Hypergraph Based Feature Selection Technique for Medical Diagnosis.

The impact of internet and information systems across various domains have resulted in substantial generation of multidimensional datasets. The use of data mining and knowledge discovery techniques to extract the original information contained in the multidimensional datasets play a significant role in the exploitation of complete benefit provided by them. The presence of large number of features in the high dimensional datasets incurs high computational cost in terms of computing power and time. Hence, feature selection technique has been commonly used to build robust machine learning models to select a subset of relevant features which projects the maximal information content of the original dataset. In this paper, a novel Rough Set based K - Helly feature selection technique (RSKHT) which hybridize Rough Set Theory (RST) and K - Helly property of hypergraph representation had been designed to identify the optimal feature subset or reduct for medical diagnostic applications. Experiments carried out using the medical datasets from the UCI repository proves the dominance of the RSKHT over other feature selection techniques with respect to the reduct size, classification accuracy and time complexity. The performance of the RSKHT had been validated using WEKA tool, which shows that RSKHT had been computationally attractive and flexible over massive datasets.

An improved robust heteroscedastic probabilistic neural network based trust prediction approach for cloud service selection.

Trustworthiness is a comprehensive quality metric which is used to assess the quality of the services in service-oriented environments. However, trust prediction of cloud services based on the multi-faceted Quality of Service (QoS) attributes is a challenging task due to the complicated and non-linear relationships between the QoS values and the corresponding trust result. Recent research works reveal the significance of Artificial Neural Network (ANN) and its variants in providing a reasonable degree of success in trust prediction problems. However, the challenges with respect to weight assignment, training time and kernel functions make ANN and its variants under continuous advancements. Hence, this work presents a novel multi-level Hypergraph Coarsening based Robust Heteroscedastic Probabilistic Neural Network (HC-RHRPNN) to predict trustworthiness of cloud services to build high-quality service applications. HC-RHRPNN employs hypergraph coarsening to identify the informative samples, which were then used to train HRPNN to improve its prediction accuracy and minimize the runtime. The performance of HC-RHRPNN was evaluated using Quality of Web Service (QWS) dataset, a public QoS dataset in terms of classifier accuracy, precision, recall, and F-Score.

A Hypergraph and Arithmetic Residue-based Probabilistic Neural Network for classification in Intrusion Detection Systems.

Over the past few decades, the design of an intelligent Intrusion Detection System (IDS) remains an open challenge to the research community. Continuous efforts by the researchers have resulted in the development of several learning models based on Artificial Neural Network (ANN) to improve the performance of the IDSs. However, there exists a tradeoff with respect to the stability of ANN architecture and the detection rate for less frequent attacks. This paper presents a novel approach based on Helly property of Hypergraph and Arithmetic Residue-based Probabilistic Neural Network (HG AR-PNN) to address the classification problem in IDS. The Helly property of Hypergraph was exploited for the identification of the optimal feature subset and the arithmetic residue of the optimal feature subset was used to train the PNN. The performance of HG AR-PNN was evaluated using KDD CUP 1999 intrusion dataset. Experimental results prove the dominance of HG AR-PNN classifier over the existing classifiers with respect to the stability and improved detection rate for less frequent attacks.