Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.27
Jihan M. Zoghbi, Leandro T. De La Cruz, Miguel A. Galarreta-Valverde, M. Jackowski, J. Vieira, A. Liberatore, I. Koh
Real-time detection of sepsis on a video data is a new aboard technique that aids the septic patient and decreases the high mortality rate. The progressive impairment of the micro-circulation associated with increased systemic inflammatory response in sepsis has been considered the origin of the multiple organ dysfunction syndrome that often leads to death. However, despite the recognized importance of the micro-circulatory dysfunction, analysis methods able to correlate the severity of sepsis with the degree of impairment of micro-hemodynamic captured by portable microscope Side-stream Dark Field Imaging (SDF) are rarely used. Hence, the classification of the severity of sepsis by analyzing the micro-circulatory dysfunction would be of great assistance in diagnosing severity and therapeutic management. In this context, the aim of this work is to propose a new computational methodology based on image processing to obtain graph metrics for determining the degree of micro-vascular and tissue commitment due to sepsis.
{"title":"Graph Based Characterization of Microcirculation in Sepsis Using Sidestream Dark Field Imaging","authors":"Jihan M. Zoghbi, Leandro T. De La Cruz, Miguel A. Galarreta-Valverde, M. Jackowski, J. Vieira, A. Liberatore, I. Koh","doi":"10.1109/SIBGRAPI.2014.27","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.27","url":null,"abstract":"Real-time detection of sepsis on a video data is a new aboard technique that aids the septic patient and decreases the high mortality rate. The progressive impairment of the micro-circulation associated with increased systemic inflammatory response in sepsis has been considered the origin of the multiple organ dysfunction syndrome that often leads to death. However, despite the recognized importance of the micro-circulatory dysfunction, analysis methods able to correlate the severity of sepsis with the degree of impairment of micro-hemodynamic captured by portable microscope Side-stream Dark Field Imaging (SDF) are rarely used. Hence, the classification of the severity of sepsis by analyzing the micro-circulatory dysfunction would be of great assistance in diagnosing severity and therapeutic management. In this context, the aim of this work is to propose a new computational methodology based on image processing to obtain graph metrics for determining the degree of micro-vascular and tissue commitment due to sepsis.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122660578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.48
Michel Fornaciali, S. Avila, Micael Carvalho, Eduardo Valle
According to the American Cancer Society, one person dies of melanoma every 57 minutes, although it is the most curable type of cancer if detected early. Thus, computeraided diagnosis for melanoma screening has been a topic of active research. Much of the existing art is based on the Bag-of-Visual-Words (BoVW) model, combined with color and texture descriptors. However, recent advances in the BoVW model, as well as the evaluation of the importance of the many different factors affecting the BoVW model were yet to be explored, thus motivating our work. We show that a new approach for melanoma screening, based upon the state-of-the-art BossaNova descriptors, shows very promising results for screening, reaching an AUC of up to 93.7%. An important contribution of this work is an evaluation of the factors that affect the performance of the two-layered BoVW model. Our results show that the low-level layer has a major impact on the accuracy of the model, but that the codebook size on the mid-level layer is also important. Those results may guide future works on melanoma screening.
{"title":"Statistical Learning Approach for Robust Melanoma Screening","authors":"Michel Fornaciali, S. Avila, Micael Carvalho, Eduardo Valle","doi":"10.1109/SIBGRAPI.2014.48","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.48","url":null,"abstract":"According to the American Cancer Society, one person dies of melanoma every 57 minutes, although it is the most curable type of cancer if detected early. Thus, computeraided diagnosis for melanoma screening has been a topic of active research. Much of the existing art is based on the Bag-of-Visual-Words (BoVW) model, combined with color and texture descriptors. However, recent advances in the BoVW model, as well as the evaluation of the importance of the many different factors affecting the BoVW model were yet to be explored, thus motivating our work. We show that a new approach for melanoma screening, based upon the state-of-the-art BossaNova descriptors, shows very promising results for screening, reaching an AUC of up to 93.7%. An important contribution of this work is an evaluation of the factors that affect the performance of the two-layered BoVW model. Our results show that the low-level layer has a major impact on the accuracy of the model, but that the codebook size on the mid-level layer is also important. Those results may guide future works on melanoma screening.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130138895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.20
Suzana Matos França de Oliveira, C. Vidal, J. B. C. Neto, Laise Lima De Carvalho, J. G. R. Maia
In the last decades, cloth animation has been the focus of much research, because of demands from the entertainment industry and from e-commerce. That type of animation is usually produced by means of physics simulations that are computationally expensive. Cloth folding during oscillations or due to contact with rigid objects often requires a very dense mesh when high curvatures are present. In those situations, the dynamics simulation will involve huge matrices and vectors. So, in the attempt to reduce costs, adaptive remeshing is frequently proposed. In this work, we investigate a remeshing approach during dynamics simulation of cloth. Mesh refinement is applied only to regions that need a fine level of detail. Our remeshing strategy refines the mesh in regions of high curvature and simplifies the mesh in regions of low curvature. No matter how regular and coarse the initial mesh is, our remeshing strategy produces meshes that are well adapted to the irregularities of the solid objects at every time step of the draping simulation. The fabric model consists of a triangular mesh and uses a spring-mass-damper system to compute the forces between particles, which are located at the mesh's vertices. Collision detection depends on the arrangement of the cloth model and the objects in the scene. Although the tests show that, for comparable mesh sizes, the adaptive method does not always outperforms non-adaptive methods, the quality of the draping is much better when adaptive methods are used. Thus, adaptive methods can deliver comparable draping quality with fewer elements and less cost.
{"title":"Cloth Simulation with Triangular Mesh Adaptivity","authors":"Suzana Matos França de Oliveira, C. Vidal, J. B. C. Neto, Laise Lima De Carvalho, J. G. R. Maia","doi":"10.1109/SIBGRAPI.2014.20","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.20","url":null,"abstract":"In the last decades, cloth animation has been the focus of much research, because of demands from the entertainment industry and from e-commerce. That type of animation is usually produced by means of physics simulations that are computationally expensive. Cloth folding during oscillations or due to contact with rigid objects often requires a very dense mesh when high curvatures are present. In those situations, the dynamics simulation will involve huge matrices and vectors. So, in the attempt to reduce costs, adaptive remeshing is frequently proposed. In this work, we investigate a remeshing approach during dynamics simulation of cloth. Mesh refinement is applied only to regions that need a fine level of detail. Our remeshing strategy refines the mesh in regions of high curvature and simplifies the mesh in regions of low curvature. No matter how regular and coarse the initial mesh is, our remeshing strategy produces meshes that are well adapted to the irregularities of the solid objects at every time step of the draping simulation. The fabric model consists of a triangular mesh and uses a spring-mass-damper system to compute the forces between particles, which are located at the mesh's vertices. Collision detection depends on the arrangement of the cloth model and the objects in the scene. Although the tests show that, for comparable mesh sizes, the adaptive method does not always outperforms non-adaptive methods, the quality of the draping is much better when adaptive methods are used. Thus, adaptive methods can deliver comparable draping quality with fewer elements and less cost.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133075365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.52
D. Menotti, G. Chiachia, A. Falcão, Vantuil J. Oliveira Neto
Despite decades of research on automatic license plate recognition (ALPR), optical character recognition (OCR) still leaves room for improvement in this context, given that a single OCR miss is enough to miss the entire plate. We propose an OCR approach based on convolutional neural networks (CNNs) for feature extraction. The architecture of our CNN is chosen from thousands of random possibilities and its filter weights are set at random and normalized to zero mean and unit norm. By training linear support vector machines (SVMs) on the resulting CNN features, we can achieve recognition rates of over 98% for digits and 96% for letters, something that neither SVMs operating on image pixels nor CNNs trained via back-propagation can achieve. The results are obtained in a dataset that has 182 samples per digit and 28 per letter, and suggest the use of random CNNs as a promising alternative approach to ALPR systems.
