International Journal of Advanced Intelligence Paradigms http://www.inderscience.com/browse/index.php?journalID=272&year=2011&vol=3&issue=3/4 Inderscience Publishers Ltd en-uk International Journal of Advanced Intelligence Paradigms 1755-0386 1755-0394 © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijaip_scoverijaip.jpg http://www.inderscience.com/browse/index.php?journalID=272&year=2011&vol=3&issue=3/4 http://www.inderscience.com/link.php?id=43426 We propose a novel unifying framework for building a novel granular modular architecture for a machine visual system that accommodates a large spectrum of potential vision problems. Thus removing the ad hoc nature of present solutions and providing the basis for new generation of machine visual systems. Such a framework works by integrating some useful concepts from the human vision processes and adding some interesting granular functionalities of human cognition and it advocates further hybridisation of non-linear digital filters and soft computing in implementing such machine intelligent visual systems. Our focus herein will be on the low level and mid-level stages of such a framework. The goal is to build an automatic system that can be used for degraded multi-modal image processing, including x-rays, MRI, Sonar, etc. for diagnosis, recognition, registration and information fusion purposes. For illustration purposes, an investigation concerning its application to a real world problem is also provided. We are interested by an application to automatic detection and classification of patients' spines affected by idiopathic scoliosis from X-rays images. A unified granular hybrid soft computing framework for vision engineering
Mokhtar Beldjehem
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 189 - 202
We propose a novel unifying framework for building a novel granular modular architecture for a machine visual system that accommodates a large spectrum of potential vision problems. Thus removing the ad hoc nature of present solutions and providing the basis for new generation of machine visual systems. Such a framework works by integrating some useful concepts from the human vision processes and adding some interesting granular functionalities of human cognition and it advocates further hybridisation of non-linear digital filters and soft computing in implementing such machine intelligent visual systems. Our focus herein will be on the low level and mid-level stages of such a framework. The goal is to build an automatic system that can be used for degraded multi-modal image processing, including x-rays, MRI, Sonar, etc. for diagnosis, recognition, registration and information fusion purposes. For illustration purposes, an investigation concerning its application to a real world problem is also provided. We are interested by an application to automatic detection and classification of patients' spines affected by idiopathic scoliosis from X-rays images.

]]> 10.1504/IJAIP.2011.043426 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 189 - 202 Mokhtar Beldjehem Sainte-Anne's University, 1589 Walnut Street, Halifax, Nova Scotia, B3H 3S1, Canada perception engineering modular granular vision architecture visual front-end module mid-level module fuzzy sets fuzzy logic possibility theory hybrid fuzzy-neuro models granulation nonlinear digital filters x-rays images neural networks degraded images multi-modal image processing automatic detection automatic classification spine images idiopathic scoliosis medical imaging. 2011-10-29T23:20:50-05:00 3 3/4 189 202 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43427 In this paper, the basis of the models of the condensate water and the air cooled condenser are presented. The models are part of a full scope simulator of a 450 MW combined cycle power plant. The simulator is executed in real time and is intended to be a support for the training of the operators of the Comisión Federal de Electricidad (the Mexican utility company). The simulator is presently in the final acceptance tests stage and is programmed to be in commercial operation in 2010. Here, are included a summary of the modelling methodology used to develop the referred models and the mathematical fundaments used to obtain the main equations. The tendencies of selected variables during a transient are displayed and analysed in order to probe the validity of the new generic models. Condensate system modelling in real time for a training power plant simulator
Yadira Mendoza-Alegría; Edgardo J. Roldán-Villasana
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 203 - 222
In this paper, the basis of the models of the condensate water and the air cooled condenser are presented. The models are part of a full scope simulator of a 450 MW combined cycle power plant. The simulator is executed in real time and is intended to be a support for the training of the operators of the Comisión Federal de Electricidad (the Mexican utility company). The simulator is presently in the final acceptance tests stage and is programmed to be in commercial operation in 2010. Here, are included a summary of the modelling methodology used to develop the referred models and the mathematical fundaments used to obtain the main equations. The tendencies of selected variables during a transient are displayed and analysed in order to probe the validity of the new generic models.

