M. A. Hossain

Hybrid decision tree and naïve Bayes classifiers for multi-class classification tasks

In this paper, we introduce two independent hybrid mining algorithms to improve the classification accuracy rates of decision tree (DT) and naive Bayes (NB) classifiers for the classification of multi-class problems. Both DT and NB classifiers are useful, efficient and commonly used for solving classification problems in data mining. Since the presence of noisy contradictory instances in the training set may cause the generated decision tree suffers from overfitting and its accuracy may decrease, in our first proposed hybrid DT algorithm, we employ a naive Bayes (NB) classifier to remove the noisy troublesome instances from the training set before the DT induction. Moreover, it is extremely computationally expensive for a NB classifier to compute class conditional independence for a dataset with high dimensional attributes. Thus, in the second proposed hybrid NB classifier, we employ a DT induction to select a comparatively more important subset of attributes for the production of naive assumption of class conditional independence. We tested the performances of the two proposed hybrid algorithms against those of the existing DT and NB classifiers respectively using the classification accuracy, precision, sensitivity-specificity analysis, and 10-fold cross validation on 10 real benchmark datasets from UCI (University of California, Irvine) machine learning repository. The experimental results indicate that the proposed methods have produced impressive results in the classification of real life challenging multi-class problems. They are also able to automatically extract the most valuable training datasets and identify the most effective attributes for the description of instances from noisy complex training databases with large dimensions of attributes.

Intelligent facial emotion recognition and semantic-based topic detection for a humanoid robot

Automatic perception of human affective behaviour from facial expressions and recognition of intentions and social goals from dialogue contexts would greatly enhance natural human robot interaction. This research concentrates on intelligent neural network based facial emotion recognition and Latent Semantic Analysis based topic detection for a humanoid robot. The work has first of all incorporated Facial Action Coding System describing physical cues and anatomical knowledge of facial behaviour for the detection of neutral and six basic emotions from real-time posed facial expressions. Feedforward neural networks (NN) are used to respectively implement both upper and lower facial Action Units (AU) analysers to recognise six upper and 11 lower facial actions including Inner and Outer Brow Raiser, Lid Tightener, Lip Corner Puller, Upper Lip Raiser, Nose Wrinkler, Mouth Stretch etc. An artificial neural network based facial emotion recogniser is subsequently used to accept the derived 17 Action Units as inputs to decode neutral and six basic emotions from facial expressions. Moreover, in order to advise the robot to make appropriate responses based on the detected affective facial behaviours, Latent Semantic Analysis is used to focus on underlying semantic structures of the data and go beyond linguistic restrictions to identify topics embedded in the users’ conversations. The overall development is integrated with a modern humanoid robot platform under its Linux C++ SDKs. The work presented here shows great potential in developing personalised intelligent agents/robots with emotion and social intelligence.

Intelligent Learning Algorithms for Active Vibration Control

This correspondence presents an investigation into the comparative performance of an active vibration control (AVC) system using a number of intelligent learning algorithms. Recursive least square (RLS), evolutionary genetic algorithms (GAs), general regression neural network (GRNN), and adaptive neuro-fuzzy inference system (ANFIS) algorithms are proposed to develop the mechanisms of an AVC system. The controller is designed on the basis of optimal vibration suppression using a plant model. A simulation platform of a flexible beam system in transverse vibration using a finite difference method is considered to demonstrate the capabilities of the AVC system using RLS, GAs, GRNN, and ANFIS. The simulation model of the AVC system is implemented, tested, and its performance is assessed for the system identification models using the proposed algorithms. Finally, a comparative performance of the algorithms in implementing the model of the AVC system is presented and discussed through a set of experiments.

