Heart disease diagnosis is found to be a challenging issue which can offer a computerized estimate about the level of heart disease so that supplementary action can be made easy. Thus, heart disease diagnosis has expected massive attention worldwide among the healthcare environment. Optimization algorithms played a significant role in heart disease diagnosis with good efficiency. The objective of this paper is to propose an optimization function on the basis of support vector machine (SVM). This objective function is used in the genetic algorithm (GA) for selecting the more significant features to get heart disease. The experimental results of the GA–SVM are compared with the various existing feature selection algorithms such as Relief, CFS, Filtered subset, Info gain, Consistency subset, Chi squared, One attribute based, Filtered attribute, Gain ratio, and GA. The receiver operating characteristic analysis is performed to evaluate the good performance of SVM classifier. The proposed framework is demonstrated in the MATLAB environment with a dataset collected from Cleveland heart disease database.

An optimized feature selection based on genetic approach and support vector machine for heart disease

Speech recognition is one of the entrancing fields in the zone of computer science. Exactness of speech recognition framework may decrease because of the nearness of noise exhibited by the speech signal. Consequently, noise removal is a fundamental advance in automatic speech recognition (ASR) system. ASR is researched for various languages in light of the fact that every language has its particular highlights. Particularly, the requirement for ASR framework in Tamil language has been expanded broadly over the most recent couple of years. In this work, bidirectional recurrent neural network (BRNN) with self-organizing map (SOM)-based classification scheme is suggested for Tamil speech recognition. At first, the input speech signal is pre-prepared by utilizing Savitzky–Golay filter keeping in mind the end goal to evacuate the background noise and to improve the signal. At that point, Multivariate Autoregressive based highlights by presenting discrete cosine transformation piece to give a proficient signal investigation. And in addition, perceptual linear predictive coefficients likewise separated to enhance the classification accuracy. The feature vector is shifted in measure, for picking the right length of feature vector SOM utilized. At long last, Tamil digits and words are ordered by utilizing BRNN classifier where the settled length feature vector from SOM is given as input, named as BRNN-SOM. The experimental analysis demonstrates that the suggested conspire accomplished preferable outcomes looked at over exist deep neural network–hidden Markov model algorithm regarding signal-to-noise ratio, classification accuracy, and mean square error.

An Automatic Tamil Speech Recognition system by using Bidirectional Recurrent Neural Network with Self-Organizing Map

A survey and taxonomy of the fuzzy signature-based Intrusion Detection Systems

Twitter is a social media that developed rapidly in today’s modern world. As millions of Twitter messages are sent day by day, the value and importance of developing a new technique for detecting spammers become significant. Moreover, legitimate users are affected by means of spams in the form of unwanted URLs, irrelevant messages, etc. Another hot topic of research is sentiment analysis that is based on each tweet sent by the user and opinion mining of the customer reviews. Most commonly natural language processing is used for sentiment analysis. The text is collected from user’s tweets by opinion mining and automatic sentiment analysis that are oriented with ternary classifications, such as “positive,” “neutral,” and “negative.” Due to limited size, unstructured nature, misspells, slangs, and abbreviations, it is more challenging for researchers to find sentiments for Twitter data. In this paper, we collected 600 million public tweets using URL-based security tool and feature generation is applied for sentiment analysis. The ternary classification is processed based on preprocessing technique, and the results of tweets sent by the users are obtained. We use a hybridization technique using two optimization algorithms and one machine learning classifier, namely particle swarm optimization and genetic algorithm and decision tree for classification accuracy by sentiment analysis. The results are compared with previous works, and our proposed method shows a better analysis than that of other classifiers.

Classifying streaming of Twitter data based on sentiment analysis using hybridization

In this research, a new speech recognition method based on improved feature extraction and improved support vector machine (ISVM) is developed. A Gaussian filter is used to denoise the input speech signal. The feature extraction method extracts five features such as peak values, Mel frequency cepstral coefficient (MFCC), tri-spectral features, discrete wavelet transform (DWT), and the difference values between the input and the standard signal. Next, these features are scaled using linear identical scaling (LIS) method with the same scaling method and the same scaling factors for each set of features in both training and testing phases. Following this, to accomplish the training process, an ISVM is developed with best fitness validation. The ISVM consists of two stages: (i) linear dual classifier that finds the same class attributes and different class attributes simultaneously and (ii) cross fitness validation (CFV) method to prevent over fitting problem. The proposed speech recognition method offers 98.2% accuracy.