]]> 10.1504/IJAIP.2011.043427 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 203 - 222 Yadira Mendoza-Alegría; Edgardo J. Roldán-Villasana Simulation Department, Instituto de Investigaciones Eléctricas, Av Reforma 113, Col. Palmira, 62440 Cuernavaca, Mor., México. ' Simulation Department, Instituto de Investigaciones Eléctricas, Av Reforma 113, Col. Palmira, 62440 Cuernavaca, Mor., México combined cycle power plants real time simulator process modelling air cooled condensers simulation condensate water operator training. 2011-10-29T23:20:50-05:00 3 3/4 203 222 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43428 Medical errors are a major cause of harm to patients. The World Health Organization has, therefore, formed an Alliance for Patient Safety. Reports on error are a rich source for understanding of causes, cascades and consequences. Improvements in safety can result through lessons learnt from these. There are loud and clear calls for the development of appropriate error reporting and taxonomy systems, that are useful at the point of care and policy levels. The urgency expressed in these calls presents a challenge and an opportunity to harness the power of computer visualisation that can help structure and illustrate the 'story' of an error in a universal language. This can overcome the shortcomings of current reporting methods and help create an unambiguous international error taxonomy. Presented here is a concept for a web-based visual error reporting system. Although the ambulatory care domain is used for illustration, this concept can provide a user-friendly, efficient means of reporting errors in any domain of healthcare. This unambiguous structured visual modelling, aided by touch-screen technology, is useful to all members of healthcare teams, especially policymakers and patients. Patients particularly are a major source of knowledge on the state of safety in all healthcare settings that is waiting to be tapped. Creating a common vision for all stakeholders to make healthcare safer with interactive visual modelling
Ranjit Singh; Ashok Singh; Sonjoy Singh; Gurdev Singh
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 223 - 239
Medical errors are a major cause of harm to patients. The World Health Organization has, therefore, formed an Alliance for Patient Safety. Reports on error are a rich source for understanding of causes, cascades and consequences. Improvements in safety can result through lessons learnt from these. There are loud and clear calls for the development of appropriate error reporting and taxonomy systems, that are useful at the point of care and policy levels. The urgency expressed in these calls presents a challenge and an opportunity to harness the power of computer visualisation that can help structure and illustrate the 'story' of an error in a universal language. This can overcome the shortcomings of current reporting methods and help create an unambiguous international error taxonomy. Presented here is a concept for a web-based visual error reporting system. Although the ambulatory care domain is used for illustration, this concept can provide a user-friendly, efficient means of reporting errors in any domain of healthcare. This unambiguous structured visual modelling, aided by touch-screen technology, is useful to all members of healthcare teams, especially policymakers and patients. Patients particularly are a major source of knowledge on the state of safety in all healthcare settings that is waiting to be tapped.

]]> 10.1504/IJAIP.2011.043428 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 223 - 239 Ranjit Singh; Ashok Singh; Sonjoy Singh; Gurdev Singh UB Patient Safety Research Center, University at Buffalo, Room CC155, 462 Grider Street, Buffalo, NY 14215, USA. ' Niagara Family Medicine Associates, Porter Rd., Niagara Falls, NY 14092, USA. ' Niagara Family Medicine Associates, Porter Rd., Niagara Falls, NY 14092, USA. ' UB Patient Safety Research Center, University at Buffalo, Room CC155, 462 Grider Street, Buffalo, NY 14215, USA common vision healthcare technology interactive patient safety visual modelling web-based visual error reporting medical errors ambulatory care healthcare management. 2011-10-29T23:20:50-05:00 3 3/4 223 239 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43429 Subjects identified letters or judged the sizes of squares presented visually and/or haptically. The stimuli were presented as spatiotemporal patterns (pre-recorded movement pathways) matched to avoid favouring either mode. Visual explorers were shown pathways as either a 1 cm line tracing out the shape (moving window condition) or as a line moving behind a stationary 1 cm window (stationary window condition). Haptic explorers' fingertips were guided along raised-line pathways (moving window condition) or felt the shapes, depicted in raised-line drawings, moving under their static fingertip (stationary window condition). Visual and haptic performance did not differ but the moving window conditions yielded lower latencies than stationary window conditions in both modes. When squares of different sizes were presented simultaneously to vision and kinesthesis, vision was dominant. The reverse was true when tactile (cutaneous) input was added to the kinesthetic information. These findings support the optimal integration hypothesis in that precision of information is critically related to dominance, and they challenge the concept of sensory capture as a modality-specific phenomenon. A precision-of-information explanation of sensory dominance
George H. Van Doorn; Mark A. Symmons; Barry L. Richardson
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 240 - 256
Subjects identified letters or judged the sizes of squares presented visually and/or haptically. The stimuli were presented as spatiotemporal patterns (pre-recorded movement pathways) matched to avoid favouring either mode. Visual explorers were shown pathways as either a 1 cm line tracing out the shape (moving window condition) or as a line moving behind a stationary 1 cm window (stationary window condition). Haptic explorers' fingertips were guided along raised-line pathways (moving window condition) or felt the shapes, depicted in raised-line drawings, moving under their static fingertip (stationary window condition). Visual and haptic performance did not differ but the moving window conditions yielded lower latencies than stationary window conditions in both modes. When squares of different sizes were presented simultaneously to vision and kinesthesis, vision was dominant. The reverse was true when tactile (cutaneous) input was added to the kinesthetic information. These findings support the optimal integration hypothesis in that precision of information is critically related to dominance, and they challenge the concept of sensory capture as a modality-specific phenomenon.

