Tasadduq Imam

Association rule mining to detect factors which contribute to heart disease in males and females

This paper investigates the sick and healthy factors which contribute to heart disease for males and females. Association rule mining, a computational intelligence approach, is used to identify these factors and the UCI Cleveland dataset, a biological database, is considered along with the three rule generation algorithms - Apriori, Predictive Apriori and Tertius. Analyzing the information available on sick and healthy individuals and taking confidence as an indicator, females are seen to have less chance of coronary heart disease then males. Also, the attributes indicating healthy and sick conditions were identified. It is seen that factors such as chest pain being asymptomatic and the presence of exercise-induced angina indicate the likely existence of heart disease for both men and women. However, resting ECG being either normal or hyper and slope being flat are potential high risk factors for women only. For men, on the other hand, only a single rule expressing resting ECG being hyper was shown to be a significant factor. This means, for women, resting ECG status is a key distinct factor for heart disease prediction. Comparing the healthy status of men and women, slope being up, number of coloured vessels being zero, and oldpeak being less than or equal to 0.56 indicate a healthy status for both genders.

z-SVM: an SVM for improved classification of imbalanced data

Recent literature has revealed that the decision boundary of a Support Vector Machine (SVM) classifier skews towards the minority class for imbalanced data, resulting in high misclassification rate for minority samples. In this paper, we present a novel strategy for SVM in class imbalanced scenario. In particular, we focus on orienting the trained decision boundary of SVM so that a good margin between the decision boundary and each of the classes is maintained, and also classification performance is improved for imbalanced data. In contrast to existing strategies that introduce additional parameters, the values of which are determined through empirical search involving multiple SVM training, our strategy corrects the skew of the learned SVM model automatically irrespective of the choice of learning parameters without multiple SVM training. We compare our strategy with SVM and SMOTE, a widely accepted strategy for imbalanced data, applied to SVM on five well known imbalanced datasets. Our strategy demonstrates improved classification performance for imbalanced data and is less sensitive to the selection of SVM learning parameters.

Computational intelligence for heart disease diagnosis: A medical knowledge driven approach

This paper investigates a number of computational intelligence techniques in the detection of heart disease. Particularly, comparison of six well known classifiers for the well used Cleveland data is performed. Further, this paper highlights the potential of an expert judgment based (i.e., medical knowledge driven) feature selection process (termed as MFS), and compare against the generally employed computational intelligence based feature selection mechanism. Also, this article recognizes that the publicly available Cleveland data becomes imbalanced when considering binary classification. Performance of classifiers, and also the potential of MFS are investigated considering this imbalanced data issue. The experimental results demonstrate that the use of MFS noticeably improved the performance, especially in terms of accuracy, for most of the classifiers considered and for majority of the datasets (generated by converting the Cleveland dataset for binary classification). MFS combined with the computerized feature selection process (CFS) has also been investigated and showed encouraging results particularly for NaiveBayes, IBK and SMO. In summary, the medical knowledge based feature selection method has shown promise for use in heart disease diagnostics.

Computational intelligence for microarray data and biomedical image analysis for the early diagnosis of breast cancer

The objective of this paper was to perform a comparative analysis of the computational intelligence algorithms to identify breast cancer in its early stages. Two types of data representations were considered: microarray based and medical imaging based. In contrast to previous researches, this research also considered the imbalanced nature of these data. It was observed that the SMO algorithm performed better for the majority of the test data, especially for microarray based data when accuracy was used as performance measure. Considering the imbalanced characteristic of the data, the Naive Bayes algorithm was seen to perform highly in terms of true positive rate (TPR). Regarding the influence of SMOTE, a well-known imbalanced data classification technique, it was observed that there was a notable performance improvement for J48, while the performance of SMO remained comparable for the majority of the datasets. Overall, the results indicated SMO as the most potential candidate for the microarray and image dataset considered in this research.