Speech recognition with improved support vector machine using dual classifiers and cross fitness validation

Due to raising concerns about the privacy preserving of personal information, organizations which are using the customers' records in data mining activities are rammed to take actions for protecting the individual's privacy. Preserving of sensitive and personal information is vital for the success of data mining techniques. Privacy Preserving Data Mining (PPDM) handles such consequences by reconciliation of both preserving privacy and data utilization. Conventionally, Geometrical Data Transformation Methods (GDTMs) have been extensively used for privacy conserving cluster. The major drawback in these GDTMs are geometric conversion function are not reversible, that results in a low level assurance of security. In this paper, the technique that preserves the privacy of delicate information in a multiparty cluster situation called the guideline segment investigation based technique is proposed. The function of this proficiency is assessed advance by employing a classic K-means cluster algorithms and machine learning-based cluster methodology on artificial and realistic world information sets. The effectiveness of grouping is computed prior and then afterward the change of security preserving. Our suggested transformation established on PCA when competed to the traditional GDTMs resulted in superior protection of privacy and improve performance.

Preservation of privacy in data mining by using PCA based perturbation technique

In today's computer world security is the major issue. For every project most of the money spent on the security and testing than developing. Because security issue is one of the major issue for everyone to protect data. According to the security analysts more than seven billion hackers are existing over one hundred and five billion computers. Almost all of them trying to collapse the security system. There are so many security attacks are rotating throughout the network. Phishing is one of the popular security attack on the websites due to fall in this attack we lose our valuable information. Today most of us are using e-commerce websites for online shopping. Most of them are paying money through online. By taking this as an advantage so many hackers are host phishing website for stealing our bank and credit card detail. No only this so many social accounts are hacking daily. Other than this there is a new model of attack that is Desktop phishing. It is one of the advance attack which is applied on victim computer it can prevent the victim user actions in websites. By that we don't allow to the real page even to modify of change our password. By that the attacker success his goal. For phishing detection there are so many solutions are available. But Till now so many antiviruses can't find this attack. So we prose a TSO programmatically solution to Desktop phishing attack. It has a capability to detection and prevention of the attack.

Desktop phishing attack detection and elimination using TSO program

Security in communication is an important and challenging issue in the recent years. In the past, many secure routing algorithms have been proposed to provide energy efficiency and security in Mobile Ad hoc Networks. However due to the increase in attackers and new types of attacks, the existing secure routing techniques are challenged by malicious users. In order to handle these problems, a new trust and fuzzy cluster based dynamic secure routing algorithm is proposed in this paper for enhancing energy efficiency and security. For this purpose, a new trust model which uses historical trust, neighbor trust and behavioral trust is proposed in this work for isolating the malicious nodes in the routing process. Moreover, the fuzzy clustering technique proposed in this paper provides energy efficiency by applying cluster head based routing, cluster head rotation and fuzzy decision making. The fuzzy rules also help to handle the uncertainty occurring due to the movement of nodes in the network. From the experiments conducted in this work, it is proved that the proposed algorithm enhances the security of communication which in turn increases the packet delivery ratio and reduces the delay.

A Trust and Fuzzy Cluster Based Dynamic Secure Routing Algorithm for Mobile Ad Hoc Networks

Cyber attack detection is an important and challenging area of research in the field of information technology. In such a scenario, intruders introduce new mechanisms by applying polymorphic mechanisms in order to escape from the intrusion detection systems. This leads to loss in data and increase in security vulnerabilities. In the past, many soft computing techniques were used from the field of machine learning for enhancing the efficiency of intrusion detection systems (IDSs) in computer networks. Among them, fuzzy logic played a major role for making effective decisions. In addition, the neural networks are also contributing more in this area for training the datasets to form rules which can be used to develop an effective intrusion detection system. In this paper, we propose a new intrusion detection system by combining neural networks with temporal and type-2 fuzzy logic for performing effective classification of the dataset. In addition, a new feature selection algorithm is also proposed in this paper which uses information gain of attributes with fuzzy logic decision making for selecting the optimal number of features from the dataset. This work has been tested by using NSL-KDD dataset and through the experiments conducted in this work it is proved that the proposed system increases the intrusion detection accuracy and reduces the false positive rate when it is compared with other existing systems.

K.P. Rama Prabha

Papers

Preservation of privacy in data mining by using PCA based perturbation technique

Desktop phishing attack detection and elimination using TSO program

A Trust and Fuzzy Cluster Based Dynamic Secure Routing Algorithm for Mobile Ad Hoc Networks

Intelligent intrusion detection system using temporal analysis and type-2 fuzzy neural classification