A multi-tier ensemble construction of classifiers for phishing email detection and filtering

This paper is devoted to multi-tier ensemble classifiers for the detection and filtering of phishing emails. We introduce a new construction of ensemble classifiers, based on the well known and productive multi-tier approach. Our experiments evaluate their performance for the detection and filtering of phishing emails. The multi-tier constructions are well known and have been used to design effective classifiers for email classification and other applications previously. We investigate new multi-tier ensemble classifiers, where diverse ensemble methods are combined in a unified system by incorporating different ensembles at a lower tier as an integral part of another ensemble at the top tier. Our novel contribution is to investigate the possibility and effectiveness of combining diverse ensemble methods into one large multi-tier ensemble for the example of detection and filtering of phishing emails. Our study handled a few essential ensemble methods and more recent approaches incorporated into a combined multi-tier ensemble classifier. The results show that new large multi-tier ensemble classifiers achieved better performance compared with the outcomes of the base classifiers and ensemble classifiers incorporated in the multi-tier system. This demonstrates that the new method of combining diverse ensembles into one unified multi-tier ensemble can be applied to increase the performance of classifiers if diverse ensembles are incorporated in the system.

Improving classifications for cardiac autonomic neuropathy using multi-level ensemble classifiers and feature selection based on random forest

This paper is devoted to empirical investigation of novel multi-level ensemble meta classifiers for the detection and monitoring of progression of cardiac autonomic neuropathy, CAN, in diabetes patients. Our experiments relied on an extensive database and concentrated on ensembles of ensembles, or multi-level meta classifiers, for the classification of cardiac autonomic neuropathy progression. First, we carried out a thorough investigation comparing the performance of various base classifiers for several known sets of the most essential features in this database and determined that Random Forest significantly and consistently outperforms all other base classifiers in this new application. Second, we used feature selection and ranking implemented in Random Forest. It was able to identify a new set of features, which has turned out better than all other sets considered for this large and well-known database previously. Random Forest remained the very best classier for the new set of features too. Third, we investigated meta classifiers and new multi-level meta classifiers based on Random Forest, which have improved its performance. The results obtained show that novel multi-level meta classifiers achieved further improvement and obtained new outcomes that are significantly better compared with the outcomes published in the literature previously for cardiac autonomic neuropathy.

Sectoral analysis on capital structure determinants among the Malaysia listed firms

This study highlights the sensitivity of capital structure determinants in each sector within the ensembles of Malaysia Listed Companies. Based on pooled OLS, fixed effect and Generalized Method of Moments analysis, the findings revealed that capital structure determinants vary across sectors due to its nature or characteristics.

Neural network ensemble : evaluation of aggregation algorithms for electricity demand forecasting

This paper examines and analyzes different aggregation algorithms to improve accuracy of forecasts obtained using neural network (NN) ensembles. These algorithms include equal-weights combination of Best NN models, combination of trimmed forecasts, and Bayesian Model Averaging (BMA). The predictive performance of these algorithms are evaluated using Australian electricity demand data. The output of the aggregation algorithms of NN ensembles are compared with a Naive approach. Mean absolute percentage error is applied as the performance index for assessing the quality of aggregated forecasts. Through comprehensive simulations, it is found that the aggregation algorithms can significantly improve the forecasting accuracies. The BMA algorithm also demonstrates the best performance amongst aggregation algorithms investigated in this study.

Bayesian model averaging of load demand forecasts from neural network models

Creating a set of a number of neural network (NN) models in an ensemble and accumulating them can achieve better overview capability as compared to single neural network. Neural network ensembles are designed to provide solutions to particular problems. Many researchers and academicians have adopted this NN ensemble technique, especially in machine learning, and has been applied in various fields of engineering, medicine and information technology. This paper present a robust aggregation methodology for load demand forecasting based on Bayesian Model Averaging of a set of neural network models in an ensemble. This paper estimate a vector of coefficient for individual NN models' forecasts using validation data-set. These coefficients, also known as weights, are equal to posterior probabilities of the models generating the forecasts. These BMA weights are then used in combining forecasts generated from NN models with test data-set. By comparing the Bayesian results with the Simple Averaging method, it was observed that benefits are obtained by utilizing an advanced method like BMA for forecast combinations.

