Experimental Analysis Towards Realizing Breast Cancer Prognosis Using Diverse Machine Learning Classifiers

Chaurasia, Sandeep; Chakrabarti, Prasun; Yu Cheng
June 2014
Australian Journal of Basic & Applied Sciences;Jun2014, Vol. 8 Issue 9, p31
Academic Journal
The adequate diagnosis of breast cancer is one of the major challenges in the medical field. Supervised machine learning has been used to simulate a model of the distribution of class label in terms of predictor features. The resultant classifier is then used for helping doctors' forms a secondary opinion for better diagnosis. The performance of various machine learning techniques has been analyzed over the four distinguishes breast cancer data sets. A comparison on the performance of the results has produced among the classifiers as decision tree, Naïve Bayes, Naïve Bayes using kernel, neural network, auto association multi layer Perceptron and support vector machine. The obtained results shows that SVM could classify more accurate when there is no missing data, but with missing data Naïve Bayes using kernel method works fast and generate hypothesis more accurately.


Related Articles

  • Predicting the Severity of Breast Masses with Data Mining Methods. Mokhtar, Sahar A.; Elsayad, Alaa. M. // International Journal of Computer Science Issues (IJCSI);Mar2013, Vol. 10 Issue 2, p160 

    Mammography is the most effective and available tool for breast cancer screening. However, the low positive predictive value of breast biopsy resulting from mammogram interpretation leads to approximately 70% unnecessary biopsies with benign outcomes. Data mining algorithms could be used to help...

  • Peripheral blood smear image analysis: A comprehensive review. Mohammed, Emad A.; Mohamed, Mostafa M. A.; Far, Behrouz H.; Naugler, Christopher // Journal of Pathology Informatics;2014, Vol. 5 Issue 1, p60 

    Peripheral blood smear image examination is a part of the routine work of every laboratory. The manual examination of these images is tedious, time-consuming and suffers from interobserver variation. This has motivated researchers to develop different algorithms and methods to automate...

  • Machine Learning Algorithms and Predictive Models for Undergraduate Student Retention. Jia, Ji-Wu; Mareboyana, Manohar // Proceedings of the World Congress on Engineering & Computer Scie;2013, p1 

    In this paper, we have presented some results of undergraduate student retention using machine learning algorithms classifying the student data. We have also made some improvements to the classification algorithms such as Decision tree, Support Vector Machines (SVM), and neural networks...

  • Evaluation of Different Machine Learning Methods for Caesarean Data Classification. Alsharif, O. S. S.; Elbayoudi, K. M.; Aldrawi, A. A. S.; Akyol, K. // International Journal of Information Engineering & Electronic Bu;Sep2019, Vol. 11 Issue 5, p19 

    Recently, a new dataset has been introduced about the caesarean data. In this paper, the caesarean data was classified with five different algorithms; Support Vector Machine, K Nearest Neighbours, Naïve Bayes, Decision Tree Classifier, and Random Forest Classifier. The dataset is retrieved...

  • Statistical Measures to Determine Optimal Structure of Decision Tree: One versus One Support Vector Machine. Bala, Manju; Agrawal, R. K. // Defence Science Journal;2010, Vol. 60 Issue 4, p399 

    In this paper, one versus one optimal decision tree support vector machine (OvO-ODT SVM) framework is proposed to solve multi-class problems where the optimal structure of decision tree is determined using statistical measures, i.e., information gain, gini index, and chi-square. The performance...

  • Research on the Optimal Information Retrieval Based on SVM. Sun Jianming; Sun Qingli // International Journal of Control & Automation;2014, Vol. 7 Issue 8, p419 

    Research on the retrieval with time limitation in distributed retrieval, the optimal resource description and selection strategy is proposed with the SVM method combing the retrieval method based on topic clustering. Pre-treatment text database is treated by practicing the SVM method. The...

  • A hybrid Evolutionary Functional Link Artificial Neural Network for Data mining and Classification. MILI, Faissal; HAMDI, Manel // International Journal of Advanced Computer Science & Application;Aug2012, Vol. 3 Issue 8, p89 

    This paper presents a specific structure of neural network as the functional link artificial neural network (FLANN). This technique has been employed for classification tasks of data mining. In fact, there are a few studies that used this tool for solving classification problems. In this present...

  • Data Mining Techniques in Customer Churn Prediction. Tsai, Chih-Fong; Lu, Yu-Hsin // Recent Patents on Computer Science;2010, Vol. 3 Issue 1, p28 

    Customer churn prediction is one of the most important problems in customer relationship management (CRM). Its aim is to retain valuable customers to maximize the profit of a company. To predict whether a customer will be a churner or non-churner, there are a number of data mining techniques...

  • Predicting Students' Performance using Modified ID3 Algorithm. L., Ramanathan; Dhanda, Saksham; D., Suresh Kumar // International Journal of Engineering & Technology (0975-4024);Jun/Jul2013, Vol. 5 Issue 3, p2491 

    The ability to predict performance of students is very crucial in our present education system. We can use data mining concepts for this purpose. ID3 algorithm is one of the famous algorithms present today to generate decision trees. But this algorithm has a shortcoming that it is inclined to...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics