Jesus A. Gonzalez

The segmented and annotated IAPR TC-12 benchmark

Automatic image annotation (AIA), a highly popular topic in the field of information retrieval research, has experienced significant progress within the last decade. Yet, the lack of a standardized evaluation platform tailored to the needs of AIA, has hindered effective evaluation of its methods, especially for region-based AIA. Therefore in this paper, we introduce the segmented and annotated IAPR TC-12 benchmark; an extended resource for the evaluation of AIA methods as well as the analysis of their impact on multimedia information retrieval. We describe the methodology adopted for the manual segmentation and annotation of images, and present statistics for the extended collection. The extended collection is publicly available and can be used to evaluate a variety of tasks in addition to image annotation. We also propose a soft measure for the evaluation of annotation performance and identify future research areas in which this extended test collection is likely to make a contribution.

Advances in Artificial Intelligence – IBERAMIA 2004

Many approaches of the agent paradigm emphasize the social and intentional features of their systems, what are called social properties. The study of these aspects demands their own new techniques. Traditional Software Engineering approaches cannot manage with all the information about these components, which are as related with software development as with social disciplines. Following previous work, this paper presents a framework based in the Activity Theory to specify and verify social properties in a development process for multi-agent systems. Using this framework developers acquire tools for requirements elicitation and traceability, to detect inconsistencies in their specifications, and to get new insights into their systems. The way of working with these tools is shown with a case study.

Acute leukemia classification by ensemble particle swarm model selection

OBJECTIVEnAcute leukemia is a malignant disease that affects a large proportion of the world population. Different types and subtypes of acute leukemia require different treatments. In order to assign the correct treatment, a physician must identify the leukemia type or subtype. Advanced and precise methods are available for identifying leukemia types, but they are very expensive and not available in most hospitals in developing countries. Thus, alternative methods have been proposed. An option explored in this paper is based on the morphological properties of bone marrow images, where features are extracted from medical images and standard machine learning techniques are used to build leukemia type classifiers.nnnMETHODS AND MATERIALSnThis paper studies the use of ensemble particle swarm model selection (EPSMS), which is an automated tool for the selection of classification models, in the context of acute leukemia classification. EPSMS is the application of particle swarm optimization to the exploration of the search space of ensembles that can be formed by heterogeneous classification models in a machine learning toolbox. EPSMS does not require prior domain knowledge and it is able to select highly accurate classification models without user intervention. Furthermore, specific models can be used for different classification tasks.nnnRESULTSnWe report experimental results for acute leukemia classification with real data and show that EPSMS outperformed the best results obtained using manually designed classifiers with the same data. The highest performance using EPSMS was of 97.68% for two-type classification problems and of 94.21% for more than two types problems. To the best of our knowledge, these are the best results reported for this data set. Compared with previous studies, these improvements were consistent among different type/subtype classification tasks, different features extracted from images, and different feature extraction regions. The performance improvements were statistically significant. We improved previous results by an average of 6% and there are improvements of more than 20% with some settings. In addition to the performance improvements, we demonstrated that no manual effort was required during acute leukemia type/subtype classification.nnnCONCLUSIONSnMorphological classification of acute leukemia using EPSMS provides an alternative to expensive diagnostic methods in developing countries. EPSMS is a highly effective method for the automated construction of ensemble classifiers for acute leukemia classification, which requires no significant user intervention. EPSMS could also be used to address other medical classification tasks.

Image segmentation using automatic seeded region growing and instance-based learning

Segmentation through seeded region growing is widely used because it is fast, robust and free of tuning parameters. However, the seeded region growing algorithm requires an automatic seed generator, and has problems to label unconnected pixels (the unconnected pixel problem). This paper introduces a new automatic seeded region growing algorithm called ASRG-IB1 that performs the segmentation of color (RGB) and multispectral images. The seeds are automatically generated via histogram analysis; the histogram of each band is analyzed to obtain intervals of representative pixel values. An image pixel is considered a seed if its gray values for each band fall in some representative interval. After that, our new seeded region growing algorithm is applied to segment the image. This algorithm uses instance-based learning as distance criteria. Finally, according to the user needs, the regions are merged using ownership tables. The algorithm was tested on several leukemia medical images showing good results.

Mobile Personal Health System for Ambulatory Blood Pressure Monitoring

The ARVmobile v1.0 is a multiplatform mobile personal health monitor (PHM) application for ambulatory blood pressure (ABP) monitoring that has the potential to aid in the acquisition and analysis of detailed profile of ABP and heart rate (HR), improve the early detection and intervention of hypertension, and detect potential abnormal BP and HR levels for timely medical feedback. The PHM system consisted of ABP sensor to detect BP and HR signals and smartphone as receiver to collect the transmitted digital data and process them to provide immediate personalized information to the user. Android and Blackberry platforms were developed to detect and alert of potential abnormal values, offer friendly graphical user interface for elderly people, and provide feedback to professional healthcare providers via e-mail. ABP data were obtained from twenty-one healthy individuals (>51 years) to test the utility of the PHM application. The ARVmobile v1.0 was able to reliably receive and process the ABP readings from the volunteers. The preliminary results demonstrate that the ARVmobile 1.0 application could be used to perform a detailed profile of ABP and HR in an ordinary daily life environment, bedsides of estimating potential diagnostic thresholds of abnormal BP variability measured as average real variability.

