Comparative analysis of genetic algorithm, simulated annealing and cutting angle method for artificial neural networks
- Authors: Ghosh, Ranadhir , Ghosh, Moumita , Yearwood, John , Bagirov, Adil
- Date: 2005
- Type: Text , Journal article
- Relation: Machine Learning and Data Mining in Pattern Recognition, Proceedings Vol. 3587, no. (2005), p. 62-70
- Full Text: false
- Reviewed:
- Description: Neural network learning is the main essence of ANN. There are many problems associated with the multiple local minima in neural networks. Global optimization methods are capable of finding global optimal solution. In this paper we investigate and present a comparative study for the effects of probabilistic and deterministic global search method for artificial neural network using fully connected feed forward multi-layered perceptron architecture. We investigate two probabilistic global search method namely Genetic algorithm and Simulated annealing method and a deterministic cutting angle method to find weights in neural network. Experiments were carried out on UCI benchmark dataset.
- Description: C1
- Description: 2003003398
Consensus clustering and supervised classification for profiling phishing emails in internet commerce security
- Authors: Dazeley, Richard , Yearwood, John , Kang, Byeongho , Kelarev, Andrei
- Date: 2010
- Type: Text , Conference paper
- Relation: Paper presented at 11th International Workshop on Knowledge Management and Acquisition for Smart Systems and Services, PKAW 2010 Vol. 6232 LNAI, p. 235-246
- Full Text:
- Reviewed:
- Description: This article investigates internet commerce security applications of a novel combined method, which uses unsupervised consensus clustering algorithms in combination with supervised classification methods. First, a variety of independent clustering algorithms are applied to a randomized sample of data. Second, several consensus functions and sophisticated algorithms are used to combine these independent clusterings into one final consensus clustering. Third, the consensus clustering of the randomized sample is used as a training set to train several fast supervised classification algorithms. Finally, these fast classification algorithms are used to classify the whole large data set. One of the advantages of this approach is in its ability to facilitate the inclusion of contributions from domain experts in order to adjust the training set created by consensus clustering. We apply this approach to profiling phishing emails selected from a very large data set supplied by the industry partners of the Centre for Informatics and Applied Optimization. Our experiments compare the performance of several classification algorithms incorporated in this scheme. © 2010 Springer-Verlag Berlin Heidelberg.
Constructing an inter-post similarity measure to differentiate the psychological stages in offensive chats
- Authors: Miah, Md Waliur Rahman , Yearwood, John , Kulkarni, Siddhivinayak
- Date: 2015
- Type: Text , Journal article
- Relation: Journal of the Association for Information Science and Technology Vol. 66, no. 5 (2015), p. 1065-1081
- Full Text: false
- Reviewed:
- Description: Offensive Internet chats, particularly the child-exploiting type, tend to follow a documented psychological behavioral pattern. Researchers have identified some important stages in this pattern. The psychological stages broadly include befriending, information exchange, grooming, and approach. Similarities among the posts of a chat play an important role in differentiating as well as in identifying these stages. In this article a novel similarity measure is constructed which gives high Inter-post-similarity among the chat-posts within a particular behavioral stage and low inter-post-similarity across different behavioral stages. A psychological stage corpus-based dictionary is constructed from mining the terms associated with each stage. The dictionary works as a background knowledge-base to support the similarity measure. To find the inter-post similarity a modified sentence similarity measure is used. The proposed measure gives improved recognition of inter-stage and intra-stage similarity among the chat posts compared with other types of similarity measures. The pairwise inter-post similarity is used for clustering chat-posts into the psychological stages. Results of experiments demonstrate that the new clustering method gives better results than some current clustering methods.
Decisions surrounding adverse drug reaction prescribing : Insights from consumers and implications for decision support
- Authors: O'Brien, Michelle , Yearwood, John
- Date: 2005
- Type: Text , Journal article
- Relation: Journal of Research and Practice in Information Technology Vol. 37, no. 1 (2005), p. 57-71
- Full Text:
- Reviewed:
- Description: This paper presents findings from case studies of health consumers who each suspect they may have experienced an adverse drug reaction (ADR). These case studies are part of a larger study involving consumer/doctor decisions surrounding suspected adverse drug reactions and prescribing. Decision support to assist with the diagnosis and management of ADRs has, to date, primarily focused on providing in-time information to prescribers about factors that pertain to the consumer and the medications they are taking. Decision support that includes consumers usually targets treatment decisions. The results of this paper indicate the prescriber is only one decision contributor in a rich tapestry of decision contributors and decision types, and consumer decision types are significantly broader than treatment decisions. The results provide guidance for the development of decision support within this domain.