]]> 10.1504/IJAIP.2011.043429 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 240 - 256 George H. Van Doorn; Mark A. Symmons; Barry L. Richardson School of Applied Media and Social Sciences, Monash University, Churchill, Victoria 3842, Australia. ' School of Applied Media and Social Sciences, Monash University, Churchill, Victoria 3842, Australia. ' School of Applied Media and Social Sciences, Monash University, Churchill, Victoria 3842, Australia vision haptics cutaneous input kinesthesis sensory dominance sensory integration tactile input sensory capture. 2011-10-29T23:20:50-05:00 3 3/4 240 256 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43430 Most modern plants are multivariable, non-linear and time-variant. Therefore, they are difficult to model and control especially when measurements are insufficient or imprecise due to variables interactions, disturbances and noise impact. A perspective model-free approach is based on fuzzy logic, which has proved efficient in ensuring both robust and economic control, employing linguistic expert knowledge in production of simple and feasible non-linear controllers that outperform their linear counterparts. The aim of this investigation and the main contributions are related to the development of a method for the design of multivariable robust fuzzy logic controllers and its implementation for the control of a laboratory-scale aerodynamic plant in real time using MATLAB. Design and implementation of robust multivariable PI-like fuzzy logic controller for aerodynamic plant
Snejana Yordanova; Elena Haralanova
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 257 - 272
Most modern plants are multivariable, non-linear and time-variant. Therefore, they are difficult to model and control especially when measurements are insufficient or imprecise due to variables interactions, disturbances and noise impact. A perspective model-free approach is based on fuzzy logic, which has proved efficient in ensuring both robust and economic control, employing linguistic expert knowledge in production of simple and feasible non-linear controllers that outperform their linear counterparts. The aim of this investigation and the main contributions are related to the development of a method for the design of multivariable robust fuzzy logic controllers and its implementation for the control of a laboratory-scale aerodynamic plant in real time using MATLAB.

]]> 10.1504/IJAIP.2011.043430 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 257 - 272 Snejana Yordanova; Elena Haralanova Faculty of Automation, Technical University of Sofia, 8 Kliment Ohridski Blvd., Sofia 1000, Bulgaria. ' Faculty of Automation, Technical University of Sofia, 8 Kliment Ohridski Blvd., Sofia 1000, Bulgaria two-rotor aerodynamic systems two-variable nonlinear plant MATLAB real time control robust performance fuzzy logic fuzzy control controller design multivariable control robust control. 2011-10-29T23:20:50-05:00 3 3/4 257 272 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43431 The goal of this paper is to find Wardrop equilibrium in transport networks at case of uncertainty situations, where the uncertainty comes from lack of information. The uncertainty has been handled by Dempster-Shafer theory, an interval-based solution has been developed for handling the paths with cost. Adaptive simulation tool has been constructed in order to find the equilibrium, which gives only estimated solution, but this is sufficient for large networks as well. A new developed adaptive run length control algorithm helps for the reliability in the simulation run. Equilibrium estimation based on unreliable information in transport networks by adaptive simulation
Gábor Sz?cs
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 273 - 285
The goal of this paper is to find Wardrop equilibrium in transport networks at case of uncertainty situations, where the uncertainty comes from lack of information. The uncertainty has been handled by Dempster-Shafer theory, an interval-based solution has been developed for handling the paths with cost. Adaptive simulation tool has been constructed in order to find the equilibrium, which gives only estimated solution, but this is sufficient for large networks as well. A new developed adaptive run length control algorithm helps for the reliability in the simulation run.

