International Journal of Computational Intelligence in Bioinformatics and Systems Biology http://www.inderscience.com/browse/index.php?journalID=281&year=2010&vol=1&issue=4 Inderscience Publishers Ltd en-uk International Journal of Computational Intelligence in Bioinformatics and Systems Biology 1755-8034 1755-8042 © 2010 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijcibsb_scoverijcibsb.jpg http://www.inderscience.com/browse/index.php?journalID=281&year=2010&vol=1&issue=4 http://www.inderscience.com/link.php?id=38216 This paper presents an autonomous intelligent agent developed for healthcare in geriatric residences. The paper focuses on the role of ambient intelligence in the automation of healthcare services. The work here presented shows the development of an autonomous agent, TaskCBP, which incorporates a model of human thinking, such as reasoning based on past experiences. The planning mechanism integrated within the agent has been implemented by means of a novel QSOR neural network. The system has been tested and this paper presents the results obtained. TaskCBP: an intelligent agent for task planning in elderly care
Juan F. De Paz, Yanira De Paz, Juan M. Corchado, Javier Bajo
International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 349 - 369
This paper presents an autonomous intelligent agent developed for healthcare in geriatric residences. The paper focuses on the role of ambient intelligence in the automation of healthcare services. The work here presented shows the development of an autonomous agent, TaskCBP, which incorporates a model of human thinking, such as reasoning based on past experiences. The planning mechanism integrated within the agent has been implemented by means of a novel QSOR neural network. The system has been tested and this paper presents the results obtained.

]]> 10.1504/IJCIBSB.2010.038216 International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 349 - 369 Juan F. De Paz Yanira De Paz Juan M. Corchado Javier Bajo Departamento Informatica y Automatica Universidad de Salamanca, Plaza de la Merced s/n, 37008, Salamanca, Spain. ' Departamento Informatica y Automatica Universidad de Salamanca, Plaza de la Merced s/n, 37008, Salamanca, Spain. ' Departamento Informatica y Automatica Universidad de Salamanca, Plaza de la Merced s/n, 37008, Salamanca, Spain. ' Departamento Informatica y Automatica Universidad de Salamanca, Plaza de la Merced s/n, 37008, Salamanca, Spain case-based planning CBP case-based reasoning CBR radio frequency identification RFID healthcare technology self-organising neural networks QSOR neural networks ambient intelligence location system multi-agent systems MAS agent-based systems intelligent agents geriatric residences residential care elderly care autonomous agents task planning. 2011-01-23T23:20:50-05:00 1 4 349 369 2011-01-23T23:20:50-05:00 http://www.inderscience.com/link.php?id=38217 SeqTrim is a pipeline designed to preprocessing sequence reads. It is easy to install and configure, flexible even if default parameters are accurate for most purposes and usable as a web interface or a standalone command line application. It identifies the sequence insert by removing low quality sequences, cloning vector, poly-A or poly-T tails, adaptors and any contaminant sequence or unwanted feature. Several input and output formats are available, which enables its inclusion in already or newly defined sequence processing work flows. It outperforms preprocessors implemented in other web servers and standalone applications at least in detecting adaptors and chimeric clones. SeqTrim is under continuous refinement to deal with most sequence events due to collaboration between biologists and computer scientists. SeqTrim07: a pipeline for preprocessing sequence reads
Juan Falgueras, Antonio J. Lara, Guillermo Perez-Trabado, Noe Fernandez-Pozo, Francisco R. Canton, M. Gonzalo Claros
International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 370 - 382
SeqTrim is a pipeline designed to preprocessing sequence reads. It is easy to install and configure, flexible even if default parameters are accurate for most purposes and usable as a web interface or a standalone command line application. It identifies the sequence insert by removing low quality sequences, cloning vector, poly-A or poly-T tails, adaptors and any contaminant sequence or unwanted feature. Several input and output formats are available, which enables its inclusion in already or newly defined sequence processing work flows. It outperforms preprocessors implemented in other web servers and standalone applications at least in detecting adaptors and chimeric clones. SeqTrim is under continuous refinement to deal with most sequence events due to collaboration between biologists and computer scientists.

