Informatics Publishing Limited

M. Vasanthi ¹, P. Supriya ¹, R. Priya ¹, P. C. J. Peter ¹, V. Mohan ², Balasubramanian ¹

Affiliations
1 Department of Endocrinology, Dr. ALM Post Graduate Institute of Basic Medical Sciences, University of Madras, Taramani Campus, Chennai-600 113, IN
2 MV Diabetes Specialties Centre (P) Ltd., Chennai-600 086, IN

Abstract

This study was designed to understand the biochemical and hormonal changes associated with type-2 diabetes in South Indian men and menopausal women. Three groups of subjects were recruited for the study viz., age-matched normal (control), untreated and treated type-2 diabetic men and menopausal women. Untreated type-2 diabetic men had low levels of serum testosterone with unalteredestradiol and elevated insulin and Cortisol. Oral hypoglycemic agents did not influence serum insulin level but decreased the Cortisol with no change in testosterone and estradiol levels. Among biochemical parameters, blood glucose, glycosylated hemoglobin, triglycerides and creatinine were higher in both treated and untreated type-2 diabetic men. The levels of the HDL and LDL did not reflect any significant change.

Full Text

     

R. Priya ¹, Vasantha Kalyani David ²

Affiliations
1 Department of Computer Science, Sree Narayana Guru College, Coimbatore, IN
2 Department of Computer Science, Avinashilingam Deemed University, Coimbatore, IN

Abstract

Recently the usage of multimedia contents like images and videos has increased. This usage has created the problem of locating from a very large database. This paper presents Content Based Image Retrieval (CBIR) system that uses multiple feature fusion to retrieve images. The features like color, shape and texture are used. The color histogram is used to extract color feature and active contour model is used for shape extraction. K-means and SOM algorithms are used for clustering and dimensional reduction. The experimental results show that the proposed CBIR system is better in terms of precision, recall and speed of image retrieval.

Keywords

Content Based Image Retrieval, Color Histogram, Contour Model, K-Means, Self Organizing Map.

Full Text

     

R. Priya ¹, P. Aruna ¹

Affiliations
1 Department of Computer science and Engineering, Annamalai University, IN
2 Department of Computer Science and Engineering, Annamalai University, IN

Abstract

This paper proposes an automated system for the detection of important anatomical structures such as the Blood Vessels, Optic Disc (OD), Macula and also Exudates in digital fundus retinal images. Blood vessel Detection (BVD) was done using canny edge detection. Optic disc localization was done using pyramidal decomposition and Hausdorff-based template matching. Macula was located using pyramidal decomposition. Exudates are found using machine learning algorithm which uses k-nearest neighbor classifier and a linear discriminant classifier. The procedure has been tested on a database of about 100 color fundus images acquired from a digital non-mydriatic fundus camera and the experimental results show the accuracy of the system.

Keywords

Blood Vessels, Exudates, Macula, Optic Disc.

Full Text

     

R. Priya ¹, P. Aruna ¹, B. Ramkumar ¹

Affiliations
1 Computer Science and Engineering Department, Annamalai University, Chidambaram, Tamil Nadu, IN

Abstract

Glaucoma is one of the major reasons for blindness. Untreated glaucoma can lead to permanent damage of the optic nerve and resultant visual field loss, which over time can progress to blindness. For this reason, early detection of glaucoma is essential for affected patients. This paper is focused on classifying glaucoma with image-based features from fundus photographs. So in this work, we have detected the glaucoma disease in the retinal optical images. The extent of the disease spread can be identified by extracting the features of the retina. Detection of the disease is done using Probabilistic Neural Network (PNN) classifier. The accuracy of the proposed system is 94.54 %.

Keywords

Retina, Probabilistic Neural Network, Accuracy, Sensitivity, Specificity.

Full Text

     

S. Annapurani ¹, R. Priya ¹

Affiliations
1 Department of Biochemistry, Avinashilingam Institute for Home Science and Higher Education for Women, Deemed University, Coimbatore - 641 043, IN

Abstract

The challenge of chemotherapy is to produce effective tumour killing with minimum impact on normal tissues. Global estimates indicate that over three-fourth of the population cannot afford the products of western pharmaceutical industry and have to rely upon traditional medicines which are mainly derived from plants. Within the next decade or two, cancer is likely to become one of the leading causes of death. However, the bulk of cancer should be preventable because most of its causes are available.

Full Text

     

S. Annapurani ¹, R. Priya ¹

Affiliations
1 Department of Biochemistry, Avinashilingam Institute for Home Science and Higher Education for Women, Deemed University, Coimbatore - 641 043, IN

Abstract

Cancer is a genetic disease, arising from an accumulation of mutations that promote clonal selection of cells with increasingly aggressive behaviour. An individual who carries a mutant allels of an inherited cancer gene has a variable risk of cancer that is influenced by the particular mutation, other cellular genes and dietary, lifestyle and environmental factors. However cancer is largely a preventable disease. There are several protective agents in our diet including fiber, vitamins, certain minerals and non-nutrients which protect our body from carcinogens.

