MEGA: Predicting the best classifier combination using meta-learning and a genetic algorithm

Classifier combination through ensemble systems is one of the most effective approaches to improve the accuracy of classification systems. Ensemble systems are generally used to combine classifiers; However, selecting the best combination of individual classifiers is a challenging task. In this paper, we propose an efficient assembling method that employs both meta-learning and a genetic algorithm for the selection of the best classifiers. Our method is called MEGA, standing for using MEta-learning and a Genetic Algorithm for algorithm recommendation. MEGA has three main components: Training, Model Interpretation and Testing. The Training component extracts meta-features of each training dataset and uses a genetic algorithm to discover the best classifier combination. The Model Interpretation component interprets the relationships between meta-features and classifiers using a priori and multi-label decision tree algorithms. Finally, the Testing component uses a weighted k-nearest-neighbors algorithm to predict the best combination of classifiers for unseen datasets. We present extensive experimental results that demonstrate the performance of MEGA. MEGA achieves superior results in a comparison of three other methods and, most importantly, is able to find novel interpretable rules that can be used to select the best combination of classifiers for an unseen dataset.

Comparative Study of Classification algorithms used for the Prediction of Non-communicable diseases

Quality of life is considered as an important outcome in health research. The information science and technological advances plays a major role in public healthcare. Clinical Decision Support System helps to healthcare professionals to give better diagnostic decisions. Diagnosing Non-Communicable Diseases (NCD) viz., Cardio Vascular Diseases (CVD) and Diabetes Mellitus (DM) required accurate analysis and prediction. To overcome the problems of knowledge based CDSS, machine learning techniques acquire knowledge automatically from the previous patient’s clinical data. The techniques used for the diagnosis are depending on a one or more combination of classifiers. The proposed system uses ensemble based methods to give better performance of particular disease prediction. The current ensemble approaches are the enhancement techniques which are based on each stage of outputs.

DFC

Knowledge discovery data (KDD) is a research theme evolving to exploit a large data set collected every day from various fields of computing applications. The underlying idea is to extract hidden knowledge from a data set. It includes several tasks that form a process, such as data mining. Classification and clustering are data mining techniques. Several approaches were proposed in classification such as induction of decision trees, Bayes net, support vector machine, and formal concept analysis (FCA). The choice of FCA could be explained by its ability to extract hidden knowledge. Recently, researchers have been interested in the ensemble methods (sequential/parallel) to combine a set of classifiers. The combination of classifiers is made by a vote technique. There has been little focus on FCA in the context of ensemble learning. This paper presents a new approach to building a single part of the lattice with best possible concepts. This approach is based on parallel ensemble learning. It improves the state-of-the-art methods based on FCA since it handles more voluminous data.

Combination of Pattern Classifiers Based on Naive Bayes and Fuzzy Integral Method for Biological Signal Applications

Background: Achieving the best possible classification accuracy is the main purpose of each pattern recognition scheme. An interesting area of classifier design is to design for biomedical signal and image processing. Materials and Methods: In the current work, in order to increase recognition accuracy, a theoretical frame for combination of classifiers is developed. This method uses different pattern representations to show that a wide range of existing algorithms could be incorporated as the particular cases of compound classification where all the pattern representations are used jointly to make an accurate decision. Results: The results show that the combination rules developed under the Naive Bayes and Fuzzy integral method outperforms other classifier combination schemes. Conclusion: The performance of different combination schemes has been studied through an experimental comparison of different classifier combination plans. The dataset used in the article has been obtained from biological signals.

Identification and Implementation Perspective on the Stratification Algorithms in the Prognostication of Heart Disease using Machine Learning Techniques

Analysis of patient’s data is always a great idea to get accurate results on using classifiers. A combination of classifiers would give an accurate result than using a single classifier because one single classifier does not give accurate results but always appropriate ones. The aim is to predict the outcome feature of the data set. The “outcome” can contain only two values that is 0 and 1. 0 means patient doesn’t have heart disease and 1 means patient have heart diseases. So, there is a need to build a classification algorithm that can predict the Outcome feature of the test dataset with good accuracy. For this understanding the data is important, and then various classification algorithm can be tested. Then the best model can be selected which gives highest accuracy among all. The built model can then be given to the software developer for building the end user application using the selected machine learning model that will be able to predict the heart disease in a patient.

Enhancing the Credit Card Fraud Detection Through Ensemble Techniques

Nowadays people prefer to use e-commerce because of easiness, timesaving, convenience, etc. By the increase in e-commerce use, credit card fraud increases. The fraudsters get the benefit of online payments and stealing the card details. Therefore, it is essential to improve the detection methods to overcome with the fraudster’s activity and secure the card transactions. The purpose of this study is to investigate the performance of several individual different classifiers and the combination of classifiers using ensemble methods for credit card fraud detection. The study is organized as initially the three well-known classifiers i.e., Decision Tree, Naïve Bayes and SVM have been applied. Afterwards the ensemble learning module have been applied using the boosting technique with the previously mentioned classification algorithms. The dataset used is open source credit card transaction dataset containing 3075 transactions. The performance of the classification techniques is evaluated based on accuracy, sensitivity, specificity, precision, ROC value and F-measure. The result shows that Boosting with Decision Tree outperforms the other techniques.