Byoungtak Zhang - Academia.edu (original) (raw)

Papers by Byoungtak Zhang

Integrated Computer-Aided Engineering, 2002

Evolutionary algorithms have been successfully applied to the design and training of neural netwo... more Evolutionary algorithms have been successfully applied to the design and training of neural networks, such as in optimization of network architecture, learning connection weights, and selecting training data. While most of existing evolutionary methods are focused on one of these aspects, we present in this paper an integrated approach that employs evolutionary mechanisms for the optimization of these components simultaneously. This approach is especially effective when evolving irregular, notstrictly-layered networks of heterogeneous neurons with variable receptive fields. The core of our method is the neural tree representation scheme combined with the Bayesian evolutionary learning framework. The generality and flexibility of neural trees make it easy to express and modify complex neural architectures by means of standard crossover and mutation operators. The Bayesian evolutionary framework provides a theoretical foundation for finding compact neural networks using a small data set by principled exploitation of background knowledge available in the problem domain. Performance of the presented method is demonstrated on a suite of benchmark problems and compared with those of related methods.

Genetic Programming and Evolvable Machines, Jul 1, 2000

A Bayesian framework for genetic programming GP is presented. This is motivated by the observatio... more A Bayesian framework for genetic programming GP is presented. This is motivated by the observation that genetic programming iteratively searches populations of fitter programs and thus the information gained in the previous generation can be used in the next generation. The Bayesian GP makes use of Bayes theorem to estimate the posterior distribution of programs from their prior distribution and likelihood for the fitness data observed. Offspring programs are then generated by sampling from the posterior distribution by genetic variation operators. We present two GP algorithms derived from the Bayesian GP framework. One is the genetic programming with the adaptive Occam's Ž. razor AOR designed to evolve parsimonious programs. The other is the genetic programming with Ž. incremental data inheritance IDI designed to accelerate evolution by active selection of fitness cases. A multiagent learning task is used to demonstrate the effectiveness of the presented methods. In a series of experiments, AOR reduced solution complexity by 20% and IDI doubled evolution speed, both without loss of solution accuracy.

Applied Intelligence, May 1, 2003

Web-documents have a number of tags indicating the structure of texts. Text segments marked by HT... more Web-documents have a number of tags indicating the structure of texts. Text segments marked by HTML tags have specific meaning which can be utilized to improve the performance of document retrieval systems. In this paper, we present a machine learning approach to mine the structure of HTML documents for effective Webdocument retrieval. A genetic algorithm is described that learns the importance factors of HTML tags which are used to re-rank the documents retrieved by standard weighting schemes. The proposed method has been evaluated on artificial text sets and a large-scale TREC document collection. Experimental evidence supports that the tag weights are well trained by the proposed algorithm in accordance with the importance factors for retrieval, and indicates that the proposed approach significantly improves the performance in retrieval accuracy. In particular, the use of the document-structure mining approach tends to move relevant documents to upper ranks, which is especially important in interactive Web-information retrieval environments.

Machine Learning, Jul 1, 2003

Lecture Notes in Computer Science, 2004

DNA microarrays are widely used techniques in molecular biology and DNA computing area. It consis... more DNA microarrays are widely used techniques in molecular biology and DNA computing area. It consists of the DNA sequences called probes, which are DNA complementaries to the genes of interest, on solid surfaces. And its reliability seriously depends on the quality of the probe sequences. Therefore, one must carefully choose the probe sets in target sequences. In this paper, the probe design for DNA microarrays is formulated as the multi-objective optimization problem. We propose a multi-objective evolutionary approach, which is known to be suitable for this kind of optimization problem. Since a multi-objective evolutionary algorithm can find multiple solutions at a time, we used thermodynamic criteria to choose the most suitable one. For the experiments, the probe set generated by the proposed method is compared to the sequences used in commercial microarrays, which detects a set of Human Papillomavirus (HPV). The comparison result supports that our approach can be useful to optimize probe sequences.