{"title":"Vehicle License Plate Recognition With Random Convolutional Networks","authors":"D. Menotti, G. Chiachia, A. Falcão, Vantuil J. Oliveira Neto","doi":"10.1109/SIBGRAPI.2014.52","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.52","url":null,"abstract":"Despite decades of research on automatic license plate recognition (ALPR), optical character recognition (OCR) still leaves room for improvement in this context, given that a single OCR miss is enough to miss the entire plate. We propose an OCR approach based on convolutional neural networks (CNNs) for feature extraction. The architecture of our CNN is chosen from thousands of random possibilities and its filter weights are set at random and normalized to zero mean and unit norm. By training linear support vector machines (SVMs) on the resulting CNN features, we can achieve recognition rates of over 98% for digits and 96% for letters, something that neither SVMs operating on image pixels nor CNNs trained via back-propagation can achieve. The results are obtained in a dataset that has 182 samples per digit and 28 per letter, and suggest the use of random CNNs as a promising alternative approach to ALPR systems.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116333961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.37
Adriano Veloso, J. A. D. Santos, Keiller Nogueira
In this paper, we present an effective algorithm to automatically annotate clothes in everyday photos posted in online social networks, such as Facebook and Instagram. Specifically, clothing annotation can be informally stated as predicting, as accurately as possible, the garment items appearing in the target photo. This task not only poses interesting challenges for existing vision and recognition algorithms, but also brings huge opportunities for recommender and e-commerce systems. We formulate the annotation task as a multi-modal, multi-label and multi-instance classification problem: (i) both image and textual content (i.e., comments about the image) are available for learning classifiers, (ii) the classifiers must predict a set of labels (i.e., a set of garment items), and (iii) the decision on which labels to predict comes from a bag of instances that are used to build a function, which separates labels that should be predicted from those that should not be. Under this setting, we propose a classification algorithm which employs association rules in order to build a prediction model that combines image and textual information, and adopts an entropy-minimization strategy in order to the find the best set of labels to predict. We conducted a systematic evaluation of the proposed algorithm using everyday photos collected from two major fashion-related social networks, namely pose.com and chictopia.com. Our results show that the proposed algorithm provides improvements when compared to popular first choice multi-label algorithms that range from 2% to 40% in terms of accuracy.
{"title":"Learning to Annotate Clothes in Everyday Photos: Multi-modal, Multi-label, Multi-instance Approach","authors":"Adriano Veloso, J. A. D. Santos, Keiller Nogueira","doi":"10.1109/SIBGRAPI.2014.37","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.37","url":null,"abstract":"In this paper, we present an effective algorithm to automatically annotate clothes in everyday photos posted in online social networks, such as Facebook and Instagram. Specifically, clothing annotation can be informally stated as predicting, as accurately as possible, the garment items appearing in the target photo. This task not only poses interesting challenges for existing vision and recognition algorithms, but also brings huge opportunities for recommender and e-commerce systems. We formulate the annotation task as a multi-modal, multi-label and multi-instance classification problem: (i) both image and textual content (i.e., comments about the image) are available for learning classifiers, (ii) the classifiers must predict a set of labels (i.e., a set of garment items), and (iii) the decision on which labels to predict comes from a bag of instances that are used to build a function, which separates labels that should be predicted from those that should not be. Under this setting, we propose a classification algorithm which employs association rules in order to build a prediction model that combines image and textual information, and adopts an entropy-minimization strategy in order to the find the best set of labels to predict. We conducted a systematic evaluation of the proposed algorithm using everyday photos collected from two major fashion-related social networks, namely pose.com and chictopia.com. Our results show that the proposed algorithm provides improvements when compared to popular first choice multi-label algorithms that range from 2% to 40% in terms of accuracy.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116831444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.32
Cícero A. L. Pahins, C. Pozzer
This paper presents a new Divide-and-Conquer Ray-Tracing (DACRT) algorithm that is designed to perform on multi-core processors. This new algorithm proposes a parallel and generic scheme that, without the use of any data structure for spatial subdivision, maintains memory management minimal and deterministic. Initially, the scene is divided into sub-scenes and those uniformly distributed across available hardware resources, processing each sub-scene individually. After, an iterative step to ensure the correct results is performed until the final frame is obtained. Results show that our algorithm is up to 2.4x times faster than the original DACRT in a common quad-core processor setup, allowing very high interactive frame rates in well-known benchmark scenes.