Personal, musical and social benefits of singing in a community ensemble: three case studies in Melbourne (Australia)

Australia has a diverse, multilayered society that reflects its rich musical life. There are many community choirs formed by various cultural and linguistically diverse groups. This article is part of an ongoing project, Well-being and ageing: community, diversity and the arts (since 2008), undertaken by Deakin University and Monash University, that explores the cultural diversity within Australian society and how active music engagement fosters well-being. The singing groups selected for this discussion are the Skylarkers, the Bosnian Behar Choir, and the Coro Furlan. The Skylarkers and the Bosnian Behar Choir are mixed groups who respectively perform popular music from their generation and celebrate their culture through music. The Coro Furlan is an Italian male choir who understand themselves as custodians of their heritage. In these interpretative, qualitative case studies semi-structured interviews were undertaken and analyzed using Interpretative Phenomenological Analysis. In this approach there is an exploration of participants’ understanding of their lived experiences. The analysis of the combined data identified musical and social benefits that contribute to participants’ sense of individual well-being. Musical benefits occurred through sharing, learning and singing together. Social benefits included opportunities to build friendships, overcome isolation and gain a sense of validation. Many found that singing enhanced their health and happiness. Active music making in community choirs and music ensembles continues to be an effective way to support individuals, build community, and share culture and heritage.

Iterative construction of hierarchical classifiers for phishing website detection

This article is devoted to a new iterative construction of hierarchical classifiers in SimpleCLI for the detection of phishing websites. Our new construction of hierarchical systems creates ensembles of ensembles in SimpleCLI by iteratively linking a top-level ensemble to another middle-level ensemble instead of a base classifier so that the top-level ensemble can generate a large multilevel system. This new construction makes it easy to set up and run such large systems in SimpleCLI. The present article concentrates on the investigation of performance of the iterative construction of such classifiers for the example of detection of phishing websites. We carried out systematic experiments evaluating several essential ensemble techniques as well as more recent approaches and studying their performance as parts of the iterative construction of hierarchical classifiers. The results presented here demonstrate that the iterative construction of hierarchical classifiers performed better than the base classifiers and standard ensembles. This example of application to the classification of phishing websites shows that the new iterative construction combining diverse ensemble techniques into the iterative construction of hierarchical classifiers can be applied to increase the performance in situations where data can be processed on a large computer. © 2014 ACADEMY PUBLISHER.

Cultural pedagogies in the museum: walking, listening and feeling

Pedagogy is often glossed as the ‘art and science of teaching’ but this focus typically ties it to the instructional practices of formalised schooling. Like the emerging work on ‘public pedagogies’, the notion of cultural pedagogies signals the importance of the pedagogic in realms other than institutionalised education, but goes beyond the notion of public pedagogies in two ways: it includes spaces which are not so public, and it includes an emphasis on material and non-human actors. This collection foregrounds this broader understanding of pedagogy by framing enquiry through a series of questions and across a range of settings. How, for example, are the processes of ‘teaching’ and ‘learning’ realised within and across the pedagogic processes specific to various social sites? What ensembles of people, things and practices are brought together in specific institutional and everyday settings to accomplish these processes? This collection brings together researchers whose work across the interdisciplinary nexus of cultural studies, sociology, media studies, education and museology offers significant insights into these ‘cultural pedagogies’ – the practices and relations through which cumulative changes in how we act, feel and think occur. Cultural Pedagogies and Human Conduct opens up debate across disciplines, theoretical perspectives and empirical foci to explore both what is pedagogical about culture and what is cultural about pedagogy.

Intelligent facial emotion recognition using a layered encoding cascade optimization model

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.

Improving the quality of prediction intervals through optimal aggregation

Neural networks (NNs) are an effective tool to model nonlinear systems. However, their forecasting performance significantly drops in the presence of process uncertainties and disturbances. NN-based prediction intervals (PIs) offer an alternative solution to appropriately quantify uncertainties and disturbances associated with point forecasts. In this paper, an NN ensemble procedure is proposed to construct quality PIs. A recently developed lower-upper bound estimation method is applied to develop NN-based PIs. Then, constructed PIs from the NN ensemble members are combined using a weighted averaging mechanism. Simulated annealing and a genetic algorithm are used to optimally adjust the weights for the aggregation mechanism. The proposed method is examined for three different case studies. Simulation results reveal that the proposed method improves the average PI quality of individual NNs by 22%, 18%, and 78% for the first, second, and third case studies, respectively. The simulation study also demonstrates that a 3%-4% improvement in the quality of PIs can be achieved using the proposed method compared to the simple averaging aggregation method.

Examining performance of aggregation algorithms for neural network-based electricity demand forecasting

The aim of this research is to examine the efficiency of different aggregation algorithms to the forecasts obtained from individual neural network (NN) models in an ensemble. In this study an ensemble of 100 NN models are constructed with a heterogeneous architecture. The outputs from NN models are combined by three different aggregation algorithms. These aggregation algorithms comprise of a simple average, trimmed mean, and a Bayesian model averaging. These methods are utilized with certain modifications and are employed on the forecasts obtained from all individual NN models. The output of the aggregation algorithms is analyzed and compared with the individual NN models used in NN ensemble and with a Naive approach. Thirty-minutes interval electricity demand data from Australian Energy Market Operator (AEMO) and the New York Independent System Operator's web site (NYISO) are used in the empirical analysis. It is observed that the aggregation algorithm perform better than many of the individual NN models. In comparison with the Naive approach, the aggregation algorithms exhibit somewhat better forecasting performance.

