A rough set approach for selecting clustering attribute

A few of clustering techniques for categorical data exist to group objects having similar characteristics. Some are able to handle uncertainty in the clustering process while others have stability issues. However, the performance of these techniques is an issue due to low accuracy and high computational complexity. This paper proposes a new technique called maximum dependency attributes (MDA) for selecting clustering attribute. The proposed approach is based on rough set theory by taking into account the dependency of attributes of the database. We analyze and compare the performance of MDA technique with the bi-clustering, total roughness (TR) and min–min roughness (MMR) techniques based on four test cases. The results establish the better performance of the proposed approach.

Risk-based trust management for e-commerce

Electronic commerce (e-commerce) offers enormous opportunities for online trading while at the same time presenting potential risks. Although various mechanisms have been developed to elevate trust in e-commerce, research shows that shoppers continue to be skeptical about buying online and lack of trust is often cited as the main reason for it. Thus, enhancing success in e-commerce requires eliminating or reducing the risks. In this chapter, we present a multi-attribute trust management model that incorporates trust, transaction costs and product warranties. The new trust management system enables potential buyers to determine the risk level of a product before committing to proceed with the transaction. This is useful to online buyers as it allows them to be aware of the risk level and subsequently take the appropriate actions to minimize potential risks before engaging in risky businesses. Results of various simulation experiments show that the proposed multi-attribute trust management system can be highly effective in identifying risky transaction in electronic market places.

Negotiation strategy for mobile agent-based e-negotiation

Negotiation is a vital component of electronic trading. It is the key decision-making approach used to reach consensus between trading partners. Generally, the trading partners implement various negotiation strategies in an attempt to maximize their utilities. As negotiation strategies have impact on the outcomes of negotiation, it is imperative to have efficient negotiation strategies that truly maximize clients’ utilities. In this paper, we propose a multi-attribute mobile agent-based negotiation strategy that maximizes client’s utility. The strategy focuses on one-to-many bilateral negotiation. It considers different factors that have significant effect on the scheduling of various negotiation phases: offer collection, evaluation, negotiation, and bid settlement. The factors include offers expiry time, market search space, communication delays, processing queues, and transportation times. We reasoned about the correctness of the proposed negotiation strategy with respect to the existing negotiation strategies. The analysis showed that the proposed strategy boosts client’s utility, shortens negotiation time, and ensures adequate market search.

Missing value estimation for mixed-attribute data sets

Missing data imputation is a key issue in learning from incomplete data. Various techniques have been developed with great successes on dealing with missing values in data sets with homogeneous attributes (their independent attributes are all either continuous or discrete). This paper studies a new setting of missing data imputation, i.e., imputing missing data in data sets with heterogeneous attributes (their independent attributes are of different types), referred to as imputing mixed-attribute data sets. Although many real applications are in this setting, there is no estimator designed for imputing mixed-attribute data sets. This paper first proposes two consistent estimators for discrete and continuous missing target values, respectively. And then, a mixture-kernel-based iterative estimator is advocated to impute mixed-attribute data sets. The proposed method is evaluated with extensive experiments compared with some typical algorithms, and the result demonstrates that the proposed approach is better than these existing imputation methods in terms of classification accuracy and root mean square error (RMSE) at different missing ratios.

Classification of malware based on string and function feature selection

Anti-malware software producers are continually challenged to identify and counter new malware as it is released into the wild. A dramatic increase in malware production in recent years has rendered the conventional method of manually determining a signature for each new malware sample untenable. This paper presents a scalable, automated approach for detecting and classifying malware by using pattern recognition algorithms and statistical methods at various stages of the malware analysis life cycle. Our framework combines the static features of function length and printable string information extracted from malware samples into a single test which gives classification results better than those achieved by using either feature individually. In our testing we input feature information from close to 1400 unpacked malware samples to a number of different classification algorithms. Using k-fold cross validation on the malware, which includes Trojans and viruses, along with 151 clean files, we achieve an overall classification accuracy of over 98%.

Integrating instance-level and attribute-level knowledge into document clustering

In this paper, we present a document clustering framework incorporating instance-level knowledge in the form of pairwise constraints and attribute-level knowledge in the form of keyphrases. Firstly, we initialize weights based on metric learning with pairwise constraints, then simultaneously learn two kinds of knowledge by combining the distance-based and the constraint-based approaches, finally evaluate and select clustering result based on the degree of users’ satisfaction. The experimental results demonstrate the effectiveness and potential of the proposed method.