Full Text

     

R. Priya ¹, P. M. Sulfath ¹

Affiliations
1 Sree Narayana Guru College, K.G Chavadi, Coimbatore, IN

Abstract

Objectives: The main objective of this work is to survey various techniques used in the field of data dissemination in Vehicular Ad hoc NETwork (VANET).

Methods: There are different approaches used to improve data dissemination in vehicular ad-hoc network. Such approaches are context-aware information dissemination, Space-time network coding, geo-based Named data networking forwarding strategy, Route-based data pre-fetch model and etc.

Findings: VANET has become more popular in the areas of vehicular transportation systems. Data dissemination which is the base of communication plays a major role in VANET system. Various data dissemination technologies were developed for avoiding the issues such as data routing, vehicle mobility and network security. This paper provides brief explanation about several data dissemination techniques and compares their performance based on the output parameters, merits and demerits. Comparison result shows that, the prefetching based data dissemination technique outperforms than other techniques.

Application/Improvements: the result of this work shows that prefetching based data dissemination technique provides better result than the other dissemination techniques.

Keywords

VANET, Data Dissemination, Data Routing, Vehicle Mobility, Network Security.

Full Text

   

G. Kavitha ¹, R. Priya ¹

Affiliations
1 School of Computing Sciences, Vels University, Pallavaram, Chennai - 600117, Tamil Nadu, IN

Abstract

Objectives: Cloud computing is the sort of computing process that shares the data and its resources in the Internet. Data Leakage is the main challenge prevails in the federated cloud storage service. This challenge is overcome by proposing an efficient searchable encryption system. Methodology: An improved searchable encryption is designed to apportion the data among the multi-users. An efficient key management is the required phase of the encryption schemes. Owing to adversaries, a promising approach using conglomerate keys invents as a better searchable encryption schemes in multiowner applications. Findings: By reducing the count of trapdoor function to cloud data from the multi-user, an effective search over the encrypted data is performed. In compare to existing models, tree based approach and one to one function, the proposed, improved SE-CK works efficient in terms of lessened delegation ratio and conglomerate keys. Applications/ Improvements: This method can also be extended to the hybrid architecture like Indexing schemes, Re-encryption schemes etc.

Keywords

Data Sharing, Data Leakage and Multi-Owner Applications, Federate Cloud Storage, Searchable Encryption, Trapdoor Functions

Full Text

   

R. Priya ¹, P. Aruna ¹

Affiliations
1 Department of Computer Science and Engineering, Annamalai University, IN

Abstract

Diabetic retinopathy (DR) is an eye disease caused by the complication of diabetes and we should detect it early for effective treatment. As diabetes progresses, the vision of a patient may start to deteriorate and lead to diabetic retinopathy. As a result, two groups were identified, namely non-proliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR). In this paper, to diagnose diabetic retinopathy, three models like Probabilistic Neural network (PNN), Bayesian Classification and Support vector machine (SVM) are described and their performances are compared. The amount of the disease spread in the retina can be identified by extracting the features of the retina. The features like blood vessels, haemmoraghes of NPDR image and exudates of PDR image are extracted from the raw images using the image processing techniques and fed to the classifier for classification. A total of 350 fundus images were used, out of which 100 were used for training and 250 images were used for testing. Experimental results show that PNN has an accuracy of 89.6 % Bayes Classifier has an accuracy of 94.4% and SVM has an accuracy of 97.6%. This infers that the SVM model outperforms all other models. Also our system is also run on 130 images available from "DIARETDB0: Evaluation Database and Methodology for Diabetic Retinopathy" and the results show that PNN has an accuracy of 87.69% Bayes Classifier has an accuracy of 90.76% and SVM has an accuracy of 95.38%.

Keywords

Probabilistic Neural Network, Bayesian Classification, Support Vector Machine, Sensitivity, Specificity, Accuracy.

