Search

Motivation: Many enzymes are not absolutely specific, or even promiscuous: they can catalyze transformations of more compounds than the traditional ones as listed in e.g. KEGG. This information is currently only available in databases, such as the BRENDA enzyme activity database. In this paper, we propose to model enzyme aspecificity by predicting whether an input compound is likely to be transformed by a certain enzyme. Such a predictor has many applications, for example to complete reconstructed metabolic networks, to aid in metabolic engineering or to help identify unknown peaks in mass spectra. Results: We have developed a system for metabolite and reaction inference based on enzyme specificities (MaRIboES). It employs structural and stereochemistry similarity measures and molecular fingerprints to generalise enzymatic reactions based on data available in BRENDA. Leave-one-out cross-validation shows that 80% of known reactions are predicted well. Application to the yeast glycolytic and pentose phosphate pathways predicts a large number of known and new reactions, often leading to the formation of novel compounds, as well as a number of interesting bypasses and cross-links., Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Background: Large discrepancies in signature composition and outcome concordance have been observed between different microarray breast cancer expression profiling studies. This is often ascribed to differences in array platform as well as biological variability. We conjecture that other reasons for the observed discrepancies are the measurement error associated with each feature and the choice of preprocessing method. Microarray data are known to be subject to technical variation and the confidence intervals around individual point estimates of expression levels can be wide. Furthermore, the estimated expression values also vary depending on the selected preprocessing scheme. In microarray breast cancer classification studies, however, these two forms of feature variability are almost always ignored and hence their exact role is unclear. Results: We have performed a comprehensive sensitivity analysis of microarray breast cancer classification under the two types of feature variability mentioned above. We used data from six state of the art preprocessing methods, using a compendium consisting of eight diferent datasets, involving 1131 hybridizations, containing data from both one and two-color array technology. For a wide range of classifiers, we performed a joint study on performance, concordance and stability. In the stability analysis we explicitly tested classifiers for their noise tolerance by using perturbed expression profiles that are based on uncertainty information directly related to the preprocessing methods. Our results indicate that signature composition is strongly influenced by feature variability, even if the array platform and the stratification of patient samples are identical. In addition, we show that there is often a high level of discordance between individual class assignments for signatures constructed on data coming from different preprocessing schemes, even if the actual signature composition is identical. Conclusion: Feature variability c, Mediamatics, Electrical Engineering, Mathematics and Computer Science

Current automatic sign language recognition (ASLR) seldom uses perceptual knowledge about the recognition of sign language. Using such knowledge can improve ASLR because it can give an indication which elements or phases of a sign are important for its meaning. Also, the current generation of data-driven ASLR methods has shortcomings which may not be solvable without the use of knowledge on human sign language processing. Handling variation in the precise execution of signs is an example of such shortcomings: data-driven methods (which include almost all current methods) have difficulty recognizing signs that deviate too much from the examples that were used to train the method. Insight into human sign processing is needed to solve these problems. Perceptual research on sign language can provide such insights. This paper discusses knowledge derived from a set of sign perception experiments, and the application of such knowledge in ASLR. Among the findings are the facts that not all phases and elements of a sign are equally informative, that defining the ‘correct’ form for a sign is not trivial, and that statistical ASLR methods do not necessarily arrive at sign representations that resemble those of human beings. Apparently, current ASLR methods are quite different from human observers: their method of learning gives them different sign definitions, they regard each moment and element of a sign as equally important and they employ a single definition of ‘correct’ for all circumstances. If the object is for an ASLR method to handle natural sign language, then the insights from sign perception research must be integrated into ASLR., Human Information Communication Design, Industrial Design Engineering

Electrical Engineering, Mathematics and Computer Science

Pattern Recognition and Bioinformatics

In recent work, attempts have been made to link the structure of biochemical networks to their complex dynamics. It was shown that structurally stable network motifs are enriched in such networks. In this work, we investigate to what extent these findings apply to metabolic networks. To this end, we extend a previously proposed method by changing the null model for determining motif enrichment, by using interaction types directly obtained from structural interaction matrices, by generating a distribution of partial derivatives of reaction rates and by simulating enzymatic regulation on metabolic networks. Our findings suggest that the conclusions drawn in previous work cannot be extended to metabolic networks, that is, structurally stable network motifs are not enriched in metabolic networks., Mediamatics, Electrical Engineering, Mathematics and Computer Science