An intelligent mobile based decision support system for retinal disease diagnosis

Diabetes and Cataract are the key causes of retinal blindness for millions of people. Current detection of diabetes and Cataract from retinal images using Fundus camera is expensive and inconvenient since such detection is not portable and requires specialists to perform an operation. This paper presents an innovative development of a low cost Smartphone based intelligent system integrated with microscopic lens that allows patients in remote and isolated areas for regular eye examinations and disease diagnosis. This mobile diagnosis system uses an artificial Neural Network algorithm to analyze the retinal images captured by the microscopic lens to identify retinal disease conditions. The algorithm is first of all trained with infected and normal retinal images using a personal computer and then further developed into a mobile-based diagnosis application for Android environments. The application is optimized by using the rooted method in order to increase battery lifetime and processing capacity. A duty cycle method is also proposed to greatly improve the energy efficiency of this retinal scan and diagnosis system in Smartphone environments. The proposed mobile-based system is tested and verified using two well-known medical ophthalmology databases to demonstrate its merits and capabilities. The evaluation results indicate that the system shows competitive retinal disease detection accuracy rates (>87%). It also offers early detection of retinal diseases and shows great potential to be further developed to identify skin cancer.

Intelligent phishing detection and protection scheme for online transactions

Phishing is an instance of social engineering techniques used to deceive users into giving their sensitive information using an illegitimate website that looks and feels exactly like the target organization website. Most phishing detection approaches utilizes Uniform Resource Locator (URL) blacklists or phishing website features combined with machine learning techniques to combat phishing. Despite the existing approaches that utilize URL blacklists, they cannot generalize well with new phishing attacks due to human weakness in verifying blacklists, while the existing feature-based methods suffer high false positive rates and insufficient phishing features. As a result, this leads to an inadequacy in the online transactions. To solve this problem robustly, the proposed study introduces new inputs (Legitimate site rules, User-behavior profile, PhishTank, User-specific sites, Pop-Ups from emails) which were not considered previously in a single protection platform. The idea is to utilize a Neuro-Fuzzy Scheme with 5 inputs to detect phishing sites with high accuracy in real-time. In this study, 2-Fold cross-validation is applied for training and testing the proposed model. A total of 288 features with 5 inputs were used and has so far achieved the best performance as compared to all previously reported results in the field.

Predicting Phishing Websites Using Classification Mining Techniques with Experimental Case Studies

Classification Data Mining (DM) Techniques can be a very useful tool in detecting and identifying e-banking phishing websites. In this paper, we present a novel approach to overcome the difficulty and complexity in detecting and predicting e-banking phishing website. We proposed an intelligent resilient and effective model that is based on using association and classification Data Mining algorithms. These algorithms were used to characterize and identify all the factors and rules in order to classify the phishing website and the relationship that correlate them with each other. We implemented six different classification algorithm and techniques to extract the phishing training data sets criteria to classify their legitimacy. We also compared their performances, accuracy, number of rules generated and speed. A Phishing Case study was applied to illustrate the website phishing process. The rules generated from the associative classification model showed the relationship between some important characteristics like URL and Domain Identity, and Security and Encryption criteria in the final phishing detection rate. The experimental results demonstrated the feasibility of using Associative Classification techniques in real applications and its better performance as compared to other traditional classifications algorithms.

Intelligent facial emotion recognition using a layered encoding cascade optimization model

A layered cascade optimization model is developed for facial emotion recognition.Two layered cascade-based evolutionary algorithms are proposed for feature selection.They focus on within-class and between-class variations for feature optimization.Both a neural network and an adaptive ensemble classifier are employed for expression recognition.Superior performance is shown in both frontal and 90? side-view expression recognition. In this research, we propose a facial expression recognition system with a layered encoding cascade optimization model. Since generating an effective facial representation is a vital step to the success of facial emotion recognition, a modified Local Gabor Binary Pattern operator is first employed to derive a refined initial face representation and we then propose two evolutionary algorithms for feature optimization including (i) direct similarity and (ii) Pareto-based feature selection, under the layered cascade model. The direct similarity feature selection considers characteristics within the same emotion category that give the minimum within-class variation while the Pareto-based feature optimization focuses on features that best represent each expression category and at the same time provide the most distinctions to other expressions. Both a neural network and an ensemble classifier with weighted majority vote are implemented for the recognition of seven expressions based on the selected optimized features. The ensemble model also automatically updates itself with the most recent concepts in the data. Evaluated with the Cohn-Kanade database, our system achieves the best accuracies when the ensemble classifier is applied, and outperforms other research reported in the literature with 96.8% for direct similarity based optimization and 97.4% for the Pareto-based feature selection. Cross-database evaluation with frontal images from the MMI database has also been conducted to further prove system efficiency where it achieves 97.5% for Pareto-based approach and 90.7% for direct similarity-based feature selection and outperforms related research for MMI. When evaluated with 90? side-view images extracted from the videos of the MMI database, the system achieves superior performances with >80% accuracies for both optimization algorithms. Experiments with other weighting and meta-learning combination methods for the construction of ensembles are also explored with our proposed ensemble showing great adpativity to new test data stream for cross-database evaluation. In future work, we aim to incorporate other filtering techniques and evolutionary algorithms into the optimization models to further enhance the recognition performance.

