathematical Methods in Medicine | Year: 2015
The advantages of magnetic resonance imaging (MRI) over other diagnostic imaging modalities are its higher spatial resolution and its better discrimination of soft tissue. In the previous tissues classification method, the healthy and pathological tissues are classified from the MRI brain images using HGANN. But the method lacks sensitivity and accuracy measures. The classification method is inadequate in its performance in terms of these two parameters. So, to avoid these drawbacks, a new classification method is proposed in this paper. Here, new tissues classification method is proposed with improved particle swarm optimization (IPSO) technique to classify the healthy and pathological tissues from the given MRI images. Our proposed classification method includes the same four stages, namely, tissue segmentation, feature extraction, heuristic feature selection, and tissue classification. The method is implemented and the results are analyzed in terms of various statistical performance measures. The results show the effectiveness of the proposed classification method in classifying the tissues and the achieved improvement in sensitivity and accuracy measures. Furthermore, the performance of the proposed technique is evaluated by comparing it with the other segmentation methods. © 2015 V. Sheejakumari and B. Sankara Gomathi.
Bhagavathi Perumal S.,Rajaas Engineering College |
Thamarai P.,Salem College |
Elango L.,Anna University
Indian Journal of Environmental Protection | Year: 2010
A three - dimensional mathematical model to simulate regional groundwater flow was used in the coastal area of Kanyakumari district in South Tamil Nadu. The study area is characterized by heavy rainfall, less extraction of groundwater for agricultural, industrial and drinking water supplies. The types of soil in the study area aquifer are sandy clay. There are 75 well stations in the study area are located used to design the model as major pumping stations. A regional groundwater model using MODFLOW was developed for the Kanyakumari aquifers in order to simulate the groundwater head. The MODFLOW model simulates groundwater flow over an area of about 860 km 2, 70km long and 18km width with a grid size of 500m X 940m, 20 rows and 140 columns with a total of 1828 numbers of grids and one layer. The model simulated a transient- state condition for the period 2000 - 2010. The MODFLOW model was calibrated for steady and transient state conditions. There was a reasonable match between the computed and observed heads. The transient MODFLOW model was run until the year 2010 to forecast groundwater flow under various scenarios of pumping and recharge. Based on the modeling results, it is shown that the aquifer system is stable at the present rate of pumping along the coastal area of Kanyakumari. © 2010 - Kalpana Corporation.
Kumar P.S.,Rajaas Engineering College
European Journal of Scientific Research | Year: 2012
Now a day, Copper-based sintered composites produced by powder metallurgy processes are widely used in bearings and bushes. Also composites based on copper-tin alloys containing a solid lubricant have been developed as self-lubricating materials under onerous conditions of load, atmosphere and temperature. It is well known that the addition of graphite serves to reduce friction and wear in copper-tin alloys. However it should be noted that the addition of graphite or molybdenum disulfide (MoS2) has an adverse effect on the composites mechanical properties. In this paper, the lubricant MoS2 powders were coated with Cu to reinforce their bonding to the Cu particles in the composites during sintering. The hardness, microstructure and compression strength of the sintered specimens were examined. The friction and wear properties of the materials were estimated by a pinon- disc wear testing machine under multi-pass dry conditions at room temperature in air. Although mechanical properties of the composites decreased with increasing amount of added MoS2, the use of Cu-coated lubricant powders improved the compressive strength, impact strength. MoS2 was effective in reducing the wear and friction of the composites. Results showed that the wear rate of the composites decreases at room temperature with MoS2 addition. Particularly, the 5% MoS2 composites showed a very low coefficient of friction of 0.4. Wear Morphology was also studied by using SEM. It is also observed that the wear rates of the MoS2 composites increased considerably with the amount of MoS2 addition. This behavior is thought to be due to the absence of MoS2 and the presence of brittle CuMo2S3 compounds in the sintered composites. © 2012 EuroJournals Publishing, Inc.
Kumar S.J.J.,Rajaas Engineering College |
Madheswaran M.,Center for Advanced Research
Journal of Medical Systems | Year: 2012
An improved Computer Aided Clinical Decision Support System has been developed to classify the retinal images using Neural Network and presented in this paper. The Optic Disc Parameters, thickness of the blood vessels, main vessel, and branch vessel and vein diameter have been extracted. Various types of Neural Network have been used for classification. The percentage of False Acceptance Rate and False Rejection Rate of the SVM classifier is found less than other classifiers. The accuracy of the proposed system has been verified and found to be 97.47%. © 2012 Springer Science+Business Media, LLC.
Mariarputham E.J.,Rajaas Engineering College
Computational and Mathematical Methods in Medicine | Year: 2015
Accurate classification of Pap smear images becomes the challenging task in medical image processing. This can be improved in two ways. One way is by selecting suitable well defined specific features and the other is by selecting the best classifier. This paper presents a nominated texture based cervical cancer (NTCC) classification system which classifies the Pap smear images into any one of the seven classes. This can be achieved by extracting well defined texture features and selecting best classifier. Seven sets of texture features (24 features) are extracted which include relative size of nucleus and cytoplasm, dynamic range and first four moments of intensities of nucleus and cytoplasm, relative displacement of nucleus within the cytoplasm, gray level cooccurrence matrix, local binary pattern histogram, tamura features, and edge orientation histogram. Few types of support vector machine (SVM) and neural network (NN) classifiers are used for the classification. The performance of the NTCC algorithm is tested and compared to other algorithms on public image database of Herlev University Hospital, Denmark, with 917 Pap smear images. The output of SVM is found to be best for the most of the classes and better results for the remaining classes. © 2015 Edwin Jayasingh Mariarputham and Allwin Stephen.