OA Fund TU delft Background: Microorganisms adapt their transcriptome by integrating multiple chemical and physical signals from their environment. Shake-flask cultivation does not allow precise manipulation of individual culture parameters and therefore precludes a quantitative analysis of the (combinatorial) influence of these parameters on transcriptional regulation. Steady-state chemostat cultures, which do enable accurate control, measurement and manipulation of individual cultivation parameters (e.g. specific growth rate, temperature, identity of the growth-limiting nutrient) appear to provide a promising experimental platform for such a combinatorial analysis. Results: A microarray compendium of 170 steady-state chemostat cultures of the yeast Saccharomyces cerevisiae is presented and analyzed. The 170 microarrays encompass 55 unique conditions, which can be characterized by the combined settings of 10 different cultivation parameters. By applying a regression model to assess the impact of (combinations of) cultivation parameters on the transcriptome, most S. cerevisiae genes were shown to be influenced by multiple cultivation parameters, and in many cases by combinatorial effects of cultivation parameters. The inclusion of these combinatorial effects in the regression model led to higher explained variance of the gene expression patterns and resulted in higher function enrichment in subsequent analysis. We further demonstrate the usefulness of the compendium and regression analysis for interpretation of shake-flask-based transcriptome studies and for guiding functional analysis of (uncharacterized) genes and pathways. Conclusion: Modeling the combinatorial effects of environmental parameters on the transcriptome is crucial for understanding transcriptional regulation. Chemostat cultivation offers a powerful tool for such an approach., Mediamatics, Electrical Engineering, Mathematics and Computer Science

Motivation: Many enzymes are not absolutely specific, or even promiscuous: they can catalyze transformations of more compounds than the traditional ones as listed in e.g. KEGG. This information is currently only available in databases, such as the BRENDA enzyme activity database. In this paper, we propose to model enzyme aspecificity by predicting whether an input compound is likely to be transformed by a certain enzyme. Such a predictor has many applications, for example to complete reconstructed metabolic networks, to aid in metabolic engineering or to help identify unknown peaks in mass spectra. Results: We have developed a system for metabolite and reaction inference based on enzyme specificities (MaRIboES). It employs structural and stereochemistry similarity measures and molecular fingerprints to generalise enzymatic reactions based on data available in BRENDA. Leave-one-out cross-validation shows that 80% of known reactions are predicted well. Application to the yeast glycolytic and pentose phosphate pathways predicts a large number of known and new reactions, often leading to the formation of novel compounds, as well as a number of interesting bypasses and cross-links., Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Background: Large discrepancies in signature composition and outcome concordance have been observed between different microarray breast cancer expression profiling studies. This is often ascribed to differences in array platform as well as biological variability. We conjecture that other reasons for the observed discrepancies are the measurement error associated with each feature and the choice of preprocessing method. Microarray data are known to be subject to technical variation and the confidence intervals around individual point estimates of expression levels can be wide. Furthermore, the estimated expression values also vary depending on the selected preprocessing scheme. In microarray breast cancer classification studies, however, these two forms of feature variability are almost always ignored and hence their exact role is unclear. Results: We have performed a comprehensive sensitivity analysis of microarray breast cancer classification under the two types of feature variability mentioned above. We used data from six state of the art preprocessing methods, using a compendium consisting of eight diferent datasets, involving 1131 hybridizations, containing data from both one and two-color array technology. For a wide range of classifiers, we performed a joint study on performance, concordance and stability. In the stability analysis we explicitly tested classifiers for their noise tolerance by using perturbed expression profiles that are based on uncertainty information directly related to the preprocessing methods. Our results indicate that signature composition is strongly influenced by feature variability, even if the array platform and the stratification of patient samples are identical. In addition, we show that there is often a high level of discordance between individual class assignments for signatures constructed on data coming from different preprocessing schemes, even if the actual signature composition is identical. Conclusion: Feature variability c, Mediamatics, Electrical Engineering, Mathematics and Computer Science