]]> 10.1504/IJCIBSB.2010.038217 International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 370 - 382 Juan Falgueras Antonio J. Lara Guillermo Perez-Trabado Noe Fernandez-Pozo Francisco R. Canton M. Gonzalo Claros Dep. Lenguajes y Ciencias de la Computacion, Universidad de Malaga, 29071 Malaga, Spain. ' Centro de Supercomputacion y Bioinformatica, Universidad de Malaga, 29071 Malaga, Spain. ' Dep. Arquitectura de Computadores, Universidad de Malaga, 29071 Malaga, Spain. ' Dep. Biologia Molecular y Bioq., Universidad de Malaga, 29071 Malaga, Spain. ' Dep. Biologia Molecular y Bioq., Universidad de Malaga, 29071 Malaga, Spain. ' Dep. Biologia Molecular y Bioq., Universidad de Malaga, 29071 Malaga, Spain preprocessing sequence reads chromatograms assembly poly-A&#43 poly-T&#43 quality web interface command line workflow bioinformatics sequences sequencing adaptors chimeric clones. 2011-01-23T23:20:50-05:00 1 4 370 382 2011-01-23T23:20:50-05:00 http://www.inderscience.com/link.php?id=38219 This paper investigates the use of a dimensional reduction method, called cascaded non-linear components analysis (C-NLPCA), in the protein secondary structure prediction problem. C-NLPCA treats dimensional reductions considering the non-linearity of the data. In order to prove the effectiveness of the C-NLPCA, a set of tests are presented, comparing our approach with other existing predictors. The C-NLPCA is revealed to be efficient, propelling a new field of research. Dimensional reduction in the protein secondary structure prediction: non-linear method improvements
Gisele M. Simas, Silvia S.C. Botelho, Rafael G. Colares, Renan R. Almeida
International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 383 - 401
This paper investigates the use of a dimensional reduction method, called cascaded non-linear components analysis (C-NLPCA), in the protein secondary structure prediction problem. C-NLPCA treats dimensional reductions considering the non-linearity of the data. In order to prove the effectiveness of the C-NLPCA, a set of tests are presented, comparing our approach with other existing predictors. The C-NLPCA is revealed to be efficient, propelling a new field of research.

]]> 10.1504/IJCIBSB.2010.038219 International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 383 - 401 Gisele M. Simas Silvia S.C. Botelho Rafael G. Colares Renan R. Almeida Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil. ' Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil. ' Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil. ' Fundacao Universidade Federal do Rio Grande do Sul (FURG), Av. Italia Km 8 – 96.200-090 – Rio Grande – RS – Brazil cascaded nonlinear component analysis C-NLPCA nonlinear dimensional reduction protein secondary structure prediction neural networks ANNs bioinformatics. 2011-01-23T23:20:50-05:00 1 4 383 401 2011-01-23T23:20:50-05:00 http://www.inderscience.com/link.php?id=38222 Soft (fuzzy) clustering techniques are often used in the study of high-dimensional datasets, such as microarray and other high-throughput bioinformatics data. The most widely used method is the fuzzy C-means (FCM) algorithm, but it can present difficulties when dealing with some datasets. A fuzzy clustering algorithm, DifFUZZY, which utilises concepts from diffusion processes in graphs and is applicable to a larger class of clustering problems than other fuzzy clustering algorithms is developed. Examples of datasets (synthetic and real) for which this method outperforms other frequently used algorithms are presented, including two benchmark biological datasets, a genetic expression dataset and a dataset that contains taxonomic measurements. This method is better than traditional fuzzy clustering algorithms at handling datasets that are 'curved', elongated or those which contain clusters of different dispersion. The algorithm has been implemented in Matlab and C++ and is available at http://www.maths.ox.ac.uk/cmb/difFUZZY. DifFUZZY: a fuzzy clustering algorithm for complex datasets
Ornella Cominetti, Anastasios Matzavinos, Sandhya Samarasinghe, Don Kulasiri, Sijia Liu, Philip K. Maini, Radek Erban
International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 402 - 417
Soft (fuzzy) clustering techniques are often used in the study of high-dimensional datasets, such as microarray and other high-throughput bioinformatics data. The most widely used method is the fuzzy C-means (FCM) algorithm, but it can present difficulties when dealing with some datasets. A fuzzy clustering algorithm, DifFUZZY, which utilises concepts from diffusion processes in graphs and is applicable to a larger class of clustering problems than other fuzzy clustering algorithms is developed. Examples of datasets (synthetic and real) for which this method outperforms other frequently used algorithms are presented, including two benchmark biological datasets, a genetic expression dataset and a dataset that contains taxonomic measurements. This method is better than traditional fuzzy clustering algorithms at handling datasets that are 'curved', elongated or those which contain clusters of different dispersion. The algorithm has been implemented in Matlab and C++ and is available at http://www.maths.ox.ac.uk/cmb/difFUZZY.