Full Text

     

R. Priya ¹, R. Padmajavalli ²

Affiliations
1 Research and Development Centre, Bharathiar University, Coimbatore - 641046, Tamil Nadu, IN
2 Department of Computer Applications, Bhaktavatsalam Memorial College for Women, Chennai - 600080, Tamil Nadu, IN

Abstract

Diagnosis of diseases is a difficult work that has to do in accurate manner. Text mining deals a great job in this field. A huge mass of data is available in biomedical field, using this data we can diagnosis many diseases by text mining techniques in efficient manner. Text mining methods are used to retrieve useful knowledge from large data. Objective: The aim of this paper is to review several text mining methods used in biomedical field. This survey is helpful to select a best text mining method for biomedical data. Methods/Analysis: In this paper, classification method is used to study the biomedical text mining for diagnosing diseases. In the field of biomedical, classification can be done on the basis of patient disease pattern to separate the patients into high risk or low risk The classification techniques have two methods they are Binary contains two classes and multilevel contains more than two classes. Classification method is widely used in biomedical text mining. In this paper different classification techniques can be applied to categorize the text they are SVM (Support Vector Machine) NN (Neural Network), K-NN (K-Nearest Neighbor), Bayesian Method and DT (Decision Tree). Findings: In this paper, different classification techniques were surveyed and their merits and limitations have been discussed. The various classification techniques were applied in medical data where useful patterns and knowledge were extracted. The important task is that to select the suitable data and classification method for disease diagnosis. The objective of this survey is that how the classification methods are applied in biomedical application and to select which method is suitable and efficient for diagnosis of a particular disease. Novelty/Improvement: The main advantage of the survey is that it can be applied to any kind of dataset, it is a description dataset or not. For future improvement, we will implement our proposed methodology on using some major chest diseases datasets and measured performance in terms of training time and accurate diagnosis.

Keywords

Biomedical Text Mining, Classification, Concept Linkage, IE (Information Extraction), Topic Tracking.

Full Text

   

R. Thanigaivelan ¹, N. Rajan ², M. Soundarrajan ¹, R. Priya ¹

Affiliations
1 Muthayammal Engineering College, Rasipuram, IN
2 Vinayaka Missions Kirupananda Variyar Engineering College, Salem, IN

Abstract

The Electrochemical Micromachining (EMM) is an micromachining techniques for machining electrically conducting, tough and difficult to machine materials with suitable machining parameter combinations. In EMM, an electrolyte characteristic shows significant effect on output characteristics namely Material Removal Rate (MRR), Overcut (OC) and Taper OC. Hence in this research mixed electrolyte along with varying concentration, machine voltage and duty cycle are taken as key input parameters. Sodium nitrate and oxalic acid used as an electrolyte between tool and work piece. The MRR, OC and taper overcut are significantly influenced by the electrolyte type. Optimization of multiple performance characteristics were analyzed by CRiteria Importance Through Intercriteria Correlation (CRITIC) and Simple Additive Weighting (SAW) methods. The mixed electrolyte shows higher MRR, lesser OC and lesser taper OC and the optimal parameter combination is mixed electrolyte with 20g/l, 8V and 85% duty cycle and micro hole circumference is analysed using the SEM pictures.

Keywords

Oxalic Electrolyte, Sodium Nitrate, CRITIC Method, SAW Method, Taper Overcut.

Full Text

     

Shri Krishna Tripathi ¹, Avinash Kumar ¹, R. Priya ¹, P. Ramesh ¹, Hemant Kumar ¹, G. Ramesh ¹

Affiliations
1 Indira Gandhi Centre for Atomic Research, Kalpakkam – 603 102, IN

Abstract

The Purex process is opted for reprocessing of spent fuel from fast breeder reactors. The process employs nitric acid with concentrations up to 11M. Nitric Acid Grade (NAG) SS304L is opted as material of construction for equipments, process tanks and piping of such process plants so as to minimise the corrosion losses due to nitric acid. Practice C test as per ASTM A262-15(2021) (Standard Practices for Detecting Susceptibility to Intergrannular Attack in Austenitic Stainless Steels), with maximum average corrosion rate of 15 mils/year (mpy) for five cycles of 48 hrs, and 18 mpy in any cycle, is one of the criteria for qualification of material among others. A similar acceptance criterion is adopted for qualification of undiluted weld metal deposit of filler material and welding procedure specification (WPS) used therein. However, conventional tests may not always accurately represent the corrosion behaviour of surfaces at all locations. One of such are the surfaces which abut each other, and hence are not approachable for visual examination and thereafter cleaning, such as unwelded open abutted surfaces of fillet weld joint (root), partial penetration (pp) weld joints facing process fluids in abutted portions not in a welded portion of joint. Multiple factors like remains of heat tints, adjacent inter-spaces and type of surface finish may collectively contribute to corrosion rates exceeding acceptable limits. This study delves into the often-neglected corrosion behaviour of these challenging regions. The samples with abutting surfaces are prepared by using EDM cutting and and Gas tungsten arc welding (GTAW) and subjected to corrosion test. The samples made by using base material, filler and WPS that already qualified for corrosion test for groove weld joints and hence fillet weld joints as per ASME BPVC sec IX (2021). Higher corrosion rates are being observed in these weld joints than standard test specimens during study.

Keywords

Abutting Surfaces, Heat Tint, Gas Tungsten Arc Welding, Huey Test.

Full Text