Current automatic sign language recognition (ASLR) seldom uses perceptual knowledge about the recognition of sign language. Using such knowledge can improve ASLR because it can give an indication which elements or phases of a sign are important for its meaning. Also, the current generation of data-driven ASLR methods has shortcomings which may not be solvable without the use of knowledge on human sign language processing. Handling variation in the precise execution of signs is an example of such shortcomings: data-driven methods (which include almost all current methods) have difficulty recognizing signs that deviate too much from the examples that were used to train the method. Insight into human sign processing is needed to solve these problems. Perceptual research on sign language can provide such insights. This paper discusses knowledge derived from a set of sign perception experiments, and the application of such knowledge in ASLR. Among the findings are the facts that not all phases and elements of a sign are equally informative, that defining the ‘correct’ form for a sign is not trivial, and that statistical ASLR methods do not necessarily arrive at sign representations that resemble those of human beings. Apparently, current ASLR methods are quite different from human observers: their method of learning gives them different sign definitions, they regard each moment and element of a sign as equally important and they employ a single definition of ‘correct’ for all circumstances. If the object is for an ASLR method to handle natural sign language, then the insights from sign perception research must be integrated into ASLR., Human Information Communication Design, Industrial Design Engineering

Comparative analysis of metabolic networks in multiple species yields important information on their evolution, and has great practical value in metabolic engineering, human disease analysis, drug design etc. In this work, we aim to systematically search for conserved pathways in two species, quantify their similarities, and focus on the variations between them, Electrical Engineering, Mathematics and Computer Science

Motivation: Cells receive a wide variety of environmental signals, which are often processed combinatorially to generate specific genetic responses. Changes in transcript levels, as observed across different environmental conditions, can, to a large extent, be attributed to changes in the activity of transcription factors (TFs). However, in unraveling these transcription regulation networks, the actual environmental signals are often not incorporated into the model, simply because they have not been measured. The unquantified heterogeneity of the environmental parameters across microarray experiments frustrates regulatory network inference. Results: We propose an inference algorithm that models the influence of environmental parameters on gene expression. The approach is based on a yeast microarray compendium of chemostat steady-state experiments. Chemostat cultivation enables the accurate control and measurement of many of the key cultivation parameters, such as nutrient concentrations, growth rate and temperature. The observed transcript levels are explained by inferring the activity of TFs in response to combinations of cultivation parameters. The interplay between activated enhancers and repressors that bind a gene promoter determine the possible up- or downregulation of the gene. The model is translated into a linear integer optimization problem. The resulting regulatory network identifies the combinatorial effects of environmental parameters on TF activity and gene expression., Mediamatics, Electrical Engineering, Mathematics and Computer Science

In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression, and interactions). The integration of these different data sources can be challenging. Recently, it has been recognized that kernel-based classifiers are well suited for this task. However, the different kernels (data sources) are often combined using equal weights. Although several methods have been developed to optimize kernel weights, no large-scale example of an improvement in classifier performance has been shown yet. In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC curve. We show that setting the right kernel weights can indeed improve performance. We compare this to the existing kernel weight optimization methods (i.e., (regularized) optimization of the SVM criterion or aligning the kernel with an ideal kernel) and find that these do not result in a significant performance improvement and can even cause a decrease in performance. Results also show that an expert approach of assigning high weights to features with high individual performance is not necessarily the best strategy., Mediamatics, Electrical Engineering, Mathematics and Computer Science

OA Fund TU Delft, Electrical Engineering, Mathematics and Computer Science

Methods commonly used for speech and sign language recognition often rely on outputs of Hidden Markov Models (HMM) or Dynamic TimeWarping (DTW) for classification, which aremerely factorized observation likelihoods. Instead, we propose to use Statistical DTW (SDTW) only for warping, while classifying the synchronized features with either of two proposed discriminants. This hybrid approach is shown to outperform HMM and SDTW. However, we have found that combining likelihoods of multiple models in a second classification stage degrades performance of the proposed classifiers, while improving performance with HMM and SDTW. A proof-of-concept experiment, combining DFFM mappings of multiple SDTW models with SDTW likelihoods, shows that also for model-combining, hybrid classification can provide significant improvement over SDTW., Intelligent Systems, Electrical Engineering, Mathematics and Computer Science

OA fund TU Delft, Electrical Engineering, Mathematics and Computer Science

Collaborative filtering is concerned with making recommendations about items to users. Most formulations of the problem are specifically designed for predicting user ratings, assuming past data of explicit user ratings is available. However, in practice we may only have implicit evidence of user preference; and furthermore, a better view of the task is of generating a top-N list of items that the user is most likely to like. In this regard, we argue that collaborative filtering can be directly cast as a relevance ranking problem. We begin with the classic Probability Ranking Principle of information retrieval, proposing a probabilistic item ranking framework. In the framework, we derive two different ranking models, showing that despite their common origin, different factorizations reflect two distinctive ways to approach item ranking. For the model estimations, we limit our discussions to implicit user preference data, and adopt an approximation method introduced in the classic text retrieval model (i.e. the Okapi BM25 formula) to effectively decouple frequency counts and presence/absence counts in the preference data. Furthermore, we extend the basic formula by proposing the Bayesian inference to estimate the probability of relevance (and non-relevance), which largely alleviates the data sparsity problem. Apart from a theoretical contribution, our experiments on real data sets demonstrate that the proposed methods perform significantly better than other strong baselines., Mediamatics, Electrical Engineering, Mathematics and Computer Science