Professional training in applied psychology : towards a signature pedagogy for forensic psychology training

Forensic Psychology is a recognised and important sub-specialty of the Psychology discipline. However, after an expansion in the number of training places that were offered when programmes were first developed, recent years have seen these diminish in response to changes in university policies, resulting from reformulated Federal government funding models. In this article, we argue that it is important for the future of specialist areas of professional psychology to not only articulate the core skills and competencies that are associated with specialist practice but also to develop unique and distinctive approaches to teaching and learning signature pedagogies. Based on the premise that forensic psychological practice is, indeed, a distinctive activity that requires different skills and, importantly, different ways of thinking about the work from other areas of professional psychology, it is suggested that professional training in this area should aim to develop a signature pedagogy which combines methods of teaching and learning that have been developed in legal training programmes with principles of problem-based learning.

A 'respectful relationships' approach : could it be the answer to preventing gender-based violence?

A representation-intensive signature pedagogy for school science?

In this paper we examine Shulman’s notion of signature pedagogies for its usefulness extended to school science. We argue that school science is in an important sense an apprenticeship, and that calls for reform in school science are compatible with Shulman’s practice-based vision of professional learning. Two case studies of teaching and learning will be presented based on research in primary and secondary schools that involved working closely with teachers to develop and validate involving a representation-intensive pedagogy that lays claim to bringing school science closer to the knowledge building practices of science. Video images of classrooms, interviews with students and teachers, and documentation of students’ work, were used to construct insights into the teaching and learning process. It is argued that Shulman’s notion of professional practice as involving apprenticeships of knowledge, practice and identity provides a useful lens through which to view this innovation. Shulman’s characterisation of signature pedagogy is used to identify key features of the approach.

Characterising secondary school teacher imperatives as subject (signature) pedagogies : a pedagogy of support in maths and a pedagogy of engagement in science

The ideas of Lee Shulman have played a major role in reconceptualising pedagogical description. In 2005, Shulman described a construct called “signature pedagogies” in order to describe recognisable and distinctive pedagogies used to prepare future practitioners for their profession. As a broader application of Shulman’s ideas, this paper asks, what is the efficacy of describing pedagogies that have become entrenched in secondary school subjects as signature pedagogies? Approached from a cultural perspective these questions are examined by comparing the subject cultures of junior school maths and science as experienced by, and represented in the classrooms of, a small number of teachers from two secondary schools in Victoria, Australia. In this research, subject culture is underpinned by shared basic assumptions that govern the dominance of certain “subject paradigms” (what should be taught) and “subject pedagogies” (how this should be taught) (Ball & Lacey, 1980). In this secondary school setting, the term signature pedagogies can be equated to the term subject pedagogies on the basis that both aim to characterise practice across the subject, or discipline, based on what was perceived as central to the task of teaching and learning. The paper draws on classroom observation and teacher interview data to show how six teachers positioned two aspects of their teaching in relation to what they believed was central in shaping their maths and science teaching: the effect of the arrangement of curriculum content on teachers’ conceptualisations of the teaching task; and a pedagogical imperative to engage students through activity-based learning experiences. The cultural expectations surrounding these two aspects of teaching appear to have a strong influence on practice, and in some senses teachers’ pedagogical responses were clear. These common responses are what I am calling “subject pedagogies” (see Ball & Lacey, 1980) because there was general agreement about what was central to the teaching task. Two subject pedagogies were seen to represent strong discourses occurring in both subjects: a “Pedagogy of Support” in maths, and “Pedagogy of Engagement” in science. Their established and shared character resembled Shulman’s posited “signature pedagogies” (Shulman, 2005). The data shows that by evaluating cultural practices that teachers have in common, and assumptions underpinning these, there is potential for highlighting imbalances, strengths and weaknesses, and connections and disconnections, associated with prevailing subject pedagogies.