]]> 10.1504/IJAIP.2011.043431 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 273 - 285 Gábor Sz?cs Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, 2nd Magyar Tudósok Krt., H-1117, Budapest, Hungary Wardrop equilibrium information uncertainty Dempster-Shafer theory adaptive simulation transport networks. 2011-10-29T23:20:50-05:00 3 3/4 273 285 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43432 In this paper, comparative study of morphological edge detection and region growing segmentation technique is introduced to detect and assess the flaws from the radiographic images. In the proposed method, segmentation algorithms are applied to detect the different types of flaws and calculate the necessary features such as major axis length, minor axis length, area, and perimeter. Computing time is optimised and algorithm is simpler to implement. These methodologies are compared and concluded to be effective for all possible nine types of weld flaws detection (slag inclusion, worm hole, porosity incomplete penetration, under cuts, cracks, lack of fusion, and weaving fault slag line). The experimental results show that our proposed method gives good performance for non-destructive evaluation (NDE) of radiographic images. NDE weld defect detection and feature extraction using segmentation approach
Vijay R. Rathod; R.S. Anand
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 286 - 304
In this paper, comparative study of morphological edge detection and region growing segmentation technique is introduced to detect and assess the flaws from the radiographic images. In the proposed method, segmentation algorithms are applied to detect the different types of flaws and calculate the necessary features such as major axis length, minor axis length, area, and perimeter. Computing time is optimised and algorithm is simpler to implement. These methodologies are compared and concluded to be effective for all possible nine types of weld flaws detection (slag inclusion, worm hole, porosity incomplete penetration, under cuts, cracks, lack of fusion, and weaving fault slag line). The experimental results show that our proposed method gives good performance for non-destructive evaluation (NDE) of radiographic images.

]]> 10.1504/IJAIP.2011.043432 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 286 - 304 Vijay R. Rathod; R.S. Anand Department of Electrical Engineering, Indian Institute of Technology, Roorkee, Roorkee-247667, India. ' Department of Electrical Engineering, Indian Institute of Technology, Roorkee, Roorkee-247667, India radiographic images weld flaws image segmentation region growing morphological edge detection NDE nondestructive evaluation weld defects defect detection feature extraction welding. 2011-10-29T23:20:50-05:00 3 3/4 286 304 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43433 High learning and adaptation ability of intelligent agents based on artificial neural networks (ANNs) has made them a popular tool in design and implementation of intrusion detection systems (IDS). However, ANN might consume significant resources during their retraining because of network changes. The paper investigates the design of ANN structures that may reduce the resource consumption without a substantial performance degradation. It describes the results of empirical studies examining a variety of design solutions, such as the choice of the ANN architecture and its parameters, the choice of an ANN fully connected topology versus a partial connectivity and the IDS design in a form of a hierarchical system of heterogeneous ANN-based agents. The results are analysed and design recommendations are provided. The fully connected ANN structure optimised with genetic algorithms has been found to achieve the best performance, while partial connectivity might save resources without a significant sacrifice of possible accomplishments. Resource awareness in computational intelligence
Roman V. Yampolskiy; Leon Reznik; Mike Adams; Joshua Harlow; Dima Novikov
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 305 - 322
High learning and adaptation ability of intelligent agents based on artificial neural networks (ANNs) has made them a popular tool in design and implementation of intrusion detection systems (IDS). However, ANN might consume significant resources during their retraining because of network changes. The paper investigates the design of ANN structures that may reduce the resource consumption without a substantial performance degradation. It describes the results of empirical studies examining a variety of design solutions, such as the choice of the ANN architecture and its parameters, the choice of an ANN fully connected topology versus a partial connectivity and the IDS design in a form of a hierarchical system of heterogeneous ANN-based agents. The results are analysed and design recommendations are provided. The fully connected ANN structure optimised with genetic algorithms has been found to achieve the best performance, while partial connectivity might save resources without a significant sacrifice of possible accomplishments.