Experimental Case Studies for Investigating E-Banking Phishing Techniques and Attack Strategies

Phishing is a form of electronic identity theft in which a combination of social engineering and Web site spoofing techniques is used to trick a user into revealing confidential information with economic value. The problem of social engineering attack is that there is no single solution to eliminate it completely, since it deals largely with the human factor. This is why implementing empirical experiments is very crucial in order to study and to analyze all malicious and deceiving phishing Web site attack techniques and strategies. In this paper, three different kinds of phishing experiment case studies have been conducted to shed some light into social engineering attacks, such as phone phishing and phishing Web site attacks for designing effective countermeasures and analyzing the efficiency of performing security awareness about phishing threats. Results and reactions to our experiments show the importance of conducting phishing training awareness for all users and doubling our efforts in developing phishing prevention techniques. Results also suggest that traditional standard security phishing factor indicators are not always effective for detecting phishing websites, and alternative intelligent phishing detection approaches are needed.

Multi-objective optimal chemotherapy control model for cancer treatment

This article presents an investigation into the development of a multi-objective optimal chemotherapy control model to reduce the number of cancer cells after a number of fixed treatment cycles with minimum side effects. Mathematical models for cancer chemotherapy are designed to predict the number of tumour cells and control the tumour growth during treatment. This requires an understanding of the system in the absence of treatment and a description of the effects of the treatment. In order to achieve multi-objective optimal control model, we used the proportional, integral and derivative (PID) and I-PD (modified PID with Integrator used as series) controllers based on Martin’s model for drug concentration. To the best of our knowledge, this is the first PID/IPD-based optimal chemotherapy control model used to investigate the cancer treatment. The proposed control schemes are designed based on the optimal solution of three objective functions, which include (i) maximising tumour cell killing, for (ii) minimum toxicity, and (iii) tolerable drug concentration. Multi-objective genetic algorithm (MOGA) is used to find suitable parameters of controllers that trade-off among design objectives considered in this work. The results of the different optimal scheduling patterns of the proposed models are presented and discussed through a set of experiments. Finally, the observations are compared with the existing models in order to demonstrate the merits and capabilities of the proposed multi-objective optimisation models. It is noted that the proposed model offers best performance as compared to any models reported earlier.

An Intelligent Decision Support System for Leukaemia Diagnosis using Microscopic Blood Images

This research proposes an intelligent decision support system for acute lymphoblastic leukaemia diagnosis from microscopic blood images. A novel clustering algorithm with stimulating discriminant measures (SDM) of both within- and between-cluster scatter variances is proposed to produce robust segmentation of nucleus and cytoplasm of lymphocytes/lymphoblasts. Specifically, the proposed between-cluster evaluation is formulated based on the trade-off of several between-cluster measures of well-known feature extraction methods. The SDM measures are used in conjuction with Genetic Algorithm for clustering nucleus, cytoplasm, and background regions. Subsequently, a total of eighty features consisting of shape, texture, and colour information of the nucleus and cytoplasm sub-images are extracted. A number of classifiers (multi-layer perceptron, Support Vector Machine (SVM) and Dempster-Shafer ensemble) are employed for lymphocyte/lymphoblast classification. Evaluated with the ALL-IDB2 database, the proposed SDM-based clustering overcomes the shortcomings of Fuzzy C-means which focuses purely on within-cluster scatter variance. It also outperforms Linear Discriminant Analysis and Fuzzy Compactness and Separation for nucleus-cytoplasm separation. The overall system achieves superior recognition rates of 96.72% and 96.67% accuracies using bootstrapping and 10-fold cross validation with Dempster-Shafer and SVM, respectively. The results also compare favourably with those reported in the literature, indicating the usefulness of the proposed SDM-based clustering method.