Lecture Notes in Computer Science, 2004

MicroRNA (miRNA), one of non-coding RNAs (ncRNAs), regulates gene expression directly by arrestin... more MicroRNA (miRNA), one of non-coding RNAs (ncRNAs), regulates gene expression directly by arresting the messenger RNA (mRNA) translation, which is important for identifying putative miRNAs. In this study, we suggest a searching procedure for human miRNA precursors using genetic programming that automatically learn common structures of miRNAs from a set of known miRNA precursors. Our method consists of three-steps. At first, for each miRNA precursor, we adopted genetic programming techniques to optimize the RNA Common-Structural Grammar (RCSG) of populations until certain fitness is achieved. In this step, the specificity and the sensitivity of a RCSG for the training data set were used as the fitness criteria. Next, for each optimized RCSG, we collected candidates of matching miRNA precursors with the corresponding grammar from genome databases. Finally, we selected miRNA precursors over a threshold (=365) of scoring model from the candidates. This step would reduce false positives in the candidates. To validate the effectiveness of our miRNA method, we evaluated the learned RCSG and the scoring model with test data. Here, we obtained satisfactory results, with high specificity (= 51/64) and proper sensitivity (= 51/82) using human miRNA precursors as a test data set.

IEEE Transactions on Affective Computing, 2015

Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, 2000

Several machine learning algorithms have recently been used for text categorization and filtering... more Several machine learning algorithms have recently been used for text categorization and filtering. In particular, boosting methods such as AdaBoost have shown good performance applied to real text data. However, most of existing boosting algorithms are based on classifiers that use binary-valued features. Thus, they do not fully make use of the weight information provided by standard term weighting methods. In this paper, we present a boosting-based learning method for text filtering that uses naive Bayes classifiers as a weak learner. The use of naive Bayes allows the boosting algorithm to utilize term frequency information while maintaining probabilisti-caUy accurate confidence ratio. Applied to TREC-7 and TREC-8 filtering track documents, the proposed method obtained a significant improvement in LF1, LF2, F1 and F3 measures compared to the best results submitted by other TREC entries. Permlsmon to make digital or hard copies of all or part of this work for personal or classroom use is granted wlthotJt fee provided that copies are not made or distributed for profit or commercial advantage and that copras bear this notice and the full citation on the first page. To Copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.

The 2003 Congress on Evolutionary Computation, 2003. CEC '03.

We propose the concept of molecular immunocomputing which is a kind of peptide computing. Molecul... more We propose the concept of molecular immunocomputing which is a kind of peptide computing. Molecular immunocomputing is basically implemented by direct antigen-antibody biomolecular recognition on the basis of Fab fragments diversity. In this paper, we consider how molecular immunocomputing can tell the alphabet "O" from the characters "A" and "B" similar to the characterization of ABO blood type. To implement molecular immunocomputing, the two-dimensional figures are coded on the one-dimensional DNA strings. The informations coded on the virtual DNA strings are transcribed to virtual RNA sequences, and then translated to the polypeptide sequences. The resulting peptide sequences are artificially synthesized and coupled to the carrier proteins. The resulting conjugate proteins are injected as input antigens to immunize the experimental animals. After immunization, we could purify the corresponding antibodies. These antibodies can be arrayed onto the protein microarray chips. The recent developments in the field of protein microarrays show the feasibility of molecular immunocomputing.

Natural Computing Series, 2003

A probabilistic evolutionary framework is presented and shown to be applicable to both learning a... more A probabilistic evolutionary framework is presented and shown to be applicable to both learning and optimization problems. In this framework, evolutionary computation is viewed as Bayesian inference that iteratively updates the posterior distribution of a population from the prior knowledge and observation of new individuals to find an individual with the maximum posterior probability. Theoretical foundations of Bayesian evolutionary computation are given and its generality is demonstrated by showing specific Bayesian evolutionary algorithms for learning and optimization. We also discuss how the probabilistic framework can be used to develop novel evolutionary algorithms that embed evolutionary learning for evolutionary optimization and vice versa.

Lecture Notes in Computer Science, 2006

We introduce a class of generalized DNF formulae called wDNF or weighted disjunctive normal form,... more We introduce a class of generalized DNF formulae called wDNF or weighted disjunctive normal form, and present a molecular algorithm that learns a wDNF formula from training examples. Realized in DNA molecules, the wDNF machines have a natural probabilistic semantics, allowing for their application beyond the pure Boolean logical structure of the standard DNF to real-life problems with uncertainty. The potential of the molecular wDNF machines is evaluated on real-life genomics data in simulation. Our empirical results suggest the possibility of building error-resilient molecular computers that are able to learn from data, potentially from wet DNA data.