{"title":"Improving Divide-and-Conquer Ray-Tracing Using a Parallel Approach","authors":"Cícero A. L. Pahins, C. Pozzer","doi":"10.1109/SIBGRAPI.2014.32","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.32","url":null,"abstract":"This paper presents a new Divide-and-Conquer Ray-Tracing (DACRT) algorithm that is designed to perform on multi-core processors. This new algorithm proposes a parallel and generic scheme that, without the use of any data structure for spatial subdivision, maintains memory management minimal and deterministic. Initially, the scene is divided into sub-scenes and those uniformly distributed across available hardware resources, processing each sub-scene individually. After, an iterative step to ensure the correct results is performed until the final frame is obtained. Results show that our algorithm is up to 2.4x times faster than the original DACRT in a common quad-core processor setup, allowing very high interactive frame rates in well-known benchmark scenes.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130412019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.47
Luiz Fernando de Souza Andrade, Marcos Sandim, Fabiano Petronetto, P. Pagliosa, Afonso Paiva
We present a novel meshfree technique for animating free surface viscous liquids with jet buckling effects, such as coiling and folding. Our technique is based on Smoothed Particle Hydrodynamics (SPH) fluids and allows more realistic and complex viscous behaviors than the preceding SPH frameworks in computer animation literature. The viscous liquid is modeled by a non-Newtonian fluid flow and the variable viscosity under shear stress is achieved using a viscosity model known as Cross model. The proposed technique is efficient and stable, and our framework can animate scenarios with high resolution of SPH particles in which the simulation speed is significantly accelerated by using Computer Unified Device Architecture (CUDA) computing platform. This work also includes several examples that demonstrate the ability of our technique.
{"title":"SPH Fluids for Viscous Jet Buckling","authors":"Luiz Fernando de Souza Andrade, Marcos Sandim, Fabiano Petronetto, P. Pagliosa, Afonso Paiva","doi":"10.1109/SIBGRAPI.2014.47","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.47","url":null,"abstract":"We present a novel meshfree technique for animating free surface viscous liquids with jet buckling effects, such as coiling and folding. Our technique is based on Smoothed Particle Hydrodynamics (SPH) fluids and allows more realistic and complex viscous behaviors than the preceding SPH frameworks in computer animation literature. The viscous liquid is modeled by a non-Newtonian fluid flow and the variable viscosity under shear stress is achieved using a viscosity model known as Cross model. The proposed technique is efficient and stable, and our framework can animate scenarios with high resolution of SPH particles in which the simulation speed is significantly accelerated by using Computer Unified Device Architecture (CUDA) computing platform. This work also includes several examples that demonstrate the ability of our technique.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116838921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.53
Aurea Soriano-Vargas, F. Paulovich, L. G. Nonato, Maria Cristina Ferreira de Oliveira
Users interact a lot with their personal music collections, typically using standard text-based interfaces that offer constrained functionalities based on assigned metadata or tags. Alternative visual interfaces have been developed, both to display graphical views of music collections that attempt to reflect some chosen property or organization, or to display abstract visual representations of specific songs. Yet, there are many dimensions involved in the perception and handling of music and mapping musical information into computer tractable models is a challenging problem. With a wide variety of possible approaches, the search for novel strategies to visually represent songs and/or collections persists, targeted either at the general public or at musically trained individuals. In this paper we describe a visual interface to browse music collections that relies on a graphical metaphor designed to convey the underlying musical structure of a song. An iconic representation of individual songs is coupled with a spatial placement of songs that reflects their structural similarity. The song icon is derived from features extracted from MIDI files, rather than from audio signals. The very nature of MIDI descriptions enables the identification of simple, yet meaningful, musical structures, allowing us to extract features that support both creating the icon and comparing songs. A similarity-based spatial placement is created projecting the feature vectors with the Least Square Projection multidimensional projection, employing the Dynamic Time Warping distance function to evaluate feature similarity. We describe the process of generating such visual representations and illustrate potentially interesting usage scenarios.