Comparative analysis of metabolic networks in multiple species yields important information on their evolution, and has great practical value in metabolic engineering, human disease analysis, drug design etc. In this work, we aim to systematically search for conserved pathways in two species, quantify their similarities, and focus on the variations between them, Electrical Engineering, Mathematics and Computer Science

Motivation: Cells receive a wide variety of environmental signals, which are often processed combinatorially to generate specific genetic responses. Changes in transcript levels, as observed across different environmental conditions, can, to a large extent, be attributed to changes in the activity of transcription factors (TFs). However, in unraveling these transcription regulation networks, the actual environmental signals are often not incorporated into the model, simply because they have not been measured. The unquantified heterogeneity of the environmental parameters across microarray experiments frustrates regulatory network inference. Results: We propose an inference algorithm that models the influence of environmental parameters on gene expression. The approach is based on a yeast microarray compendium of chemostat steady-state experiments. Chemostat cultivation enables the accurate control and measurement of many of the key cultivation parameters, such as nutrient concentrations, growth rate and temperature. The observed transcript levels are explained by inferring the activity of TFs in response to combinations of cultivation parameters. The interplay between activated enhancers and repressors that bind a gene promoter determine the possible up- or downregulation of the gene. The model is translated into a linear integer optimization problem. The resulting regulatory network identifies the combinatorial effects of environmental parameters on TF activity and gene expression., Mediamatics, Electrical Engineering, Mathematics and Computer Science

In recent years, more and more high-throughput data sources useful for protein complex prediction have become available (e.g., gene sequence, mRNA expression, and interactions). The integration of these different data sources can be challenging. Recently, it has been recognized that kernel-based classifiers are well suited for this task. However, the different kernels (data sources) are often combined using equal weights. Although several methods have been developed to optimize kernel weights, no large-scale example of an improvement in classifier performance has been shown yet. In this work, we employ an evolutionary algorithm to determine weights for a larger set of kernels by optimizing a criterion based on the area under the ROC curve. We show that setting the right kernel weights can indeed improve performance. We compare this to the existing kernel weight optimization methods (i.e., (regularized) optimization of the SVM criterion or aligning the kernel with an ideal kernel) and find that these do not result in a significant performance improvement and can even cause a decrease in performance. Results also show that an expert approach of assigning high weights to features with high individual performance is not necessarily the best strategy., Mediamatics, Electrical Engineering, Mathematics and Computer Science

To recognize speech, handwriting, or sign language, many hybrid approaches have been proposed that combine Dynamic Time Warping (DTW) or Hidden Markov Models (HMMs) with discriminative classifiers. However, all methods rely directly on the likelihood models of DTW/HMM. We hypothesize that time warping and classification should be separated because of conflicting likelihood modeling demands. To overcome these restrictions, we propose using Statistical DTW (SDTW) only for time warping, while classifying the warped features with a different method. Two novel statistical classifiers are proposed—Combined Discriminative Feature Detectors (CDFDs) and Quadratic Classification on DF Fisher Mapping (Q-DFFM)—both using a selection of discriminative features (DFs), and are shown to outperform HMM and SDTW. However, we have found that combining likelihoods of multiple models in a second classification stage degrades performance of the proposed classifiers, while improving performance with HMM and SDTW. A proof-of-concept experiment, combining DFFM mappings of multiple SDTW models with SDTW likelihoods, shows that, also for model-combining, hybrid classification can provide significant improvement over SDTW. Although recognition is mainly based on 3D hand motion features, these results can be expected to generalize to recognition with more detailed measurements such as hand/body pose and facial expression., Mediamatics, Electrical Engineering, Mathematics and Computer Science