Testing the transferability of a coarse-grained model to intrinsically disordered proteins

The intermediate-resolution coarse-grained protein model PLUM [T. Bereau and M. Deserno, J. Chem. Phys., 2009, 130, 235106] is used to simulate small systems of intrinsically disordered proteins involved in biomineralisation. With minor adjustments to reduce bias toward stable secondary structure, the model generates conformational ensembles conforming to structural predictions from atomistic simulation. Without additional structural information as input, the model distinguishes regions of the chain by predicted degree of disorder, manifestation of structure, and involvement in chain dimerisation. The model is also able to distinguish dimerisation behaviour between one intrinsically disordered peptide and a closely related mutant. We contrast this against the poor ability of PLUM to model the S1 quartz-binding peptide.

A clustering-based multi-layer distributed ensemble for neurological diagnostics in cloud services

This paper investigates the problem of minimizing data transfer between different data centers of the cloud during the neurological diagnostics of cardiac autonomic neuropathy (CAN). This problem has never been considered in the literature before. All classifiers considered for the diagnostics of CAN previously assume complete access to all data, which would lead to enormous burden of data transfer during training if such classifiers were deployed in the cloud. We introduce a new model of clustering-based multi-layer distributed ensembles (CBMLDE). It is designed to eliminate the need to transfer data between different data centers for training of the classifiers. We conducted experiments utilizing a dataset derived from an extensive DiScRi database. Our comprehensive tests have determined the best combinations of options for setting up CBMLDE classifiers. The results demonstrate that CBMLDE classifiers not only completely eliminate the need in patient data transfer, but also have significantly outperformed all base classifiers and simpler counterpart models in all cloud frameworks.

Molecular dynamics approach to the structural characterization and transport properties of poly(acrylonitrile)/N,N-dimethylformamide solutions

Poly(acrylonitrile) (PAN) in N,N-dimethylformamide (DMF) is a popular solution for producing large variety of polymer products. To precisely describe the behaviours of PAN and DMF in the synthesis processes, it is significant to call for more details about the structure, some thermodynamic and dynamical properties of PAN-DMF solutions. A PAN-DMF solution was simulated via molecular dynamics with an all-atom OPLS type potential in both the NPT and NVT ensembles. The simulation results were evaluated with quantum mechanical calculations (MP2/6-311 ++G(d,p) and counterpoise procedure) and were compared with available experimental results. The liquid structure was illustrated with pair correlation functions and transport and dynamics properties were calculated with the mean-square displacements MSD and the velocity autocorrelation functions. The strong H-bonds of C≡N « H-C=O, CH » O=C-H and CH2 O=C-H, with distances of 2.55 Å, 2.55 Å and 2.65 Å, respectively, were found. The largest interaction energy of - 7.157 kcal/mol between DMF molecules and PAN molecules was found at 4.9 Å center-of-mass distance. A potential profile of intermolecular interaction of DMF with PAN along the interaction distance was presented, clearly showing an increase of DMF vaporisation heat when it getting close to PAN molecules. This provided very useful information to analyse the vaporisation behaviours of DMF at the microscopic level, which is essential to comprehensively understand molecular rearrangements towards the design of synthetic processes. The impact of the presence of the PAN on the DMF solution properties were also benchmarked with pure DMF solution.

Multilayer hybrid strategy for phishing email zero-day filtering

The cyber security threats from phishing emails have been growing buoyed by the capacity of their distributors to fine-tune their trickery and defeat previously known filtering techniques. The detection of novel phishing emails that had not appeared previously, also known as zero-day phishing emails, remains a particular challenge. This paper proposes a multilayer hybrid strategy (MHS) for zero-day filtering of phishing emails that appear during a separate time span by using training data collected previously during another time span. This strategy creates a large ensemble of classifiers and then applies a novel method for pruning the ensemble. The majority of known pruning algorithms belong to the following three categories: ranking based, clustering based, and optimization-based pruning. This paper introduces and investigates a multilayer hybrid pruning. Its application in MHS combines all three approaches in one scheme: ranking, clustering, and optimization. Furthermore, we carry out thorough empirical study of the performance of the MHS for the filtering of phishing emails. Our empirical study compares the performance of MHS strategy with other machine learning classifiers. The results of our empirical study demonstrate that MHS achieved the best outcomes and multilayer hybrid pruning performed better than other pruning techniques.