]]> 10.1504/IJCIBSB.2010.038222 International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 402 - 417 Ornella Cominetti Anastasios Matzavinos Sandhya Samarasinghe Don Kulasiri Sijia Liu Philip K. Maini Radek Erban Centre for Mathematical Biology, Mathematical Institute, University of Oxford, 24-29 St. Giles', Oxford, OX1 3LB, UK. ' Department of Mathematics, Iowa State University, Ames, IA 50011, USA. ' Centre for Advanced Computational Solutions (C-fACS), Lincoln University, P.O. Box 84, Christchurch, New Zealand. ' Centre for Advanced Computational Solutions (C-fACS), Lincoln University, P.O. Box 84, Christchurch, New Zealand. ' Department of Mathematics, Iowa State University, Ames, IA 50011, USA. ' Centre for Mathematical Biology, Mathematical Institute, University of Oxford, 24-29 St. Giles', Oxford, OX1 3LB, UK; Oxford Centre for Integrative Systems Biology, Department of Biochemistry, University of Oxford, South Parks Road, Oxford, OX1 3QU, UK. ' Oxford Centre for Collaborative Applied Mathematics, Mathematical Institute, University of Oxford, 24-29 St. Giles', Oxford, OX1 3LB, UK clustering algorithms fuzzy clustering diffusion distance genetic expression data clustering complex datasets bioinformatics. 2011-01-23T23:20:50-05:00 1 4 402 417 2011-01-23T23:20:50-05:00 http://www.inderscience.com/link.php?id=38225 Classifier fusion techniques are gaining more popularity for their capability of improving the accuracy achieved by individual classifiers. A common approach is to combine the classifiers' outcome using simple methods, such as majority voting. In this paper, we build a meta-classifier by fusing some already well-known classifiers for protein structure prediction. Each individual classifier outputs a unique structure for every input residue. We have used the confusion matrix of each protein secondary structure classifier, which is representative of classifiers' expertness, as a general reusable pattern for converting its simple class-label assignment to class-preference score. The results obtained using several classifier fusion operators have been compared, on some standard datasets from the EVA server, with simple majority voting and with the results provided by the individual classifiers. The comparative analysis showed that the Choquet fuzzy integral operator had the highest improvement with respect to accuracy, multi-class sensitivity and specificity criteria over both the best performing individual classifier and the other fusion operators, while all of the classifier fusion techniques yielded some improvements too. Using classifier fusion techniques for protein secondary structure prediction
Majid Kazemian, Behzad Moshiri, Vasile Palade, Hamid Nikbakht, Caro Lucas
International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 418 - 434
Classifier fusion techniques are gaining more popularity for their capability of improving the accuracy achieved by individual classifiers. A common approach is to combine the classifiers' outcome using simple methods, such as majority voting. In this paper, we build a meta-classifier by fusing some already well-known classifiers for protein structure prediction. Each individual classifier outputs a unique structure for every input residue. We have used the confusion matrix of each protein secondary structure classifier, which is representative of classifiers' expertness, as a general reusable pattern for converting its simple class-label assignment to class-preference score. The results obtained using several classifier fusion operators have been compared, on some standard datasets from the EVA server, with simple majority voting and with the results provided by the individual classifiers. The comparative analysis showed that the Choquet fuzzy integral operator had the highest improvement with respect to accuracy, multi-class sensitivity and specificity criteria over both the best performing individual classifier and the other fusion operators, while all of the classifier fusion techniques yielded some improvements too.

]]> 10.1504/IJCIBSB.2010.038225 International Journal of Computational Intelligence in Bioinformatics and Systems Biology, Vol. 1, No. 4 (2010) pp. 418 - 434 Majid Kazemian Behzad Moshiri Vasile Palade Hamid Nikbakht Caro Lucas Control and Intelligent Processing Center, School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran. ' Control and Intelligent Processing Center, School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran. ' Computing Laboratory, Oxford University, Parks Road, Oxford, OX1 3QD, UK. ' Laboratory of Biophysics and Molecular Biology, Institute of Biochemistry and Biophysics, University of Tehran, Tehran, Iran. ' Control and Intelligent Processing Center, School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran protein secondary structure prediction classifier fusion Choquet fuzzy integral operator metaclassifiers confusion matrix multi-class sensitivity protein structure bioinformatics. 2011-01-23T23:20:50-05:00 1 4 418 434 2011-01-23T23:20:50-05:00