]]> 10.1504/IJAIP.2011.043433 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 305 - 322 Roman V. Yampolskiy; Leon Reznik; Mike Adams; Joshua Harlow; Dima Novikov Duthie Center for Engineering 215, Speed School of Engineering, University of Louisville, Louisville, KY 40292, USA. ' Computer Science, Rochester Institute of Technology, Room 3-521, Building 70, Rochester, NY 14623, USA. ' Acme Packet, Inc., 100 Crosby Drive, Bedford, MA 01730, USA. ' Yahoo!, Inc., 701 First Avenue Sunnyvale, #A1334, San Jose, CA 94089, USA. ' VirtualScopics, Inc., 500 Linden Oaks, Rochester, NY 14625, USA intrusion detection design genetic algorithms artificial neural networks ANNs resource awareness computational intelligence intelligent agents. 2011-10-29T23:20:50-05:00 3 3/4 305 322 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43434 In this paper, a modular approach is investigated an educational response to the fundamental characteristics and requirements of the new era, whose main determinants are globalisation and networking, rapid technological development, information-based economy and the rapid obsolescence of information and knowledge. Education is one of the most important factors responsible for the development of society and its adaptation to changes brought by the information age is very important. In order to successfully achieve this adjustment, it is not enough to only change and update the content. It is equally important to make changes in teaching forms and methods. Modern education requires a new model of learning active learning based on real-world information resources. Modular approach to modelling of higher education in information technology
Djordje Nadrljanski; Mila Nadrljanski; Ivan Boži?evi?
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 323 - 340
In this paper, a modular approach is investigated an educational response to the fundamental characteristics and requirements of the new era, whose main determinants are globalisation and networking, rapid technological development, information-based economy and the rapid obsolescence of information and knowledge. Education is one of the most important factors responsible for the development of society and its adaptation to changes brought by the information age is very important. In order to successfully achieve this adjustment, it is not enough to only change and update the content. It is equally important to make changes in teaching forms and methods. Modern education requires a new model of learning active learning based on real-world information resources.

]]> 10.1504/IJAIP.2011.043434 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 323 - 340 Djordje Nadrljanski; Mila Nadrljanski; Ivan Boži?evi? Faculty of Management, Vase Stai?a 6, 21000 Novi Sad, Srbija. ' Faculty of Maritime Studies, University of Split, Zrinsko Frankopanska 37, 21000 Split, Croatia. ' Studia Intermedia, Ilica 8, 10000 Zagreb, Croatia IT knowledge curriculum society of knowledge education modelling IT education information technology higher education active learning. 2011-10-29T23:20:50-05:00 3 3/4 323 340 2011-10-29T23:20:50-05:00 http://www.inderscience.com/link.php?id=43435 Classes of real world datasets have various properties (such as imbalance, size, complexity, and class distribution) that make the classification task more difficult. We investigate the robustness of six classification techniques over data having various combinations of the above mentioned properties. One artificial domain and six real world datasets are used in these experiments. Results of our analysis point to the frequency-based classifiers (such as the fuzzy and the Bayes classifiers) as being more robust over various imbalance, size, complexity, and training distribution. The effect of class imbalance, complexity, size, and learning distribution on classifier performance
Sofia Visa
International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 341 - 366
Classes of real world datasets have various properties (such as imbalance, size, complexity, and class distribution) that make the classification task more difficult. We investigate the robustness of six classification techniques over data having various combinations of the above mentioned properties. One artificial domain and six real world datasets are used in these experiments. Results of our analysis point to the frequency-based classifiers (such as the fuzzy and the Bayes classifiers) as being more robust over various imbalance, size, complexity, and training distribution.

]]> 10.1504/IJAIP.2011.043435 International Journal of Advanced Intelligence Paradigms, Vol. 3, No. 3/4 (2011) pp. 341 - 366 Sofia Visa Department of Mathematics and Computer Science, College of Wooster, 1189 Beall Ave., Wooster, OH 44691, USA classification techniques learning distribution imbalance data fuzzy sets fuzzy logic classifier performance data complexity size. 2011-10-29T23:20:50-05:00 3 3/4 341 366 2011-10-29T23:20:50-05:00