Proceedings of the 7th annual conference on Genetic and evolutionary computation, 2005

BioChip Journal, 2013

Molecular computing using programmable nucleic acids has been attracting attention for use in aut... more Molecular computing using programmable nucleic acids has been attracting attention for use in autonomous sensing systems and information processing systems by interacting with a biological environment. Here, we introduce a rule-based in vitro molecular classification system that can classify disease patterns using several microRNA (miRNA) markers via the assembly of programmed DNA strands. The classification rules were derived by analyzing large-scale miRNA expression data obtained from a public database, and the identified rules were converted into DNA sequences. Classification was performed via the detection of miRNA markers in the rules. The classification results were reported as a binary output pattern according to their hybridization to the rule sequences, which can be conveniently visualized using gold nanoparticle aggregation. Our results demonstrate the utility of in vitro molecular classification by illustrating one of the ways in which molecular computing can be used in future biological and medical applications.

PeerJ, 2013

MicroRNAs (miRNAs) are small regulatory molecules that repress the translational processes of the... more MicroRNAs (miRNAs) are small regulatory molecules that repress the translational processes of their target genes by binding to their 3' untranslated regions (3' UTRs). Because the target genes are predominantly determined by their sequence complementarity to the miRNA seed regions (nucleotides 2-7) which are evolutionarily conserved, it is inferred that the target relationships and functions of the miRNA family members are conserved across many species. Therefore, detecting the relevant miRNA families with confidence would help to clarify the conserved miRNA functions, and elucidate miRNA-mediated biological processes. We present a mixture model of position weight matrices for constructing miRNA functional families. This model systematically finds not only evolutionarily conserved miRNA family members but also functionally related miRNAs, as it simultaneously generates position weight matrices representing the conserved sequences. Using mammalian miRNA sequences, in our expe...

2012 IEEE Congress on Evolutionary Computation, 2012

We describe a novel learning scheme for hidden dependencies in video streams. The proposed scheme... more We describe a novel learning scheme for hidden dependencies in video streams. The proposed scheme aims to transform a given sequential stream into a dependency structure of particle populations. Each particle population summarizes an associated segment. The novel point of the proposed scheme is that both of dependency learning and segment summarization are performed in an unsupervised online manner without assuming priors. The proposed scheme is executed in two-stage learning. At the first stage, a segment corresponding to a common dominant image is estimated using evolutionary particle filtering. Each dominant image is depicted based on combinations of image descriptors. Prevailing features of a dominant image are selected through evolution. Genetic operators introduce the essential diversity preventing sample impoverishment. At the second stage, transitional probability between the estimated segments is computed and stored. The proposed scheme is applied to extract dependencies in an episode of a TV drama. We demonstrate performance by comparing to human estimations.

Lecture Notes in Computer Science, 2010

This document will continue to evolve as the IR expands. Additional guidelines will be drafted, a... more This document will continue to evolve as the IR expands. Additional guidelines will be drafted, as needed, over the coming months.

2009 IEEE International Conference on Bioinformatics and Biomedicine, 2009

The imbalanced data problem is popular in biomedical classification tasks. Since trained classifi... more The imbalanced data problem is popular in biomedical classification tasks. Since trained classifiers using imbalanced data are mostly derived from the majority class, their prediction performance is poor for the minority class. In this paper, we propose a novel ensemble learning method based on an active example selection algorithm to resolve the imbalanced data problem. To compensate a possible sub-optimal classifier, our proposed ensemble learning methods aggregates classifiers built by the active example selection algorithm. We implement this ensemble learning method based on the active example selection algorithm using incremental naïve Bayes classifiers. Our empirical results show that we greatly improve the performance of classification models trained by five real world imbalanced biomedical data. The proposed ensemble learning methods outperforms other approaches by 0.03~0.15 in terms of AUC which solve imbalanced data problem.