SYMBOLIC ONE-CLASS LEARNING FROM IMBALANCED DATASETS: APPLICATION IN MEDICAL DIAGNOSIS

When working with real-world applications we often find imbalanced datasets, those for which there exists a majority class with normal data and a minority class with abnormal or important data. In this work, we make an overview of the class imbalance problem; we review consequences, possible causes and existing strategies to cope with the inconveniences associated to this problem. As an effort to contribute to the solution of this problem, we propose a new rule induction algorithm named Rule Extraction for MEdical Diagnosis (REMED), as a symbolic one-class learning approach. For the evaluation of the proposed method, we use different medical diagnosis datasets taking into account quantitative metrics, comprehensibility, and reliability. We performed a comparison of REMED versus C4.5 and RIPPER combined with over-sampling and cost-sensitive strategies. This empirical analysis of the REMED algorithm showed it to be quantitatively competitive with C4.5 and RIPPER in terms of the area under the Receiver Operating Characteristic curve (AUC) and the geometric mean, but overcame them in terms of comprehensibility and reliability. Results of our experiments show that REMED generated rules systems with a larger degree of abstraction and patterns closer to well-known abnormal values associated to each considered medical dataset.

Graph-based knowledge representation for GIS data

This paper presents a proposal to create a graph representation for GIS, using both spatial and non-spatial data and also including spatial relations between spatial objects. Because graphs are a powerful and flexible knowledge representation we are able to combine spatial and non-spatial data at the same time and this is one of the strengths of the proposal. We hope to apply this knowledge representation to the data mining process with GIS data including three types of spatial relations: topological, orientation and distance.

Segmentation and Classification of Bone Marrow Cells Images Using Contextual Information for Medical Diagnosis of Acute Leukemias

Morphological identification of acute leukemia is a powerful tool used by hematologists to determine the family of such a disease. In some cases, experienced physicians are even able to determine the leukemia subtype of the sample. However, the identification process may have error rates up to 40% (when classifying acute leukemia subtypes) depending on the physician’s experience and the sample quality. This problem raises the need to create automatic tools that provide hematologists with a second opinion during the classification process. Our research presents a contextual analysis methodology for the detection of acute leukemia subtypes from bone marrow cells images. We propose a cells separation algorithm to break up overlapped regions. In this phase, we achieved an average accuracy of 95% in the evaluation of the segmentation process. In a second phase, we extract descriptive features to the nucleus and cytoplasm obtained in the segmentation phase in order to classify leukemia families and subtypes. We finally created a decision algorithm that provides an automatic diagnosis for a patient. In our experiments, we achieved an overall accuracy of 92% in the supervised classification of acute leukemia families, 84% for the lymphoblastic subtypes, and 92% for the myeloblastic subtypes. Finally, we achieved accuracies of 95% in the diagnosis of leukemia families and 90% in the diagnosis of leukemia subtypes.

Defining new argumentation-based semantics by minimal models

Dungs argumentation approach is a unifying approach which has played an influential role on argumentation research and artificial intelligence (AT). Based on a proper representation of Dungs argumentation approach and minimal models, we introduce a novel argumentation semantics called preferred+ semantics which follows the preferred semantics philosophy. Also, we show how to infer preferred+ semantics using a software tool called SI-COBRA that was introduced recently

A hybrid surrogate-based approach for evolutionary multi-objective optimization

Evolutionary algorithms have gained popularity as an alternative for dealing with multi-objective optimization problems. However, these algorithms require to perform a relatively high number of fitness function evaluations in order to generate a reasonably good approximation of the Pareto front. This can be a shortcoming when fitness evaluations are computationally expensive. In this paper, we propose an approach that combines an evolutionary algorithm with an ensemble of surrogate models based on support vector machines (SVM), which are used to approximate the fitness functions of a problem. The proposed approach performs a model selection process for determining the appropriate hyperparameters values for each SVM in the ensemble. The ensemble is constructed in an incremental fashion, such that the models are updated with the knowledge gained during the evolutionary process, but the information from previous evaluated regions is also preserved. A criterion based on surrogate fidelity is also proposed for determining when should the surrogates be updated. We evaluate the performance of our proposal using a benchmark of test problems widely used in the literature and we compare our results with respect to those obtained by the NSGA-II. Our proposed approach is able to significantly reduce the number of fitness function evaluations performed, while producing solutions which are close to the true Pareto front.