- Description: C1
- Description: 2003001435
Deliberative discourse and reasoning from generic argument structures
- Authors: Yearwood, John , Stranieri, Andrew
- Date: 2009
- Type: Text , Journal article
- Relation: AI and Society Vol. 23, no. 3 (2009), p. 353-377
- Full Text: false
- Reviewed:
- Description: In this article a dialectical model for practical reasoning within a community, based on the Generic/Actual Argument Model (GAAM) is advanced and its application to deliberative dialogue discussed. The GAAM, offers a dynamic template for structuring knowledge within a domain of discourse that is connected to and regulated by a community. The paper demonstrates how the community accepted generic argument structure acts to normatively influence both admissible reasoning and the progression of dialectical reasoning between participants. It is further demonstrated that these types of deliberation dialogues supported by the GAAM comply with criteria for normative principles for deliberation, specifically, Alexy's rules for discourse ethics and Hitchcock's Principles of Rational Mutual Inquiry. The connection of reasoning to the community in a documented and transparent structure assists in providing best justified reasons, principles of deliberation and ethical discourse which are important advantages for reasoning communities. © Springer-Verlag London Limited 2006.
Demand driven web services
- Authors: Sun, Zhaohao , Dong, Dong , Yearwood, John
- Date: 2011
- Type: Text , Book chapter
- Relation: Service intelligence and service science: Evolutionary technologies and challenges p. 35-55
- Full Text: false
- Reviewed:
- Description: Web services are playing a pivotal role in e-business, service intelligence, and service science. Demand-driven web services are becoming important for web services and service computing. However, many fundamental issues are still ignored to some extent. For example, what is the demand theory for web services, what is a demand-driven architecture for web services and what is a demand-driven web service lifecycle remain open. This chapter addresses these issues by examining fundamentals for demand analysis in web services, and proposing a demand-driven architecture for web services. It also proposes a demand-driven web service lifecycle for the main players in web services: Service providers, service requestors and service brokers, respectively. It then provides a unified perspective on demand-driven web service lifecycles. The proposed approaches will facilitate research and development of web services, e-services, service intelligence, service science and service computing.
- Description: 2003009207
Derivative-free optimization and neural networks for robust regression
- Authors: Beliakov, Gleb , Kelarev, Andrei , Yearwood, John
- Date: 2012
- Type: Text , Journal article
- Relation: Optimization Vol. 61, no. 12 (2012), p. 1467-1490
- Full Text:
- Reviewed:
- Description: Large outliers break down linear and nonlinear regression models. Robust regression methods allow one to filter out the outliers when building a model. By replacing the traditional least squares criterion with the least trimmed squares (LTS) criterion, in which half of data is treated as potential outliers, one can fit accurate regression models to strongly contaminated data. High-breakdown methods have become very well established in linear regression, but have started being applied for non-linear regression only recently. In this work, we examine the problem of fitting artificial neural networks (ANNs) to contaminated data using LTS criterion. We introduce a penalized LTS criterion which prevents unnecessary removal of valid data. Training of ANNs leads to a challenging non-smooth global optimization problem. We compare the efficiency of several derivative-free optimization methods in solving it, and show that our approach identifies the outliers correctly when ANNs are used for nonlinear regression. © 2012 Copyright Taylor and Francis Group, LLC.
Designing a decision module for modular artificial neural networks
- Authors: Ferguson, Brent , Ghosh, Ranadhir , Yearwood, John
- Date: 2004
- Type: Text , Conference paper
- Relation: Paper presented at the ICOTA6: 6th International Conference on Optimization - Techniques and Applications, Ballarat, Victoria : 9th December, 2004
- Full Text: false
- Reviewed:
- Description: E1
- Description: 2003000854
Detection of CAN by ensemble classifiers based on Ripple Down rules
- Authors: Kelarev, Andrei , Dazeley, Richard , Stranieri, Andrew , Yearwood, John , Jelinek, Herbert
- Date: 2012
- Type: Text , Book chapter
- Relation: Knowledge Management and Acquisition for Intelligent Systems p. 147-159
- Full Text: false
- Reviewed:
- Description: It is well known that classification models produced by the Ripple Down Rules are easier to maintain and update. They are compact and can provide an explanation of their reasoning making them easy to understand for medical practitioners. This article is devoted to an empirical investigation and comparison of several ensemble methods based on Ripple Down Rules in a novel application for the detection of cardiovascular autonomic neuropathy (CAN) from an extensive data set collected by the Diabetes Complications Screening Research Initiative at Charles Sturt University. Our experiments included essential ensemble methods, several more recent state-of-the-art techniques, and a novel consensus function based on graph partitioning. The results show that our novel application of Ripple Down Rules in ensemble classifiers for the detection of CAN achieved better performance parameters compared with the outcomes obtained previously in the literature.