Lecture Notes in Computer Science, 2013

Sum-product networks (SPNs) are deep architectures that can learn and infer at low computational ... more Sum-product networks (SPNs) are deep architectures that can learn and infer at low computational costs. The structure of SPNs is especially important for their performance; however, structure learning for SPNs has until now been introduced only for batch-type dataset. In this study, we propose a new online incremental structure learning method for SPNs. We note that SPNs can be represented by mixtures of basis distributions. Online learning of SPNs can be formulated as an online clustering problem, in which a local assigning instance corresponds to modifying the tree-structure of the SPN incrementally. In the method, the number of hidden units and even layers are evolved dynamically on incoming data. The experimental results show that the proposed method outperforms the online version of the previous method. In addition, it achieves the performance of batch structure learning.

2006 IEEE International Conference on Evolutionary Computation

The use of synthetic DNA molecules for computing provides various insights to evolutionary comput... more The use of synthetic DNA molecules for computing provides various insights to evolutionary computation. A molecular computing algorithm to evolve DNA-encoded genetic patterns has been previously reported in [1], [2]. Here we improve on the previous work by studying the convergence behavior of the molecular evolutionary algorithm in the context of text classification problems. In particular, we study the error reduction behavior of the evolutionary learning algorithm, both theoretically and experimentally. The individuals represent decision lists of variable length and the whole population takes part in making probabilistic decisions. The evolutionary process is to change each individual towards correct classification of training data, which is based on an error minimization strategy. The evolved molecular classifiers show a performance competitive to the standard algorithms such as naïve Bayes and neural network classifiers on the data set we studied. The possibility of molecular implementation by use of DNA-encoded individuals combined with simple molecular operations on a very big population distinguishes this approach from other existing evolutionary algorithms.

Natural Computing, 2004

Simulators for biomolecular computing, (both in vitro and in silico), have come to play an import... more Simulators for biomolecular computing, (both in vitro and in silico), have come to play an important role in experimentation, analysis, and evaluation of the efficiency and scalability of DNA and biomolecule based computing. Simulation in silico of DNA computing is useful to support DNA-computing algorithm design and to reduce the cost and effort of lab experiments. Although many simulations have now been developed, there exists no standard for simulation software in this area. Reliability, performance benchmarks, user interfaces, and accessibility are arguably the most important criteria for development and wide spread use of simulation software for BMC. The requirements and evaluation of such software packages for DNA computing software are discussed, particularly questions about software development, appropriate user environments, standardization of benchmark data sets, and centrally available common repositories for software and/or data.

Integrated Computer-Aided Engineering, 2002

Evolutionary algorithms have been successfully applied to the design and training of neural netwo... more Evolutionary algorithms have been successfully applied to the design and training of neural networks, such as in optimization of network architecture, learning connection weights, and selecting training data. While most of existing evolutionary methods are focused on one of these aspects, we present in this paper an integrated approach that employs evolutionary mechanisms for the optimization of these components simultaneously. This approach is especially effective when evolving irregular, notstrictly-layered networks of heterogeneous neurons with variable receptive fields. The core of our method is the neural tree representation scheme combined with the Bayesian evolutionary learning framework. The generality and flexibility of neural trees make it easy to express and modify complex neural architectures by means of standard crossover and mutation operators. The Bayesian evolutionary framework provides a theoretical foundation for finding compact neural networks using a small data set by principled exploitation of background knowledge available in the problem domain. Performance of the presented method is demonstrated on a suite of benchmark problems and compared with those of related methods.

Genetic Programming and Evolvable Machines, Jul 1, 2000

A Bayesian framework for genetic programming GP is presented. This is motivated by the observatio... more A Bayesian framework for genetic programming GP is presented. This is motivated by the observation that genetic programming iteratively searches populations of fitter programs and thus the information gained in the previous generation can be used in the next generation. The Bayesian GP makes use of Bayes theorem to estimate the posterior distribution of programs from their prior distribution and likelihood for the fitness data observed. Offspring programs are then generated by sampling from the posterior distribution by genetic variation operators. We present two GP algorithms derived from the Bayesian GP framework. One is the genetic programming with the adaptive Occam's Ž. razor AOR designed to evolve parsimonious programs. The other is the genetic programming with Ž. incremental data inheritance IDI designed to accelerate evolution by active selection of fitness cases. A multiagent learning task is used to demonstrate the effectiveness of the presented methods. In a series of experiments, AOR reduced solution complexity by 20% and IDI doubled evolution speed, both without loss of solution accuracy.