OA Fund TU Delft, Electrical Engineering, Mathematics and Computer Science

Methods commonly used for speech and sign language recognition often rely on outputs of Hidden Markov Models (HMM) or Dynamic TimeWarping (DTW) for classification, which aremerely factorized observation likelihoods. Instead, we propose to use Statistical DTW (SDTW) only for warping, while classifying the synchronized features with either of two proposed discriminants. This hybrid approach is shown to outperform HMM and SDTW. However, we have found that combining likelihoods of multiple models in a second classification stage degrades performance of the proposed classifiers, while improving performance with HMM and SDTW. A proof-of-concept experiment, combining DFFM mappings of multiple SDTW models with SDTW likelihoods, shows that also for model-combining, hybrid classification can provide significant improvement over SDTW., Intelligent Systems, Electrical Engineering, Mathematics and Computer Science

OA fund TU Delft, Electrical Engineering, Mathematics and Computer Science

Collaborative filtering is concerned with making recommendations about items to users. Most formulations of the problem are specifically designed for predicting user ratings, assuming past data of explicit user ratings is available. However, in practice we may only have implicit evidence of user preference; and furthermore, a better view of the task is of generating a top-N list of items that the user is most likely to like. In this regard, we argue that collaborative filtering can be directly cast as a relevance ranking problem. We begin with the classic Probability Ranking Principle of information retrieval, proposing a probabilistic item ranking framework. In the framework, we derive two different ranking models, showing that despite their common origin, different factorizations reflect two distinctive ways to approach item ranking. For the model estimations, we limit our discussions to implicit user preference data, and adopt an approximation method introduced in the classic text retrieval model (i.e. the Okapi BM25 formula) to effectively decouple frequency counts and presence/absence counts in the preference data. Furthermore, we extend the basic formula by proposing the Bayesian inference to estimate the probability of relevance (and non-relevance), which largely alleviates the data sparsity problem. Apart from a theoretical contribution, our experiments on real data sets demonstrate that the proposed methods perform significantly better than other strong baselines., Mediamatics, Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Background. The availability of large collections of microarray datasets (compendia), or knowledge about grouping of genes into pathways (gene sets), is typically not exploited when training predictors of disease outcome. These can be useful since a compendium increases the number of samples, while gene sets reduce the size of the feature space. This should be favorable from a machine learning perspective and result in more robust predictors. Methodology. We extracted modules of regulated genes from gene sets, and compendia. Through supervised analysis, we constructed predictors which employ modules predictive of breast cancer outcome. To validate these predictors we applied them to independent data, from the same institution (intra-dataset), and other institutions (inter-dataset). Conclusions. We show that modules derived from single breast cancer datasets achieve better performance on the validation data compared to gene-based predictors. We also show that there is a trend in compendium specificity and predictive performance: modules derived from a single breast cancer dataset, and a breast cancer specific compendium perform better compared to those derived from a human cancer compendium. Additionally, the module-based predictor provides a much richer insight into the underlying biology. Frequently selected gene sets are associated with processes such as cell cycle, E2F regulation, DNA damage response, proteasome and glycolysis. We analyzed two modules related to cell cycle, and the OCT1 transcription factor, respectively. On an individual basis, these modules provide a significant separation in survival subgroups on the training and independent validation data., Mediamatics, Electrical Engineering, Mathematics and Computer Science

We introduce personalization on Tribler, a peer-to-peer (P2P) television system. Personalization allows users to browse programs much more efficiently according to their taste. It also enables to build social networks that can improve the performance of current P2P systems considerably, by increasing content availability, trust and the realization of proper incentives to exchange content. This paper presents a novel scheme, called BuddyCast, that builds such a social network for a user by exchanging user interest profiles using exploitation and exploration principles. Additionally, we show how the interest of a user in TV programs can be predicted from the zapping behavior by the introduced user-item relevance models, thereby avoiding the explicit rating of TV programs. Further, we present how the social network of a user can be used to realize a truly distributed recommendation of TV programs. Finally, we demonstrate a novel user interface for the personalized peer-to-peer television system that encompasses a personalized tag-based navigation to browse the available distributed content. The user interface also visualizes the social network of a user, thereby increasing community feeling which increases trust amongst users and within available content and creates incentives of to exchange content within the community., Telecommunications, Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Background. The availability of large collections of microarray datasets (compendia), or knowledge about grouping of genes into pathways (gene sets), is typically not exploited when training predictors of disease outcome. These can be useful since a compendium increases the number of samples, while gene sets reduce the size of the feature space. This should be favorable from a machine learning perspective and result in more robust predictors. Methodology. We extracted modules of regulated genes from gene sets, and compendia. Through supervised analysis, we constructed predictors which employ modules predictive of breast cancer outcome. To validate these predictors we applied them to independent data, from the same institution (intra-dataset), and other institutions (inter-dataset). Conclusions. We show that modules derived from single breast cancer datasets achieve better performance on the validation data compared to gene-based predictors. We also show that there is a trend in compendium specificity and predictive performance: modules derived from a single breast cancer dataset, and a breast cancer specific compendium perform better compared to those derived from a human cancer compendium. Additionally, the module-based predictor provides a much richer insight into the underlying biology. Frequently selected gene sets are associated with processes such as cell cycle, E2F regulation, DNA damage response, proteasome and glycolysis. We analyzed two modules related to cell cycle, and the OCT1 transcription factor, respectively. On an individual basis, these modules provide a significant separation in survival subgroups on the training and independent validation data., Mediamatics, Electrical Engineering, Mathematics and Computer Science