A distinct DNA methylation signature defines pediatric pre-B cell acute lymphoblastic leukemia

Pre-B cell acute lymphoblastic leukemia (ALL) is the most prevalent childhood malignancy and remains one of the highest causes of childhood mortality. Despite this, the mechanisms leading to disease remain poorly understood. We asked if recurrent aberrant DNA methylation plays a role in childhood ALL and have defined a genome-scale DNA methylation profile associated with the ETV6-RUNX1 subtype of pediatric ALL. Archival bone marrow smears from 19 children collected at diagnosis and remission were used to derive a disease specific DNA methylation profile. The gene signature was confirmed in an independent cohort of 86 patients. A further 163 patients were analyzed for DNA methylation of a three gene signature. We found that the DNA methylation signature at diagnosis was unique from remission. Fifteen loci were sufficient to discriminate leukemia from disease-free samples and purified CD34+ cells. DNA methylation of these loci was recurrent irrespective of cytogenetic subtype of pre-B cell ALL. We show that recurrent aberrant genomic methylation is a common feature of pre-B ALL, suggesting a shared pathway for disease development. By revealing new DNA methylation markers associated with disease, this study has identified putative targets for development of novel epigenetic-based therapies.

Hub-based reliable gene expression algorithm to classify ER+ and ER- breast cancer subtypes

Identifying gene signatures that are associatedwith the estrogen receptor based breast cancer samples is achallenging problem that has significant implications in breastcancer diagnosis and treatment. Various existing approaches foridentifying gene signatures have been developed but are not ableto achieve the satisfactory results because of their severallimitations. Subnetwork-based approaches have shown to be arobust classification method that uses interaction datasets suchas protein-protein interaction datasets. It has been reported thatthese interaction datasets contain many irrelevant interactionsthat have no biological meaning associated with them, and thusit is essential to filter out those interactions which can improvethe classification results. In this paper, we therefore, proposed ahub-based reliable gene expression algorithm (HRGE) thateffectively extracts the significant biologically-relevantinteractions and uses hub-gene topology to generate thesubnetwork based gene signatures for ER+ and ER- breastcancer subtypes. The proposed approach shows the superiorclassification accuracy amongst the other existing classifiers, inthe validation dataset.

Malware detection and prevention system based on multi-stage rules

The continuously rising Internet attacks pose severe challenges to develop an effective Intrusion Detection System (IDS) to detect known and unknown malicious attack. In order to address the problem of detecting known, unknown attacks and identify an attack grouped, the authors provide a new multi stage rules for detecting anomalies in multi-stage rules. The authors used the RIPPER for rule generation, which is capable to create rule sets more quickly and can determine the attack types with smaller numbers of rules. These rules would be efficient to apply for Signature Intrusion Detection System (SIDS) and Anomaly Intrusion Detection System (AIDS).

The signature pedagogy in chemistry education

Laboratories are the signature pedagogy in chemistry education. The chemical sciences are based in investigations that are reproducible, and objectively testable. Some investigations might involve testing a hypothesis – does a carbonate produce carbon dioxide gas when reacted with acid? Other activities may not have an obvious hypothesis – how much salt is in this detergent package? Nevertheless, laboratory work is a distinctive part of science generally, and of chemistry in particular.

Laboratory work is a significant part of working in the chemistry profession. The best way for students to learn what scientists do, is to do what scientists do. The only way to conduct a laboratory investigation is to get into a laboratory and to do it!

Learning and doing chemistry in a laboratory is an important and irreplaceable part of a chemistry education.

Time correlated anomaly detection based on inferences

Anomaly detection techniques are used to find the presence of anomalous activities in a network by comparing traffic data activities against a "normal" baseline. Although it has several advantages which include detection of "zero-day" attacks, the question surrounding absolute definition of systems deviations from its "normal" behaviour is important to reduce the number of false positives in the system. This study proposes a novel multi-agent network-based framework known as Statistical model for Correlation and Detection (SCoDe), an anomaly detection framework that looks for timecorrelated anomalies by leveraging statistical properties of a large network, monitoring the rate of events occurrence based on their intensity. SCoDe is an instantaneous learning-based anomaly detector, practically shifting away from the conventional technique of having a training phase prior to detection. It does acquire its training using the improved extension of Exponential Weighted Moving Average (EWMA) which is proposed in this study. SCoDe does not require any previous knowledge of the network traffic, or network administrators chosen reference window as normal but effectively builds upon the statistical properties from different attributes of the network traffic, to correlate undesirable deviations in order to identify abnormal patterns. The approach is generic as it can be easily modified to fit particular types of problems, with a predefined attribute, and it is highly robust because of the proposed statistical approach. The proposed framework was targeted to detect attacks that increase the number of activities on the network server, examples which include Distributed Denial of Service (DDoS) and, flood and flash-crowd events. This paper provides a mathematical foundation for SCoDe, describing the specific implementation and testing of the approach based on a network log file generated from the cyber range simulation experiment of the industrial partner of this project.