{"title":"Visualization of Music Collections Based on Structural Content Similarity","authors":"Aurea Soriano-Vargas, F. Paulovich, L. G. Nonato, Maria Cristina Ferreira de Oliveira","doi":"10.1109/SIBGRAPI.2014.53","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.53","url":null,"abstract":"Users interact a lot with their personal music collections, typically using standard text-based interfaces that offer constrained functionalities based on assigned metadata or tags. Alternative visual interfaces have been developed, both to display graphical views of music collections that attempt to reflect some chosen property or organization, or to display abstract visual representations of specific songs. Yet, there are many dimensions involved in the perception and handling of music and mapping musical information into computer tractable models is a challenging problem. With a wide variety of possible approaches, the search for novel strategies to visually represent songs and/or collections persists, targeted either at the general public or at musically trained individuals. In this paper we describe a visual interface to browse music collections that relies on a graphical metaphor designed to convey the underlying musical structure of a song. An iconic representation of individual songs is coupled with a spatial placement of songs that reflects their structural similarity. The song icon is derived from features extracted from MIDI files, rather than from audio signals. The very nature of MIDI descriptions enables the identification of simple, yet meaningful, musical structures, allowing us to extract features that support both creating the icon and comparing songs. A similarity-based spatial placement is created projecting the feature vectors with the Least Square Projection multidimensional projection, employing the Dynamic Time Warping distance function to evaluate feature similarity. We describe the process of generating such visual representations and illustrate potentially interesting usage scenarios.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131717238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.19
F. Rocha, C. Thomaz, A. Rocha, E. Massad
Difficulties in learning to read may have a number of causes and children tend to experience on the phonological route the most common disturbance in this cognitive task. Using two sample groups of children with and without reading difficulties and their corresponding EEG signals captured during the reading processing, we describe in this work a set of techniques that investigates such disturbance by generating whole brain mappings based on the entropy of each EEG electrode and non-supervised and supervised multivariate statistical analyses. Our experimental results have clearly showed specific neural organizations well suited to interpreting the word/phrase reading processing in these children. We believe that these techniques might become an effective computational tool in helping the diagnostic process of children with learning disabilities.
{"title":"Brain Mapping and Interpretation of Reading Processing in Children Using EEG and Multivariate Statistical Analysis","authors":"F. Rocha, C. Thomaz, A. Rocha, E. Massad","doi":"10.1109/SIBGRAPI.2014.19","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.19","url":null,"abstract":"Difficulties in learning to read may have a number of causes and children tend to experience on the phonological route the most common disturbance in this cognitive task. Using two sample groups of children with and without reading difficulties and their corresponding EEG signals captured during the reading processing, we describe in this work a set of techniques that investigates such disturbance by generating whole brain mappings based on the entropy of each EEG electrode and non-supervised and supervised multivariate statistical analyses. Our experimental results have clearly showed specific neural organizations well suited to interpreting the word/phrase reading processing in these children. We believe that these techniques might become an effective computational tool in helping the diagnostic process of children with learning disabilities.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131865177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-08-26DOI: 10.1109/SIBGRAPI.2014.36
S. Fernandes, A. Pilastri, Luís A. M. Pereira, R. G. Pires, J. Papa
In the pattern recognition research field, Support Vector Machines (SVM) have been an effectiveness tool for classification purposes, being successively employed in many applications. The SVM input data is transformed into a high dimensional space using some kernel functions where linear separation is more likely. However, there are some computational drawbacks associated to SVM. One of them is the computational burden required to find out the more adequate parameters for the kernel mapping considering each non-linearly separable input data space, which reflects the performance of SVM. This paper introduces the Polynomial-Powers of Sigmoid for SVM kernel mapping, and it shows their advantages over well-known kernel functions using real and synthetic datasets.
{"title":"Learning Kernels for Support Vector Machines with Polynomial Powers of Sigmoid","authors":"S. Fernandes, A. Pilastri, Luís A. M. Pereira, R. G. Pires, J. Papa","doi":"10.1109/SIBGRAPI.2014.36","DOIUrl":"https://doi.org/10.1109/SIBGRAPI.2014.36","url":null,"abstract":"In the pattern recognition research field, Support Vector Machines (SVM) have been an effectiveness tool for classification purposes, being successively employed in many applications. The SVM input data is transformed into a high dimensional space using some kernel functions where linear separation is more likely. However, there are some computational drawbacks associated to SVM. One of them is the computational burden required to find out the more adequate parameters for the kernel mapping considering each non-linearly separable input data space, which reflects the performance of SVM. This paper introduces the Polynomial-Powers of Sigmoid for SVM kernel mapping, and it shows their advantages over well-known kernel functions using real and synthetic datasets.","PeriodicalId":146229,"journal":{"name":"2014 27th SIBGRAPI Conference on Graphics, Patterns and Images","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128824383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：