Applied Intelligence, May 1, 2003

Web-documents have a number of tags indicating the structure of texts. Text segments marked by HT... more Web-documents have a number of tags indicating the structure of texts. Text segments marked by HTML tags have specific meaning which can be utilized to improve the performance of document retrieval systems. In this paper, we present a machine learning approach to mine the structure of HTML documents for effective Webdocument retrieval. A genetic algorithm is described that learns the importance factors of HTML tags which are used to re-rank the documents retrieved by standard weighting schemes. The proposed method has been evaluated on artificial text sets and a large-scale TREC document collection. Experimental evidence supports that the tag weights are well trained by the proposed algorithm in accordance with the importance factors for retrieval, and indicates that the proposed approach significantly improves the performance in retrieval accuracy. In particular, the use of the document-structure mining approach tends to move relevant documents to upper ranks, which is especially important in interactive Web-information retrieval environments.

Machine Learning, Jul 1, 2003

Lecture Notes in Computer Science, 2004

DNA microarrays are widely used techniques in molecular biology and DNA computing area. It consis... more DNA microarrays are widely used techniques in molecular biology and DNA computing area. It consists of the DNA sequences called probes, which are DNA complementaries to the genes of interest, on solid surfaces. And its reliability seriously depends on the quality of the probe sequences. Therefore, one must carefully choose the probe sets in target sequences. In this paper, the probe design for DNA microarrays is formulated as the multi-objective optimization problem. We propose a multi-objective evolutionary approach, which is known to be suitable for this kind of optimization problem. Since a multi-objective evolutionary algorithm can find multiple solutions at a time, we used thermodynamic criteria to choose the most suitable one. For the experiments, the probe set generated by the proposed method is compared to the sequences used in commercial microarrays, which detects a set of Human Papillomavirus (HPV). The comparison result supports that our approach can be useful to optimize probe sequences.

Lecture Notes in Computer Science, 2004

MicroRNA (miRNA), one of non-coding RNAs (ncRNAs), regulates gene expression directly by arrestin... more MicroRNA (miRNA), one of non-coding RNAs (ncRNAs), regulates gene expression directly by arresting the messenger RNA (mRNA) translation, which is important for identifying putative miRNAs. In this study, we suggest a searching procedure for human miRNA precursors using genetic programming that automatically learn common structures of miRNAs from a set of known miRNA precursors. Our method consists of three-steps. At first, for each miRNA precursor, we adopted genetic programming techniques to optimize the RNA Common-Structural Grammar (RCSG) of populations until certain fitness is achieved. In this step, the specificity and the sensitivity of a RCSG for the training data set were used as the fitness criteria. Next, for each optimized RCSG, we collected candidates of matching miRNA precursors with the corresponding grammar from genome databases. Finally, we selected miRNA precursors over a threshold (=365) of scoring model from the candidates. This step would reduce false positives in the candidates. To validate the effectiveness of our miRNA method, we evaluated the learned RCSG and the scoring model with test data. Here, we obtained satisfactory results, with high specificity (= 51/64) and proper sensitivity (= 51/82) using human miRNA precursors as a test data set.

IEEE Transactions on Affective Computing, 2015

Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, 2000

Several machine learning algorithms have recently been used for text categorization and filtering... more Several machine learning algorithms have recently been used for text categorization and filtering. In particular, boosting methods such as AdaBoost have shown good performance applied to real text data. However, most of existing boosting algorithms are based on classifiers that use binary-valued features. Thus, they do not fully make use of the weight information provided by standard term weighting methods. In this paper, we present a boosting-based learning method for text filtering that uses naive Bayes classifiers as a weak learner. The use of naive Bayes allows the boosting algorithm to utilize term frequency information while maintaining probabilisti-caUy accurate confidence ratio. Applied to TREC-7 and TREC-8 filtering track documents, the proposed method obtained a significant improvement in LF1, LF2, F1 and F3 measures compared to the best results submitted by other TREC entries. Permlsmon to make digital or hard copies of all or part of this work for personal or classroom use is granted wlthotJt fee provided that copies are not made or distributed for profit or commercial advantage and that copras bear this notice and the full citation on the first page. To Copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.

The 2003 Congress on Evolutionary Computation, 2003. CEC '03.