Detection of child exploiting chatsfrom a mixed chat dataset as a text classification task
- Authors: Yearwood, John , Miah, Md Waliur Rahman , Kulkarni, Siddhivinayak
- Date: 2011
- Type: Text , Conference paper
- Relation: Proceedings of Australasian Language Technology Association Workshop
- Full Text: false
- Reviewed:
- Description: There is a rapidly growing body of work in the use of Embodied Conversational Agents (ECA) to convey complex contextual relationships through verbal and non-verbal communication, in domains ranging from military C2 to e-learning. In these applications the subject matter expert in often naive to the technical requirements of ECAs. ENGAGE (the Extensible Natural Gesture Animation Generation Engine) is desgined to automatically generate appropriate and 'realistic' animation for ECAs based on the content provided to them. It employs syntactic analysis of the surface text and uses predefined behaviours for the ECA. We discuss the design of this system, its current applications and plans for its future development.
Determining regularization parameters for derivative free neural learning
- Authors: Ghosh, Ranadhir , Ghosh, Moumita , Yearwood, John , Bagirov, Adil
- Date: 2005
- Type: Text , Conference paper
- Relation: Paper presented at 4th International Conference, MLDM 2005: Machine Learning and Data Mining in Pattern Recognition, Leipzig, Germany : 9th-11th July 2005 p. 71-79
- Full Text: false
- Description: Derivative free optimization methods have recently gained a lot of attractions for neural learning. The curse of dimensionality for the neural learning problem makes local optimization methods very attractive; however the error surface contains many local minima. Discrete gradient method is a special case of derivative free methods based on bundle methods and has the ability to jump over many local minima. There are two types of problems that are associated with this when local optimization methods are used for neural learning. The first type of problems is initial sensitivity dependence problem- that is commonly solved by using a hybrid model. Our early research has shown that discrete gradient method combining with other global methods such as evolutionary algorithm makes them even more attractive. These types of hybrid models have been studied by other researchers also. Another less mentioned problem is the problem of large weight values for the synaptic connections of the network. Large synaptic weight values often lead to the problem of paralysis and convergence problem especially when a hybrid model is used for fine tuning the learning task. In this paper we study and analyse the effect of different regularization parameters for our objective function to restrict the weight values without compromising the classification accuracy.
- Description: 2003001362
Discovering interesting association rules from legal databases
- Authors: Ivkovic, Sasha , Yearwood, John , Stranieri, Andrew
- Date: 2002
- Type: Text , Journal article
- Relation: Information & Communication Technology Law Vol. 11, no. 1 (2002), p. 35-47
- Full Text:
- Reviewed:
- Description: The Knowledge Discovery from Databases (KDD) technique called 'association rules' is applied to a large data set representing applicants for government-funded legal aid. Results indicate that KDD can be an invaluable tool for legal analysts. Association rules discovered identify associations between variables that are present in the data set though are not necessarily causal. Interesting rules can prompt analysts to formulate hypotheses for further investigation. The identification of interesting rules is typically performed using an objective measure of 'interesting' although this measure is often not sufficiently accurate to eliminate all uninteresting rules. In this article, a subjective measure of interestingness is adopted in conjunction with the objective measures. This leads to the ability to focus more accurately on those rules that surprise the analyst and are therefore more likely to be interesting. In general, KDD techniques have not been applied to law despite possible benefits because data is often stored in narrative form rather than in structured databases. However, the impending introduction of data warehouses that collect data from a number of organizations across a legal system presents invaluable opportunities for analysts using KDD.
- Description: C1
- Description: 2003000037
Does the Delphi process lead to increased accuracy in group-based judgmental forecasts or does it simply induce consensus amongst judgmental forecasters?
- Authors: Bolger, Fergus , Stranieri, Andrew , Wright, George , Yearwood, John
- Date: 2011
- Type: Text , Journal article
- Relation: Technological Forecasting and Social Change Vol. , no. (2011), p.
- Full Text: false
- Reviewed:
- Description: We investigate the relative impact of internal Delphi process factors - including panelists' degree of confidence, expertise, majority/minority positioning - and an external factor, richness of feedback - on opinion change and subsequent accuracy of judgmental forecasts. We found that panelists who had low confidence in their judgmental forecast and/or who were in a minority were more likely to change their opinion than those who were more confident and/or in a majority. The addition of rationales, or reasons, to the numeric feedback had little impact upon panelists' final forecasts, despite the quality of panelists' rationales being significantly positively correlated with accurate forecasts and thus of potential use to aid forecast improvement over Delphi rounds. Rather, the effect of rationales was similar to that of confidence: to pull panelists towards the majority opinion regardless of its correctness. We conclude that majority opinion is the strongest influence on panelists' opinion change in both the 'standard' Delphi, and Delphi-with-reasons. We make some suggestions for improved variants of the Delphi-with-reasons technique that should help reduce majority influence and thereby permit reasoned arguments to exert their proper pull on opinion change, resulting in forecast accuracy improvements over Delphi rounds. © 2011.
