scispace - formally typeset
Search or ask a question
Author

N. Savitha

Bio: N. Savitha is an academic researcher from VIT University. The author has contributed to research in topics: Higher education & Emerging markets. The author has an hindex of 2, co-authored 4 publications receiving 7 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: In this article, a comparative study on various classification approaches such as Decision Tree, Support Vector Machine, K-Nearest Neighbor and Random Forest have also been conducted with a focus on cross validation to identify the best performing model.
Abstract: Objective: To suggest an automated diagnostic system for the early detection of breast cancer. Methods: This problem has been addressed by making use of machine learning algorithms that can accurately classify a tumor as either malignant or benign by identifying the minimum number of image features. A comparative study on various classification approaches such as Decision Tree, Support Vector Machine, K-Nearest Neighbor and Random Forest have also been conducted with a focus on cross validation to identify the best performing model. Findings: The study shows that Random Forest classifier gives the maximum accuracy. It also highlights that cross validation and fine tuning are necessary to prevent over fitting of data. Improvements: It has been observed that the selection of parameters play a very important role in correct classification as multicollinearity among attributes can render classifier models ineffective. Keywords: Breast Cancer, Classification, Cross Validation, Decision Tree, K-Nearest Neighbor, Logistic Regression, Random Forest, Support Vector Machine

3 citations

Journal ArticleDOI
N. Savitha1
01 Jan 2015
TL;DR: It is found that workers who have been born and brought up in urban areas have shown higher tendency to avail private health care services than those workers whose nativity status is rural areas, and the reverse pattern is noticed among the sample workers in the case of government health services.
Abstract: Industrial workers constitute only a segment of general population and the factors that influence the health of the population also apply equally to industrial workers. The present study would bring out the availability and adequacy of health facilities in the urban Coimbatore. Therefore, the study of the people’s perception of health care services would indicate the line of improvement to be made in the health care services in future. Coimbatore is one of the most industrially developed Districts in Tamil Nadu and has the pride of being called the “Manchester of South India”. The data collected from both the textile and engineering industries in Coimbatore city was 1447 employees. It is found that workers who have been born and brought up in urban areas have shown higher tendency to avail private health care services (81%) than those workers whose nativity status is rural areas. Obviously, the reverse pattern is noticed among the sample workers in the case of government health services. The chi-square results between the nativity status and workers’ choice of health care services is found to be highly significant (p

2 citations

Journal ArticleDOI
TL;DR: It is suggested that increasing formal education on patients with diabetes would help them in choosing the appropriate healthcare services and they would be able to afford healthcare charges on their own.
Abstract: Introduction: Diabetes is a global health concern and also a major contributor to mortality in most developing countries. People usually choose the best available option to derive maximum satisfaction from healthcare services. Based on this the present study has been done to the factors influencing the choice of healthcare services of diabetic patients. Objective: The main aim of this study is to analyse the factors determining the diabetic patient’s choice of healthcare services. Methods: To analyse the socio-economic factors determining the diabetic patient’s choice of healthcare services, a binary logistic regression model was used. Results: Factors such as age, education, gender, monthly income and treatment cost were found to be the determinants. People’s choice of health care services was not identical and needs to be improved. At .000 p – valve treatment cost had a significant impact on healthcare choice. Conclusion: The study suggests that increasing formal education on patients with diabetes would help them in choosing the appropriate healthcare services and they would be able to afford healthcare charges on their own.

2 citations

Journal ArticleDOI
TL;DR: In this paper, an attempt has been made in this paper to study the relationship between education and economic development in general and India in particular, where an extensive survey of earlier studies on this ground has been surveyed and the present study envisages the importance of investment in higher education and human capital to attain sustainable economic development.
Abstract: “Education” as a key determinant of economic development and growth is believed to be the central focus of many emerging economies since they have managed to restructure their entire economic policies towards enhancing education (especially higher education) to attain economic development and growth at global standard in the recent past. Keeping all the facts in mind, an attempt has been made in this paper to study the relationship between education and economic development in general and India in particular. India has the 3rd largest higher education system in the world in terms of education after Chine and the US. For the purpose of the study, an extensive survey of earlier studies on this ground has been surveyed. On the basis of the assertion made by the earlier studies and evidence, the present study envisages the importance of investment in higher education and human capital to attain sustainable economic development.