We propose the concept of molecular immunocomputing which is a kind of peptide computing. Molecul... more We propose the concept of molecular immunocomputing which is a kind of peptide computing. Molecular immunocomputing is basically implemented by direct antigen-antibody biomolecular recognition on the basis of Fab fragments diversity. In this paper, we consider how molecular immunocomputing can tell the alphabet "O" from the characters "A" and "B" similar to the characterization of ABO blood type. To implement molecular immunocomputing, the two-dimensional figures are coded on the one-dimensional DNA strings. The informations coded on the virtual DNA strings are transcribed to virtual RNA sequences, and then translated to the polypeptide sequences. The resulting peptide sequences are artificially synthesized and coupled to the carrier proteins. The resulting conjugate proteins are injected as input antigens to immunize the experimental animals. After immunization, we could purify the corresponding antibodies. These antibodies can be arrayed onto the protein microarray chips. The recent developments in the field of protein microarrays show the feasibility of molecular immunocomputing.

Natural Computing Series, 2003

A probabilistic evolutionary framework is presented and shown to be applicable to both learning a... more A probabilistic evolutionary framework is presented and shown to be applicable to both learning and optimization problems. In this framework, evolutionary computation is viewed as Bayesian inference that iteratively updates the posterior distribution of a population from the prior knowledge and observation of new individuals to find an individual with the maximum posterior probability. Theoretical foundations of Bayesian evolutionary computation are given and its generality is demonstrated by showing specific Bayesian evolutionary algorithms for learning and optimization. We also discuss how the probabilistic framework can be used to develop novel evolutionary algorithms that embed evolutionary learning for evolutionary optimization and vice versa.

Lecture Notes in Computer Science, 2006

We introduce a class of generalized DNF formulae called wDNF or weighted disjunctive normal form,... more We introduce a class of generalized DNF formulae called wDNF or weighted disjunctive normal form, and present a molecular algorithm that learns a wDNF formula from training examples. Realized in DNA molecules, the wDNF machines have a natural probabilistic semantics, allowing for their application beyond the pure Boolean logical structure of the standard DNF to real-life problems with uncertainty. The potential of the molecular wDNF machines is evaluated on real-life genomics data in simulation. Our empirical results suggest the possibility of building error-resilient molecular computers that are able to learn from data, potentially from wet DNA data.

Proceedings of the 7th annual conference on Genetic and evolutionary computation, 2005

BioChip Journal, 2013

Molecular computing using programmable nucleic acids has been attracting attention for use in aut... more Molecular computing using programmable nucleic acids has been attracting attention for use in autonomous sensing systems and information processing systems by interacting with a biological environment. Here, we introduce a rule-based in vitro molecular classification system that can classify disease patterns using several microRNA (miRNA) markers via the assembly of programmed DNA strands. The classification rules were derived by analyzing large-scale miRNA expression data obtained from a public database, and the identified rules were converted into DNA sequences. Classification was performed via the detection of miRNA markers in the rules. The classification results were reported as a binary output pattern according to their hybridization to the rule sequences, which can be conveniently visualized using gold nanoparticle aggregation. Our results demonstrate the utility of in vitro molecular classification by illustrating one of the ways in which molecular computing can be used in future biological and medical applications.

PeerJ, 2013

MicroRNAs (miRNAs) are small regulatory molecules that repress the translational processes of the... more MicroRNAs (miRNAs) are small regulatory molecules that repress the translational processes of their target genes by binding to their 3' untranslated regions (3' UTRs). Because the target genes are predominantly determined by their sequence complementarity to the miRNA seed regions (nucleotides 2-7) which are evolutionarily conserved, it is inferred that the target relationships and functions of the miRNA family members are conserved across many species. Therefore, detecting the relevant miRNA families with confidence would help to clarify the conserved miRNA functions, and elucidate miRNA-mediated biological processes. We present a mixture model of position weight matrices for constructing miRNA functional families. This model systematically finds not only evolutionarily conserved miRNA family members but also functionally related miRNAs, as it simultaneously generates position weight matrices representing the conserved sequences. Using mammalian miRNA sequences, in our expe...