Linear Relationship Between The AUD/USD Exchange Rate And The Respective Stock Market Indices: A Computational Finance Perspective

In the recent era, computational intelligence techniques have found an increased popularity in addressing varied financial issues, including foreign exchange rate prediction. This article, through an intelligent system research framework, relates the Australian dollar (AUD)/US dollar (USD) exchange rate to the Australian and the US stock market indices. Information for exchange rate, All Ordinaries Index (AOI) and Dow Jones Industrial Average (DJI) for the trading days over the period January 1991–May 2011 is considered in this research. Utilizing a set of statistical and computational intelligence techniques, the research establishes that the AUD/USD exchange rate is best estimated by a linear forecast model compared with the nonlinear and ensemble-based intelligent system models. This research further highlights that, among the competing linear models, the model with both the stock market indices and historical exchange rate values as the predictors is the best forecaster. Parameters of the linear model are deduced through a Monte Carlo stochastic approach. Relative importance of the predictors is also studied, and the influence of historical exchange rates, the immediate impact of AOI and the lagged effect of DJI are noted. Copyright

Brain Cancer Diagnosis-Association Rule Based Computational Intelligence Approach

This research employs a computational intelligence based approach to identify the risk factors of brain cancer. More specifically this research utilizes association rule mining techniques to determine the risk factors derived from the brain cancer literature. The research also develops a novel database extracting data from existing literature. Arguably, the outcomes may aid designing brain cancer diagnostic systems and contribute to early diagnosis of the mortal disease. Additionally, it demonstrates the effectiveness of computational intelligence techniques in cancer disease diagnosis. The benefits of this research could apply to different stakeholders such as the CAD (Computer aided diagnosis) designers and the data mining community, the medical field and in particular general practitioners as well as the general public.

Medical knowledge based data mining for cardiac stress test diagnostics

Though an important preliminary process to diagnose cardiac abnormality, cardiac stress test is often inaccurate and involves costly follow-up procedures. Data mining based approaches have potentials to reduce the uncertainties in this respect. However, the exploration on such data mining approaches is still limited. Further, traditionally employed data mining techniques like feature selection often ignore features which are medically important, and as a consequence the results are doubted by the medical practitioners. The objective of this research is to compare the effectiveness of Medical Feature Selection against the traditional Computer-Automated Feature Selection mechanism employed by data mining community for a real life stress test scenario. Considering six different classification algorithms, its noted that the medical knowledge motivated feature selection (MFS) improved performance of the classifiers in terms of majority of the measures, as compared to the computer-automated feature selection (CFS). While a unique classifier was not observed as the best technique, MFS had the most notable effect on Support Vector Machine (SMO) and Decision Tree (J48) for the dataset. The findings are expected to assist better computer-aided heart disease diagnostics, and is thus of interest to medical practitioners and researchers.

Curriculum coherence when subject-specific standards are absent: a case study using coursework-based master of finance programs at Australian universities

ABSTRACT The standardisation of a curriculum is a contentious issue, with critics complaining it leads to a loss of control and creativity. What is less clear, however, is how the lack of standardisation impacts a discipline’s curriculum. This article, taking the coursework-based Master of Finance programs at Australian universities as the case study, demonstrates that lack of standardisation results in graduates with non-uniform employability, ignorance of essential professional knowledge and the incorporation of non-integrated non-discipline subjects. Further, such lack of standards causes high disparity in the structures of the programs – an issue outlined in this article through a proposed similarity metric. Overall, this article calls for subject-specific standards to overcome these issues.

Class information adapted kernel for support vector machine

This article presents a support vector machine (SVM) learning approach that adapts class information within the kernel computation. Experiments on fifteen publicly available datasets are conducted and the impact of proposed approach for varied settings are observed. It is noted that the new approach generally improves minority class prediction, depicting it as a well-suited scheme for imbalanced data. However, a SVM based customization is also developed that significantly improves prediction performance in terms of different measures. Overall, the proposed method holds promise with potential for future extensions.