1 citations


Cited by
More filters
01 Jan 1998

38 citations

Journal ArticleDOI
TL;DR: Among the three approaches, TAN produced the best performance regarding classification and accuracy, and the results obtained provide clear evidence for benefits of TAN usage in breast cancer classification.
Abstract: Data analytics play vital roles in diagnosis and treatment in the health care sector. To enable practitioner decisionmaking, huge volumes of data should be processed with machine learning techniques to produce tools for prediction and classification. Diseases like breast cancer can be classified based on the nature of the tumor. Finding an effective algorithm for classification should help resolve the challenges present in analyzing large volume of data. The objective with this paper was to present a report on the performance of Bayes classifiers like Tree Augmented Naive Bayes (TAN), Boosted Augmented Naive Bayes (BAN) and Bayes Belief Network (BBN). Among the three approaches, TAN produced the best performance regarding classification and accuracy. The results obtained provide clear evidence for benefits of TAN usage in breast cancer classification. Applications of various machine learning algorithms could clearly assist breast cancer control efforts for identification, prediction, prevention and health care planning.

29 citations

Journal ArticleDOI
TL;DR: This study reviews article provides a holistic view of the types of data mining techniques used in prediction of breast cancer and attempts to provide a mean to understand the approaches involved in the early prediction.
Abstract: © 2019 International Association of Computer Science and Information Technology. Survivability of patients suffering from breast cancer varies according to the stages. The early detection of breast cancer increase the longevity of patients. However, the number of risk factors involved in the detection exponentially increases with the medical examinations. The need for automated data mining techniques to enable cost-effective and early prediction of cancer is rapidly becoming a trend in healthcare industry. The optimal techniques for prediction and diagnosis differs significantly due to the risk factors. This study reviews article provides a holistic view of the types of data mining techniques used in prediction of breast cancer. On a whole, the computer-aided automatic data mining techniques that are commonly employed in diagnosis and prognosis of chronic diseases include Decision Tree, Naive Bayes, Association rule, Multilayer Perceptron (MLP), Random Forest, and Support Vector Machines (SVM), among others. The accuracy and overall performance of the classifiers differ for every dataset and thereby this article attempts to provide a mean to understand the approaches involved in the early prediction.

8 citations

Journal ArticleDOI
TL;DR: Light is thrown light on models explicit to the Indian scene in how students can benefit from social media beyond the classroom and challenges in its adoption in Indian higher education and ways to meet these challenges are discussed.
Abstract: Purpose Digital India’s attempts to transform India into a digitally empowered society and knowledge economy. This research examines three questions: What is the educational importance of social media in Indian higher education? What gains and dangers does it pose when used for formal learning? Could informal learning via technology powerfully supplement learning through the formal system? Design/methodology/approach In total, 640 students were contacted through email lists provided by their institutions after these institutions had obtained their consent to participate in the study. The response rate is worked out at 44.84 per cent. Telephone interviews were conducted with 22 “veterans” in the field of higher education in India. All this provided areas of importance on which this study is based. Findings India is no doubt experimenting with more creative methods of learning and teaching. Educational technology is at embryonic stage compared to many of the advanced countries. The results show that even when all facilities are present, students are not fully taking advantage of the benefits technology affords for formal learning. Not only is there a digital divide between generations but also within generations. How the technology is integrated into the learning process is important. The entire learning infrastructure is certainly available in India and it is struggling to meet student expectations and offer a more dynamic and appropriate pedagogy. Practical implications This paper throws light on models explicit to the Indian scene in how students can benefit from social media beyond the classroom. It discusses challenges in its adoption in Indian higher education and ways to meet these challenges. Social implications Technology-led learning brings about a difference and the present generation in India is better equipped to tackle the challenges of the workplace, will be helpful to their employers and would fit well into a global business environment. Originality/value Because of the relative newness of the approach in India and fairly restricted use in the Indian higher education system, the impact of social media on student engagement in the higher education sector in India is not fully known.

7 citations

Journal ArticleDOI
TL;DR: In this article, the authors have analyzed the impact of SERVQUAL on overall satisfaction and brand loyalty in the healthcare industry by conducting a survey of various hospitals of Delhi NCR.
Abstract: This paper analyses the impact of SERVQUAL on overall satisfaction and brand loyalty in the healthcare industry. SERVQUAL is a standard instrument consisting of five dimensions namely reliability, empathy, responsiveness, tangibility and assurance for measuring functional service quality. The study has been initiated by conducting a survey of various hospitals of Delhi NCR. A conceptual model is designed and confirmatory test of the model is done by using the confirmatory factor analysis technique. Structural equation modelling (SEM) using AMOS 4.0, a software program is used to analyse the causal relationship between SERVQUAL, overall satisfaction and brand loyalty. The outcome arrives that SERVQUAL has a positive effect on overall satisfaction and overall satisfaction also has a positive effect on brand loyalty.

2 citations