2012 IEEE Congress on Evolutionary Computation, 2012

We describe a novel learning scheme for hidden dependencies in video streams. The proposed scheme... more We describe a novel learning scheme for hidden dependencies in video streams. The proposed scheme aims to transform a given sequential stream into a dependency structure of particle populations. Each particle population summarizes an associated segment. The novel point of the proposed scheme is that both of dependency learning and segment summarization are performed in an unsupervised online manner without assuming priors. The proposed scheme is executed in two-stage learning. At the first stage, a segment corresponding to a common dominant image is estimated using evolutionary particle filtering. Each dominant image is depicted based on combinations of image descriptors. Prevailing features of a dominant image are selected through evolution. Genetic operators introduce the essential diversity preventing sample impoverishment. At the second stage, transitional probability between the estimated segments is computed and stored. The proposed scheme is applied to extract dependencies in an episode of a TV drama. We demonstrate performance by comparing to human estimations.

Lecture Notes in Computer Science, 2010

This document will continue to evolve as the IR expands. Additional guidelines will be drafted, a... more This document will continue to evolve as the IR expands. Additional guidelines will be drafted, as needed, over the coming months.

2009 IEEE International Conference on Bioinformatics and Biomedicine, 2009

The imbalanced data problem is popular in biomedical classification tasks. Since trained classifi... more The imbalanced data problem is popular in biomedical classification tasks. Since trained classifiers using imbalanced data are mostly derived from the majority class, their prediction performance is poor for the minority class. In this paper, we propose a novel ensemble learning method based on an active example selection algorithm to resolve the imbalanced data problem. To compensate a possible sub-optimal classifier, our proposed ensemble learning methods aggregates classifiers built by the active example selection algorithm. We implement this ensemble learning method based on the active example selection algorithm using incremental naïve Bayes classifiers. Our empirical results show that we greatly improve the performance of classification models trained by five real world imbalanced biomedical data. The proposed ensemble learning methods outperforms other approaches by 0.03~0.15 in terms of AUC which solve imbalanced data problem.

Lecture Notes in Computer Science, 2013

Sum-product networks (SPNs) are deep architectures that can learn and infer at low computational ... more Sum-product networks (SPNs) are deep architectures that can learn and infer at low computational costs. The structure of SPNs is especially important for their performance; however, structure learning for SPNs has until now been introduced only for batch-type dataset. In this study, we propose a new online incremental structure learning method for SPNs. We note that SPNs can be represented by mixtures of basis distributions. Online learning of SPNs can be formulated as an online clustering problem, in which a local assigning instance corresponds to modifying the tree-structure of the SPN incrementally. In the method, the number of hidden units and even layers are evolved dynamically on incoming data. The experimental results show that the proposed method outperforms the online version of the previous method. In addition, it achieves the performance of batch structure learning.

2006 IEEE International Conference on Evolutionary Computation

The use of synthetic DNA molecules for computing provides various insights to evolutionary comput... more The use of synthetic DNA molecules for computing provides various insights to evolutionary computation. A molecular computing algorithm to evolve DNA-encoded genetic patterns has been previously reported in [1], [2]. Here we improve on the previous work by studying the convergence behavior of the molecular evolutionary algorithm in the context of text classification problems. In particular, we study the error reduction behavior of the evolutionary learning algorithm, both theoretically and experimentally. The individuals represent decision lists of variable length and the whole population takes part in making probabilistic decisions. The evolutionary process is to change each individual towards correct classification of training data, which is based on an error minimization strategy. The evolved molecular classifiers show a performance competitive to the standard algorithms such as naïve Bayes and neural network classifiers on the data set we studied. The possibility of molecular implementation by use of DNA-encoded individuals combined with simple molecular operations on a very big population distinguishes this approach from other existing evolutionary algorithms.

Natural Computing, 2004

Simulators for biomolecular computing, (both in vitro and in silico), have come to play an import... more Simulators for biomolecular computing, (both in vitro and in silico), have come to play an important role in experimentation, analysis, and evaluation of the efficiency and scalability of DNA and biomolecule based computing. Simulation in silico of DNA computing is useful to support DNA-computing algorithm design and to reduce the cost and effort of lab experiments. Although many simulations have now been developed, there exists no standard for simulation software in this area. Reliability, performance benchmarks, user interfaces, and accessibility are arguably the most important criteria for development and wide spread use of simulation software for BMC. The requirements and evaluation of such software packages for DNA computing software are discussed, particularly questions about software development, appropriate user environments, standardization of benchmark data sets, and centrally available common repositories for software and/or data.