We introduce personalization on Tribler, a peer-to-peer (P2P) television system. Personalization allows users to browse programs much more efficiently according to their taste. It also enables to build social networks that can improve the performance of current P2P systems considerably, by increasing content availability, trust and the realization of proper incentives to exchange content. This paper presents a novel scheme, called BuddyCast, that builds such a social network for a user by exchanging user interest profiles using exploitation and exploration principles. Additionally, we show how the interest of a user in TV programs can be predicted from the zapping behavior by the introduced user-item relevance models, thereby avoiding the explicit rating of TV programs. Further, we present how the social network of a user can be used to realize a truly distributed recommendation of TV programs. Finally, we demonstrate a novel user interface for the personalized peer-to-peer television system that encompasses a personalized tag-based navigation to browse the available distributed content. The user interface also visualizes the social network of a user, thereby increasing community feeling which increases trust amongst users and within available content and creates incentives of to exchange content within the community., Telecommunications, Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

Electrical Engineering, Mathematics and Computer Science

The Wi-Fi walkman is a mobile multimedia application that we developed to investigate the technological and usability aspects of human-computer interaction with personalized, intelligent and context-aware wearable devices in peer-to-peer wireless environments such as the future home, office, or university campuses. It is a small handheld device with a wireless link that contains music content. Users carry their own walkman around and listen to music. All this music content is distributed in the peer-to-peer network and is shared using ad-hoc networking. The walkman naturally interacts with the users and users’ interest with each other in a peer-to-peer environment. Without annoying interactions, it can learn the users’ music interest/taste and consequently provide personalized music recommendation according to the current situated context and user’s interest., Pattern Recognition and Bioinformatics, Electrical Engineering, Mathematics and Computer Science

A method is proposed for filling in missing areas of degraded images through explicit structure reconstruction, followed by texture synthesis. The structure being reconstructed represents meaningful edges from the image, which are traced inside the artefact. The structure reconstruction step relies on different properties of the edges touching the artefact and of the areas between them, in order to sketch the missing edges within the artefact area. The texture synthesis step is based on Markov random fields and is constrained by the traced edges in order to preserve both the shape and the appearance of the various regions in the image. The novelty of our contribution concerns constraining the texture synthesis, which proves to give results superior to the original texture synthesis alone, or to the smoothness-preserving structure-based restoration., Electrical Engineering, Mathematics and Computer Science

The Wi-Fi walkman is a mobile multimedia application that we developed to investigate the technological and usability aspects of human-computer interaction with personalized, intelligent and context-aware wearable devices in peer-to-peer wireless environments such as the future home, office, or university campuses. It is a small handheld device with a wireless link that contains music content. Users carry their own walkman around and listen to music. All this music content is distributed in the peer-to-peer network and is shared using ad-hoc networking. The walkman naturally interacts with the users and users’ interest with each other in a peer-to-peer environment. Without annoying interactions, it can learn the users’ music interest/taste and consequently provide personalized music recommendation according to the current situated context and user’s interest., Pattern Recognition and Bioinformatics, Electrical Engineering, Mathematics and Computer Science

A method is proposed for filling in missing areas of degraded images through explicit structure reconstruction, followed by texture synthesis. The structure being reconstructed represents meaningful edges from the image, which are traced inside the artefact. The structure reconstruction step relies on different properties of the edges touching the artefact and of the areas between them, in order to sketch the missing edges within the artefact area. The texture synthesis step is based on Markov random fields and is constrained by the traced edges in order to preserve both the shape and the appearance of the various regions in the image. The novelty of our contribution concerns constraining the texture synthesis, which proves to give results superior to the original texture synthesis alone, or to the smoothness-preserving structure-based restoration., Electrical Engineering, Mathematics and Computer Science