DOWL : A dynamic ontology language
- Authors: Avery, John , Yearwood, John
- Date: 2003
- Type: Text , Conference paper
- Relation: Paper presented at IADIS International Conference WWW/Internet 2003, Algarve, Portugal : 5th August, 2003
- Full Text:
- Reviewed:
- Description: Abstract: Ontologies in a web setting, particularly those used in a group context (such as a virtual community), need to be flexible and open to changes that reflect the evolution of knowledge. OWL the ontology language of the semantic web provides very little for facilitating the description of evolutionary changes in an ontology. We propose a dynamic web ontology language (dOWL), an extension to OWL, which consists of a set of elements that can be used to model these evolutionary changes in an ontology.
- Description: E1
- Description: 2003000552
Dramatic flow in interactive 3D narrative
- Authors: Macfadyen, Alyx , Stranieri, Andrew , Yearwood, John
- Date: 2007
- Type: Text , Conference paper
- Relation: Paper presented at Fourth Australiasian Conference on Interactive Entertainment, IE2007, RMIT University, Melbourne, Victoria : 3rd-5th December 2007
- Full Text:
- Description: The concept of dramatic level is crucial for a model of dramatic flow. We present a framework to maintain optimal dramatic flow in an interactive 3D environment where both linear and emergent narratives co-exist. Unlike all other interactive narrative prototypes the framework advanced focuses on the optimal dramatic flow of the emerging user narrative so that although fragmented, it can be engaging and make sense. Using a sample narrative from Ovid’s Metamorphoses [18] we demonstrate a method to evaluate dramatic levels as plot points so that movement across narratives retains a strong dramatic flow. Although users may never choose to explore any given linear narrative in its entirety, the result is an engaging and rich narrative experience.
- Description: 2003004706
Dramatic level analysis for interactive narrative
- Authors: Macfadyen, Alyx , Stranieri, Andrew , Yearwood, John
- Date: 2008
- Type: Text , Conference paper
- Relation: Paper presented at NILE 2008: 5th International Conference on Narrative and Interactive Learning Environments, Edinburgh, Scotland : 6th-8th August 2008 p. 17-22
- Full Text:
- Description: In interactive 3D narratives, a user’s narrative emerges through interactions with the system and embodied agencies (characters) mediated through the 3D environment. We present a methodology that identifies and measures four factors in interactive narrative where agency is present. We describe a technique for measuring drama, agency and engagement and compare the centrality of a designed interactive narrative with the emergent participatory narrative. This methodology has application as an analytic device for any interactive narrative where agency is fundamental. The adoption of the FrameNet semantic resource and the interpretation of interaction in narrative, situate this work in the domain of 3D interactive narratives, mixed and augmented realities and polymorphic narratives that cross forms of media.
- Description: 2003006540
Dynamical systems based on a fuzzy derivative and its applications to data classification
- Authors: Mammadov, Musa , Rubinov, Alex , Yearwood, John
- Date: 2003
- Type: Text , Conference paper
- Relation: Paper presented at the Industrial Optimisation 2003 Conference, Perth : 30th September, 2002
- Full Text: false
- Reviewed:
- Description: E1
- Description: 2003000339
Dynamical systems described by relational elasticities with applications to global optimization
- Authors: Mammadov, Musa , Rubinov, Alex , Yearwood, John
- Date: 2005
- Type: Text , Book chapter
- Relation: Continuous Optimization: Current Trends and Modern Applications Chapter p. 365-385
- Full Text: false
- Reviewed:
- Description: B1
Editorial
- Authors: Yearwood, John
- Date: 2010
- Type: Text , Journal article
- Relation: Journal of Research and Practice in Information Technology Vol. 42, no. 1 (2010), p. 1
- Full Text: false
- Reviewed:
Empirical investigation of consensus clustering for large ECG data sets
- Authors: Kelarev, Andrei , Stranieri, Andrew , Yearwood, John , Jelinek, Herbert
- Date: 2012
- Type: Text , Conference proceedings
- Full Text: false
- Description: This article investigates a novel machine learning approach applying consensus clustering in conjunction with classification for the data mining of very large and highly dimensional ECG data sets. To obtain robust and stable clusterings, consensus functions can be applied for clustering ensembles combining a multitude of independent initial clusterings. Direct applications of consensus functions to highly dimensional ECG data sets remain computationally expensive and impracticable. We introduce a multistage scheme including various procedures for dimensionality reduction, consensus clustering of randomized samples, followed by the use of a fast supervised classification algorithm. Applying the Hybrid Bipartite Graph Formulation combined with rank ordering and SMO we obtained an area under the receiver operating curve of 0.987. The performance of the classification algorithm at the final stage is crucial for the effectiveness of this technique. It can be regarded as an indication of the reliability, quality and stability of the combined consensus clustering. © 2012 IEEE.